162 results on '"Kohonen maps"'
Search Results
2. ФОРМУВАННЯ ДИНАМІЧНИХ ПАТЕРНІВ ПОВЕДІНКИ ЦІН DEFI-АКТИВІВ У СКЛАДІ РИНКУ КРИПТОВАЛЮТ.
- Author
-
Доценко, Олексій, Глущенко, Ольга, Проноза, Павло, Швайко, Мар’яна, and Давидов, Олександр
- Abstract
The scientific work is devoted to the study of dynamic behavior patterns of the prices of DeFi assets as part of the cryptocurrency market. The DeFi segment has shown an unprecedented level of growth over the past 5 years of its existence. The uniqueness of the innovative decentralized approach to the provision of financial services in the ecosystem provides opportunities to provide new high-tech financial products and services. The DeFi ecosystem is becoming stable and has many prospects for expansion and improvement. All these factors determine the relevance of this work and research on this topic. The purpose of this research is to create clusters of asset behavior patterns in the field of decentralized finance (DeFi) on the cryptocurrency market. This includes identifying key innovations, examining market trends in asset dynamics, analyzing the impact of DeFi on traditional financial systems, and assessing possible risks and challenges associated with this rapidly growing segment. During the research, various general scientific and special methods of scientific knowledge were used for a comprehensive approach to solving tasks and achieving the goal. Dynamic patterns of price behavior are revealed using methods of hierarchical clustering and Kohonen maps. The article discusses the technological innovations and functional aspects of the DeFi ecosystem, such as smart contracts, liquid pools, stablecoins, and democratic governance. These innovations form the core of the effective operation of DeFi projects. Aspects of how the DeFi ecosystem affects the financial system have been identified, providing easy access to classic services, but there are threats of fraud and theft, especially among uninformed users. The question of international legal regulation remains open, slowing down the development of DeFi. The study found consistent pricing patterns of DeFi assets, which demonstrates their dynamic patterns and differences from traditional cryptocurrencies. The obtained research results define DeFi as a stable cryptocurrency ecosystem. They can be used to improve and develop new DeFi projects, improving the functionality of the ecosystem. The regularities of the dynamics of DeFi assets can serve as a tool for managing and investing in a volatile market. The findings also point to the need for further development of the regulatory environment, educational programs and research for DeFi tools. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Artificial neural networks optimize the establishment of a Brazilian germplasm core collection of winter squash (Cucurbita moschata D.)
- Author
-
Ronaldo Silva Gomes, Ronaldo Machado Júnior, Cleverson Freitas de Almeida, Rebeca Lourenço de Oliveira, Moysés Nascimento, Maicon Nardino, Wellington Ferreira do Nascimento, and Derly José Henriques da Silva
- Subjects
Computational intelligence ,Cucurbita ,Fatty acid profile ,Germplasm collection ,Kohonen maps ,Medicine ,Science - Abstract
Abstract With widespread cultivation, Cucurbita moschata stands out for the carotenoid content of its fruits such as β and α-carotene, components with pronounced provitamin A function and antioxidant activity. C. moschata seed oil has a high monounsaturated fatty acid content and vitamin E, constituting a lipid source of high chemical–nutritional quality. The present study evaluates the agronomic and chemical–nutritional aspects of 91 accessions of C. moschata kept at the BGH-UFV and propose the establishment of a core collection based on multivariate approaches and on the implementation of Artificial Neural Networks (ANNs). ANNs was more efficient in identifying similarity patterns and in organizing the distance between the genotypes in the groups. The averages and variances of traits in the CC formed using a 15% sampling of accessions, were closer to those of the complete collection, particularly for accumulated degree days for flowering, the mass of seeds per fruit, and seed and oil productivity. Establishing the 15% CC, based on the broad characterization of this germplasm, will be crucial to optimize the evaluation and use of promising accessions from this collection in C. moschata breeding programs, especially for traits of high chemical–nutritional importance such as the carotenoid content and the fatty acid profile.
- Published
- 2024
- Full Text
- View/download PDF
4. TRANSFORMATIONS OF THE RESOURCE MANAGEMENT STRATEGY OF UKRAINIAN BANKS.
- Author
-
Zarutska, Olena, Pavlov, Roman, Pavlova, Tetiana, Grynko, Tetiana, Levkovich, Oksana, and Hviniashvili, Tetiana
- Subjects
BANK management ,SELF-organizing maps ,BANK assets ,BANK accounts ,BANKING industry ,RESOURCE management ,ASSET backed financing - Abstract
This article examines the peculiarities of the management of assets and liabilities of Ukrainian banks in the conditions of significant structural transformations of the resource base during the period of martial law. The analysis is carried out at the level of homogeneous structural and functional groups of banks (SFGBs), which are formed using published reporting data and the application of Kohonen's self-organizing map (SOM). Accumulation of statistical data has been carried out for 5 years, special attention is paid to structural changes in the resource base and directions of placement of bank assets over the past two years. Over the past two years, the bank has been under the influence of shock factors affecting assets and liabilities. At the beginning of 2022, there was an outflow of funds from bank accounts, which was gradually compensated by the inflow of current funds from corporations and the population of individuals. In 2023, the National Bank of Ukraine actively stimulated the development of the term resource base, the basis for ensuring the growth of credit operations. Transactions with state securities continue to grow in the structure of bank assets. The priority task of the banking system remains the financial support of business, but in the conditions of a full-scale war, such development of credit operations is limited. It is expedient to study the strategy of banks by combining the structure of assets and liabilities according to similar characteristics and analyzing the dynamics of groups. Observation of homogeneous groups confirms their stable nature, features of strategy, risk profile and development priorities. It has been proven that banks within homogeneous SFGBs demonstrate similar behaviour in the formation of management strategies and reactions to internal and external shocks. At the macro level, the SOM structure allows you to quantitatively assess the main processes taking place in the banking system, conduct comparisons with maps, and identify problems and priorities in the management of bank assets and liabilities. The SFGB method allows you to evaluate the trajectory of individual banks on the map and develop recommendations for improving the strategy of managing assets and liabilities. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
5. DEVELOPMENT OF PASSENGER CAR SAFETY.
- Author
-
KOVAC, VILÉM, KOVÁČIKOVÁ, NIKOLA, and TURINSKA, LIBUŠE
- Subjects
- *
SELF-organizing maps , *ACCIDENT prevention , *TRAFFIC accidents , *SAFETY factor in engineering , *CLUSTER analysis (Statistics) - Abstract
The goal of the paper was to assess safety of passenger cars sold in the Czech Republic in terms of the development of both active and passive safety features of cars sold between 2020-2022. Using content analysis aimed at collecting secondary data, the sales of passenger cars and their safety ratings were examined. Cluster analysis and neural networks were subsequently used to classify vehicles into selforganizing Kohonen maps, within which the movement between individual clusters was monitored. It was found that more than 25 % of vehicles sold between 2021 and 2022 changed their position compared to the year 2020. When taking into account vehicles newly introduced to the market, the average level of safety of vehicles sold compared to the year 2020. Further research could focus on a more detailed analysis of factors affecting safety on roads and their quantification for making better predictions and prevention of road accidents. It should be considered that vehicle safety ratings are based on a specific methodology and criteria and can vary significantly. [ABSTRACT FROM AUTHOR]
- Published
- 2023
6. Artificial neural networks optimize the establishment of a Brazilian germplasm core collection of winter squash (Cucurbita moschata D.)
- Author
-
Gomes, Ronaldo Silva, Machado Júnior, Ronaldo, de Almeida, Cleverson Freitas, de Oliveira, Rebeca Lourenço, Nascimento, Moysés, Nardino, Maicon, do Nascimento, Wellington Ferreira, and da Silva, Derly José Henriques
- Published
- 2024
- Full Text
- View/download PDF
7. Disease Severity Index in Parkinson's Disease Based on Self-Organizing Maps.
- Author
-
Araújo, Suellen M., Nery, Sabrina B. M., Magalhães, Bianca G., Almeida, Kelson James, and Gaspar, Pedro D.
- Subjects
PARKINSON'S disease ,SELF-organizing maps ,DEEP brain stimulation ,NEURAL circuitry ,ARTIFICIAL intelligence ,DATABASES - Abstract
Parkinson's disease is a progressive neurodegenerative condition whose prevalence has significantly increased. This work proposes the development of a severity index to classify patients from symptoms, mainly motor ones, using an Artificial Neuronal Network (ANN) trained by the Self-Organizing Maps (SOMs) algorithm. The FOX Insight database was used, which offers data in the form of questionnaires answered by patients or caregivers from all over the world, with information regarding this pathology. After pre-processing the data, a set of 597 questionnaires containing 28 defined questions was selected. The symptoms were individually analyzed after mapping and divided into four classes. In class 1, most symptoms were not present. In class 2, the presence of certain symptoms demonstrated early milestones of the disease. In class 3, symptoms related to the patient's mobility, in particular pain, stand out among the most reported. In class 4, the intense presence of all symptoms is observed. To test the tool, data were used from some of these patients, who answered the same questionnaire at different times (simulating medical appointments). The presented severity index to classify patients allowed identifying the current stage of the disease allowing the follow-up. This AI-based decision-support tool can help medical professionals to predict the evolution of Parkinson's disease, which can result in longer life quality of patients, in terms of symptoms and medication requirements. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
8. Analysis of the Structure of Germany’s Energy Sector with Self-organizing Kohonen Maps
- Author
-
Potapenko, Irina, Kukartsev, Vladislav, Tynchenko, Vadim, Mikhalev, Anton, Ershova, Evgeniia, van der Aalst, Wil, Series Editor, Mylopoulos, John, Series Editor, Ram, Sudha, Series Editor, Rosemann, Michael, Series Editor, Szyperski, Clemens, Series Editor, Abramowicz, Witold, editor, Auer, Sören, editor, and Stróżyna, Milena, editor
- Published
- 2022
- Full Text
- View/download PDF
9. Create Partial Table Indexing for Search Sources
- Author
-
Artem Mironov and Victor Munerman
- Subjects
parallel programming ,bigdata ,complex structure search ,clustering ,databases ,distributed computing ,partial indexing ,kohonen maps ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
Due to the growing number of data and the growing variety of requirements for their processing, now we have to move away from data processing at the time of the request and increasingly shift the main work on its implementation or the implementation of its main aspects to pre-stored and prepared results. In many ways, DBMS thus try to solve performance problems by increasing memory consumption, but in many ways, it is necessary to think about saving the latter, while preferably preserving the results of methods based on a similar approach – indexing, hashing, neural network algorithms. The article discusses a method for improving the efficiency of solving search problems for large tables. The proposed method is based on partial indexing of elements near convergence centers and the introduction of the concept of metadata for these centers. Such clustering with stored metadata for the centers, near which the next intermediate nodes are formed, allows you to reduce the memory costs for indexing, because, firstly, with this approach there is no need for nested indexing, which can lead to serious spatial costs. Secondly, such an approach can make it possible to use one indexing for different combinations of the presence of columns in the search image, without losing most of the search efficiency during indexing. Such a combination, if used correctly, can make it possible to efficiently process tables with different search needs, for different groups of columns, for which storing indexing for each large type of query or group of queries can naturally lead to serious memory consumption costs as well as loss of performance when working with large arrays of memory, which also increases far from linearly.
