Search

The object of research is the processes of pulse metalworking (hydroexplosive, magnetic pulse, electrohydraulic, gas detonation forming, etc.). Among these methods of forming for the production of aircrafts engines parts from cylindrical and conical blanks, the most efficient in terms of its energy capabilities and overall dimensions is explosive. The modern level of theory and practice of metal forming processes allows, on the basis of a systematic approach and control theory, to determine the optimal parameters of plastic forming processes, select the best technical solutions, and create a precondition for the transition to complex automation. The most difficult task of metals forming methods optimizing is to find the best solution among many potentially possible ones, considering the introduced restrictions and efficiency criteria, environmental, economic, technical, ergonomic, and other requirements. The most problematic is that it is impossible to optimize the process of forming post-factum (finishing works, elimination of defects in shape and size, welding of cracks, etc. are required), therefore, when solving optimization problems, the implementation of the feedback principle is required - comparison of the value of the controlled variable, determined by the control program, with the desired value. In general, the processes of metal forming by pressure are characterized by a variety of problems of the theory of optimal control, the solution of which is carried out by methods of mathematical programming. And, although the equipment for pulse processing can have a different design, it necessarily includes structural elements that make it possible to convert the energy of the source and with its help (through the action of a solid body, transmitting medium, or field) to deform the metal of the workpiece. Due to this, in this work, it is proposed to control the quality of the obtained parts by varying the degree of deformation of the workpiece in the process of forming. The result of the work is the development of an integrated intelligent system, with the help of which it is possible to carry out the computer-aided design of almost all pulse-action processes based on the intelligent selection of suitable forming parameters.

Stigmergy is a communication method based on changing the surrounding environment according to reference feedbacks. It is typical within animal colonies that are able to process even complex information by releasing signals into the environment, which are subsequently received and processed by other elements of the colony. For example, ants searching for food leave traces of a pheromone, like Hansel and Gretel’s breadcrumbs, along the way. When food is found, they return to the anthill reinforcing this pheromone trace as a signal and reminder to all the others. Similar techniques are used in routing software even if stigmergic hardware might be even more efficient, fast, and energy saving. Recently, a stigmergic photonic gate based on soliton waveguides has been proposed; this particular stigmergic hardware can switch the output ratio of the channels as a result of optical feedback. Based on these results, in this study, we analyze stigmergic electronic gates that can be addressed through external feedback, as the photonic ones do. We show that the nonlinear response of such gates must be based on quadratic saturating conductances driven by feedback signals. For this purpose, networks of stigmergic gates require two parallel and communicating current circuits: one to transmit information, and another for feedback signals to control the gate switching. We also show that by increasing the number of terminals per single gate, from 2 × 2 to 3 × 3 or higher, the overall power consumption can be reduced by a few orders of magnitude.

When the COVID-19 coronavirus hit, the context-aware application users were willing to relax their context privacy preferences during the lockdown to cope their lives while staying home. Such disturbance in the privacy behavior affected the performance of Machine Learning (ML) algorithm that is trained on normal behavior. In this paper, we present the impact of the pandemic on the efficiency of the learning algorithm implementation of a privacy protection system. The system is composed of three modules, in this work we focus on Privacy Preferences Manager (PPM) module which is implemented using hybrid methodology based on a Statistical Model (SM) and Logistic Regression (LR) learning algorithm. The efficiency of the hybrid methodology is assessed using two real-world datasets collected prior and during the COVID-19 pandemic. The results show that the pandemic significantly impacted the efficiency of the hybrid methodology by 13.05% and 15.22% for the accuracy and F1 score respectively.

The article presents the authors` position on the development and application of a functional approach to the design and development of intelligent control systems for technical objects of various nature (cyberphysical systems) based on the principles of complex engineering. Complex engineering and a functional approach can, for example, be used together to manage such complex technical objects as intelligent buildings, which in the future allows us to transfer their functioning to a higher level of efficiency not only of the management object itself, but also of the hierarchy of its super – systems from the municipality and the region to the state as a whole. However, the system approach can also be applied in conjunction with complex engineering, which allows us, at least partially, to smooth out certain shortcomings of the functional approach, which are manifested when it is applied exclusively within the framework of system engineering when considering aspects of managing cyber-physical systems with a high degree of intelligence based on the system approach.The authors clearly show the techniques and methods of this set of complex engineering, functional and system approaches in the proposed article using infographic models. Complex engineering allows you to solve the problem of transferring the control object to a connected intellectualized control complex, which, in turn, increases the level of its intelligence. At the same time, the authors use an interdisciplinary approach, since it is the most effective one when considering complex cyberphysical systems. Complex engineering initially includes an interdisciplinary approach, which allows us to apply it to the analysis and study of cyberphysical systems with the subsequent application of already a functional approach to solving problems of intellectualization. According to the authors, this will allow us to reach new frontiers in the field of creating “smart” systems for managing technological and managerial processes in various branches of human economic activity.

Application of the technology of consecutive construction of the functionally expanding model range of structural system prototypes is an advanced conceptual development direction of intellectual systems construction methods. The guiding principle of intellectual system construction under the suggested technology is that a highly sophisticated system is worked out and adjusted by stages with the use of the structural increment and functional complexity parallel-sequential scheme. At every construction step it is implemented in the form of a hardware and software complex – the structural prototype with a certain set of allocated components and performed functions. The structural prototype is understood as a certain version of its construction in the form of a logical or physical model, which includes a predetermined set of information, technical and software tools, performs system functions, makes it possible to evaluate the achieved parameter levels, as well as ensures further system build-up and development. Verbal-heuristic and graphic-heuristic models, which reflect the set of original requirements and the intelligent system structure, are used as mandatory prototypes of primary levels. The mandatory prototype of subsequent levels of the system technology includes a material model of the system nucleus, which combines hardware and software components, where joint functioning delivers the required set of integrative systematic properties. Sequential step-by-step choice of all the more complex prototypes with simultaneous enrichment of the composition of applied tools and performed system functions forms the expanded model range of the system. In the practice of systems development it is limited with a certain upper level prototype, which meets preset technical requirements to the system. Step-by- step development and adjustment of models, which are highly complicated prototypes, with the use of the parallel-sequential scheme of their structural enrichment and functional complication, is the effective technological trend of co-engineering.

This 21st century is notable for experiencing so many disturbances at economic, social, cultural, and political levels in the entire world. The outbreak of novel corona virus 2019 (COVID-19) has been treated as a Public Health crisis of global Concern by the World Health Organization (WHO). Various outbreak models for COVID-19 are being utilized by researchers throughout the world to get well-versed decisions and impose significant control measures. Amid the standard methods for COVID-19 worldwide epidemic prediction, easy statistical, as well as epidemiological methods have got more consideration by researchers and authorities. One main difficulty in controlling the spreading of COVID-19 is the inadequacy and lack of medical tests for detecting as well as identifying a solution. To solve this problem, a few statistical-based advances are being enhanced and turn into a partial resolution up-to some level. To deal with the challenges of the medical field, a broad range of intelligent based methods, frameworks, and equipment have been recommended by Machine Learning (ML) and Deep Learning. As ML and DL have the ability of identifying and predicting patterns in complex large datasets, they are recognized as a suitable procedure for producing effective solutions for the diagnosis of COVID-19. In this paper, a perspective research has been conducted in the applicability of intelligent systems such as ML, DL and others in solving COVID-19 related outbreak issues. The main intention behind this study is (i) to understand the importance of intelligent approaches such as ML and DL for COVID-19 pandemic, (ii) discussing the efficiency and impact of these methods in the prognosis of COVID-19, (iii) the growth in the development of type of ML and advanced ML methods for COVID-19 prognosis,(iv) analyzing the impact of data types and the nature of data along with challenges in processing the data for COVID-19,(v) to focus on some future challenges in COVID-19 prognosis to inspire the researchers for innovating and enhancing their knowledge and research on other impacted sectors due to COVID-19.

