Search

The process of partitioning into different objects of an image is segmentation. In different major fields like face tracking, Satellite, Object Identification, Remote Sensing and majorly in medical field segmentation process is very important to find the different objects in the image. To investigate the functions and processes of human boy in radiology magnetic resonance imaging (MRI) will be used. MRI technique is using in many hospitals for the diagnosis purpose widely in finding the stage of a particular disease. In this paper, we proposed a new method for detecting the tumor with enhanced performance over traditional techniques such as K-Means Clustering, fuzzy c means (FCM). Different research methods have been proposed by researchers to detect the tumor in brain. To classify normal and abnormal form of brain, a system for screening is discussed in this paper which is developed with a framework of artificial intelligence with deep learning probabilistic neural networks by focusing on hybrid clustering for segmentation on brain image and crystal contrast enhancement. Feature's extraction and classification are included in the developing process. Performance in Simulation of proposed design has shown the superior results than the traditional methods. [ABSTRACT FROM AUTHOR]

This document is a call for a new era of artificial intelligence (AI) in the connected world, specifically focusing on the field of Web Intelligence (WI). WI has evolved over the past 20 years, with three significant stages: WI 1.0 (Wisdom Web), WI 2.0 (Wisdom Web of Thing), and WI 3.0 (Wisdom Web of Everything). The document highlights several papers published in the Web Intelligence journal that explore different aspects of WI, including its impact on a better connected world, cross-cutting areas with brain informatics, biases in recommender systems, the influence of ChatGPT on information retrieval, the role of big data in the retail industry, order pairing mechanisms in real-time ride-sharing, data replication in cloud systems, and security risks in IoT-fog architecture. The document calls for more collaboration and communication among researchers in the WI field and emphasizes the importance of global interactions for co-intelligence and co-creation. [Extracted from the article]

With the continuous development of artificial intelligence research, computer vision research has shifted from traditional "feature engineering"-based methods to deep learning-based "network engineering" methods, which automatically extracts and classifies features by using deep neural networks. Traditional methods based on artificial design features are computationally expensive and are usually used to solve simple research problems, which is not conducive for large-scale data feature extraction. Deep learning-based methods greatly reduce the difficulty of artificial features by learning features from large-scale data and are successfully applied in many visual recognition tasks. Video action recognition methods also shift from traditional methods based on artificial design features to deep learning-based methods, which is oriented to building more effective deep neural network models. Through collecting and sorting related research results found that academic for timing segment network of football and basketball video action research is relatively rich, but lack of badminton research given the above research results, this study based on timing segment network of badminton video action identification can enrich the research results, provide reference for follow-up research. This paper introduces the lightweight attention mechanism into the temporal segmentation network, forming the attention mechanism-timing segmentation network, and trains the neural network to get the classifier of badminton stroke action, which can be predicted as four common types: forehand stroke, backhand stroke, overhead stroke and pick ball. The experimental results show that the recognition recall and accuracy of various stroke movements reach more than 86%, and the average size of recall and accuracy is 91.2% and 91.6% respectively, indicating that the method based on timing segmentation network can be close to the human judgment level and can effectively conduct the identification task of badminton video strokes. [ABSTRACT FROM AUTHOR]

In this paper, 1,538 papers retrieved with the keywords "sports artificial intelligence (AI)" on the Web of Science database since 2007 were taken as the data source, and the Cite Space V software was used to visualize and analyze them. A visual knowledge graph was used to streamline the countries, institutions and authors conducting sports AI research, discipline distribution, research hotspots and development trends in the past 15 years. Subsequently, its development direction and research progress were discussed. Sports AI was widely distributed, with the US, China and the UK leading the way. The most prolific authors and teams in research on sports AI were concentrated in American universities. Their main research direction is to develop and improve smart wearable devices based on machine learning and deep learning technologies for different groups of people. Research on sports AI involved multiple disciplines, which mainly applied and referred to research methodologies and theories on engineering, computer science and sports science. It could be seen from the frequency and centrality of keywords that in the current field of sports AI, machine learning is the main direction, artificial neural networks is the main algorithm, and practical and empirical research based on data mining is the focus. The research hotspots were divided into three major clusters: physical health promotion, sports injury prevention and control, and athletic performance enhancement. How to introduce intelligent technology into sports for a perfect integration still has an arduous and long way to go. Future development requires joint efforts and participation of scientific researchers, professionals and common people. [ABSTRACT FROM AUTHOR]

The case-based reasoning method has a high potential for solving tasks of intelligence decision-support. To implement it, it is necessary to solve the problem of comparing situations and selecting the one that is most similar to the current situation in the knowledge base. The problem arises in the case of heterogeneous objects and situations with many different types of parameters and their possible uncertainty. In this paper, an approach based on machine (deep) learning is investigated for this task. It is proposed to carry out the process of selecting situations and solutions from the knowledge base in two stages: recognition of the states of the elements of a complex object and the relationships between them, then the formation of a representation of the situation in the state space and its use for comparing situations using neural networks. An ensemble neural network model based on a multi-layer network is proposed. It successfully simulates the cognitive functions of a human (expert), correctly selects similar situations and ranks them according to the similarity parameter. Proposed neural network models provide the implementation of a hybrid-CBR approach for decision-making on complex objects. [ABSTRACT FROM AUTHOR]