- Published
- 2022
- Full Text
- View/download PDF
10. CHANGES IN UKRAINIAN BANKS ‘BUSINESS MODELS IN TIMES OF MILITARY CRISIS.
- Author
-
Zarutska, Оlena, Ponomarоva, Oksana, Pavlov, Roman, Pavlova, Tetiana, and Levkovich, Oksana
- Subjects
MILITARY miniatures ,SELF-organizing maps ,BANK loans ,BUSINESS models ,LOANS ,COMMUNITY banks ,CREDIT risk ,STATE banks ,MILITARY spending - Abstract
The article analyzes changes in the business models of Ukrainian banks using the author's method of structural and functional groups of banks (SFGB). The method’s basis is the processing, systematization, and visualization of the system’s values of banks’ financial indicators using Kohonen’s self-organizing map (SOM). Depending on the level distribution of a large number of indicators that characterize the structure of assets, liabilities, income, expenses, and other qualitative indicators that describe the business models of each bank on successive reporting dates, homogeneous groups of banks are formed. The purpose of this study is to compare the key features of the banking system as of January 1 and September 1, 2022, and the corresponding changes in business models. Over the eight months of 2022, the number of banks with corporate lending increased slightly, but the resource base of these banks gradually changed. The number of banks with retail financing decreased at the expense of banks with current resources. During an increase in the discount rate and in the price of refinancing loans, banks’ business model that attracts resources on the interbank market and places them in securities has shrunk. At the same time, the number of banks with an increased level of securities in assets and corporate financing increased. The quality of the portfolio indicates the increased credit risks of the respective large state banks. The drawback of the proposed method is the dependence of conclusions on official banks 'statements that do not always reflect nuisances of financial position. Within small banks, we can sometimes observe that current changes in clients' account balances affect the position in SFGB. The SFGB method can be applied to analyze trends and estimate the probability of subsequent structural changes. For each bank, one can observe the trajectory change on the map and investigate the reasons for the change in business strategy. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. EVALUATION OF UKRAINIAN BANKS’ BUSINESS MODELS BY THE STRUCTURAL AND FUNCTIONAL GROUPS ANALYSIS METHOD.
- Author
-
Zarutska, Оlena, Novikova, Lyudmila, Pavlov, Roman, Pavlova, Tetiana, and Levkovich, Oksana
- Subjects
BUSINESS valuation ,SELF-organizing maps ,STRUCTURAL models ,FUNCTIONAL analysis ,FUNCTIONAL groups ,BUSINESS models - Abstract
A method of identifying banks’ business models and studying the features of their risk profile, considering the system of indicators featuring the structure of assets, liabilities, income, expenses, and other qualitative indicators based on monthly statistical reporting. Kohonen's self-organizing maps (SOM) are used to process large data sets, revealing objects’ hidden features by forming homogeneous groups according to similar values of a large system of indicators. The choice of the system of indicators that play the most significant role in describing the business models of modern banks is substantiated. The proposed method makes it possible to group banks with homogeneous characteristics into so-called structural-functional groups and studies the change in the characteristics of groups of banks over time to compare their behavior during periods of active development of the system and during a crisis. That approach is useful for studying the banking system at the macro level, as it provides a quantitative measure of its financial stability. The more banks are in groups with negative values of parameters, increased risks, and unprofitable performance, the worse the general state of the system. The method also allows studying the features of each structural and functional group and the business models’ features at the meso-level. The number and composition of banks inherent in any group change dynamically, which characterizes the features of the relevant business model in a particular period. The averages of each group reflect the objective changes in the banking system structure. In addition, the SOM trajectory can be built for each individual bank determining the development of its strategy, features of a particular business model, and risk profile. At the micro-level, it allows comparing the features of individual banks within the SFGB and models’ ways to improve efficiency and financial stability by forecast values for SOM. An extensive system of indicators used to form structural and functional groups of banks allows to quickly respond to changes in the banking system, identify areas of increased risk and explore the adequacy and effectiveness of banks’ business models. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. Disease Severity Index in Parkinson’s Disease Based on Self-Organizing Maps
- Author
-
Suellen M. Araújo, Sabrina B. M. Nery, Bianca G. Magalhães, Kelson James Almeida, and Pedro D. Gaspar
- Subjects
neural networks ,Kohonen maps ,Parkinson’s disease ,Technology ,Engineering (General). Civil engineering (General) ,TA1-2040 ,Biology (General) ,QH301-705.5 ,Physics ,QC1-999 ,Chemistry ,QD1-999 - Abstract
Parkinson’s disease is a progressive neurodegenerative condition whose prevalence has significantly increased. This work proposes the development of a severity index to classify patients from symptoms, mainly motor ones, using an Artificial Neuronal Network (ANN) trained by the Self-Organizing Maps (SOMs) algorithm. The FOX Insight database was used, which offers data in the form of questionnaires answered by patients or caregivers from all over the world, with information regarding this pathology. After pre-processing the data, a set of 597 questionnaires containing 28 defined questions was selected. The symptoms were individually analyzed after mapping and divided into four classes. In class 1, most symptoms were not present. In class 2, the presence of certain symptoms demonstrated early milestones of the disease. In class 3, symptoms related to the patient’s mobility, in particular pain, stand out among the most reported. In class 4, the intense presence of all symptoms is observed. To test the tool, data were used from some of these patients, who answered the same questionnaire at different times (simulating medical appointments). The presented severity index to classify patients allowed identifying the current stage of the disease allowing the follow-up. This AI-based decision-support tool can help medical professionals to predict the evolution of Parkinson’s disease, which can result in longer life quality of patients, in terms of symptoms and medication requirements.
- Published
- 2023
- Full Text
- View/download PDF
13. CHANGES IN UKRAINIAN BANKS ‘BUSINESS MODELS IN TIMES OF MILITARY CRISIS
- Author
-
Олена Заруцька, Оксана Пономарьова, Роман Павлов, Тетяна Павлова, and Оксана Левкович
- Subjects
banking risks ,business models of banks ,banking system ,cluster analysis ,Kohonen maps ,structure of bank assets ,Economics as a science ,HB71-74 ,Business ,HF5001-6182 - Abstract
The article analyzes changes in the business models of Ukrainian banks using the author's method of structural and functional groups of banks (SFGB). The method’s basis is the processing, systematization, and visualization of the system’s values of banks’ financial indicators using Kohonen’s self-organizing map (SOM). Depending on the level distribution of a large number of indicators that characterize the structure of assets, liabilities, income, expenses, and other qualitative indicators that describe the business models of each bank on successive reporting dates, homogeneous groups of banks are formed. The purpose of this study is to compare the key features of the banking system as of January 1 and September 1, 2022, and the corresponding changes in business models. Over the eight months of 2022, the number of banks with corporate lending increased slightly, but the resource base of these banks gradually changed. The number of banks with retail financing decreased at the expense of banks with current resources. During an increase in the discount rate and in the price of refinancing loans, banks’ business model that attracts resources on the interbank market and places them in securities has shrunk. At the same time, the number of banks with an increased level of securities in assets and corporate financing increased. The quality of the portfolio indicates the increased credit risks of the respective large state banks. The drawback of the proposed method is the dependence of conclusions on official banks 'statements that do not always reflect nuisances of financial position. Within small banks, we can sometimes observe that current changes in clients' account balances affect the position in SFGB. The SFGB method can be applied to analyze trends and estimate the probability of subsequent structural changes. For each bank, one can observe the trajectory change on the map and investigate the reasons for the change in business strategy.