Choosing optimal Deep Learning (DL) architecture and hyperparameters for a particular problem is still not a trivial task among researchers. The most common approach relies on popular architectures proven to work on specific problem domains led on the same experiment environment and setup. However, this limits the opportunity to choose or invent novel DL networks that could lead to better results. This paper proposes a novel approach for providing general recommendations of an appropriate DL architecture and its hyperparameters based on different configurations presented in thousands of published research papers that examine various problem domains. This architecture can further serve as a starting point of investigating DL architecture for a concrete data set. Natural language processing (NLP) methods are used to create structured data from unstructured scientific papers upon which intelligent models are learned to propose optimal DL architecture, layer type, and activation functions. The advantage of the proposed methodology is multifold. The first is the ability to eventually use the knowledge and experience from thousands of DL papers published through the years. The second is the contribution to the forthcoming novel researches by aiding the process of choosing optimal DL setup based on the particular problem to be analyzed. The third advantage is the scalability and flexibility of the model, meaning that it can be easily retrained as new papers are published in the future, and therefore to be constantly improved.

Electrical discharge machining (EDM) can effectively solve the shortcomings of traditional machining processes that cannot process special materials, so it is widely used on workpieces with strong hardness materials, such as titanium alloys and tool steels to produce various molds and dies. However, the operating procedures of EDM are quite complicated and low machining productivity. To improve machining efficiency, this study develops an intelligent system that adaptively controls debris removal operations instead of using preset debris removal parameters. A feature extraction method is proposed in this study to effectively identify the machining states from streaming images of the machining curve for evaluating the appropriate time of the debris removal operation. Then, the extracted features feed into the artificial neural network model to establish a debris removal predicted model. The preliminary experimental result shows that the established predicted model can achieve an accuracy of 96.93% for a testing dataset containing 750 machining curve images. To further verify the effectiveness of the proposed intelligent system in improving EDM efficiency, we integrate the debris removal predicted model into the EDM machine and test it on the manufacturing site. Compared with the preset debris removal parameter, the proposed intelligent system can save nearly 38.60% of machining time for the machining depth of 6.45mm under specific EDM conditions.

Nowadays, rehabilitation training for stroke survivors is mainly completed under the guidance of the physician. There are various treatment ways, however, most of them are affected by various factors such as experience of physician and training intensity. The treatment effect cannot be fed back in time, and objective evaluation data is lacking. In addition, the treatment method is complicated, costly, and highly dependent on physicians. Moreover, stroke survivors’ compliance is poor, which leads to various limitations. This paper combines the Internet-of-Things, machine learning, and intelligence system technologies to design a smartphone-based intelligence system to help stroke survivors to improve upper limb rehabilitation. With the built-in multi-modal sensors of the smart phone, training action data of users can be obtained, and then transfer to the server through the Internet. This research presents a DTW-KNN joint algorithm to recognize accuracy of rehabilitation actions and classify to multiple training completion levels. The experimental results show that the DTW-KNN algorithm can evaluate the rehabilitation actions, the accuracy rates of the classification in excellent, good, and normal are 85.7%, 66.7%, and 80% respectively. The intelligence system presented in this paper can help stroke survivors to proceed rehabilitation training independently and remotely, which reduces medical costs and psychological burden.

The purpose of the article is developing the locomotive structure of intellectual system of support of decision-making and to find a criterion by which to adequately assess different control action to the train. System of decision support for locomotive crew is seen as a complex structure with complex interactions located at a great distance, on-board locomotive systems. The quality of the organization determines the effectiveness of the system as a whole. To solve the problem of creating the optimal structure of the DSS applies the aggregate-decomposition method that involves two steps: decomposition of the problem into a number of subproblems and aggregating the partial results. To evaluate the quality control of a locomotive used the concept of control strategy with specific indicators. Design is developed and structure of locomotive DSS is obtained, taking into account peculiarities of operation of railway transport. To ac-count for not only quantitative but also qualitative characteristics of activity of the locomotive or intellectual systems of decision support, it is proposed to use methods of fuzzy logic. So were able to deduce and calculate the additive criterion of the quality control activities of the intelligent system. Formal indicator of the quality of the train control process using different strategies is received. In the work theoretically grounded definition of the weighting factors for each partial criterion of the quality of train control. Using the dependencies derived, the nature of the influence of the value of partial criteria on the quality of train control in relation to a strategy. The results of the work allow to more accurately simulate the operations of a locomotive crew, which in the future will serve as the basis for the development of autonomous intelligent systems of locomotive control. The developed method is shown to be three main criteria which values the safety, energy consumption, and execution time schedule. However, for more flexible and accurate model, this approach allows to enter additional criteria, and the simplicity of the calculation provides the necessary speed when implemented on on-board locomotive computers.

Current machine intelligence metrics rely on a different philosophy, hindering their effective comparison. There is no standardization of what is machine intelligence and what should be measured to quantify it. In this study, we investigate the measurement of intelligence from the viewpoint of real-life difficult-problem-solving abilities, and we highlight the importance of being able to make accurate and robust comparisons between multiple cooperative multiagent systems (CMASs) using a novel metric. A recent metric presented in the scientific literature, calledMetrIntPair, is capable of comparing the intelligence of only two CMASs at an application. In this paper, we propose a generalization of that metric calledMetrIntPairII.MetrIntPairIIis based on pairwise problem-solving intelligence comparisons (for the same problem, the problem-solving intelligence of the studied CMASs is evaluated experimentally in pairs). The pairwise intelligence comparison is proposed to decrease the necessary number of experimental intelligence measurements.MetrIntPairIIhas the same properties asMetrIntPair, with the main advantage that it can be applied to any number of CMASs conserving the accuracy of the comparison, while it exhibits enhanced robustness. An important property of the proposed metric is the universality, as it can be applied as a black-box method to intelligent agent-based systems (IABSs) generally, not depending on the aspect of IABS architecture. To demonstrate the effectiveness of theMetrIntPairIImetric, we provide a representative experimental study, comparing the intelligence of several CMASs composed of agents specialized in solving an NP-hard problem.

Aim . The study describes a prototype of an intelligent system for modelling climate variability based on a database of multi-year series and historical evidence. The presented intelligent system allows climate events to be simulated as follows: one phenomenon at one point; one phenomenon in space; many phenomena at one point and many phenomena in space. Methods . The choice of research methods was determined by the properties of source information and its volume: a series of observations over a long period, sampling over a short period, historical and archival materials, etc. Results . The article describes the main functions of the presented intelligent system, which expand the possibility of assessing the variability of climate characteristics by combining quantitative and qualitative information in the form of historical and archival evidence. The main functions of the system include the generation of event flows; estimation of the event probability; physical reconstruction of data using geoinformation systems; determination of the period between two rare events; and management of agricultural production under risk conditions. Conclusion . The advantage of the proposed system consists in increasing information about extreme events and improving the management efficiency by means of reducing risks.

Capture fisheries and aquaculture provide a significant amount of high-quality protein to human beings and thus play an essential role in ending global hunger and malnutrition. The availability of tens of hundreds of fish genomes and the advances of genomics have allowed addressing many challenging issues such as overfishing and germplasm degradation faced by fisheries and aquaculture. In this review, we describe the current status of genomics in fisheries and aquaculture, with an emphasis on 14 species of fish that are considerably important to global fisheries and aquaculture, in the context of genome sequencing and assembly, annotation, GC contents, and repeats. The majority of these genomes are assembled at the chromosome level and annotated with proteins and pathways, with functional relevance to fisheries and aquaculture, such as environmental adaptation and phenotypic variation. We summarize potential genomic applications in fisheries and aquaculture that are related to assessment and use of genetic resources, disease resistance, growth and development, sexual determination, and fisheries management. Although much progress has been achieved in genomic application to fisheries and aquaculture, the full potential remains to be explored and reaped. We discuss the challenges and perspectives of genomics in translational aquaculture and fisheries, which include genome assembly and annotation, genomic selection and breeding, genomics in fisheries management, and integrated artificial intelligence systems. In the coming decades, we anticipate the applications of genomic techniques such as genome editing and genomic selection, along with the use of emerging intelligence systems, in aquaculture and fisheries will contribute significantly to genetic improvements of farmed fish and sustainable exploitation of fishery resources, which consequently lead to eradicating global poverty by 2030, an ambitious goal set by the United Nations.