Smart city has come a long way since the development of emerging technology like Information and communications technology (ICT), Internet of Things (IoT), Machine Learning (ML), Block chain and Artificial Intelligence. The Intelligent Transportation System (ITS) is an important application in a rapidly growing smart city. Prediction of the automotive accident severity plays a very crucial role in the smart transportation system. The main motive behind this research is to determine the specific features which could affect vehicle accident severity. In this paper, some of the classification models, specifically Logistic Regression, Artificial Neural network, Decision Tree, K-Nearest Neighbors, and Random Forest have been implemented for predicting the accident severity. All the models have been verified, and the experimental results prove that these classification models have attained considerable accuracy. The paper also explained a secure communication architecture model for secure information exchange among all the components associated with the ITS. Finally paper implemented web base Message alert system which will be used for alert the users through smart IoT devices. [ABSTRACT FROM AUTHOR]

As the stability of surrounding rock of coal roadway is affected by many factors, which makes the classification result hard to be consistent with the field practice. To solve the above problems, this paper proposes a method for the classification of stability of rock which is present in roadway of coal using the artificial intelligence algorithm. In this paper, the influencing factors of stability of rock which is present in roadway are analyzed, and seven influential factors are selected as classification indexes. To solve the problem of slow convergence speed and easy to fall into the local minimum of the back propagation artificial neural network (BP-ANN), an improved BP-ANN algorithm based on additional momentum and Levenberg-Marquardt optimization is proposed based on the analysis of the existing improved methods, which improves the convergence speed and avoids the local minimum effectively. Based on the learning model available, classification system based on fuzzy rule have been implemented and yielded better behavior in the situation of uncertain data sets. Finally, the stability classification model of surrounding rocks of coal roadway using BP-ANN was established in MATLAB environment, and the model was applied to 13 data samples of coal roadway for testing, with the identification rate of 92.3%. The experimental results verify that the method proposed based on fuzzy rule classification system in this paper has a high accuracy of type identification and is applicable to the stability classification of surrounding rock in the coal roadway. [ABSTRACT FROM AUTHOR]

Learning performance evaluation is an important part of computer English teaching. Through evaluation, students can understand whether they have reached the learning goals of a lesson, and what are their shortcomings, so that they can continuously improve and improve themselves against these shortcomings. Combining actual needs, based on neural network and artificial intelligence technology, this paper constructs a computer English learning performance evaluation model based on machine learning. The computer English learning performance evaluation system in this paper is constructed on the basis of auditory characteristics and introduces a wavelet entropy feature based on the best tree wavelet packet decomposition, and it is applied to the establishment of an adaptive model. Moreover, this paper uses controlled experiments to analyze the model performance and combines mathematical statistics to visually display the model effect. From the research results, it can be seen that the performance of the model constructed in this paper basically meets the expected requirements and actual needs. [ABSTRACT FROM AUTHOR]

Anomaly-based detection is coupled with recognizing the uncommon, to catch the unusual activity, and to find the strange action behind that activity. Anomaly-based detection has a wide scope of critical applications, from bank application security to regular sciences to medical systems to marketing apps. Anomaly-based detection adopted by various Machine Learning techniques is really a type of system that consists of artificial intelligence. With the ever-expanding volume and new sorts of information, for example, sensor information from an incontestably enormous amount of IoT devices and from network flow data from cloud computing, it is implicitly understood without surprise that there is a developing enthusiasm for having the option to deal with more conclusions automatically by means of AI and ML applications. But with respect to anomaly detection, many applications of the scheme are simply the passion for detection. In this paper, Machine Learning (ML) techniques, namely the SVM, Isolation forest classifiers experimented and with reference to Deep Learning (DL) techniques, the proposed DA-LSTM (Deep Auto-Encoder LSTM) model are adopted for preprocessing of log data and anomaly-based detection to get better performance measures of detection. An enhanced LSTM (long-short-term memory) model, optimizing for the suitable parameter using a genetic algorithm (GA), is utilized to recognize better the anomaly from the log data that is filtered, adopting a Deep Auto-Encoder (DA). The Deep Neural network models are utilized to change over unstructured log information to training ready features, which are reasonable for log classification in detecting anomalies. These models are assessed, utilizing two benchmark datasets, the Openstack logs, and CIDDS-001 intrusion detection OpenStack server dataset. The outcomes acquired show that the DA-LSTM model performs better than other notable ML techniques. We further investigated the performance metrics of the ML and DL models through the well-known indicator measurements, specifically, the F-measure, Accuracy, Recall, and Precision. The exploratory conclusion shows that the Isolation Forest, and Support vector machine classifiers perform roughly 81%and 79%accuracy with respect to the performance metrics measurement on the CIDDS-001 OpenStack server dataset while the proposed DA-LSTM classifier performs around 99.1%of improved accuracy than the familiar ML algorithms. Further, the DA-LSTM outcomes on the OpenStack log data-sets show better anomaly detection compared with other notable machine learning models. [ABSTRACT FROM AUTHOR]

Automotive aftermarket industry is possessed of a wide product portfolio range which is in the 4th rank by its worldwide trade volume. The demand characteristic of automotive aftermarket parts is volatile and uncertain. Nevertheless, the cause-and-effect relationship of automotive aftermarket industry has not been defined obviously heretofore. These conditions bring automotive aftermarket sales forecasting into a challenging process. This paper is composed to determine the relevant external factors for automotive aftermarket sales based on expert reviews and to propose a sales forecasting model for automotive aftermarket industry. Since computational intelligence techniques yield a framework to focus on predictive analytics and prescriptive analytics, an artificial neural network model constructed for Turkey automotive aftermarket industry. Artificial intelligence is a subset of computational intelligence that focused on problems which have complex and nonlinear relationships. The data which have complex and nonlinear relationships could be modelled successfully even though incomplete data in case of implementation of appropriate model. The proposed ANN model for sales forecast is compared with multiple linear regression and revealed a higher prediction performance. [ABSTRACT FROM AUTHOR]