- Published
- 2022
- Full Text
- View/download PDF
14. EVALUATION OF UKRAINIAN BANKS’ BUSINESS MODELS BY THE STRUCTURAL AND FUNCTIONAL GROUPS ANALYSIS METHOD
- Author
-
Olena Zarutska, Lyudmila Novikova, Roman Pavlov, Tetiana Pavlova, and Oksana Levkovich
- Subjects
banking risks ,bank risk profile ,business models of banks ,banking system ,cluster analysis ,Kohonen maps ,Economics as a science ,HB71-74 ,Business ,HF5001-6182 - Abstract
A method of identifying banks’ business models and studying the features of their risk profile, considering the system of indicators featuring the structure of assets, liabilities, income, expenses, and other qualitative indicators based on monthly statistical reporting. Kohonen's self-organizing maps (SOM) are used to process large data sets, revealing objects’ hidden features by forming homogeneous groups according to similar values of a large system of indicators. The choice of the system of indicators that play the most significant role in describing the business models of modern banks is substantiated. The proposed method makes it possible to group banks with homogeneous characteristics into so-called structural-functional groups and studies the change in the characteristics of groups of banks over time to compare their behavior during periods of active development of the system and during a crisis. That approach is useful for studying the banking system at the macro level, as it provides a quantitative measure of its financial stability. The more banks are in groups with negative values of parameters, increased risks, and unprofitable performance, the worse the general state of the system. The method also allows studying the features of each structural and functional group and the business models’ features at the meso-level. The number and composition of banks inherent in any group change dynamically, which characterizes the features of the relevant business model in a particular period. The averages of each group reflect the objective changes in the banking system structure. In addition, the SOM trajectory can be built for each individual bank determining the development of its strategy, features of a particular business model, and risk profile. At the micro-level, it allows comparing the features of individual banks within the SFGB and models ways to improve efficiency and financial stability by forecast values for SOM. An extensive system of indicators used to form structural and functional groups of banks allows to quickly respond to changes in the banking system, identify areas of increased risk and explore the adequacy and effectiveness of banks’ business models.
- Published
- 2022
- Full Text
- View/download PDF
15. Classification of steels according to their sensitivity to fracture using a synergetic model.
- Author
-
Karnaukh, Sergii G., Markov, Oleg E., Kukhar, Volodymyr V., and Shapoval, Alexander A.
- Subjects
- *
FRACTURE mechanics , *SELF-organizing maps , *CUTTING (Materials) , *BRITTLENESS , *STEEL , *CLUSTER analysis (Statistics) , *CLASSIFICATION - Abstract
To select a rational method for cutting of rolled stocks made from materials with different physical and mechanical properties, an engineer must have the tools to make such a choice. In order to find the most informative system of fracture criteria allowing to classify materials authentically by their fracture sensitivity, the software was developed. It allows to solve the clustering problem in a multidimensional space of parameters and present the obtained information in a visual form using self-organizing Kohonen maps. The cluster analysis of the material fracture criteria was carried out. The most informative criterion among the ones characterizing the mechanical properties of steels is the «offset yield strength», among the synergistic ones – «scale criterion». At the same time, among the traditional mechanical features of steels, a set allowing to classify materials with a given integrity by their cutting sensitivity has not been found. It was established that the fracture criteria: «crack growth criterion» and «brittleness criterion» are basic informative features. When adding any of the remaining complex criteria («crack nucleation criterion» or «scale criterion»), they form the most informative sets of minimal power, providing the classification of materials by their cutting sensitivity with a given integrity. In order to obtain high-quality workpieces at a minimum conversion cost, recommendations were developed for choice of the method for cutting of rolled stocks in magnitude of criteria values: «crack growth criterion» and «brittleness criterion». To cut materials «in plastic state», the cutting by shear should be used, specifically—a closed cutoff scheme or an incompletely closed cutoff scheme with an active transverse clamp or a cutoff scheme with a differentiated clamp of rolled stocks. If increased requirements are imposed on the geometric accuracy of the workpieces, it is recommended to use complex blanking and cutting processes. For cutting materials «in elastoplastic state» there are good reasons to use the cutting by shear, and in particular—an incompletely closed cutoff scheme with an active and passive transverse clamp. Closer to the class interval, it is possible to apply breaking by bending with the application of an effective stress concentrator. Breaking by bending should be used to cut «brittle» materials. The carried out experiments confirmed the adequacy of theoretical conclusions and recommendations on the choice of a rational method for cutting of the rolled stocks to obtain high-quality workpieces. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
16. Data mining for faster, interpretable solutions to inverse problems: A case study using additive manufacturing
- Author
-
Chandrika Kamath, Juliette Franzman, and Ravi Ponmalai
- Subjects
Inverse problem ,Code surrogate ,Gaussian process ,Kohonen maps ,Cybernetics ,Q300-390 ,Electronic computers. Computer science ,QA75.5-76.95 - Abstract
Solving inverse problems, where we find the input values that result in desired values of outputs, can be challenging. The solution process is often computationally expensive and it can be difficult to interpret the solution in high-dimensional input spaces. In this paper, we use a problem from additive manufacturing to address these two issues with the intent of making it easier to solve inverse problems and exploit their results. First, focusing on Gaussian process surrogates that are used to solve inverse problems, we describe how a simple modification to the idea of tapering can substantially speed up the surrogate without losing accuracy in prediction. Unlike block tapering, which approximates the covariance matrix by diagonal blocks, our approach divides the data itself into blocks. Both approaches reduce the computational cost by replacing the Cholesky decomposition of the full matrix by the decomposition of multiple smaller matrices, but our approach gives accurate predictions despite the approximation as we identify hyperparameters optimal for each block. Second, we demonstrate that Kohonen self-organizing maps can be used to visualize and interpret the solution to the inverse problem in the high-dimensional input space. For our data set, as not all input dimensions are equally important, we show that using weighted distances results in a better organized map that not only makes the relationships among the inputs obvious, but also indicates the location of the solution in the input space so an additive manufacturing engineer can control the inputs appropriately for a desired output.
- Published
- 2021
- Full Text
- View/download PDF
17. INTELLIGENT APPROACHES TO ORGANIZING REMOTE QUALITY CONTROL OF STORAGE OF GRAIN PRODUCTS
- Author
-
Vladyslav Diachenko, Oleksii Liashenko, Oleg Mikhal, and Mariia Umanets
- Subjects
Grain ,Kohonen Maps ,Conditions Identification System ,Energy Saving ,Computer software ,QA76.75-76.765 ,Information theory ,Q350-390 - Abstract
Cereals are an essential part of the diet of Homo sapiens. Since late Neolithic times, with the transition to sedentary farming, working with grain (growing, storing, processing, cooking food) has become a traditional type of professional human activity. As part of the accumulated historical experience, numerous technological processes have been developed and optimized for this type of activity. The relevant technologies evolved in close correlation with the changing conditions of life, literally under the pressure of Darwinian natural selection, because they were directly related to the survival of the Homo sapiens. Further development of grain-processing technologies remains invariably urgent today, as evidenced by the report [1] presented by the UN on the state of food security and nutrition in the world - with horrifying figures depicting the need and misery of the wide masses of the population of the planet. An important component of grain processing is the technology associated with the storage of grain products. Part of the stored grain products is used as seed stock for a new cycle of grain sales, the other - a significant part - for processing into food products. At the same time, new developed (optimized, improved) grain storage technologies must be safe, low-cost, maximally compatible with previously developed (available) equipment, and scalable to large volumes of stored material. Of course, the technology must ensure proper efficiency, an indicator of which should be a reduction in the percentage of grain product losses. In this regard, management methods used in the technological processes of grain products storage are substantially important, as well as methods of control over the current state of grain products for the correct organization of the technological processes. In particular, methods using elements of artificial intelligence are of high interest. Among them, neural networks are promising, especially those capable of learning "without a teacher" - Kohonen Maps (KK). Modified KK algorithm [2] implements reduced learning time[3], which is relevant in the implementation of adaptive procedures for processing the results of measurements of controlled parameters. The purpose of this paper is to consider the principles of using modified Kohonen maps to classify situations with applicability to remote quality control of grain products storage.
- Published
- 2021
- Full Text
- View/download PDF
18. Cluster Analysis of Innovation-Active Enterprises Using Kohonen Maps as a Prerequisite for Strategic Planning
- Author
-
Myachin Valentin
- Subjects
innovation-active enterprises ,cluster analysis ,Kohonen maps ,strategic planning ,neural networks ,Business ,HF5001-6182 ,Finance ,HG1-9999 - Abstract
Introduction. Formation of prerequisites for innovative development of industrial enterprises includes strategic planning, which is one of the components of the management system. The choice of the strategy of innovative development of the portfolio of strategies for innovation-active enterprises depends on their internal and external environment. Purpose. The aim of the study is to develop conceptual approaches to clustering of innovation-active machine-building enterprises, to analyze the clusters in order to identify their significant differences, and on this basis to develop appropriate strategies for each cluster of enterprises. Results. A conceptual approach to the clustering of innovation-active machine-building enterprises in order to identify the degree of their readiness for innovation. Clustering was carried out for thirty innovation-active enterprises on two indicators – the level of the crisis and the indicator of the use of strategic capabilities of enterprises. By means of the correlation analysis the relative dependence of input factors is established and by its results it is shown that the incoming factors are practically independent from each other. The use of cluster analysis on the basis of modern research methods using neural networks – Kohonen maps allowed to differentiate the innovation-active enterprises according to the degree of their readiness for innovation. The method of neural networks – Kohonen maps was used for clustering. Clustering is carried out on the basis of two input indicators – an indicator of the level of crisis and an indicator of the use of strategic opportunities.These clusters are called «0», «1», «2», «3» and «4». The largest cluster «0» included 13 machine-building innovation-active enterprises, the smallest cluster «1» included one innovation-active enterprise. The enterprises of cluster «3» have average strategic opportunities with moderate negative dynamics of the crisis indicator. In General, this is one of the largest crisis groups of enterprises among the thirty studied innovation-active enterprises. Enterprises of clusters «1» and «2» have average strategic opportunities with stable positive dynamics of the crisis state indicator. These two clusters include only three enterprises out of the thirty innovation-active enterprises under study. Conclusions. All thirty studied enterprises are divided into five clusters, which differ significantly in parameters. For machine-building innovative-active machine-building enterprises of each cluster the corresponding innovative strategy is offered.
- Published
- 2019
- Full Text
- View/download PDF
19. The experimental study of the effectiveness of Kohonen maps and autoassociative neural networks in the qualitative analysis of multidimensional data by the example of real data describing coal susceptibility to fluidal gasification.