Cloud computing Web systems are today the most important part of the Web. Many companies transfer their services to the cloud in order to avoid infrastructure aging and thus preventing less efficient computing. Distribution of the load is a crucial problem in cloud computing systems. Due to the specifics of network traffic, providing an acceptable time of access to the Web content is not trivial. The utilization of the load distribution with adaptive intelligent distribution strategies can deliver the highest quality of service, short service time and reduce the costs. In the article, a new, two-level, intelligent HTTP request distribution strategy is presented. In the process of designing the architecture of the proposed solution, the results of earlier studies and experiments were taken into account. The proposed decision system contains fuzzy-neural models yielding minimal service times in the Web cloud. The article contains a description of the new solution and the test-bed. In the end, the results of the experiments are discussed and conclusions and presented.

A new cognitive approach is proposed for understanding the texts of planimetric tasks and for visualizing the task conditions to complement the syntactic-semantical sentence parsing. Two main difficulties in understanding texts of plane geometry tasks are observed: the ellipticity and vagueness of texts. To overcome the difficulties in understanding the task conditions it is proposed constructing cognitive models of objects and relations between them. The proposed cognitive approach is incorporated in an integrated system for automatic solving planimetric tasks with the natural language interface. The interactive visualization has been developed in the system. It depicts the syntactic and semantic structures as a result of natural language text analysis and searching for task solution. This visualization allows the users to obtain explanations associated with any elements of the images and to correct the tasks’ texts in dialog with the system. The destiny of the system is to serve for training schoolchildren in the domain of Euclidean geometry. The cognitive approach proposed can be a first step to automated analyzing plane geometry texts, in perspective, as a cognitively controlled parsing.

Ambulance services play a vital role in intelligent transportation systems (ITS). In an intelligent ambulance system, the medical images can help doctors quickly and accurately understand the patients' condition during first aid. On various display devices in different kinds of ambulances, content-aware image adaption can be used to better present the medical image among different display resolutions and aspect ratios. Most existing methods mainly focus on visual protection of salient areas, such as specific organ parts of the human body, with less attention paid to the visual effect of unimportant areas. However, the human visual system is more sensitive to the edge and contour of images, which are important for ambulance services. To improve the visual effect of adapted images, a contour-maintaining-based image adaption method for an efficient ambulance service in ITS is proposed here. Firstly, the proposed method innovatively combines the weighted gradient, saliency, and edge maps into an importance map. Secondly, energy is optimized for reducing contour distortion and interruption according to the visual slope and curvature of contours and edges in non-salient areas. Finally, applying the sub-procedure of a forward seam carving method, the optimal seams can more evenly pass through the contour areas. The experimental results demonstrate that the proposed method is more effective than other similar methods.

Brick elements are widely used for everything from designing toys to architectural designs. This article proposes an intelligent method to construct complex 3D brick models automatically. The proposed method is designed based on a set of core algorithms to generate a brick layout in accordance with a given 3D voxel model. In the system, each 3D model is sliced into tiers of flat vector polygons at first. Then, the vector polygons are converted to raster data for each tier. The bricks are built in a single tier until all tiers are completed. The proposed model is validated using two case studies: one is a series of solid sculpture models and the other is a building model. The results show that the proposed intelligent building system successfully builds visual models from brick assembly models. The proposed system can help engineers build large block models to improve the efficiency of constructing complex 3D building models.

Immediate monitoring of the conditions of the grinding wheel during the grinding process is important because it directly affects the surface accuracy of the workpiece. Because the variation in machining sound during the grinding process is very important for the field operator to judge whether the grinding wheel is worn or not, this study applies artificial intelligence technology to attempt to learn the experiences of auditory recognition of experienced operators. Therefore, we propose an intelligent system based on machining sound and deep learning to recognize the grinding wheel condition. This study uses a microphone embedded in the grinding machine to collect audio signals during the grinding process, and extracts the most discriminated feature from spectrum analysis. The features will be input the designed CNNs architecture to create a training model based on deep learning for distinguishing different conditions of the grinding wheel. Experimental results show that the proposed system can achieve an accuracy of 97.44%, a precision of 98.26% and a recall of 96.59% from 820 testing samples.

Heart disease is one of the complex diseases and globally many people suffered from this disease. On time and efficient identification of heart disease plays a key role in healthcare, particularly in the field of cardiology. In this article, we proposed an efficient and accurate system to diagnosis heart disease and the system is based on machine learning techniques. The system is developed based on classification algorithms includes Support vector machine, Logistic regression, Artificial neural network, K-nearest neighbor, Naïve bays, and Decision tree while standard features selection algorithms have been used such as Relief, Minimal redundancy maximal relevance, Least absolute shrinkage selection operator and Local learning for removing irrelevant and redundant features. We also proposed novel fast conditional mutual information feature selection algorithm to solve feature selection problem. The features selection algorithms are used for features selection to increase the classification accuracy and reduce the execution time of classification system. Furthermore, the leave one subject out cross-validation method has been used for learning the best practices of model assessment and for hyperparameter tuning. The performance measuring metrics are used for assessment of the performances of the classifiers. The performances of the classifiers have been checked on the selected features as selected by features selection algorithms. The experimental results show that the proposed feature selection algorithm (FCMIM) is feasible with classifier support vector machine for designing a high-level intelligent system to identify heart disease. The suggested diagnosis system (FCMIM-SVM) achieved good accuracy as compared to previously proposed methods. Additionally, the proposed system can easily be implemented in healthcare for the identification of heart disease.

Power factor (PF) is a measure of how effectively electricity is used. The low power factor causes considerable power losses along the power supply chain. In particular, it overloads the distribution system and increases the power plant's burden to compensate the expected power losses. Most of the existing PF correction techniques are developed based on placing centralized capacitors, assuming that power systems are static. However, the power systems are dynamic systems such that their states change over time, necessitating dynamic correction systems. In the emerging smart grid systems, real-time measurements can easily be taken for voltage, current and harmonics. Then, the measured data can be transmitted to a PF controller to reach the desired PF value. However, the problem that will arise in real-time applications is how to determine and adjust the optimal capacitor size that can balance the power factor. In this regard, we propose a real-time correction system based on multi-step capacitor banks to improve PF in co-operation with de-tuned filters to mitigate the harmonics. First, a mathematical model has been formulated for the proposed power factor correction system. The mathematical model can be employed to determine the optimal operational settings of the multi-step capacitor and the reactor value that optimize the reactive power while considering the desired PF value and restricting the harmonics. Second, a genetic optimization approach is applied to solve the proposed mathematical model as it can provide accurate solution in a short computational time. A Monte Carlo simulation approach is considered for validating the proposed PF correction system. The simulation results show that the average PF of the randomly generated test instances has improved from 0.7 to 0.95 (35% increase). Furthermore, we conducted real experiments using a PF testbed for experimental validation. The results are found to be consistent with the simulation results, which validate the effectiveness and applicability of the proposed correction system. Furthermore, the saved kVA in one day is estimated to be 26% of total kVA.