Using Context-Awareness information in human-robot shared environments enhances the characterization of the interaction scenario, improving the experience of human collaboration with the robot. Aspects such as environmental location and human-robot dialog have traditionally been used to infer the current situation, which can be helpful in the decision making process of any robot. However, the acoustic signals available in every interaction scenario are commonly obviated, thus removing an important source of information. This paper presents the design, development and tests of a Context Awareness Component that labels users' activities using localization information, dialog flow, and time of day, and adds an environment recognition component supported by acoustic signals that improves the inference system. To this end, this research proposes a feedforward neural network solution based on a multilayer perceptron approach. The paper also discusses the configuration of the neural network for optimizing the recognition of human activity in "at home" environments, using the four inputs previously mentioned. Finally, the validation of the approach proposed is done by comparing the results when the sound recognition system is used and when it is not. [ABSTRACT FROM AUTHOR]

As we know, AI is deeply integrated with all walks of life. While upgrading traditional products and transforming traditional industries, a large number of new products, new industries and new formats have emerged in large numbers, and new industrial space has been further expanded. The potential for steady economic growth remains huge. However, the influence of merelygrowing capital asset and labor force dimension in terms of boosting economic progress has been waning globally. Considering the China's data panel data outlying areas during 1978–2017 as the research sample, possible economic growing rate of Chinahas been calculated in detail according to the labor-intensive structural time-varying elastic model. It shows a U-shaped development track during 2018–2027, with an average growth rate between 5.00%and 6.00%. There are also great variances in the probable economy growing rates in different regions in China. It shows that relying solely on traditional factors of production to drive potential economic growth, China has been unable to maintain the prosperity of stable development over the past few decades. Based on the experience of typical representative countries, this paper also puts forward some relevant countermeasures and suggestions including focusing on a new round of technological revolutions such as big data, new generation AI, 5 G, IOT, cloud computing, robotics, and blockchain to progress economical growing rate of China in the future. [ABSTRACT FROM AUTHOR]

Curriculum is the basis of vocational training, its development level and teaching efficiency determine the realization of vocational training objectives, as well as the quality and level of major vocational academic training. Therefore, the development of curriculum is an important issue. And affect the school's teaching capacity building. The analysis of the latest developments in the main courses shows that there are some deviations or irrationalities in the curriculum in some colleges and universities, and the general problems of understanding the latest courses, such as lack of solid foundation in curriculum setting, unclear direction of objectives, unclear reform ideas, inadequate and systematic construction measures, lack of attention to the quality of education. This paper explains the rules for the establishment of first-level courses, clarifies the ideas and priorities of architecture, and explores strategies for building university-level courses using knowledge of artificial intelligence and neural network algorithms in order to gain experience from them. [ABSTRACT FROM AUTHOR]

Maintaining large collection of documents is an important problem in many areas of science and industry. Different analysis can be performed on large document collection with ease only if a short or reduced description can be obtained. Topic modeling offers a promising solution for this. Topic modeling is a method that learns about hidden themes from a large set of unorganized documents. Different approaches and alternatives are available for finding topics, such as Latent Dirichlet Allocation (LDA), neural networks, Latent Semantic Analysis (LSA), probabilistic LSA (pLSA), probabilistic LDA (pLDA). In topic models the topics inferred are based only on observing the term occurrence. However, the terms may not be semantically related in a manner that is relevant to the topic. Understanding the semantics can yield improved topics for representing the documents. The objective of this paper is to develop a semantically oriented probabilistic model based approach for generating topic representation from the document collection. From the modified topic model, we generate 2 matrices- a document-topic and a term-topic matrix. The reduced document-term matrix derived from these two matrices has 85% similarity with the original document-term matrix i.e. we get 85% similarity between the original document collection and the documents reconstructed from the above two matrices. Also, a classifier when applied to the document-topic matrix appended with the class label, shows an 80% improvement in F-measure score. The paper also uses the perplexity metric to find out the number of topics for a test set. [ABSTRACT FROM AUTHOR]

In this paper, we present a new algorithm for learning evaluation functions of the game of Go. Recently AlphaGo Zero and AlphaZero have shown that accurate evaluation functions can be constructed by using deep neural networks. Such a training, however, requires an enormous amount of computational resources that are not available for most researchers. One of the next challenges in this domain is constructing accurate evaluation functions with lesser computational resources. To tackle this problem, we apply the RankNet algorithm to training an AlphaGo Zero style unified Policy and Value network in a learning-to-rank fashion. Using the pairwise RankNet training increases the potential number of training examples and alleviates the requirements for the number of game records. Our modified RankNet algorithm trains both value and policy losses and its joint training makes the learning stable. Experimental results showed that neural networks trained by our algorithm showed higher playing strength than other methods, especially when the dataset sizes were relatively limited. [ABSTRACT FROM AUTHOR]

For the artificial intelligence (AI) to effectively mimic humans, understanding humans, more specifically, human emotion is important. Sentiment analysis aims to automatically uncover the underlying sentiment or emotions that humans hold towards an entity. There is high ambiguity of emotion in text data. In this paper, we consider the sentence-level sentiment classification task, and propose a novel type of convolutional neural network combined with fuzzy logic called the Fuzzy Convolutional Neural Network (FCNN) and its associated learning algorithm. The new model is an integration of modified Convolutional Neural Network (CNN) in the fuzzy logic domain. The proposed model benefits from the use of fuzzy membership degrees to produce more refined outputs, thereby reducing the ambiguities in emotional aspects of sentiment classification. Also it benefits from extracting high-level emotional features due to convolutional neural representation. We compare the performance of our proposed approach with conventional CNN for sentiment classification. The experimental results indicate that the proposed FCNN outperforms the conventional methods for sentiment classification task. [ABSTRACT FROM AUTHOR]