- Author
-
Jamróz, Dariusz
- Subjects
- *
SELF-organizing maps , *DATA analysis , *COAL , *DATA modeling , *MULTIDIMENSIONAL scaling , *COAL combustion - Abstract
The qualitative analysis of multidimensional data using their visualization allows to observe some characteristics of data in a way which is the most natural for a human, through the sense of sight. Thanks to such an approach, some characteristics of the analyzed data are simply visible. This allows to avoid using often complex algorithms allowing to examine specific data properties. Visualization of multidimensional data consists in using the representation transforming a multidimensional space into a two-dimensional space representing a computer screen. The important information which can be obtained in this way is the possibility to separate points belonging to different classes in the multidimensional space. Such information can be directly obtained if images of points belonging to different classes occupy other areas of the picture presenting these data. The paper presents the effectiveness of the qualitative analysis of multidimensional data conducted in this way through their visualization with the application of Kohonen maps and autoassociative neural networks. The obtained results were compared with results obtained using the perspective-based observational tunnels method, PCA, multidimensional scaling and relevance maps. Effectiveness tests of the above methods were performed using real seven-dimensional data describing coal samples in terms of their susceptibility to fluidal gasification. The methods' effectiveness was compared using the criterion for the readability of the multidimensional visualization results, introduced in earlier papers. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
20. Neural Networks (SOM) Applied to INAA Data of Chemical Elements in Archaeological Ceramics from Central Amazon
- Author
-
R. Hazenfratz, C. S. Munita, and E. G. Neves
- Subjects
neural networks ,Kohonen maps ,Central Amazon ,Principal component analysis ,Lago Grande archaeological site ,Osvaldo archaeological site ,Archaeology ,CC1-960 - Abstract
Artificial neural networks represent an alternative to traditional multivariate techniques, such as principal component and discriminant analysis, which rely on hypotheses regarding the normal distribution of the data and homoscedasticity. They also may be a powerful tool for multivariate modeling of systems that do not present linear correlation between variables, as well as to visualize high-dimensional data in bi- or trivariate structures. One special kind of neural network of interest in archaeometric studies is the Self-Organizing Map (SOM). SOMs can be distinguished from other neural networks for preserving the topological features of the original multivariate space. In this study, the self-organizing maps were applied to concentration data of chemical elements measured in archaeological ceramics from Central Amazon using instrumental neutron activation analysis (INAA). The main objective was testing the chemical patterns previously identified using cluster and principal component analysis, forming groups of ceramics according the multivariate chemical composition. It was verified by statistical tests that the chemical elemental data was not normally distributed and did not present homogeneity of covariance matrices for different groups, as requested by principal component analysis and other multivariate techniques. The maps obtained were consistent with the patterns identified by cluster and principal component analysis, forming two chemical groups of pottery shards for each archaeological site tested. Finally, it was verified the potential of SOMs for testing if failures in underlying hypotheses of traditional multivariate techniques might be critically influencing the results and subsequent archaeological interpretation of archaeometric data.
- Published
- 2017
- Full Text
- View/download PDF
21. Data Mining for Faster, Interpretable Solutions to Inverse Problems: A Case Study Using Additive Manufacturing
- Author
-
Ravi Ponmalai, Juliette Franzman, and Chandrika Kamath
- Subjects
Self-organizing map ,FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer science ,Diagonal ,Tapering ,Machine Learning (cs.LG) ,symbols.namesake ,FOS: Mathematics ,Neural and Evolutionary Computing (cs.NE) ,Mathematics - Numerical Analysis ,Gaussian process ,Kohonen maps ,Block (data storage) ,Covariance matrix ,Computer Science - Neural and Evolutionary Computing ,QA75.5-76.95 ,Numerical Analysis (math.NA) ,Inverse problem ,Code surrogate ,Electronic computers. Computer science ,symbols ,Q300-390 ,Cybernetics ,Algorithm ,Cholesky decomposition - Abstract
Solving inverse problems, where we find the input values that result in desired values of outputs, can be challenging. The solution process is often computationally expensive and it can be difficult to interpret the solution in high-dimensional input spaces. In this paper, we use a problem from additive manufacturing to address these two issues with the intent of making it easier to solve inverse problems and exploit their results. First, focusing on Gaussian process surrogates that are used to solve inverse problems, we describe how a simple modification to the idea of tapering can substantially speed up the surrogate without losing accuracy in prediction. Second, we demonstrate that Kohonen self-organizing maps can be used to visualize and interpret the solution to the inverse problem in the high-dimensional input space. For our data set, as not all input dimensions are equally important, we show that using weighted distances results in a better organized map that makes the relationships among the inputs obvious., 16 figures and 4 tables
- Published
- 2023
22. Some considerations on data mining from questionnaires by constructing fuzzy signatures based on factor analysis.
- Author
-
Koczy, Laszlo T., Purvinis, Ojaras, and Susniene, Dalia
- Subjects
- *
FACTOR analysis , *DATA mining , *SELF-organizing maps , *TREE graphs , *DATA reduction - Abstract
To interpret and to process the answers to questionnaires with large amount of questions may be not easy task. They are multidimensional data, sometimes with high dimensionality (in the hundreds). Therefore, it is necessary that some data reduction approach should be employed. On the other hand, answers to specific questions in questionnaires are imprecise, and the type and degree of imprecision is determined by the kind of the questions. The authors of the paper consider the imprecise answers to management type questions using a numerical scale as fuzzy degrees, and based on the semantic connections among the individual questions, a hierarchical structure is assumed. The paper suggests the use of factor analysis in order to determine this hierarchical structure, and thus the construction of fuzzy signatures from the tree graph representing the connections among the questions and answers, and the values normalized into membership degrees are assigned to the leaves of this tree. An interesting issue is how to determine the aggregations at the intermediate nodes. This may happen based on management science domain expert knowledge, and validated by the obtained results. Kohonen maps are used to demonstrate the clusters emerging among the overall fuzzy degrees representing the Fuzzy Signatures. The evaluation brings some results that partly confirm soft science based assumptions about employee behavior in the literature, and partly bring some interesting novel recognitions that may be brought in feedback to the original management science related problem, where the new method is illustrated. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
23. Evaluation of macro and micronutrient elements content from soft drinks using principal component analysis and Kohonen self-organizing maps.
- Author
-
Silva, Emanuela dos Santos, da Silva, Erik Galvão Paranhos, Silva, Daniélen dos Santos, Novaes, Cleber Galvão, Amorim, Fábio Alan Carqueija, dos Santos, Márcio José Silva, and Bezerra, Marcos Almeida
- Subjects
- *
SOFT drinks , *MICRONUTRIENTS , *CHEMOMETRICS , *SELF-organizing maps , *MULTIPLE correspondence analysis (Statistics) - Abstract
Highlights • Brazilian soft drinks could be differenced by chemometric tools. • PCA and ANN were compared in the pattern recognition capacity. • PCA and ANN were able to extract relevant information from soft drink samples. Abstract This study approaches the determination of nine elements from Brazilian carbonated soft drinks of several flavors and manufactures using inductively coupled plasma optical emission spectrometry (ICP OES). The concentrations of the elements varied as follows: (in µg L−1: Cu: 4.00–78.0; Fe: 74.0–506; Mn: 20.0–66.0; Zn: 104–584) and (in mg L−1: Ca: 4.81–16.2; K: 6.73–260; Na: 26.0–175; S: 1.43–5.41; P: 0.186–219). Principal component analysis has shown some tendencies to form two groups according to the drink flavor (orange and cola), but only cola presented a clear and complete separation. Using Kohonen maps, it was observed a tendency to form three flavor groups: (i) cola, (ii) orange and lemon, and (iii) guarana. However, this last tool proved to be more accurate in the groups' formation. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
24. Modelo híbrido de sistema tutor inteligente utilizando conhecimento do especialista e mapas de Kohonen com treinamento automatizado
- Author
-
Carvalho, Sirlon Diniz de, Flores, Edna Lúcia, Santos, Eliane Elias Ferreira dos, Teixeira, Ricardo Antonio Gonçalves, Furtado, Alzino Mendonça, and Melo, Francisco Ramos de
- Subjects
ITS based on neural networks ,Mapas de Kohonen ,Ensino a distância ,Redes SOM ,Inteligência artificial ,SOM ,Intelligent tutoring systems ,STI híbrido ,STI baseado em redes neurais ,STI ,ITS ,ENGENHARIAS::ENGENHARIA ELETRICA [CNPQ] ,Sistema tutor inteligente ,Hybrid ITS ,Self organizing maps ,Kohonen maps - Abstract
The contemporary education has a lot of challenges and among them is the adaptation of using new technologies with classical education paradigm. It hasn\'t been different with distance education. In this context, this work proposes to develop a hybrid tutoring system model with decisions based on the teachers knowledge and help from Self Organizing Maps (SOM) or Kohonen\'s Maps neural networks. The proposed system has a initial teaching method that is set by specialist teacher up and while system is being running this pedagogic method is refined by the neural networks, which use patterns extracted from students that has used the system. The model proposes the utilization of a basic neural network structure with automated training which is capable of train several networks and define the one which represents results that is more coherent with the pattern\'s set, dismissing the intervention of a specialist on the evaluation of the network training performance. The system has adaptive and reactive features related to the apprentice, being able to offer to the students a personalized and dynamic learning. The system was developed in a web environment aiming avail the advantages of this technology. At this work, besides the proposed model developing it also were performed a data gathering with fresh students from integrated learning technical of Federal Institution of Goiás, Luziânia, Goiás, Brazil, to evaluate system\'s applicability. This thesis presents the fundamentals theorists of the virtual education environment, as also the artificial neural networks SOM, used on proposed model. Likewise, it shows the system developing process, the automated training build, in addition with the system tutor structure. The knowledge\'s transmission is inspired in the content\'s didactic transposition, with organization didactic units in levels that aim develop distinct skills. The SOM networks