Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The analysis of power systems under various conditions represents one of the most important and complex tasks in electrical power engineering. Studies in this area are necessary to ensure that the reliability, efficiency, and stability of the power system is not adversely affected. This issue is devoted to reviews and applications of modern methods of signal processing used to analyze the operation of a power system and evaluate the performance of the system in all aspects. Smart grids as an emerging research field of the current decade is the focus of this issue. Monitoring capability with data integration, advanced analysis of support system control, enhanced power security and effective communication to meet the power demand, efficient energy consumption and minimum costs, and intelligent interaction between power-generating and -consuming devices depends on the selection and implementation of advanced signal analysis and processing techniques.

History of engineering & technology --- convolutional neural networks --- multi-headed CNN --- CNN-LSTM --- forecasting --- solar output --- sliding window --- renewable energy --- data mining --- cluster analysis --- power quality --- global power quality index --- electrical power network --- distributed generation --- mining industry --- ward algorithm --- different working conditions --- power supply restoration --- power supply outages --- failures --- time intervals --- obtaining information --- information recognition --- connection harmonization --- virtual power plant --- distributed energy resources --- energy storage systems --- grid codes --- power systems --- smart grids --- prosumer --- business model --- economic efficiency --- sensitivity analysis

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The analysis of power systems under various conditions represents one of the most important and complex tasks in electrical power engineering. Studies in this area are necessary to ensure that the reliability, efficiency, and stability of the power system is not adversely affected. This issue is devoted to reviews and applications of modern methods of signal processing used to analyze the operation of a power system and evaluate the performance of the system in all aspects. Smart grids as an emerging research field of the current decade is the focus of this issue. Monitoring capability with data integration, advanced analysis of support system control, enhanced power security and effective communication to meet the power demand, efficient energy consumption and minimum costs, and intelligent interaction between power-generating and -consuming devices depends on the selection and implementation of advanced signal analysis and processing techniques.

History of engineering & technology --- convolutional neural networks --- multi-headed CNN --- CNN-LSTM --- forecasting --- solar output --- sliding window --- renewable energy --- data mining --- cluster analysis --- power quality --- global power quality index --- electrical power network --- distributed generation --- mining industry --- ward algorithm --- different working conditions --- power supply restoration --- power supply outages --- failures --- time intervals --- obtaining information --- information recognition --- connection harmonization --- virtual power plant --- distributed energy resources --- energy storage systems --- grid codes --- power systems --- smart grids --- prosumer --- business model --- economic efficiency --- sensitivity analysis

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Artificial intelligence techniques, such as expert systems, fuzzy logic, and artificial neural network techniques have become efficient tools in modeling and control applications. For example, there are several benefits in optimizing cost-effectiveness, because fuzzy logic is a methodology for the handling of inexact, imprecise, qualitative, fuzzy, and verbal information systematically and rigorously. A neuro-fuzzy controller generates or tunes the rules or membership functions of a fuzzy controller with an artificial neural network approach. There are new instantaneous power theories that may address several challenges in power quality. So, this book presents different applications of artificial intelligence techniques in advanced high-tech electronics, such as applications in power electronics, motor drives, renewable energy systems and smart grids.

droop curve --- frequency regulation --- fuzzy logic --- the rate of change of frequency --- reserve power --- smart grid --- energy Internet --- convolutional neural network --- decision optimization --- deep reinforcement learning --- electric load forecasting --- non-dominated sorting genetic algorithm II --- multi-layer perceptron --- adaptive neuro-fuzzy inference system --- meta-heuristic algorithms --- automatic generation control --- fuzzy neural network control --- thermostatically controlled loads --- back propagation algorithm --- particle swarm optimization --- load disaggregation --- artificial intelligence --- cognitive meters --- machine learning --- state machine --- NILM --- non-technical losses --- semi-supervised learning --- knowledge embed --- deep learning --- distribution network equipment --- condition assessment --- multi information source --- fuzzy iteration --- current balancing algorithm --- level-shifted SPWM --- medium-voltage applications --- multilevel current source inverter --- motor drives --- phase-shifted carrier SPWM --- STATCOM --- electricity forecasting --- CNN–LSTM --- very short-term forecasting (VSTF) --- short-term forecasting (STF) --- medium-term forecasting (MTF) --- long-term forecasting (LTF) --- asynchronous motor --- linear active disturbance rejection control --- error differentiation --- vector control --- renewable energy --- solar power plant --- Data Envelopment Analysis (DEA) --- Fuzzy Analytical Network Process (FANP) --- Fuzzy Theory