The traditional fault detection system of complex electronic equipment based on image analysis theory only analyzes the image characteristics of complex electronic equipment for artificial intelligent fault diagnosis. It cannot deal with the system diagnosis problem of qualitative fault data and has the problems of low accuracy and long time consuming of fault detection. To address these problems, an artificial intelligent fault diagnosis system of complex electronic equipment based on BP neural network is designed in this paper. BP neural network model for artificial intelligent fault diagnosis of complex electronic equipment is built based on system overall structure. The structure of BP neural network and learning algorithm is determined according to the actual fault problem. Learning and training of BP neural network are carried out by using sample data of fault. Artificial intelligent fault diagnosis algorithm of complex electronic equipment based on BP neural network and qualitative fault data is used, which combines the BP neural network and qualitative fault data. The preprocessing method is applied to quantify the fault data. Fault diagnosis is achieved by BP neural network technology. The system database and the implementation process of the BP neural network are designed. Experimental results show that the designed system can significantly improve the accuracy of fault detection of complex electronic equipment, improve the effect of fault detection, and reduce the time consuming of fault detection. [ABSTRACT FROM AUTHOR]

Identifying the number of niches in multimodal optimization is vital to enhancement of efficiency of algorithms. This paper presents a genetic algorithm (GA)-based clustering method for multiple optimal determinations. The approach uses self-organizing map (SOM) neural networks to detect clusters in GA population. After clustering all population and recognizing the number of niches, the phenotypic space is partitioned. Within each partition, a simple GA is independently running to evolve to the actual optima. Before the SOM starts, we allow GA to run several generations until the borders of clusters are identified. Our proposed algorithm is easy to implement, and does not require any prior knowledge about the fitness function. The algorithm was tested for seven multimodal functions and four constrained engineering optimization functions, and the results have been compared with the other related algorithms based on three performance criteria. We found that the present algorithm has acceptable diversification and function evaluation number. [ABSTRACT FROM AUTHOR]

In this paper, the prediction of damage results for complex network is considered under grey information attack. Firstly, in order to construct more realistic networks, a new algorithm is proposed to generate 3 types of fully connected networks (normal scale-free network, scale-free network with cutoff, random network). Secondly, robustness of the 3 networks is analyzed under grey information attack. And then, a new method is proposed to predict the damage results by training the BP neural network. Thirdly, the effects of different topological parameters on the damage results are analyzed and a new method is proposed to find central nodes of the network. Finally, the damage results of a real bus network under grey information attack are predicted by the proposed method and several suggestions are given to help protect the real bus network. [ABSTRACT FROM AUTHOR]

The optimization of deburring process with fluid-impact to automobile main cylinder cross hole is studied in this paper to achieve higher processing quality and processing efficiency, so as to enable a system to automatically adapt to the change of processing state and not affect the processing quality due to the change of processing status. The improved fuzzy RBF expert system is used to optimize the processing parameters intelligently. Training and reasoning are done with fuzzy RBF neural network and double object optimization is done with particle swarm optimization based on flow dispersion and processing efficiency. A method of orthogonal combination is proposed in the number of hidden bodes in inference layer of fuzzy RBF neural network and their combination modes. Compared with the method of forming hidden nodes by combining the whole fuzzy layer, this method greatly reduces the amount of calculation and has obvious effect in solving complex problems. Experiment has been done on different processing programs, which shows that the processing quality has been greatly improved with the optimized process, the processing quality is obviously higher than that in the national standard, and the process level has been further improved. [ABSTRACT FROM AUTHOR]

Gradient descent is prevalent for large scale optimization problems in machine learning, especially its major role is computing and correcting the connection strength of neural network in deep learning. However, choosing a proper learning rate for SGD can be difficult. A too small rate may lead to painfully slow convergence, while too large one would hinder convergence. In this paper, we present a novel variance reduction technique which applies the moving average of gradient termed SMVRG. SMVRG can take a large learning rate by using variance reduction technique. And, we only need to preserve current gradient and the previous average gradient. Our method is employed to Long Short-Term Memory (LSTM). The experiment on two data sets, the IMDB (movie reviews) and SemEval-2016 (sentiment analysis in twitter) shows our method can improve the results significantly. [ABSTRACT FROM AUTHOR]

Atmospheric discharges offer great risks to the population and activities that involve different systems such as telecommunications, energy distribution and transportation. Lightning prediction can contribute to minimize the risks of this natural phenomenon. Therefore the present paper presents a model for lightning prediction based on satellite atmospheric sounding data, calibrated and validated with lightning data in an Amazon region particular area through an investigation that considered five period cases for validation of lightning prediction: case 1 (one hour), case 2 (two hours), case 3 (three hours), case 4 (four hours) and case 5 (five hours). The machine learning technique used to predict lightning was the Artificial Neural Network (ANN) trained with Levenberg-Marquardt backpropagation algorithm to classify modeling related to lightning prediction. This classification relied on the possibility of lightning prediction from the vertical profile of air temperature obtained from satellite NOAA-19. Results show that ANN was capable of identifying adequately the class to which a new event belongs to in relation to categories of occurrence and absence of lightning with better performance than traditional methodologies. [ABSTRACT FROM AUTHOR]