Fuzzy logic has created a high impact on research and development in almost all engineering applications. Recently, there has been an increasing interest in various offshoots of fuzzy logic approach and hierarchical fuzzy logic is one such area of research development and applications. With the increase in volume of data, hierarchical fuzzy logic has emerged as a highly suitable candidate for research. The objective of this paper is to develop methodology for multi-input multi-output hierarchical fuzzy systems. In particular, a system to be designed is broken into a number of sub-subsystems, where each subsystem is designed separately and then connected in hierarchical structure. The strategy used in this paper is to avoid the repetition of common terms across different subsystems of multi-input multi-output systems. This strategy has not been presented hitherto by any other author. This paper first discusses in detail the implementation of a multi-input single-output hierarchical system. It then extends the approach to multi-input multi-output hierarchical systems.

The ability to generate data has never been as powerful as today when three quintile bytes of data are generated daily. In the field of machine learning, a large number of algorithms have been developed, which can be used for intelligent data analysis and to solve prediction and descriptive problems in different domains. Developed algorithms have different effects on different problems.If one algorithmworks better on one dataset,the same algorithm may work worse on another data set. The reason is that each dataset has different features in terms of local and global characteristics. It is therefore imperative to know intrinsic algorithms behavior on different types of datasets andchoose the right algorithm for the problem solving. To address this problem, this papergives scientific contribution in meta learning field by proposing framework for identifying the specific characteristics of datasets in two domains of social sciences:education and business and develops meta models based on: ranking algorithms, calculating correlation of ranks, developing a multi-criteria model, two-component index and prediction based on machine learning algorithms. Each of the meta models serve as the basis for the development of intelligent system version. Application of such framework should include a comparative analysis of a large number of machine learning algorithms on a large number of datasetsfromsocial sciences.

Technology finance, which has attracted worldwide attention for the successful business development of small-and-medium enterprises (SMEs) or start-ups, has advanced an innovation or stagnation way-out resolution strategy for companies in line with the low-growth economic trends. Although the development of new technologies and the establishment of active R&amp, D and commercialization strategies are essential factors in a company’s management sustainability, the activation of the technology market in practice is still in progress for its golden age. In this study, to promote a technology transfer-based company’s growth and to run technology-based various financial support activities, we develop and propose a new intelligent, deep learning-based technology valuation system that enables technology holders to estimate the economic values of their innovative technologies and further to establish a firm’s commercialization strategy. For the last years, the KIBO Patent Appraisal System (KPAS-II) herein proposed has been advanced by KIBO as a web-based, artificial intelligence (AI) and evaluation data applications valuation system that automatically calculates and estimates a technology’s feasible economic value by utilizing both the intrinsic and extrinsic index information of a patent and the commercialization entity’s business capabilities, and by applying to the discounted cash flow (DCF) method in valuation theory, and finally integrating with deep learning results based on the in-advance previously established patent DB and the financial DB. The KPAS-II proposed in this study can be said to have dramatically overcome the long-term preparation period and high levels of R&amp, D and commercialization costs in terms of the limitations that the existing technology valuation method possesses by enhancing the reliability of approximate economic values from the deep learning results based on financial data and completed valuation data. In addition, it is expected that technology marketing coordinators, researchers, and non-specialty business agents, not limited to valuation experts, can easily estimate the economic values of their patents or technologies, and they can be actively utilized in a technology-based company’s decision-making and technologically dependent financial activities.

A growing portfolio of research has been reported on the use of machine learning-based architectures and models in the domain of healthcare. The development of data-driven applications and services for the diagnosis and classification of key illness conditions is challenging owing to issues of low volume, low-quality contextual data for the training, and validation of algorithms, which, in turn, compromises the accuracy of the resultant models. Here, a fusion machine learning approach is presented reporting an improvement in the accuracy of the identification of diabetes and the prediction of the onset of critical events for patients with diabetes (PwD). Globally, the cost of treating diabetes, a prevalent chronic illness condition characterized by high levels of sugar in the bloodstream over long periods, is placing severe demands on health providers and the proposed solution has the potential to support an increase in the rates of survival of PwD through informing on the optimum treatment on an individual patient basis. At the core of the proposed architecture is a fusion of machine learning classifiers (Support Vector Machine and Artificial Neural Network). Results indicate a classification accuracy of 94.67%, exceeding the performance of reported machine learning models for diabetes by ~1.8% over the best reported to date.

In recent years, the adoption of machine learning has grown steadily in different fields affecting the day-to-day decisions of individuals. This paper presents an intelligent system for recognizing human’s daily activities in a complex IoT environment. An enhanced model of capsule neural network called 1D-HARCapsNe is proposed. This proposed model consists of convolution layer, primary capsule layer, activity capsules flat layer and output layer. It is validated using WISDM dataset collected via smart devices and normalized using the random-SMOTE algorithm to handle the imbalanced behavior of the dataset. The experimental results indicate the potential and strengths of the proposed 1D-HARCapsNet that achieved enhanced performance with an accuracy of 98.67%, precision of 98.66%, recall of 98.67%, and F1-measure of 0.987 which shows major performance enhancement compared to the Conventional CapsNet (accuracy 90.11%, precision 91.88%, recall 89.94%, and F1-measure 0.93).

Railway wheelsets are the key to ensuring the safe operation of trains. To achieve zero-defect production, railway equipment manufacturers must strictly control every link in the wheelset production process. The press-fit curve output by the wheelset assembly machine is an essential indicator of the wheelset’s assembly quality. The operators will still need to manually and individually recheck press-fit curves in our practical case. However, there are many uncertainties in the manual inspection. For example, subjective judgment can easily cause inconsistent judgment results between different inspectors, or the probability of human misinterpretation can increase as the working hours increase. Therefore, this study proposes an intelligent railway wheelset inspection system based on deep learning, which improves the reliability and efficiency of manual inspection of wheelset assembly quality. To solve the severe imbalance in the number of collected images, this study establishes a predicted model of press-fit quality based on a deep Siamese network. Our experimental results show that the precision measurement is outstanding for the testing dataset contained 3863 qualified images and 28 unqualified images of press-fit curves. The proposed system will serve as a successful case of a paradigm shift from traditional manufacturing to digital manufacturing.

Tactile sensors are an important medium for artificial intelligence systems to perceive their external environment. With the rapid development of smart robots, wearable devices, and human-computer interaction interfaces, flexible tactile sensing has attracted extensive attention. An overview of the recent development in high-performance tactile sensors used for smart systems is introduced. The main transduction mechanisms of flexible tactile sensors including piezoresistive, capacitive, piezoelectric, and triboelectric sensors are discussed in detail. The development status of flexible tactile sensors with high resolution, high sensitive, self-powered, and visual capabilities are focused on. Then, for intelligent systems, the wide application prospects of flexible tactile sensors in the fields of wearable electronics, intelligent robots, human-computer interaction interfaces, and implantable electronics are systematically discussed. Finally, the future prospects of flexible tactile sensors for intelligent systems are proposed.