analysis indicate that the automated train was able to train several networks and identify a network with best topologic order. Moreover, this work presents a comparison between students performance when submitted to learn using the system with purely specialized orientation and hybrid orientation. The outcomes of this evaluation points out the viability of the proposed model, since the system has shown to be able to learn from students and adapt the teacher learning method. The apprentices that studied utilizing the system had amplified theirs grades on the learning system evaluations and the hybrid tutor was capable of take decisions which magnify the acceptation of the tutor learning indication. A educação contemporânea tem muitos desafios, dentre eles o de adequar a utilização de novas tecnologias aos paradigmas clássicos de ensino. Com a educação a distância não tem sido diferente. Nesse contexto, este trabalho apresenta o processo de desenvolvimento de um sistema tutor inteligente híbrido com decisões baseadas no conhecimento do professor, subsidiadas pelas decisões das redes neurais Self Organizing Maps (SOM) ou Mapas de Kohonen. O sistema proposto tem a sua estratégia de ensino inicial estabelecida pelo professor especialista e à medida em que o sistema é utilizado a estratégia pedagógica é refinada pelas redes neurais, que utilizam padrões extraídos dos estudantes que usaram o tutor. O modelo propõe a utilização de uma estrutura de rede neural com treinamento automatizado que é capaz de treinar diferentes redes e definir a que apresente o resultado mais coerente com conjunto de padrões, dispensando a intervenção de um especialista na avaliação do desempenho das redes. O sistema tem característica adaptativa e reativa ao aprendiz, capaz de oferecer ao estudante um ensino personalizado e dinâmico. O sistema foi desenvolvido para ambiente web com o objetivo de obter vantagens que essa tecnologia oferece. Neste trabalho, além do desenvolvimento do modelo proposto também foram realizadas coletas de dados com alunos dos anos iniciais do ensino técnico integrado do Instituto Federal de Goiás Campus Luziânia para avaliar a aplicabilidade do sistema. A tese apresenta os fundamentos teóricos de ambientes virtuais de educação, bem como das redes neurais artificiais SOM, utilizadas no modelo proposto. Também é apresentado o processo de desenvolvimento do sistema, a construção do treinamento automatizado e a estruturação do sistema tutor. A transmissão de conhecimentos é inspirada na transposição didática de conteúdos, com unidades didáticas organizadas em níveis que tem como objetivo desenvolver diferentes competências. As análises das redes SOM indicaram que o treinamento automatizado foi capaz de treinar diversas redes e identificar a rede com melhor ordenação topológica. Também são apresentadas comparações entre os desempenhos dos estudantes quando submetidos a estudos nos sistemas com orientação puramente especialista e híbrido. Os resultados dessa avaliação indicam a viabilidade do modelo proposto, pois o sistema mostrou-se capaz de aprender com os estudantes e ajustar as estratégias de ensino do professor. Os aprendizes que estudaram no sistema ampliaram suas médias nas avaliações de aprendizado do sistema e o tutor híbrido foi capaz de tomar decisões que ampliaram a aceitação das indicações de estudos do tutor. Doutor em Ciências
- Published
- 2022
25. A SOMAgent for Identification of Semantic Classes and Word Disambiguation
- Author
-
López, Vivian F., Alonso, Luis, Moreno, María, Kacprzyk, Janusz, editor, Demazeau, Yves, editor, Pavón, Juan, editor, Corchado, Juan M., editor, and Bajo, Javier, editor
- Published
- 2009
- Full Text
- View/download PDF
26. Neural Networks (SOM) Applied to INAA Data of Chemical Elements in Archaeological Ceramics from Central Amazon.
- Author
-
Hazenfratz, R., Munita, C. S., and Neves, E. G.
- Subjects
- *
NEURAL computers , *CHEMICAL elements , *CERAMICS , *HOMOSCEDASTICITY , *DATA analysis - Abstract
Artificial neural networks represent an alternative to traditional multivariate techniques, such as principal component and discriminant analysis, which rely on hypotheses regarding the normal distribution of the data and homoscedasticity. They also may be a powerful tool for multivariate modeling of systems that do not present linear correlation between variables, as well as to visualize high-dimensional data in bi- or trivariate structures. One special kind of neural network of interest in archaeometric studies is the Self-Organizing Map (SOM). SOMs can be distinguished from other neural networks for preserving the topological features of the original multivariate space. In this study, the self-organizing maps were applied to concentration data of chemical elements measured in archaeological ceramics from Central Amazon using instrumental neutron activation analysis (INAA). The main objective was testing the chemical patterns previously identified using cluster and principal component analysis, forming groups of ceramics according the multivariate chemical composition. It was verified by statistical tests that the chemical elemental data was not normally distributed and did not present homogeneity of covariance matrices for different groups, as requested by principal component analysis and other multivariate techniques. The maps obtained were consistent with the patterns identified by cluster and principal component analysis, forming two chemical groups of pottery shards for each archaeological site tested. Finally, it was verified the potential of SOMs for testing if failures in underlying hypotheses of traditional multivariate techniques might be critically influencing the results and subsequent archaeological interpretation of archaeometric data. [ABSTRACT FROM AUTHOR]
- Published
- 2017
- Full Text
- View/download PDF
27. Consumer Profile Identification and Allocation
- Author
-
Letrémy, Patrick, Cottrell, Marie, Esposito, Eric, Laffite, Valérie, Showk, Sally, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Doug, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Sandoval, Francisco, editor, Prieto, Alberto, editor, Cabestany, Joan, editor, and Graña, Manuel, editor
- Published
- 2007
- Full Text
- View/download PDF
28. Unsupervised Case Memory Organization: Analysing Computational Time and Soft Computing Capabilities
- Author
-
Fornells, A., Golobardes, E., Vernet, D., Corral, G., Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Roth-Berghofer, Thomas R., editor, Göker, Mehmet H., editor, and Güvenir, H. Altay, editor
- Published
- 2006
- Full Text
- View/download PDF
29. Combining expert knowledge and machine-learning to classify herd types in livestock systems
- Author
-
Maria Guelbenzu-Gonzalo, David Graham, Simon J. More, Jonas Brock, Martin Lange, Jamie A. Tratalos, and Hans-Hermann Thulke
- Subjects
Knowledge management ,040301 veterinary sciences ,Computer science ,Classification and taxonomy ,animal diseases ,Science ,030231 tropical medicine ,Control (management) ,Cattle Diseases ,Article ,Self-organising maps (SOMs) ,Herd production type ,0403 veterinary science ,03 medical and health sciences ,0302 clinical medicine ,media_common.cataloged_instance ,European union ,Adaptation (computer science) ,Data mining ,Kohonen maps ,media_common ,Infections diseases ,Multidisciplinary ,business.industry ,Decision tree learning ,Animal disease ,04 agricultural and veterinary sciences ,Computational biology and bioinformatics ,Herd ,Medicine ,Cattle ,Livestock ,business - Abstract
A detailed understanding of herd types is needed for animal disease control and surveillance activities, to inform epidemiological study design and interpretation, and to guide effective policy decision-making. In this paper, we present a new approach to classify herd types in livestock systems by combining expert knowledge and a machine-learning algorithm called self-organising-maps (SOMs). This approach is applied to the cattle sector in Ireland, where a detailed understanding of herd types can assist with on-going discussions on control and surveillance for endemic cattle diseases. To our knowledge, this is the first time that the SOM algorithm has been used to differentiate livestock systems. In compliance with European Union (EU) requirements, relevant data in the Irish livestock register includes the birth, movements and disposal of each individual bovine, and also the sex and breed of each bovine and its dam. In total, 17 herd types were identified in Ireland using 9 variables. We provide a data-driven classification tree using decisions derived from the Irish livestock registration data. Because of the visual capabilities of the SOM algorithm, the interpretation of results is relatively straightforward and we believe our approach, with adaptation, can be used to classify herd type in any other livestock system. Department of Agriculture, Food and the Marine Projekt DEAL
- Published
- 2021
30. Classifying hedge funds with Kohonen maps: A first attempt
- Author
-
Maillet, Bertrand, Rousset, Patrick, Lesage, Cédric, editor, and Cottrell, Marie, editor
- Published
- 2003
- Full Text
- View/download PDF
31. Working times in atypical forms of employment: the special case of part-time work
- Author
-
Letremy, Patrick, Cottrell, Marie, Lesage, Cédric, editor, and Cottrell, Marie, editor
- Published
- 2003
- Full Text
- View/download PDF
32. Work and employment policies in French establishments in 1998 : A Kohonen Algorithm-Based Analysis
- Author
-
Lemiere, Séverine, Perraudin, Corinne, Petit, Héloïse, Lesage, Cédric, editor, and Cottrell, Marie, editor
- Published
- 2003
- Full Text
- View/download PDF
33. Forecasting Ozone Peaks Using Self-organizing Maps and Fuzzy Logic
- Author
-
Glorennec, Pierre-Yves and Sportisse, Bruno, editor
- Published
- 2002
- Full Text
- View/download PDF
34. Kohonen Maps
- Author
-
Sammut, Claude, editor and Webb, Geoffrey I., editor
- Published
- 2017
- Full Text
- View/download PDF
35. Создание частичного индексирования таблицы для оптимизации поисковых запросов
- Subjects
параллельное программирование ,поиск сложных структур ,распределенные вычисления ,parallel programming ,databases ,BigData ,базы данных ,partial indexing ,complex structure search ,distributed computing ,частичное индексирование ,кластеризация ,карты Кохонена ,clustering ,Kohonen maps - Abstract