Lately, a lot of research has been conducted on the automatic design of artificial neural networks (ADANNs) using evolutionary algorithms, in the so-called neuro-evolutive algorithms (NEAs). Many of the presented proposals are not biologically inspired and are not able to generate modular, hierarchical and recurrent neural structures [25, 28, 26], such as those often found in living beings capable of solving intricate survival problems. Bearing in mind the idea that a nervous system's design and organization is a constructive process carried out by genetic information encoded in DNA, this paper proposes a biologically inspired NEA that evolves ANNs using these ideas as computational design techniques. In order to do this, we propose a Lindenmayer System with memory that implements the principles of organization, modularity, repetition (multiple use of the same sub-structure), hierarchy (recursive composition of sub-structures), minimizing the scalability problem of other methods. In our method, the basic neural codification is integrated to a Genetic Algorithm (GA) that implements the constructive approach found in the evolutionary process, making it closest to biological processes. Thus, the proposed method, is a Decision-Making (DM) process, capable to evolve ANNs architectures with optimal number of neurons and appropriate topology for any given problem. Our method was initially tested on a simple, but non-trivial, XOR problem. We also submit our method to two other problems of increasing complexity: time series prediction that represents consumer price index and prediction of the effect of a new drug on breast cancer. In most cases, our NEA outperformed the other methods, delivering the most accurate classification. These superior results are attributed to the improved effectiveness and efficiency of NEA in the decision-making process. The result is an optimized neural network architecture for solving classification problems. [ABSTRACT FROM AUTHOR]

This paper presents a proof of concept of a neural network Trojan. The neural network Trojan consists of a neural network that has been trained with a compromised dataset and modified code. The Trojan implementation is carried out by insertion of a malicious payload encoded into the weights alongside with the data of the intended application. The neural Trojan is specifically designed so that when a specific entry is fed into the trained neural network, it triggers the interpretation of the data as payload. The paper presents a background on which this attack is based and provides the assumptions that make the attack possible. Two embodiments of the attack are presented consisting of a basic backpropagation network and a Neural Network Trojan with Sequence Processing Connections (NNTSPC). The two alternatives are used depending on the underlying circumstances on which the compromise is launched. Experimental results are carried out with synthetic as well as a chosen existing binary payload. Practical issues of the attack are also discussed, as well as a discussion on detection techniques. [ABSTRACT FROM AUTHOR]

In this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing devices. It is constructed in a similar fashion of how DNA formed: built up by four essential elements. As the DNA produces phenotypes, the Neural Knowledge DNA carries information and knowledge via its four essential interrelated elements, namely, Networks, Experiences, States, and Actions; which store the detail of the artificial neural networks for training and reusing such knowledge. The novelty of this approach is that it uses previous decisional experience to collect and expand intelligence for future decision making formalized support. The experience based collective computational techniques of Set of Experience Knowledge Structure (SOEKS) and Decisional DNA (DDNA) are used to develop aforesaid decisional sustenance. Together with artificial neural networks and reinforcement learning, the proposed Neural Knowledge DNA is used to catch knowledge of a very simple maze problem, and the results show that our Neural Knowledge DNA is a very promising knowledge representation approach for artificial neural network-based intelligent systems. [ABSTRACT FROM AUTHOR]

In this paper, we show that a contextual neural network with artificial neurons performing a conditional aggregation of signals can be trained by the generalized backpropagation algorithm. To allow this algorithm to be used for training contextual neural networks, we derive appropriate generalized delta rules. Our approach is constructed on the basis of introduced generalized representation of the aggregation function in an ordered groups space and division of its attention function into binary scan-path and contribution functions. The advantage of the proposed representation is that it clarifies the description of the aggregation process by using Stark's scan-path theory and allows us to achieve results independent from the actual form of the attention functions used during aggregation. As such, the proposed solution is valid for the whole presented family of conditional aggregation functions and is a considerable extension of the previously reported results. In particular, the obtained results are valid for the introduced exemplary attention functions which illustrate performed calculations. Moreover, the presented solution can be further extended by considering real valued, non-binary contribution functions inside ordered aggregation functions. Especially promising are its possible applications in large deep neural networks and energy-limited systems. [ABSTRACT FROM AUTHOR]

The problem of Optical Character Recognition (OCR) is methodically treated in this paper. The paper discusses some traditional methods like template matching and neural networks that are employed by the more advanced and artificially intelligent systems. Though K-PCA, a non-intelligent system, provides better accuracy, it was found to occur at the cost of more processing time. Neural Networks provide a trade-off between processing time and accuracy. [ABSTRACT FROM AUTHOR]

The task scheduling problem in heterogeneous systems (TSPHS) is a NP-complete problem. It is a multiobjective optimization problem (MOP). The objectives such as makespan, average flow time, robustness and reliability of the schedule are considered for solving task scheduling problem. This paper considers only the two objectives of minimizing the makespan (schedule length) and maximizing the reliability in the multiobjective task scheduling problem. Multiobjective Evolutionary Computation algorithms (MOEAs) are well suited for Multiobjective task scheduling for heterogeneous environment. The two Multi-Objective Evolutionary Algorithms such as Multiobjective Genetic Algorithm (MOGA) and Multiobjective Evolutionary Programming (MOEP) with non-dominated sorting are developed and compared for the various random task graphs and also for a real-time numerical application graph. This paper demonstrates the capabilities of MOEAs to generate well-distributed Pareto optimal fronts in a single run. [ABSTRACT FROM AUTHOR]