Subject: the use of the apparatus of temporal logic and probabilistic approaches to construct an explanation of the results of the work of an intelligent system in order to increase the efficiency of using the solutions and recommendations obtained. Purpose: development of a method for constructing explanations in intelligent systems with the ability to form and evaluate several alternative interpretations of the results of the operation of such a system. Tasks: justification for the use of the black box principle for interactive construction of explanations; development of a pattern explanation model that provides for probabilistic estimation; development of a method of interactive construction of explanations on the basis of the probabilistic approach. Methods: methods of data analysis, methods of system analysis, methods of constructing explanations, models of knowledge representation. Results: A model of the explanation pattern is proposed, which contains temporal regulations reflecting the sequence of user interaction with an intelligent system, which allows the formation of explanations based on a comparison of the actions of the current user and other well-known users. An interactive method for constructing explanations based on a probabilistic approach has been developed; the method uses patterns of user interaction with an intelligent system and contains phases of constructing patterns of explanations and forming explanations using the obtained patterns. The method organizes the received explanations according to the likelihood of use, which makes it possible to form target and alternative explanations for the user. Conclusions: The use of the black box principle for the development of a probabilistic approach to the construction of explanations in intelligent systems has been substantiated. A model of a pattern of explanations based on temporal regulations is proposed. The model reflects the sequence of user interaction with the intelligent system when receiving decisions and recommendations and contains an interaction pattern as part of temporal regulations that have weight, and also determines the likelihood of using the user interaction pattern. An interactive method for constructing explanations has been developed, considering the interaction of the user with the intelligent system. The method includes phases and stages of the formation of regulations and patterns of user interaction with the determination of the probability of their implementation, as well as the ordering of patterns according to the probability of their implementation. The implementation of the method was carried out when constructing explanations for recommender systems., Предмет: использование аппарата темпоральной логики и вероятностных подходов для построения объяснения о результатах работы интеллектуальной системы с тем, чтобы повысить эффективность использования полученных решений и рекомендаций. Цель: разработка метода построения объяснений в интеллектуальных системах с возможностью формирования и оценки нескольких альтернативных вариантов толкований результатов работы такой системы. Задачи: обоснование использования принципа черного ящика для интерактивного построения объяснений; разработка модели паттерна объяснение, что предполагает вероятностную оценку; разработка метода интерактивного построения объяснений на основе вероятностного подхода. Методы: методы анализа данных, методы системного анализа, методы построения объяснений, модели представления знаний. Результаты: Предложена модель паттерна объяснений, содержащий темпоральные правила, отражающие последовательности взаимодействия пользователя с интеллектуальной системой, что позволяет формировать объяснения на основе сравнения действий текущего пользователя и других известных пользователей. Разработан интерактивный метод построения объяснений, основанный на вероятностном подходе; метод использует шаблоні взаимодействия пользователя с интеллектуальной системой и содержит фазы построения паттернов объяснений и формирования объяснений с использованием полученных паттернов. Метод упорядочивает полученные объяснения по вероятности использования, что позволяет сформировать целевое и альтернативные объяснения для пользователя. Выводы: Обосновано использование принципа черного ящика к разработке вероятностного подхода к построению объяснений в интеллектуальных системах. Предложена модель паттерна объяснений на базе темпоральных правил. Модель отражает последовательность взаимодействия пользователя с интеллектуальной системой при получении решений и рекомендаций и содержит паттерн взаимодействия в составе темпоральных правил, имеющих вес, а также определяет вероятность использования паттерна взаимодействия с пользователем. Разработан интерактивный метод построения объяснений с учетом взаимодействия пользователя с интеллектуальной системой. Метод включает фазы и этапы формирования правил и паттернов взаимодействия с пользователем с определением вероятности их выполнения, а также упорядочения паттернов по вероятности их реализации. Выполнена имплементация метода при построении объяснений для рекомендательных систем., Предмет: використання апарату темпоральної логіки та ймовірнісних підходів для побудови пояснення щодо результатів роботи інтелектуальної системи з тим, щоб підвищити ефективність використання отриманих рішень та рекомендацій. Ціль: розробка методу побудови пояснень в інтелектуальних системах з можливістю формування та оцінки декількох альтернативних варіантів тлумачень результатів роботи такої системи. Задачі: обґрунтування використання принципу чорного ящику для інтерактивної побудови пояснень; розробка моделі патерну пояснення, що передбачає ймовірнісну оцінку; розробка методу інтерактивної побудови пояснень на основі ймовірнісного підходу. Методи: методи аналізу даних, методи системного аналізу, методи побудови пояснень, моделі представлення знань. Результати: Запропоновано модель патерну пояснень, що містить темпоральні правила, які відображають послідовності взаємодії користувача з інтелектуальною системою, що дає можливість формувати пояснення на основі порівняння дій поточного користувача та інших відомих користувачів. Розроблено метод інтерактивної побудови пояснень, який базується на ймовірнісному підході, використовує патерни взаємодії користувача з інтелектуальною системою та містить фази побудови патернів пояснень й формування пояснень з використанням отриманих патернів. Метод упорядковує отримані пояснення за ймовірністю використання, що дає можливість сформувати цільове та альтернативні пояснення для користувача. Висновки: Обґрунтовано використання принципу чорного ящику до розробки ймовірнісного підходу до побудови пояснень в інтелектуальних системах. Запропоновано модель патерну пояснень на базі темпоральних правил. Модель відображає послідовність взаємодії користувача з інтелектуальною системою при отриманні рішень та рекомендацій та містить патерн взаємодії у складі темпоральних правил, що мають вагу, а також визначає ймовірність використання патерну взаємодії з користувачем. Розроблено метод інтерактивної побудови пояснень з урахуванням взаємодії користувача з інтелектуальною системою. Метод містить фази та етапи формування правила й патернів взаємодії з користувачем з визначенням ймовірності їх виконання, а також підбору у упорядкування патернів за ймовірністю їх реалізації. Виконано імплементацію методу при побудові пояснень для рекомендаційних систем.

The paper describes a mid-term daily peak load forecasting method using recurrent artificial neural network (RANN). Generally, the artificial neural network (ANN) algorithm is used to forecast short-term load pattern and many ANN structures have been developed and commercialized so far. Otherwise, learning and estimation for long-term and mid-term load forecasting are hard tasks due to lack of training data and increase of accumulated errors in long period estimation. The paper proposes a mid-term load forecasting structure in order to overcome these problems by input data replacement for special days and a recurrent-type NN application. Also, the proposed RANN gives good performances on estimating sudden and nonlinear demand increase during heat waves. The results of case studies using load data of South Korea are presented to show performances and effectiveness of the proposed RANN.

With the rapid development of the Internet of Things (IoT) in recent years, the popularization of different segments of IoT has emerged. The IoT technology is slowly evolving toward intelligence, convenience, low power consumption, large connectivity, and wide coverage. This evolution is significantly attributed to the emergence of Narrowband of Internet of Thing (NB-IoT). NB-IoT is an emerging technology with wide-coverage, large-connection, low-power consumption, and low-costs. The intelligent system based on NB-IoT, an important branch of the IoT field, has various functions and is widely used. However, the intelligent system based on NB-IoT also generates reliability problems, caused by hardware, software, and networks. Therefore, this study deeply evaluates the impact of the NB-IoT network on the reliability of IoT intelligent systems. We simulated the real-world scenario by using the ns-3 simulator, and then carried out several data transmission experiments and recorded the relevant data of transmission performance indicators, finally calculated and analyzed the reliability results by using quantitative reliability indicators. The three main experiments respectively change the transmission distance of the NB-IoT signal, increase the access amount of the NB-IoT signal in the system, and increase the obstacles in the transmission path. The experimental results are represented by the signal-to-interference ratio (SINR), throughput rate, packet loss rate, and correct rate of the received data block and loss. Finally, we verify the impact of the NB-IoT network on system reliability on the basis of the experimental results.