В силу роста числа данных и роста разнообразия требований к их обработке, сейчас приходится отходить от обработки данных в момент запроса и все в большей мере перекладывать основную работу по его выполнению или выполнению основных его аспектов на заранее хранимые и подготовленные результаты. Во многом СУБД таким образом стараются решить проблемы производительности за счет увеличения расходов памяти, однако во многом необходимо задуматься уже об экономии последней, при этом желательно сохраняя результаты методов, основанных на подобном подходе – индексирование, хеширование, нейросетевые алгоритмы. В статье рассматривается метод повышения эффективности решения задач поиска для немалых таблиц. Предлагаемый метод основан на частичном индексировании, элементов, возле центров сближения и введения понятия метаданных для этих центров. Такая кластеризация с хранимыми метаданным для центров, около которых складываются очередные промежуточные узлы, позволяет снизить расходы памяти на индексацию, поскольку, во-первых, при таком подходе отсутствует необходимость вложенного индексирования, которые может привести к серьезным пространственным затратам. Во-вторых, такой подход может дать возможность использовать одно индексирование для разных комбинаций наличия столбцов в поисковом образе, не теряя при это большей части эффективности поиска при индексировании. Такое сочетание при правильном применении может позволить эффективно обрабатывать таблицы имеющие разные поисковые необходимости, по разным группам столбцов, для которых хранение индексации для каждого большого типа запроса или группы запросов может приводить закономерно к серьезным затратам на расход памяти а так же потерю производительности при работе с большими массивами памяти, которая тоже увеличивается далеко не линейно., Due to the growing number of data and the growing variety of requirements for their processing, now we have to move away from data processing at the time of the request and increasingly shift the main work on its implementation or the implementation of its main aspects to pre-stored and prepared results. In many ways, DBMS thus try to solve performance problems by increasing memory consumption, but in many ways, it is necessary to think about saving the latter, while preferably preserving the results of methods based on a similar approach – indexing, hashing, neural network algorithms. The article discusses a method for improving the efficiency of solving search problems for large tables. The proposed method is based on partial indexing of elements near convergence centers and the introduction of the concept of metadata for these centers. Such clustering with stored metadata for the centers, near which the next intermediate nodes are formed, allows you to reduce the memory costs for indexing, because, firstly, with this approach there is no need for nested indexing, which can lead to serious spatial costs. Secondly, such an approach can make it possible to use one indexing for different combinations of the presence of columns in the search image, without losing most of the search efficiency during indexing. Such a combination, if used correctly, can make it possible to efficiently process tables with different search needs, for different groups of columns, for which storing indexing for each large type of query or group of queries can naturally lead to serious memory consumption costs as well as loss of performance when working with large arrays of memory, which also increases far from linearly., Международный научный журнал "Современные информационные технологии и ИТ-образование", Выпуск 3 2022, Pages 558-565
- Published
- 2022
- Full Text
- View/download PDF
36. EEG Analysis for Assessment of Depth of Anaesthesia
- Author
-
Petersen, Jörg, Stockmanns, Gudrun, Nahm, Werner, Szczepaniak, Piotr S., editor, Lisboa, Paulo J. G., editor, and Kacprzyk, Janusz, editor
- Published
- 2000
- Full Text
- View/download PDF
37. Інтелектуальні підходи до організації видаленого контролю якості зберігання зернових продуктів
- Subjects
система ідентифікації умов ,зерно ,Kohonen Maps ,Energy Saving ,Grain ,Conditions Identification System ,енергозбереження ,карти Кохонена - Abstract
Cereals are an essential part of the diet of Homo sapiens. Since late Neolithic times, with the transition to sedentary farming, working with grain (growing, storing, processing, cooking food) has become a traditional type of professional human activity. As part of the accumulated historical experience, numerous technological processes have been developed and optimized for this type of activity. The relevant technologies evolved in close correlation with the changing conditions of life, literally under the pressure of Darwinian natural selection, because they were directly related to the survival of the Homo sapiens. Further development of grain-processing technologies remains invariably urgent today, as evidenced by the report [1] presented by the UN on the state of food security and nutrition in the world - with horrifying figures depicting the need and misery of the wide masses of the population of the planet. An important component of grain processing is the technology associated with the storage of grain products. Part of the stored grain products is used as seed stock for a new cycle of grain sales, the other - a significant part - for processing into food products. At the same time, new developed (optimized, improved) grain storage technologies must be safe, low-cost, maximally compatible with previously developed (available) equipment, and scalable to large volumes of stored material. Of course, the technology must ensure proper efficiency, an indicator of which should be a reduction in the percentage of grain product losses. In this regard, management methods used in the technological processes of grain products storage are substantially important, as well as methods of control over the current state of grain products for the correct organization of the technological processes. In particular, methods using elements of artificial intelligence are of high interest. Among them, neural networks are promising, especially those capable of learning "without a teacher" - Kohonen Maps (KK). Modified KK algorithm [2] implements reduced learning time[3], which is relevant in the implementation of adaptive procedures for processing the results of measurements of controlled parameters. The purpose of this paper is to consider the principles of using modified Kohonen maps to classify situations with applicability to remote quality control of grain products storage., Зернові - значна частина поживного раціону типу Homo sapiens. З часів пізнього неоліту, з переходом на осілe землеробство, робота із зерном (вирощування, зберігання, переробка, приготування харчових продуктів) стала традиційним видом професійної людської діяльності. В рамках накопиченого історичного досвіду, за цим видом діяльності було розроблено та оптимізовано численні технологічні процеси. Відповідні технології розвивалися у зв'язку зі зміною життєвих потреб, буквально під тиском Дарвінівського природного відбору, оскільки були безпосередньо пов'язані з виживанням виду Homo sapiens. Подальший розвиток технологій зернообробки залишається незмінно актуальним і донині, на підтвердження чого – доповідь [1], подана ООН, про стан продовольчої безпеки та харчування у світі – з жахливими цифрами, що зображують потребу та лиха широких народних мас населення планети. Важливою складовою зернообробки є технології, пов'язані із зберіганням зернопродуктів. Частина зернопродуктів, що зберігаються, використовується як насіннєвий фонд для нового циклу реалізації зернозабезпечення, інша – істотна – для переробки в харчові продукти. При цьому нові технології зернозберігання, що розробляються (оптимізуються, удосконалюються), повинні бути безпечними, маловитратними, максимально сумісними з розробленим раніше обладнанням, масштабованими на великі обсяги матеріалу, що зберігається. Зрозуміло, що технології повинні забезпечувати належну ефективність, показником чого має бути зниження відсотка втрат зернопродукту. У цьому відношенні суттєво важливі методи управління, які застосовуються в рамках технологічних процесів зберігання зернопродуктів, а також методи контролю за поточним станом зернопродуктів для коректної організації роботи технологічних процесів. Цікавими, зокрема, є методи з використанням елементів штучного інтелекту. У тому числі, перспективні нейронні мережі, особливо здатні до навчання «без вчителя» - карти Кохонена (КК). Модифікований алгоритм КК [2] реалізує скорочений час навчання [3], що є актуальним при реалізації адаптивних процедур обробки результатів вимірювань контрольованих параметрів. Мета цієї роботи – розгляд принципів використання модифікованих карт Кохонена для класифікації ситуацій стосовно дистанційного контролю якості зберігання зернових продуктів.  
- Published
- 2021
38. The Kohonen algorithm: A powerful tool for analysing and representing multidimensional quantitative and qualitative data
- Author
-
Cottrell, Marie, Rousset, Patrick, Goos, Gerhard, editor, Hartmanis, Juris, editor, van Leeuwen, Jan, editor, Mira, José, editor, Moreno-Díaz, Roberto, editor, and Cabestany, Joan, editor
- Published
- 1997
- Full Text
- View/download PDF
39. Zooplankton community of Bakreswar reservoir: Assessment and visualization of distribution pattern using self-organizing maps.
- Author
-
Banerjee, Arnab, Rakshit, Nabyendu, Chakrabarty, Moitreyee, Sinha, Swagata, Ghosh, Sinchan, and Ray, Santanu
- Subjects
SELF-organizing maps ,COMMUNITIES ,ARTIFICIAL neural networks ,ZOOPLANKTON ,DRINKING water - Abstract
Self-organizing maps, otherwise known as Kohonen -maps, are one form of unsupervised artificial neural networks that can produce two-dimensional plots from multidimensional data. This tool is especially useful in community pattern analyses and has been previously used in spatial pattern analysis with different perspectives. The present study aims to find zooplankton's community pattern in the Bakreswar reservoir ecosystem. Bakreswar reservoir is a freshwater ecosystem in the Birbhum district of West Bengal, India. The reservoir is primarily used to supply freshwater to the Bakreswar thermal power plant. However, the local villages around the reservoir depend on it for drinking water and fishing sustenance. The data used in this study was collected over two years from three different stations. Thus, in addition to describing the spatial pattern of community distribution of zooplankton groups, the temporal variation was also studied. It is observed in the study that the four major groups of zooplankton – Copepoda, Cladocera, Ostracoda, and Rotifera – react differently to the different environmental attributes. Primarily directed by the physical environmental factors, the effect of the chemical factors on the patterning is also evident from the study. Copepods are the dominant group in the system, closely followed by cladocerans and rotifers. But this observation changes at different stations and throughout the study period. The temperature profiles of the reservoir primarily direct the occurrence of ostracods and rotifers, whereas cladocerans and copepods are inclined more towards a chemical factor directive. Rotifers are dominant in the monsoon, whereas the post-monsoon and winter seasons show an increased presence of copepods and cladocerans. The overall observation that the reservoir's water quality is good, and the trophic structure is healthy is in accordance with previous studies as well. • Self-Organizing Map used to analyze Bakreswar reservoirs' zooplankton community. • Spatial and temporal variations in community structure were analyzed. • Community composition varies according to season and area of collection. • Ostracods and rotifers are dominant in summer and monsoon. • Copepods and cladocerans are dominant in post-monsoon and winter. • Important regulating factors are - D O , N PP , S RAD , pH, N IT.N , P HOS.P , T DS. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
40. APLICACIÓN DE MAPAS DE KOHONEN PARA LA PRIORIZACIÓN DE ZONAS DE MERCADO: UNA APROXIMACIÓN PRÁCTICA.
- Author
-
GÁMEZ ALBÁN, HAROL MAURICIO, OREJUELA CABRERA, JUAN PABLO, SALAS ACHIPIZ, OSCAR ANCIZAR, and BRAVO BASTIDAS, JUAN JOSÉ
- Abstract
This paper shows a methodology based on neural networks to prioritize some market areas with a business approach. In this research, we try to resolve the uncertainty that exists in most organizations around the priority of a market area. The research problem is supported by the lack of tools to estimate the priority of a market area and for the lack of an effective interface between logistics and marketing departments. To solve this situation we used a special neural network (Kohonen Maps). These maps are a type of neural network to facilitate the grouping of customers and they allow determining which the most are frequently affecting the previously established criteria dealing prioritization. Finally, three scenarios are propose to validate the behavior of neural networks to prioritize market areas. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF
41. Combination of counterpropagation artificial neural networks and antioxidant activities for comprehensive evaluation of associated-extraction efficiency of various cyclodextrins in the traditional Chinese formula Xue-Zhi-Ning.