The paper contains a description of the implementation and performance evaluation of the agent-based population learning algorithm used to train the feed-forward artificial neural networks. The goal of the research was to evaluate efficiency of the agent-based approach and to establish experimentally which different factors representing the A-Team structure and topology affect the performance of the analyzed agent-based algorithm. The paper includes a general overview of the JABAT environment used to deploy the ANN training algorithm, a description of different agents employed and their roles, as well as the computational experiment plan and the discussion of the performance evaluation results. [ABSTRACT FROM AUTHOR]

The main goal of this paper is to design an electromyogram (EMG) pattern classifier which is robust against muscular fatigue effects for powered wheelchair control. When a user operates a powered wheelchair using EMG-based interface for a long time, muscular fatigue often arises from sustained duration of muscle contraction. The recognition rate thus is degraded and controlling wheelchair gets more difficult. In this paper, an important observation is addressed that the variations of feature values due to the effect of the muscular fatigue are consistent for sustained duration. Based on this observation, we design a robust pattern classifier through the adaptation process of hyperboxes of Fuzzy Min-Max Neural Network. We present, as a result, a significantly improved performance in terms of the continuous usage of wheelchair. [ABSTRACT FROM AUTHOR]

Computational Intelligence (CI) paradigms reveal to be potential tools to face under the Web uncertainty. In particular, CI techniques may be properly exploited to handle Web usage data and develop Web-based applications tailored on users preferences. The main rationale behind this success is the synergy resulting from CI components, such as fuzzy logic, neural networks and genetic algorithms. In fact, rather than being competitive, each of these computing paradigms provides complementary reasoning and searching methods that allow the use of domain knowledge and empirical data to solve complex problems. This paper focuses on the major Computational Intelligent combinations applied in the context of Web personalization, by providing different examples of intelligent systems which have been designed to provide Web users with the information they search, without expecting them to ask for it explicitly. In particular, this paper emphasizes the suitability of hybrid schemes deriving from the profitable combination of different CI methodologies for the development of effective Web personalization systems. [ABSTRACT FROM AUTHOR]

This paper describes a new approach for predicting tertiary structure of protein using artificial neural network and particle swarm optimization technique. The paper is concetrated around the well known Ab-initio approach for global minimisation of energy function. It predicts the native structure of protein by finding the main chain dihedral angles; through the optimization of CHARMM energy function, using particle swarm optimization algorithm. Side chain dihedral angle are predicted using three layered artificial neural network, realised with back propagation algorithm. This approach has merit as it reduces the dimensionality of the search space and computationally outperforms all other classical technique in atleast 80% cases. [ABSTRACT FROM AUTHOR]

This paper presents a visual speech recognition technique using facial movement video. The acoustic signals of consonants are often confusing in noisy environments. To overcome this shortcoming, the focus of this paper is identifying consonants using visual information. This paper investigates the feasibility of using facial movements to identify phonemes. The proposed approach adopts a visual speech model based on the viseme model of the Moving Picture Experts Group 4 (MPEG-4) standard. It is a movement-based system, and the facial movements are segmented from the video using an accumulative image subtraction method that results in a 2-D grayscale motion history image (MHI). The MHI is classified using a combination of the discrete stationary wavelet transform (SWT) and image moments (Hu moments, geometric moments and Zernike moments). Feedforward multilayer perceptron (MLP) neural networks with backpropagation (BPN) learning algorithm are used to classify the features to investigate the performance of the three moment features. The experimental results indicate that Zernike moments have better representation ability and provide rotational invariant property for the proposed application. The results also demonstrate that the proposed technique can identify consonants reliably using the viseme model of MPEG-4 standard with a recognition rate of 85%. [ABSTRACT FROM AUTHOR]

In studies concerned with sustainability the underlying models are, in most cases, not strictly numerical since they depend on many conditions that can be regarded as qualitative. In this paper, a model to evaluate citizens' satisfaction learnt from data collected from a survey is presented. The model, which involves the use of RBF neural networks, will provide local councillors with useful information, enabling them to evaluate trends and improve strategies focused on enhancing sustainability. In this paper a contribution describing a practical experience with a model-based system applied to a study commissioned by the town council of Vilanova i la Geltrú (Catalonia, Spain) is presented. [ABSTRACT FROM AUTHOR]

Recent advances in soft-computing based methods have seen successful applications of them in suitable fields of engineering applications where the problem can be specified in form of finding suitable single/multi-dimensional nonlinear mathematical fitting for pattern classification or function approximation. Neural networks or neuro-fuzzy based solutions have particularly been successfully applied in these fields in the last decade. The present paper deals with the feasibility of employing artificial neural network (ANN) based solutions to linearize the input-output characteristic of a thermistor based temperature measurement system. This paper proposes the development of a robust PC-based linearizer where the input-output data is obtained directly from the manufacfturers' table. The proposed system is developed on the basis of application of supervised structures of ANN. This paper also attempts to make an in-depth study on relative efficiencies of application of different popular neural networks, employing supervised learning, for the particular problem under study. The effectiveness of the proposed systems is amply demonstrated by the significantly low error indices in testing phase. [ABSTRACT FROM AUTHOR]

GEX (Genetic Rule EXtraction) method described in this paper is a method of rule extraction from a trained neural network. The acquired set of rules describes the performance of a neural network solving classification problems. The extracted rules are in the form of IF - THEN. The premises standing after IF set some constrains on the neural network input values. After THEN stands a designated class. The method is based on a genetic approach. GEX consists of subpopulations evolving on islands. The number of classes existing in the classification problem solved by the neural network assigns the number of subpopulations. The details of the method are presented in the paper. The results of experiments performed on well-known benchmark data sets are shown as well. [ABSTRACT FROM AUTHOR]