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The modeling and processing of empirical data is one of the main subjects and goals of statistics. Nowadays, with the development of computer science, the extraction of useful and often hidden information and patterns from data sets of different volumes and complex data sets in warehouses has been added to these goals. New and powerful statistical techniques with machine learning (ML) and data mining paradigms have been developed. To one degree or another, all of these techniques and algorithms originate from a rigorous mathematical basis, including probability theory and mathematical statistics, operational research, mathematical analysis, numerical methods, etc. Popular ML methods, such as artificial neural networks (ANN), support vector machines (SVM), decision trees, random forest (RF), among others, have generated models that can be considered as straightforward applications of optimization theory and statistical estimation. The wide arsenal of classical statistical approaches combined with powerful ML techniques allows many challenging and practical problems to be solved. This Special Issue belongs to the section “Mathematics and Computer Science”. Its aim is to establish a brief collection of carefully selected papers presenting new and original methods, data analyses, case studies, comparative studies, and other research on the topic of statistical data modeling and ML as well as their applications. Particular attention is given, but is not limited, to theories and applications in diverse areas such as computer science, medicine, engineering, banking, education, sociology, economics, among others. The resulting palette of methods, algorithms, and applications for statistical modeling and ML presented in this Special Issue is expected to contribute to the further development of research in this area. We also believe that the new knowledge acquired here as well as the applied results are attractive and useful for young scientists, doctoral students, and researchers from various scientific specialties.

Information technology industries --- mathematical competency --- assessment --- machine learning --- classification and regression tree --- CART ensembles and bagging --- ensemble model --- multivariate adaptive regression splines --- cross-validation --- dam inflow prediction --- long short-term memory --- wavelet transform --- input predictor selection --- hyper-parameter optimization --- brain-computer interface --- EEG motor imagery --- CNN-LSTM architectures --- real-time motion imagery recognition --- artificial neural networks --- banking --- hedonic prices --- housing --- quantile regression --- data quality --- citizen science --- consensus models --- clustering --- Gower's interpolation formula --- Gower's metric --- mixed data --- multidimensional scaling --- classification --- data-adaptive kernel functions --- image data --- multi-category classifier --- predictive models --- support vector machine --- stochastic gradient descent --- damped Newton --- convexity --- METABRIC dataset --- breast cancer subtyping --- deep forest --- multi-omics data --- categorical data --- similarity --- feature selection --- kernel density estimation --- non-linear optimization --- kernel clustering

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Artificial intelligence techniques, such as expert systems, fuzzy logic, and artificial neural network techniques have become efficient tools in modeling and control applications. For example, there are several benefits in optimizing cost-effectiveness, because fuzzy logic is a methodology for the handling of inexact, imprecise, qualitative, fuzzy, and verbal information systematically and rigorously. A neuro-fuzzy controller generates or tunes the rules or membership functions of a fuzzy controller with an artificial neural network approach. There are new instantaneous power theories that may address several challenges in power quality. So, this book presents different applications of artificial intelligence techniques in advanced high-tech electronics, such as applications in power electronics, motor drives, renewable energy systems and smart grids.

History of engineering & technology --- droop curve --- frequency regulation --- fuzzy logic --- the rate of change of frequency --- reserve power --- smart grid --- energy Internet --- convolutional neural network --- decision optimization --- deep reinforcement learning --- electric load forecasting --- non-dominated sorting genetic algorithm II --- multi-layer perceptron --- adaptive neuro-fuzzy inference system --- meta-heuristic algorithms --- automatic generation control --- fuzzy neural network control --- thermostatically controlled loads --- back propagation algorithm --- particle swarm optimization --- load disaggregation --- artificial intelligence --- cognitive meters --- machine learning --- state machine --- NILM --- non-technical losses --- semi-supervised learning --- knowledge embed --- deep learning --- distribution network equipment --- condition assessment --- multi information source --- fuzzy iteration --- current balancing algorithm --- level-shifted SPWM --- medium-voltage applications --- multilevel current source inverter --- motor drives --- phase-shifted carrier SPWM --- STATCOM --- electricity forecasting --- CNN–LSTM --- very short-term forecasting (VSTF) --- short-term forecasting (STF) --- medium-term forecasting (MTF) --- long-term forecasting (LTF) --- asynchronous motor --- linear active disturbance rejection control --- error differentiation --- vector control --- renewable energy --- solar power plant --- Data Envelopment Analysis (DEA) --- Fuzzy Analytical Network Process (FANP) --- Fuzzy Theory