- Author
-
Sun, Lili, Yang, Jianwen, Wang, Meng, Zhang, Huijie, Liu, Yanan, Ren, Xiaoliang, and Qi, Aidi
- Subjects
- *
NEURAL circuitry , *ANTIOXIDANT analysis , *CYCLODEXTRIN derivatives , *HIGH performance liquid chromatography , *DRUG bioavailability , *CHEMICAL stability - Abstract
Xue-Zhi-Ning (XZN) is a widely used traditional Chinese medicine formula to treat hyperlipidemia. Recently, cyclodextrins (CDs) have been extensively used to minimize problems relative to medicine bioavailability, such as low solubility and poor stability. The objective of this study was to determine the associated-extraction efficiency of various CDs in XZN. Three various type CDs were evaluated, including native CDs (α-CD, β-CD), hydrophilic CD derivatives (HP-β-CD and Me-β-CD), and ionic CD derivatives (SBE-β-CD and CM-β-CD). An ultra high-performance liquid chromatography (UHPLC) fingerprint was applied to determine the components in CD extracts and original aqueous extract (OAE). A counterpropagation artificial neural network (CP-ANN) was used to analyze the components in different extracts and compare the selective extraction of various CDs. Extraction efficiencies of the various CDs in terms of extracted components follow the ranking, ionic CD derivatives > hydrophilic CD derivatives > native CDs > OAE. Besides, different types of CDs have their own selective extraction and ionic CD derivatives present the strongest associated-extraction efficiency. Antioxidant potentials of various extracts were evaluated by determining the inhibition of spontaneous, H 2 O 2 -induced, CCl 4 -induced and Fe 2+ /ascorbic acid-induced lipid peroxidation (LPO) and analyzing the scavenging capacity for DPPH and hydroxyl radicals. The order of extraction efficiencies of the various CDs relative to antioxidant activities is as follows: SBE-β-CD > CM-β-CD > HP-β-CD > Me-β-CD > β-CD > α-CD. It can be demonstrated that all of the CDs studied increase the extraction efficiency and that ionic CD derivatives (SBE-β-CD and CM-β-CD) present the highest extraction capability in terms of amount extracted and antioxidant activities of extracts. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
42. COMPARISON OF SELECTED METHODS OF MULTI-PARAMETER DATA VISUALIZATION USED FOR CLASSIFICATION OF COALS.
- Author
-
JAMROZ, Dariusz and NIEDOBA, Tomasz
- Subjects
COAL ,DATA visualization ,MULTIDIMENSIONAL scaling ,PRINCIPAL components analysis ,COMPUTER interfaces - Abstract
Methods of multi-parameter data visualization through the transformation of multidimensional space into two-dimensional one allow to present multidimensional data on computer screen, thus making it possible to conduct a qualitative analysis of this data in the most natural way for human - by a sense of sight. In the paper a comparison was made to show the efficiency of selected seven methods of multidimensional visualization and further, to analyze data describing various coal type samples. Each of the methods was verified by checking how precisely a coal type can be classified when a given method is applied. For this purpose, a special criterion was designed to allow an evaluation of the results obtained by means of each of these methods. Detailed information included presentation of methods, elaborated algorithms, accepted parameters for best results as well the results. The framework for the comparison of the analyzed multi-parameter visualization methods includes: observational tunnels method multidimensional scaling MDS, principal component analysis PCA, relevance maps, autoassociative neural networks, Kohonen maps and parallel coordinates method. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
43. Metodos de classificação não-supervisionada de imagens de sensoriamento remoto usando mapas auto-organizaveis de Kohonen
- Author
-
Gonçalves, Marcio Leandro, Andrade Netto, Marcio Luiz de, 1947-2019, Costa, Jose Alfredo Ferreira, Peres, Sarajane Marques, Zullo Junior, Jurandir, Tozzi, Clésio Luis, Von Zuben, Fernando José, Universidade Estadual de Campinas. Faculdade de Engenharia Elétrica e de Computação, Programa de Pós-Graduação em Engenharia Elétrica, and UNIVERSIDADE ESTADUAL DE CAMPINAS
- Subjects
Artificial intelligence ,Processamento de imagens - Técnicas digitais ,Redes neurais (Computação) ,Sensoriamento remoto ,Inteligência artificial ,Remote sensing ,Mapas auto-organizáveis ,Digital image processing ,Neural networks ,Kohonen maps - Abstract
Orientadores: Marcio Luiz de Andrade Netto, Jose Alfredo Ferreira Costa Acompanha Anexo A: Midia com informações adicionais em CD-R Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação Resumo: Esta tese propõe novas metodologias de classificação não-supervisionada de imagens de sensoriamento remoto que particularmente exploram as características e propriedades do Mapa Auto-organizável de Kohonen (SOM - Self-Organizing Map). O ponto chave dos métodos de classificação propostos é realizar a análise de agrupamentos das imagens através do mapeamento produzido pelo SOM, ao invés de trabalhar diretamente com os padrões originais das cenas. Tal estratégia reduz significativamente a complexidade da análise dos dados, tornando possível a utilização de técnicas normalmente consideradas computacionalmente inviáveis para o processamento de imagens de sensoriamento remoto, como métodos de agrupamentos hierárquicos e índices de validação de agrupamentos. Diferentemente de outras abordagens, nas quais o SOM é utilizado como ferramenta de auxílio visual para a detecção de agrupamentos, nos métodos de classificação propostos, mecanismos para analisar de maneira automática o arranjo de neurônios de um SOM treinado são aplicados e aprimorados com o objetivo de encontrar as melhores partições para os conjuntos de dados das imagens. Baseando-se nas propriedades estatísticas do SOM, modificações nos cálculos de índices de validação agrupamentos são propostas com o objetivo de reduzir o custo computacional do processo de classificação das imagens. Técnicas de análise de textura em imagens são aplicadas para avaliar e filtrar amostras de treinamento e/ou protótipos do SOM que correspondem a regiões de transição entre classes de cobertura terrestre. Informações espaciais a respeito dos protótipos do SOM, além das informações de distância multiespectral, também são aplicadas em critérios de fusão de agrupamentos procurando facilitar a discriminação de classes de cobertura terrestre que apresentam alto grau de similaridade espectral. Resultados experimentais mostram que os métodos de classificação propostos apresentam vantagens significativas em relação às técnicas de classificação não-supervisionada mais freqüentemente utilizadas na área de sensoriamento remoto. Abstract: This thesis proposes new methods of unsupervised classification for remotely sensed images which particularly exploit the characteristics and properties of the Kohonen Self-Organizing Map (SOM). The key point is to execute the clustering process through a set of prototypes of SOM instead of analyzing directly the original patterns of the image. This strategy significantly reduces the complexity of data analysis, making it possible to use techniques that have not usually been considered computationally viable for processing remotely sensed images, such as hierarchical clustering methods and cluster validation indices. Unlike other approaches in which SOM is used as a visual tool for detection of clusters, the proposed classification methods automatically analyze the neurons grid of a trained SOM in order to find better partitions for data sets of images. Based on the statistical properties of the SOM, clustering validation indices calculated in a modified manner are proposed with the aim of reducing the computational cost of the classification process of images. Image texture analysis techniques are applied to evaluate and filter training samples and/or prototypes of the SOM that correspond to transition regions between land cover classes. Spatial information about the prototypes of the SOM, in addition to multiespectral distance information, are also incorporated in criteria for merging clusters with aim to facilitate the discrimination of land cover classes which have high spectral similarity. Experimental results show that the proposed classification methods present significant advantages when compared to unsupervised classification techniques frequently used in remote sensing. Doutorado Engenharia de Computação Doutor em Engenharia Elétrica
- Published
- 2021
44. ВИЗНАЧЕННЯ ТЕХНОЛОГІЧНИХ НІШ КОНСТРУКЦІЙ РІЗАЛЬНОГО ІНСТРУМЕНТУ З ВИКОРИСТАННЯМ МЕРЕЖІ КОХОНЕНА
- Subjects
кластеризація ,карти Кохонена ,різальний інструмент ,механічна обробка ,технологічна ніша ,clustering ,Kohonen maps ,cutting tool ,machining ,technological niche - Abstract
The variety of existing tool designs makes it possible to rationally use certain types of structures depending on specific technological conditions. Relevant selection of tool designs for each specific situation determines the efficiency of the machining process. When solving the problem of selecting existing and designing new cutting tools, it is necessary to process large amounts of multidimensional information and provide decision support at each stage of design and operation of the tool. For choice or design of the tool it is necessary to investigate the influence of technological parameters on the use of the particular construction. Actual scientific researches and issues analysis is devoted to works on search of new and existing technical solutions, determination of areas for their effective use. Adaptation and use of data clustering methods in the design and selection of the tool will allow to implement them more reasonably and with less time. The purpose of the article is to automate the determination of the zones of the most effective use of a specific tool design, i.e. the allocation of technological niches for cutters using data clustering methods. A technique for automating the search for technological niches for cutting tool designs using data clustering is presented. Kohonen maps were used for this self-organizing. An example of the choice of face mill cutter designs that are most effective for specific technological conditions is given. Analysis of multidimensional data on machining use cases was performed using the analytical platform Deductor Studio. In this work, for the first time, a general approach to solving the problem of forming technological niches to determine the areas of most efficient use of appropriate types of cutting structures, substantiation of sizes of housings and plates, as well as the creation of new constructions was presented. The obtained trained Kohonen map can be used to automate the search for technological niches., Ґрунтуючись на властивості карт Кохонена трансформувати багатовимірний простір у простір із нижчою розмірністю, у роботі вперше запропоновано загальний підхід до вирішення задачі формування технологічних ніш для визначення зон найбільш ефективного використання відповідних типів конструкції фрез. Це надає можливість релевантного вибору існуючих конструкцій, типорозмірів корпусів і пластин, а також обґрунтувати вимоги при створенні нових конструкцій. Отриману навчену карту Кохонена можна використовувати для автоматизації пошуку технологічних ніш різального інструменту.