Evolutionary Engineering (EE) is defined to be “the art of using evolutionary algorithms approach such as genetic algorithms to build complex systems”. This paper deals with a neural net based system. It analyses ability of genetically trained neural nets to control Simulated robot arm, witch tries to track a moving object. In difference from classical Approaches neural network learning is performed on line, i.e., in real time. Usually systems are built/evolved, i.e., genetically trained separately of their utilization. That is how it is commonly done. It's a fact that evolution process is heavy on time; that's why Real‐Time approach is rarely taken into consideration. The results presented in this paper show that such approach (Real‐Time EE) is possible. These successful results are essentially due to the “continuity” of the target's trajectory. In EE terms, we express this by the Neighbourhood Hypothesis (NH) concept. [ABSTRACT FROM AUTHOR]

In this paper, cellular neural networks(CNNs) with time-varying leakage delays on time scales are investigated. By applying the existence of the exponential dichotomy of linear dynamic equations on time scales, fixed point theorem and the theory of calculus on time scales, a set of sufficient conditions are obtained for the existence and exponential stability of almost automorphic solutions for the model.Anexample with its numerical simulations is given to illustrate the feasibility and effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

There are many approaches for accurate and automatic classification of brain MRI. In this paper, a simple approach for automatic detection and classification is presented. Artificial Neural Network has been utilized for brain MRI classification as malignant or benign. The approach consists of three stages namely pre processing, features' extraction and classification. In pre-processing stage, filters are applied for the removal of noise. In the features' extraction phase, color moments are extracted as mean features from the MRI images and the color moments extracted are presented to simple feed forward artificial neural network for classification. The method was applied using total 70 images with 25 normal images and 45 abnormal images. The classification accuracy was found to be 88.9% for training data, 94.9% for validation data and 94.2% for testing data whereas the overall accuracy of 91.8% was observed. [ABSTRACT FROM AUTHOR]

The neuro-evolution is a domain of artificial intelligence which uses the evolutionary approach to produce artificial neural networks. There are many neuro-evolutionary methods and one of them is Assembler Encoding. This paper compares Assembler Encoding with other methods from the range of neuro-evolution and and reinforcement learning. During comparison tests, the task was to form neuro-controllers for three variants of the inverted pendulum problem. The variants differed in the amount of information supplied to each neuro-controller and in the number of poles installed on a cart. [ABSTRACT FROM AUTHOR]

In today's world, customer purchasing behavior prediction is one of the most important aspects of customer attraction. Good prediction can help to develop marketing strategies more accurately and to spend resources more effectively. When designing a customer prediction system (CPS) two issues are key, namely, feature selection and the prediction method to be used. Furthermore, it seems necessary to design CPSs with both high computational speed and good prediction abilities. The purpose of this paper is to develop such a system by using a hybrid approach. The resulting system is a hybrid CPS (HCPS) and is based on Multiple Forward Stepwise Logistic Regression (MFSLR) model. The MFSLR model combines a forward stepwise regression (FSR) technique that rapidly selects an optimal subset of features with multiple logistic regression (MLR) technique. In practice, the new MFSLR model provides very good prediction results. Since customer identification is one of the principal concerns in the insurance industry, an insurance company dataset has been used. The obtained results show that the FSR selects around 55% of the initially available features, in this way considerably reducing computational costs. In addition, the results show that the MLR method leads to more accurate prediction than some other methods we tried, namely, feedforward neural networks, radial basis networks and regression trees. [ABSTRACT FROM AUTHOR]

In this paper we present Casep2: a hybrid neuro-symbolic system combining case-based reasoning (CBR) and artificial neural networks that aims at clustering and classifying users' behavior in an e-commerce site. A user behavior is represented by a sequence of visited web pages, in a session. Each registered behavior is associated to one of the following classes: buyer or non-buyer. Our goal is to provide a system that mines the web site access log in order to predict the class of an on-going user navigation. One major challenge to face is to provide scalable algorithms that can handle efficiently the large amount of data to learn from. Predictions should be made in real-time, during the current navigation. In addition, raw data has a sequential nature and are very noisy. In the proposed system, two original neural networks, named M-SOM-ART networks, are applied: one to implement the retrieval phase of a CBR cycle, and the second to implement the reuse phase. This hybrid scheme allows to ensure incremental learning as well as efficient treatment of large-scale sequential data. Experiments on real log data of an e-commerce site show the relevancy of the proposed approach. [ABSTRACT FROM AUTHOR]

Generalized Adaptive Resonance Theory (GART) is a neural network model based on the integration of Gaussian ARTMAP and the Generalized Regression Neural Network. As demonstrated in our previous work, GART is capable of online learning and is effective in tackling both classification and regression tasks. In this paper, we propose an Enhanced GART (EGART) network whereby the capability of GART is further enhanced with the Laplacian function, a new vigilance function, a new match-tracking mechanism, and a fuzzy rule extraction procedure. The applicability of EGART to pattern classification and fuzzy rule extraction problems is evaluated using three benchmark medical data sets and one real medical diagnosis problem. The experimental results are analyzed, discussed, and compared with other reported results. The outcomes demonstrate that EGART is capable of producing high accuracy rates and of extracting useful rules for tackling medical pattern classification problems. [ABSTRACT FROM AUTHOR]