Urgency of the research. More complex robotic systems are characterized by a certain degree of intelligent behavior where, based on input, the system is able to adapt its behavior. The implementation of elements that support intelligent behavior in robotic systems, especially those based on the image of devices, is becoming common practice. The reason is simple, such a system is faster and more accurate.Target setting. Creating machine vision, however, is a complex problem, especially when it comes to applications with non-standard requirements. For each task, the vision system needs to be adapted to the conditions and requirements of the monitored objects. Other image adjustments and algorithms need to be applied to static objects rather than moving objects. Two-dimensional image information is sufficient for some manufacturing process, while others require a third dimension to remove a given piece from a disordered pile. Creating an intelligent robotic cell with a camera system therefore requires the creation of a vision system that meets the specified requirements. This is where space is open, because there are many different procedures and principles to deal with, but not all are equally effective and reliable.Actual scientific researches and issues analysis. Many of the image processing methods can be combined with each other, or a new, better way to solve the problem can be developed using the approaches already known. Adding to this fact non-standard requirements profiled in practice, there is an undeniable reason why it is appropriate to deal with image processing for industrial use.Uninvestigated parts of general matters defining are designing and create a robotic cell, whose activity will be controlled on the basis of image perception obtained by digital camera.The research objective of this article is to design and create a robotic cell, whose activity will be controlled on the basis of image perception obtained by digital camera. The obtained image will be subjected to suitable image processing algorithms which will result in the generation of control instructions for controlling the manipulator movement.The statement of basic materials. The work deals with the design of a robotic cell whose task is to manipulate sample objects placed on the conveyor belt by means of a parallel manipulation robot based on image perception. The main part of the design is the creation of control software, which in the first level ensures the proper functioning of the individual components and in the second level their mutual cooperation, which ensures the performance of the required functionality of the robotic system as a whole. Created software runs on Windows 7 operating system, where it offers a simple tool to control the movement of the arms of a parallel robot without using other control means. This means that the robot's movements can be controlled directly from the control program, allowing the robot and object to be manipulated even in manual mode. The image obtained by the camera can be adjusted by software using the implemented tools before the automatic manipulation begins, allowing the user to set the correct input parameters to ensure reliable object identification.Conclusions. In order to design a robotic system whose operation is controlled on the basis of visual perception, it was necessary to acquire theoretical knowledge for the correct selection of individual components of the system as well as their correct placement within the robotic cell. Great emphasis was placed on suitable and economical selection of the sensing device and the way of illuminating the scanned objects. In order to obtain the camera image it was also necessary to study and understand the principle of working with the image captured by the camera via SDK issued directly by the camera manufacturer. However, obtaining an image was only the first step to start the image processing process. In order to extract the necessary data from the obtained image and then to create control instructions from the data for controlling the robot, it was necessary to study and learn in detail the individual steps and procedures of image processing. In the part of the work dealing with image processing the acquired knowledge was applied to the processing process itself, but not only known approaches were used. Owing to the reduction of CPU load and consequently shortening of the calculation process, own procedures were also introduced into the image processing process. The actual "economical" approach was applied and tested in the thresholding process where a "shortened thresholding algorithm" was created. The approach was also applied to the object-in-picture search process, creating a "network-based object-in-picture method" that uses the fact that we search and identify known objects in industrial applications as opposed to identifying objects in an unknown environment. The combination of image acquisition, image processing and robot control with one comprehensive application is also a major benefit. Of course, to ensure this functionality, it was first necessary to create a theoretical base on which to build. The main problem was to create a control part of the robot control in C # and to link it to the basic control program created in C ++., Актуальність теми дослідження. Більш складні роботизовані системи характеризуються певним рівнем інтелектуальної поведінки, де на основі входу система здатна адаптувати свою поведінку. Реалізація елементів, що підтримують інтелектуальну поведінку в робототехнічних системах, особливо тих, що базуються на зображенні пристроїв, стає загальною практикою. Причина проста – така система швидша та більш точніша.Постановка проблеми. Однак створення машинного зору є складною проблемою, особливо якщо йдеться про додатки з нестандартними вимогами. Для кожного завдання систему зору необхідно адаптувати до умов та вимог об'єктів, що контролюються. Інші налаштування зображення та алгоритми повинні застосовуватися до статичних об'єктів, а не до рухомих об'єктів. Інформація про двовимірне зображення є достатньою для певного процесу виготовлення, а для інших потрібен третій вимір для видалення заданої частини з невпорядкованого об’єднання. Створення інтелектуального роботизованого модуля із камерною системою вимагає створення системи зору, яка відповідає специфічним вимогам. Тут відкритий простір, оскільки існує багато різних процедур та принципів, з якими потрібно узгоджуватися, але не всі є однаково ефективними та надійними.Аналіз останніх досліджень і публікацій. Більшість методів обробки зображень можуть поєднуватися один з одним, або може бути розроблений новий, більш ефективний спосіб вирішення проблеми з використанням вже відомих підходів. Додавання до цього факту нестандартних вимог, що виникають на практиці, є беззаперечною причиною, чому доцільно займатися обробкою зображень для промислового використання.Виділення недосліджених частин загальної проблеми є розроблення і створення роботизованого модуля, діяльність якого буде контролюватися на основі сприйняття зображення, отриманого з цифрової камери.Постановка завдання. Основне завдання цієї статті полягає у розробці та створенні роботизованого модуля, діяльність якого буде контролюватися на основі сприйняття зображення, отриманого цифровою камерою. Отримане зображення буде оброблено узгодженими алгоритмами обробки зображень, що приведе до створення керівних дій для управління рухом маніпулятора.Виклад основного матеріалу. У роботі розглядається конструкція роботизованого модуля, завдання якого – маніпулювати зразками предметів, розміщених на конвеєрі, за допомогою паралельного робота-маніпулятора на основі сприйняття зображення. Основна частина конструкції - це створення програмного забезпечення управління, яке на першому рівні забезпечує належне функціонування окремих компонентів, а на другому рівні їх взаємну співпрацю, що забезпечує виконання необхідної функціональності роботизованої системи загалом. Створене програмне забезпечення працює в операційній системі Windows 7, де пропонується простий інструмент для управління рухом паралельного робота без використання інших засобів управління. Це означає, що рухом робота можна керувати безпосередньо з програми управління, що дозволяє впливати на робота і об'єкт навіть в ручному режимі. Зображення, отримане камерою, може коригуватися програмним забезпеченням за допомогою реалізованих інструментів до початку автоматичної маніпуляції, що дозволяє користувачеві встановити правильні вхідні параметри для забезпечення надійної ідентифікації об'єкта.Висновки відповідно до статті. Для розробки роботизованої системи, функціонування якої контролюється на основі візуального сприйняття, необхідно було придбати теоретичні знання для правильного підбору окремих компонентів системи, а також їх правильного розміщення всередині роботизованого модуля. Значну увагу приділено вибору підходящого та економного чутливого елементу пристрою та способу освітлення сканованих об'єктів. Для отримання зображення з камери необхідно було також вивчити та зрозуміти принцип роботи із зображенням, отриманим камерою через SDK, виготовленим безпосередньо виробником камери. Однак отримання зображення було лише першим кроком для початку процесу обробки зображень. Для того, щоб витягти необхідні дані з отриманого зображення, а потім створити керуючі інструкції з даних для управління роботом, необхідно було детально вивчити окремі кроки та процедури обробки зображень. У частині роботи, що стосується обробки зображень, отримані знання були застосовані до самого процесу обробки, але використовувались не лише відомі підходи. Завдяки зменшенню завантаження процесора і, отже, скороченню процесу обчислення, в процес обробки зображень також були введені власні процедури. Фактичний «економний» підхід застосовувався та перевірявся в процесі порогового визначення, де був створений «скорочений алгоритм порогової оцінки». Підхід також застосовано для процесу пошуку об’єкта в зображенні, створюючи «мережевий метод об'єкта в зображенні», який використовує той факт, що шукають та ідентифікують відомі об'єкти в промислових додатках на відміну від ідентифікації об'єктів у невідомому середовищі. Поєднання зображення, обробки зображень та управління роботом з одним комплексним використанням також є головною перевагою. Звичайно, щоб забезпечити цю функціональність, спочатку потрібно було створити теоретичну базу, на якій проводилася розробка. Основна проблема полягала в тому, щоб створити контрольну частину керування роботом в C # і пов'язати її з базовою програмою управління, створеною в C ++.