- Published
- 2021
45. A cluster validity for optimal configuration of Kohonen maps in e-learning recommendation
- Author
-
Jamal Mawane, Abdelwahab Naji, and Mohamed Ramdani
- Subjects
Coefficient of variation ,Control and Optimization ,Cluster validity ,Computer Networks and Communications ,Hardware and Architecture ,Collaborative filtering ,Signal Processing ,Homogeneity ,Electrical and Electronic Engineering ,Recommendation systems ,Kohonen maps ,Information Systems - Abstract
This paper reviews the first block of our unsupervised deep collaborative recommendation (UDCF) system and proposes a platform whose goal is to try to find the adequate parameters of the Kohonen maps, to create homogeneous clusters in profile data and results, the homogeneity is verified thanks to the very low variance rate of the results obtained by the cluster population and a second criterion which is the high prediction rate of collaborative recommendation. Although the revision concerns only the clustering block, and the use of a symmetrical autoencoder without searching for its optimization, the result obtained (82.33%) for the optimal configurations with high homogeneity of the Kohonen map is equivalent to the optimized result of the UDCF and even better than the classical recommendation methods.
- Published
- 2022
46. Application of Multidimensional Data Visualization by Means of Self-Organizing Kohonen Maps to Evaluate Classification Possibilities of Various Coal Types / Zastosowanie Wizualizacji Wielowymiarowych Danych Za Pomocą Sieci Kohonena Do Oceny Możliwości Klasyfikacji Różnych Typów Węgla
- Author
-
Jamróz, Dariusz and Niedoba, Tomasz
- Subjects
SELF-organizing maps ,METALLURGICAL analysis ,COAL ,MULTIDIMENSIONAL databases ,DATA visualization - Abstract
Copyright of Archives of Mining Sciences is the property of Polish Academy of Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2015
- Full Text
- View/download PDF
47. How to improve robustness in Kohonen maps and display additional information in Factorial Analysis: Application to text mining.
- Author
-
Bourgeois, Nicolas, Cottrell, Marie, Déruelle, Benjamin, Lamassé, Stéphane, and Letrémy, Patrick
- Subjects
- *
ROBUST control , *SELF-organizing maps , *INFORMATION processing , *FACTOR analysis , *TEXT mining - Abstract
This article is an extended version of a paper presented in the WSOM׳2012 conference (Bourgeois et al., 2012 [1] ). We display a combination of factorial projections, SOM algorithm and graph techniques applied to a text mining problem. The corpus contains eight medieval manuscripts which were used to teach arithmetic techniques to merchants. Among the techniques for Data Analysis, those used for Lexicometry (such as Factorial Analysis) highlight the discrepancies between manuscripts. The reason for this is that they focus on the deviation from the independence between words and manuscripts. Still, we also want to discover and characterize the common vocabulary among the whole corpus. Using the properties of stochastic Kohonen maps, which define neighborhood between inputs in a non-deterministic way, we highlight the words which seem to play a special role in the vocabulary. We call them fickle and use them to improve both Kohonen map robustness and significance of FCA visualization. Finally we use graph algorithmic to exploit this fickleness for classification of words. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
48. Analysis of RegCM3 generated weather regimes over central Brazil: a case study in Distrito Federal.
- Author
-
Anunciação, Yumiko, Rocha, Rosmeri, and Walde, Detlef
- Subjects
SELF-organizing maps ,METEOROLOGICAL research ,ATMOSPHERIC circulation ,ATMOSPHERIC models ,METEOROLOGICAL precipitation - Abstract
Low level atmospheric circulations downscaled by regional climate model are used to identify austral summer (December-January-February) weather regimes (WRs) over central Brazil. For the period 1989-2006, the Kohonen's self-organizing maps method is applied to provide simulated weather patterns and their relationship with daily rainfall. Six WRs were defined: two related to the active phase of the South American monsoon system (SAMS), with the large occurrence of days with extreme rainfall; two related to the break phase and few occurrences of extreme rainfall; and two others resembling transient WRs, those with fewer extreme rainfall. The WRs formed a cycle obtained from their transition probabilities, which suggests alternating phases of the convergence zone and their association with extreme rainfall. Thus, the variability of summer precipitation, related to the behavior of the simulated WRs enables the verification of the regional dynamic model on intraseasonal time scale. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
49. Comparison of criteria used to access carcinogenicity in CPANN QSAR models versus the knowledge-based expert system Toxtree.
- Author
-
Fjodorova, N. and Novi?, M.
- Subjects
- *
QSAR models , *EXPERT systems , *ARTIFICIAL neural networks , *CARCINOGENESIS , *SELF-organizing maps - Abstract
The primary goal of this study was to describe and compare the criteria used to assess carcinogenic activity. The statistically-based predictive quantitative structure–activity relationship (QSAR) models based on the counter propagation artificial neural network (CPANN) algorithm, and knowledge-based expert systems based on a decision tree structural alert (SA) approach (Toxtree application), were considered. The integration of the QSAR (CPANN models) and SAR (Toxtree SA application) approach contributed to the mechanistic understanding of the QSAR model considered. The mapping technique inherent to CPANN Kohonen enables us to relate the similarities or dissimilarities within a congeneric set of chemicals with particular SAs for carcinogenicity. The focus of our investigations was the similarities and dissimilarities of the features used in the QSAR and SAR methods. Due to the complexity of the carcinogenic endpoint, the integration of different approaches allows the models to be improved and provides a valuable technique for evaluating the safety of chemicals. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
50. Conducción autónoma con el uso de imágenes sintetizadas con Redes Generativas Adversarias
- Author
-
González González, David, Universidad Carlos III de Madrid. Departamento de Informática, and Alonso Weber, Juan Manuel
- Subjects
Informática ,Generative Adversarial Networks ,Mapas de Kohonen ,Redes Generativas Adversarias ,Conducción autónoma ,Autonomous driving ,Redes neuronales ,Neural networks ,Kohonen maps - Abstract
La conducción autónoma es uno de los temas en los que ha habido más investigación en los últimos años ya que llegar a conseguir un vehículo totalmente autónomo sería un gran avance para cualquier sociedad. Uno de los problemas de este campo de investigación es que generar nuevos agentes de conducción autónoma es lento y tedioso, impidiendo un desarrollo rápido. En este trabajo se propone un nuevo enfoque que intenta paliar este problema y que consiste en la utilización de imágenes realistas sintetizadas con Redes Generativas Adversarias para entrenar agentes de conducción autónoma que sean potencialmente aplicables en entornos reales. Siguiendo este enfoque, no solo se podrían generar imágenes sintéticas en entornos variados realistas, sino que también se podrían obtener imágenes realistas etiquetadas. Esto es posible ya que, como las imágenes sintéticas se generan a partir de un simulador, se pueden obtener de este las etiquetas como si de un vehículo real se tratara, pero de una forma mucho más flexible y rápida. Para desarrollar el sistema, se toma como base el simulador SDSandbox y se aplican una serie de modificaciones entre las cuales destaca la generación de circuitos aleatorios con mapas de Kohonen. Para producir las imágenes realistas se hace una extensa experimentación visitando las arquitecturas que conforman el estado del arte y utilizando conjuntos de datos tanto creados de forma artesanal como mundialmente conocidos. El objetivo de esta experimentación es obtener un modelo multimodal capaz de generar carreteras naturales nocturnas, de tarde y de día. Para comprobar que las imágenes generadas son realistas se hace una encuesta que implica a individuos reales, llegando a la conclusión de que las imágenes son lo suficientemente reales como para ser utilizadas para el entrenamiento de agentes de conducción autónoma. Finalmente, se crea un agente de conducción autónoma que utiliza como única entrada las imágenes producidas por las Redes Generativas Adversarias, añadiendo las líneas de la carretera. Autonomous driving is one of the subjects on which there has been more research in recent years, as achieving a totally autonomous vehicle would be a great advance for any society. One of the problems in this field of research is that generating new autonomous driving agents is slow and tedious, preventing the rapid development of autonomous driving. This paper proposes a new approach that tries to alleviate this problem and that consists in the use of synthetic realistic images with adversarial generative networks to train autonomous driving agents that are potentially applicable in real environments. Following this approach, not only could synthetic images be generated in various realistic environments, but also labelled realistic images could be obtained. This would be possible because, as the synthetic images are generated from a simulator, the labels could be obtained from it as if it was a real vehicle. To develop the system, the simulator SDSandbox is taken as a basis and a series of modifications are applied among which the generation of random circuits with Kohonen maps stands out. In order to produce the realistic images, extensive experimentation is performed by visiting the architectures that make up the state of the art and using both handmade and world-famous data sets. The objective of this experimentation is to create a multimodal model capable of generating natural roads at night, in the evening and during the day. In order to verify that the images generated are realistic, a survey is made involving real individuals, reaching the conclusion that the images are real enough to be used for the training of autonomous driving agents. Finally, an autonomous driving agent is created that uses as the only input the images produced by the generative adversarial networks, including the road lines. Ingenieria Informática
- Published
- 2020
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.