Case-based reasoning is a popular approach used in intelligent systems. It is particularly useful in domains where an abundant number of past cases is available. Cases encompass knowledge accumulated from specific (specialized) situations. Whenever a new case has to be dealt with, the most similar cases are retrieved from the case base and their encompassed knowledge is exploited in the current situation. Combinations of case-based reasoning with other intelligent methods have been explored deriving effective knowledge representation schemes. Although some types of combinations have been mostly explored, other types have not been thoroughly investigated. In this paper, we briefly outline popular case-based reasoning combinations. More specifically, we focus on combinations of case-based reasoning with rule-based reasoning, soft computing methods (i.e., fuzzy methods, neural networks, genetic algorithms) and ontologies. We illustrate basic types of such combinations and also point out future directions. [ABSTRACT FROM AUTHOR]

In this paper we present an intelligent scheme, employing a combination of fuzzy logic, pulse coupled neural networks (PCNNs), wavelets and rough sets, for analysing prostrate ultrasound images in order diagnose prostate cancer. Image noise is a principal factor which hampers the visual quality of ultrasound images and can therefore lead to misdiagnosis. To address this issue we first utilise an algorithm based on type-II fuzzy sets to enhance the contrast of the image. This is followed by performing PCNN-based segmentation in order to identify the region of interest and to detect the boundary of the prostate pattern. Then, a wavelet features are extracted and normalised, followed by application of a rough set analysis to discover the dependency between the attributes, and to generate a set of reducts consisting of a minimal number of attributes. Finally, a rough set classifier is designed for discrimination of different regions of interest to determine whether they represent cancer or not. To evaluate the performance of our approach, we present tests on different prostate ultrasound images. The experimental results obtained, show that the overall classification accuracy offered by the employed rough set approach is high compared with other intelligent techniques including decision trees, discriminant analysis, rough neural networks, fuzzy ARTMAP, and neural networks. [ABSTRACT FROM AUTHOR]

When neural networks are applied to large scale real-world classification problems, a major drawback is its inefficiency in utilizing network resources. A natural approach to overcome this drawback is to decompose the problem into several smaller sub-problems based on the "divide-and-conquer" methodology. This paper presents a hybrid method of task decomposition – OP-RPHP (Output Parallelism with Recursive Percentage-based Hybrid Pattern training). OP-RPHP employs a combination of both class decomposition and domain decomposition in its architecture thereby incorporating the advantages of both methods. OP-RPHP can be grown and trained in parallel on separate processing units to improve training time. To further improve the training time, a reduced pattern training algorithm is introduced. The reduction parameter p associated with the reduced pattern training algorithm is optimized to obtain maximum reduction in training time without compromising classification accuracy. Our approach is tested on four benchmark classification problems retrieved from the UCI repository of machine learning databases. The results show that OP-RPHP with reduced pattern training outperformed conventional OP and RPHP algorithms in both classification accuracy and training times. [ABSTRACT FROM AUTHOR]

Recently the possibility of using spiking neural P systems for solving computationally hard problems has been considered. Such solutions assume that some (possibly exponentially large) pre-computed resources are given in advance, provided that their structure is "regular" and they do not contain neither "hidden information" that simplify the solution of specific instances, nor an encoding of all possible solutions (that is, an exponential amount of information that allows to cheat while solving the instances of the problem). In this paper we continue this research line, and we investigate the possibility of solving numerical NP-complete problems such as SUBSET SUM. In particular, we first propose a semi-uniform family of spiking neural P systems in which every system solves a specific instance of SUBSET SUM. Then, we exploit a technique used to calculate ITERATED ADDITION with Boolean circuits to obtain a uniform family of spiking neural P systems in which every system is able to solve any instance of SUBSET SUM of a fixed size. All the systems here considered are deterministic, and their size generally grows exponentially with respect to the instance size. [ABSTRACT FROM AUTHOR]

The problem of finding small universal spiking neural P systems was recently investigated by Andrei Păun and Gheorghe Păun, for spiking neural P systems used as devices computing functions and as devices generating sets of numbers. For the first case, a universal spiking neural P system was produced by using 84 neurons for standard rules and using 49 neurons for extended rules. For spiking neural P systems used as generators of sets of numbers, a universal system with standard rules having 76 neurons, and one with extended rules having 50 neurons were obtained. In this paper, we continue the study of small universal spiking neural P systems and we improve in the number of neurons as follows. The small universal spiking neural P systems use 67 neurons for standard rules and 41 neurons for extended rules in the case of computing functions, and 63 neurons for standard rules and 41 neurons for extended rules in the case of generating sets of numbers. [ABSTRACT FROM AUTHOR]

In this paper we propose and analyze a multilayer perceptron-like model with matrix inputs. We applied the proposed model to the financial time series prediction problem, compared it with the standard multilayer perceptron model, and got fairly good results. [ABSTRACT FROM AUTHOR]

The design and evaluation of agents handling automated negotiations on behalf of their human or corporate owners is a quite challenging research field. This paper proposes to enhance such agents with learning techniques, in order to achieve more profitable results for the parties they represent. The proposed learning techniques are based on MLP or RBF neural networks (NNs) and are quite lightweight. Alternatively, the agents use Genetic Algorithms (GAs) to predict the behaviour of their opponents. All designed approaches aim to reduce the cases of unsuccessful negotiations and maximize the client's utility. The designed NN- and GA-assisted negotiation strategies This work has in part been supported by the project “Amigo – Ambient intelligence for the networked home environment”. The Amigo project is funded by the European Commission as an integrated project (IP) in the Sixth Framework Programme under the contract number IST 004182. For more information you may refer to www.amigo-project.org. have been compared and empirically evaluated via numerous experiments. [ABSTRACT FROM AUTHOR]