Financial support from the Spanish Ministry of Universities "Disruptive group decision making systems in fuzzy context: Applications in smart energy and people analytics" (PID2019-103880RB-I00), and Junta de Andalucia (SEJ340) is gratefully acknowledged., The maintenance of cash levels under certain security thresholds is key for the health of the banking sector. In this paper, the monitoring process of branch network cash levels is performed using a single intelligent system which should provide an alert when there are cash shortages at any point of the network. Such an integral solution would provide a unified insight that guarantees that branches with similar cash features are secured as a whole. That is to say, a triggered alarm at a specific branch would indicate that attention must also be paid to similar (in-cash-feature) branches. The system also incorporates a (complementary) specific treatment for individual branches. The Early Warning System for securing cash levels presented in this paper (cash level EWS) is deliberately free of local demographic specifications, thereby overcoming the current lack of worldwide definitions for local demographics. This aspect would be particularly valuable for banking institutions with branch networks all over the world. A further benefit is the cost reductions that are a result of replacing several approaches with a single global one. Instead of local demographic parameters, a solid theoretical model based on Markov random fields (MRFs) has been developed. The use of MRFs means a reduction in the amount of information required. This would mean a higher processing speed as well as a significant reduction in the amount of storage capacity required. To the best of the author's knowledge, this is the first time that MRFs have been applied to cash monitoring., Spanish Ministry of Universities PID2019-103880RB-I00, Junta de Andalucia SEJ340

A wide range of techniques exist to help control the thermal comfort of an occupant in indoor environments. A novel technique is presented here to adaptively estimate the occupant’s metabolic rate. This is performed by utilising occupant’s actions using computer vision system to identify the activity of an occupant. Recognized actions are then translated into metabolic rates. The widely used Predicted Mean Vote (PMV) thermal comfort index is computed using the adaptivey estimated metabolic rate value. The PMV is then used as an input to a fuzzy control system. The performance of the proposed system is evaluated using simulations of various activities. The integration of PMV thermal comfort index and action recognition system gives the opportunity to adaptively control occupant’s thermal comfort without the need to attach a sensor on an occupant all the time. The obtained results are compared with the results for the case of using one or two fixed metabolic rates. The included results appear to show improved performance, even in the presence of errors in the action recognition system.

Many algorithms use clustering to improve vehicular ad hoc network performance. The expected points of many of these approaches support multiple rounds of data to the roadside unit and constantly include clustering in every round of single-hop data transmission towards the road side unit, however, the clustering in every round maximizes the number of control messages and there could be the possibility of collision and decreases in network energy. Multi-hop transmission prolongs the cluster head node’s lifetime and boosts the network’s efficiency. Accordingly, this article proposes a new fuzzy-clustering-based routing algorithm to benefit from multi-hop transmission clustering simultaneously. This research has analyzed the limitation of clustering in each round, different algorithms were used to perform the clustering, and multi-hop routing was used to transfer the data of every cluster to the road side unit. The fuzzy logic was used to choose the head node of each cluster. Three parameters, (1) distance of each node, (2) remaining energy, and (3) number of neighbors of every node, were considered as fuzzy criteria. The results of this research were compared to various other algorithms in relation to parameters like dead node in every round, first node expire, half node expire, last node expire, and the network lifetime. The simulation results show that the proposed approach outperforms other methods. On the other hand, the vehicular ad hoc network (VANET) environment is vulnerable at the time of data transmission. The NS-2 software tool was used to simulate and evaluate the proposed fuzzy logic opportunistic routing’s performance results concerning end-to-end delay, packet delivery, and network throughput. We compare to the existing protocols, such as fuzzy Internet of Things (IoT), two fuzzy, and Fuzzy-Based Driver Monitoring System (FDMS). The performance comparison also emphasizes an effective utilization of the resources. Simulations on the highway environment show that the suggested protocol has an improved Quality of Service (QoS) efficiency compared to the above published methods in the literature.

Background With the emergence of the new coronavirus pandemic (COVID-19), distance learning, especially that mediated by information and digital communication technologies, has been adopted in all areas of knowledge and at all levels, including medical education. Imminently practical areas, such as pathology, have made traditional teaching based on conventional microscopy more flexible through the synergies of computational tools and image digitization, not only to improve teaching-learning but also to offer alternatives to repetitive and exhaustive histopathological analyzes. In this context, machine learning algorithms capable of recognizing histological patterns in kidney biopsy slides have been developed and validated with a view to building computational models capable of accurately identifying renal pathologies. In practice, the use of such algorithms can contribute to the universalization of teaching, allowing quality training even in regions where there is a lack of good nephropathologists. The purpose of this work is to describe and test the functionality of SmartPathk, a tool to support teaching of glomerulopathies using machine learning. The training for knowledge acquisition was performed automatically by machine learning methods using the J48 algorithm to create a computational model of an appropriate decision tree. Results An intelligent system, SmartPathk, was developed as a complementary remote tool in the teaching-learning process for pathology teachers and their students (undergraduate and graduate students), showing 89,47% accuracy using machine learning algorithms based on decision trees. Conclusion This artificial intelligence system can assist in teaching renal pathology to increase the training capacity of new medical professionals in this area.

Cloud-computing web systems and services revolutionized the web Nowadays, they are the most important part of the Internet Cloud-computing systems provide the opportunity for businesses to undergo digital transformation in order to improve efficiency and reduce costs The sudden shutdown of schools and offices during the pandemic of Covid 19 significantly increased the demand for cloud solutions Load balancing and sharing mechanisms are implemented in order to reduce the costs and increase the quality of web service The usage of those methods with adaptive intelligent algorithms can deliver the highest and a predictable quality of service In this article, a new HTTP request-distribution method in a two-layer architecture of a cluster-based web system is presented This method allows for the provision of efficient processing and predictable quality by servicing requests in adopted time constraints The proposed decision algorithms utilize fuzzy-neural models allowing service times to be estimated This article provides a description of this new solution It also contains the results of experiments in which the proposed method is compared with other intelligent approaches such as Fuzzy-Neural Request Distribution, and distribution methods often used in production systems © 2021 by the author Licensee MDPI, Basel, Switzerland

Big moving objects arise as a novel class of big data objects in emerging environments. Here, the main problems are the following: (i) tracking, which represents the baseline operation for a plethora of higher-level functionalities, such as detection, classification, and so forth; (ii) analysis, which meaningfully marries with big data analytics scenarios. In line with these goals, in this paper we propose a novel family of scan matching algorithms based on registration, which are enhanced by using a genetic pre-alignment phase based on a novel metrics, fist, and, second, performing a finer alignment using a deterministic approach. Our experimental assessment and analysis confirms the benefits deriving from the proposed novel family of such algorithms.

There is a growing use of intelligent systems to support human decision-making across several domains. Trust in intelligent systems, however, is pivotal in shaping their widespread adoption. Little is currently understood about how trust in an intelligent system evolves over time and how it is mediated by the accuracy of the system. We aim to address this knowledge gap by exploring trust formation over time and its relation to system accuracy. To that end, we built an intelligent house recommendation system and carried out a longitudinal study consisting of 201 participants across 3 sessions in a week. In each session, participants were tasked with finding housing that fit a given set of constraints using a conventional web interface that reflected a typical housing search website. Participants could choose to use an intelligent decision support system to help them find the right house. Depending on the group, participants received a variation of accurate or inaccurate advice from the intelligent system throughout each session. We measured trust using a trust in automation scale at the end of each session. We found evidence suggesting that trust development is a slow process that evolves over multiple sessions, and that first impressions of the intelligent system are highly influential. Our results echo earlier research on trust formation in single session interactions, corroborating that reliability, validity, predictability, and dependability all influence trust formation. We also found that the age of the participants and their affinity with technology had an effect on their trust in the intelligent system. Our findings highlight the importance of first impressions and improvement of system accuracy for trust development. Hence, our study is an important first step in understanding trust development, breakdown of trust, and trust repair over multiple system interactions, informing improved system design.

In this paper we describe a scan-matching based registration algorithm for tracking moving objects which falls in the emerging area that predicates the integration between robotics and big data applications. The scan matching approaches track paths of a mobile object by comparing maps of the environment seen by the object during its movement. Algorithms described in this paper are hybrid, i.e. they compare maps by using first a genetic pre-alignment based on a novel metrics, and then performing a finer alignment using a deterministic approach. This kind of hybridization is, indeed, not new. However, the novel metrics used in this paper leads to important new properties, namely to correct arbitrary rotational errors and to cover larger search spaces. The proposed algorithm is experimentally compared to other approaches, and better performance in terms of accuracy and robustness are reported. Finally, our algorithm is also very fast thanks to the genetic pre-alignment task and the novel metrics we propose.

We propose a novel approach to human interaction with artificial intelligence systems (HAII), alternative to the mainstream dyadic one where humans and AI are seen as interacting agents. Through two quantitative experiments and two qualitative in-field case studies, we show that the mainstream HAII paradigm presents potentially harmful design shortcomings as it can trigger negative dynamics such as automation bias and prejudices. Our proposal, on the other hand, is grounded in the Computer-Supported Cooperative Work literature, in which AI can be conceived as a component of a Knowledge Artifact (KA). This consists of an ecosystem of knowledge creation tools whose goal is to support a Ba (after Nonaka), i.e. a collective of competent decision makers. We highlight the cooperative nature of decision making and the AI functionalities that a KA should embed. These include eXplainable AI solutions, aimed at facilitating appropriation, but also functionalities that enable reasoning in a collaborative setting. Finally, we discuss how moving intelligence and agency from individual agents to the human collective can help to mitigate the shortcomings of dyadic HAII (e.g., deskilling), re-distribute responsibility in critical tasks, and revisit the HAII research agenda to align it with the needs of increasingly wide, heterogeneous and complex teams.

International audience; Since the application of information and communications technologies (ICT) to agriculture is far from the potential, we investigate how to systematize the process of transformation. In this article, we propose a new approach to design intelligent systems for the management and supervision of smart agriculture, as well as an example of its application in the beekeeping sector. It consists of the analysis of all the decisions that can be made using a spatio-temporal matrix that couples the time horizons to the modeling approaches. The final goal is to develop a reusable architecture for smart agriculture.

Modern cars include a huge number of sensors and actuators, which continuously exchange data and control commands. The most used protocol for communication of different components in automotive system is the Controller Area Network (CAN). According to CAN, components communicate by broadcasting messages on a bus. In addition, the standard definition of the protocol does not provide information for authentication, so exposing it to attacks. This paper proposes a method based on deep learning aiming at discovering attacks towards the CAN-bus. In particular, Neural Networks and MultiLayer Perceptrons are the class of networks employed in our approach. We also validate our approach by analysing a real-world dataset with the injection of messages from different types of attacks: denial of service, fuzzy pattern attacks, and attacks against specific components. The obtained results are encouraging and demonstrate the effectiveness of the approach. © 2000-2011 IEEE.

An increasing amount of research on Intelligent Systems/Artificial Intelligence (AI) in marketing has shown that AI is capable of mimicking humans and performing activities in an ‘intelligent’ manner. Considering the growing interest in AI among marketing researchers and practitioners, this review seeks to provide an overview of the trajectory of marketing and AI research fields. Building upon the review of 164 articles published in Web of Science and Scopus indexed journals, this article develops a context-specific research agenda. Our study of selected articles by means of Multiple Correspondence Analysis (MCA) procedure outlines several research avenues related to the adoption, use, and acceptance of AI technology in marketing, the role of data protection and ethics, the role of institutional support for marketing AI, as well as the revolution of the labor market and marketers’ competencies.

The COVID-19 pandemic has changed education forever because schools, universities, teachers, and students had to adapt to distance learning. Multiple differences are identified with online learning compared to face-to-face education. First, students must be more responsible. Second, users' familiarity with using computers varies significantly. Third, the traditional interaction between teacher, student and content are made more complicated by the introduction of technology. The application of new tools related to the student, teacher, content, technology, software, and communication results in the improvement of teaching methods in online learning. When new tools are applied and there is an improvement in the results in online education, the student, teacher, and educational institutions benefit from it. Emotion plays an important role in the knowledge, acquisition, and decision process of an individual. Consequently, they directly influence perception, learning process, and the way people communicate. There is also significant evidence that rational learning in humans is dependent on emotions. In this paper, we presented a solution with a new Intelligent Tutoring Framework, that analyzed emotions in a non-intrusive and non-invasive way., This work has been supported by national funds through FCT -Fundacao para a Ciencia e Tecnologia through project UIDB/04728/2020

With the increasing aging population in modern society, falls as well as fall-induced injuries in elderly people become one of the major public health problems. This study proposes a classification framework that uses floor vibrations to detect fall events as well as distinguish different fall postures. A scaled 3D-printed model with twelve fully adjustable joints that can simulate human body movement was built to generate human fall data. The mass proportion of a human body takes was carefully studied and was reflected in the model. Object drops, human falling tests were carried out and the vibration signature generated in the floor was recorded for analyses. Machine learning algorithms including K-means algorithm and K nearest neighbor algorithm were introduced in the classification process. Three classifiers (human walking versus human fall, human fall versus object drop, human falls from different postures) were developed in this study. Results showed that the three proposed classifiers can achieve the accuracy of 100, 85, and 91%. This paper developed a framework of using floor vibration to build the pattern recognition system in detecting human falls based on a machine learning approach.

In the era of big data, data volumes continue to grow in several different domains, from business to scientific fields. Sensors, edge devices, scientific applications and detectors generate huge amounts of data that are distributed for their nature. In order to extract value from such data requires a typical pipeline made of two main steps: first, the processing and then the data access. One of the main features for data access is fast response time, whose order of magnitude can vary a lot depending on the specific type of processing as well as processing patterns. The optimization of the access layer becomes more and more important while dealing with a geographically distributed environment where data must be retrieved from remote servers of a data lake. From the infrastructural perspectives, caching systems are used to mitigate latency and to serve better popular data. Thus, the role of the cache becomes a key to have an effective and efficient data access. In this article, we propose a Reinforcement Learning approach, using the Q-Learning technique, to improve the performances of a cache system in terms of data management. The proposed method uses two agents with different objectives and actions to control the addition and the eviction of files in the cache. The aim of this system is to increase the throughput reducing, at the same time, the cache costs, such as the amount of data written, and network utilization. Moreover, we tested our method in a context of data analysis, with information taken from High Energy Physics (HEP) workflow.

Buildings are one of the primary consumers of energy. In addition to the electricity grids, renewable energies can be used to supply the energy demand of buildings. Intelligent systems such as the Internet of Things (IoT) and wireless sensor technologies can also be applied to manage the energy consumption in buildings. Fortunately, integrating renewable energies with these intelligent systems enables creating nearly zero-energy buildings. In this paper, we present the results of our experimentation to demonstrate forming such a building and showing the benefits for building users and the society. We create a system by integrating photovoltaic (PV) technology with an IoT-based control mechanism to supply and consume energy. We further illustrate “how the integration of IoT and PV technology can bring added value to the users?”. To this end, we evaluate the performance of our system against conventional ways of energy supply and consumption for a lighting use case in a dairy store. We also investigate the environmental and economic impacts of our system. In our implementation, for the IoT-based control system, we have used a set of sensors, a server, and a wireless network to control the energy consumption. We developed a web application for user interaction and software-based settings. To control the lighting system, we developed an algorithm that utilizes the ambient light, users’ movements inside the store and a historical dataset. The historical dataset was collected from the users’ behaviour as a training set for the algorithm for turning on and off the lights. We also designed an electricity management system that computes the energy generation by the PV panels, controls the energy supply, and imports and exports electricity to the grid. The results show that our system is an efficient approach for creating energy-independent buildings by integrating renewable energies with IoT-based control systems. The results also show that our system not only responds to the internal demand by using domestic supply, but it also (i) offers economic benefit by exporting extra renewable electricity to the grid, and (ii) prevents producing huge amounts of CO2. Our system is one of the first works to achieve a nearly zero-energy building in the developing countries with low electricity accessibility.