Choose an application

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

Modern society is witnessing a sea change in ubiquitous computing, in which people have embraced computing systems as an indispensable part of day-to-day existence. Computation, storage, and communication abilities of smartphones, for example, have undergone monumental changes over the past decade. However, global emphasis on creating and sustaining green environments is leading to a rapid and ongoing proliferation of edge computing systems and applications. As a broad spectrum of healthcare, home, and transport applications shift to the edge of the network, near-threshold computing (NTC) is emerging as one of the promising low-power computing platforms. An NTC device sets its supply voltage close to its threshold voltage, dramatically reducing the energy consumption. Despite showing substantial promise in terms of energy efficiency, NTC is yet to see widescale commercial adoption. This is because circuits and systems operating with NTC suffer from several problems, including increased sensitivity to process variation, reliability problems, performance degradation, and security vulnerabilities, to name a few. To realize its potential, we need designs, techniques, and solutions to overcome these challenges associated with NTC circuits and systems. The readers of this book will be able to familiarize themselves with recent advances in electronics systems, focusing on near-threshold computing.

Technology: general issues --- machine learning --- neural networks --- gait analysis --- embedded system --- NTV --- NTC --- low-power --- low-voltage memory and clocking circuits --- minimum-energy design --- power-performance --- resilient adaptive computing --- edge devices --- power management --- energy efficiency --- near-threshold computing (NTC) --- deep neural network (DNN) --- accelerators --- timing error --- AI --- tensor processing unit (TPU) --- multiply and accumulate (MAC) --- reliability --- Near-Threshold Computing --- functional unit --- performance optimization --- cross-layer optimization --- machine learning --- neural networks --- gait analysis --- embedded system --- NTV --- NTC --- low-power --- low-voltage memory and clocking circuits --- minimum-energy design --- power-performance --- resilient adaptive computing --- edge devices --- power management --- energy efficiency --- near-threshold computing (NTC) --- deep neural network (DNN) --- accelerators --- timing error --- AI --- tensor processing unit (TPU) --- multiply and accumulate (MAC) --- reliability --- Near-Threshold Computing --- functional unit --- performance optimization --- cross-layer optimization

Choose an application

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

Emotions play a very important role in how we think and behave. As such, the emotions we feel every day can compel us to act and influence the decisions and plans we make about our lives. Being able to measure, analyze, and better comprehend how or why our emotions may change is thus of much relevance to understand human behavior and its consequences. Despite the great efforts made in the past in the study of human emotions, it is only now, with the advent of wearable, mobile, and ubiquitous technologies, that we can aim to sense and recognize emotions, continuously and in real time. This book brings together the latest experiences, findings, and developments regarding ubiquitous sensing, modeling, and the recognition of human emotions.

self-management interview application --- emotion analysis --- facial recognition --- image-mining --- deep convolutional neural network --- emotion recognition --- pattern recognition --- texture descriptors --- mobile tool --- neuromarketing --- brain computer interface (BCI) --- consumer preferences --- EEG signal --- deep learning --- deep neural network (DNN) --- electroencephalogram (EEG) --- logistic regression --- Gaussian kernel --- Laplacian prior --- affective computing --- human–robot interaction --- thermal IR imaging --- social robots --- facial expression analysis --- line segment feature analysis --- dimensionality reduction --- convolutional recurrent neural network --- driver health risk --- intelligent speech signal processing --- human computer interaction --- supervised learning --- computer vision --- optical flow --- micro facial expressions --- real-time processing --- driver stress state --- IR imaging --- machine learning --- support vector machine (SVR) --- advanced driver-assistance systems (ADAS) --- artificial intelligence --- image processing --- video processing

Choose an application

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

The present book contains the 10 articles finally accepted for publication in the Special Issue “Computational Optimizations for Machine Learning” of the MDPI journal Mathematics, which cover a wide range of topics connected to the theory and applications of machine learning, neural networks and artificial intelligence. These topics include, among others, various types of machine learning classes, such as supervised, unsupervised and reinforcement learning, deep neural networks, convolutional neural networks, GANs, decision trees, linear regression, SVM, K-means clustering, Q-learning, temporal difference, deep adversarial networks and more. It is hoped that the book will be interesting and useful to those developing mathematical algorithms and applications in the domain of artificial intelligence and machine learning as well as for those having the appropriate mathematical background and willing to become familiar with recent advances of machine learning computational optimization mathematics, which has nowadays permeated into almost all sectors of human life and activity.

Research & information: general --- Mathematics & science --- ARIMA model --- time series analysis --- online optimization --- online model selection --- precipitation nowcasting --- deep learning --- autoencoders --- radar data --- generalization error --- recurrent neural networks --- machine learning --- model predictive control --- nonlinear systems --- neural networks --- low power --- quantization --- CNN architecture --- multi-objective optimization --- genetic algorithms --- evolutionary computation --- swarm intelligence --- Heating, Ventilation and Air Conditioning (HVAC) --- metaheuristics search --- bio-inspired algorithms --- smart building --- soft computing --- training --- evolution of weights --- artificial intelligence --- deep neural networks --- convolutional neural network --- deep compression --- DNN --- ReLU --- floating-point numbers --- hardware acceleration --- energy dissipation --- FLOW-3D --- hydraulic jumps --- bed roughness --- sensitivity analysis --- feature selection --- evolutionary algorithms --- nature inspired algorithms --- meta-heuristic optimization --- computational intelligence --- ARIMA model --- time series analysis --- online optimization --- online model selection --- precipitation nowcasting --- deep learning --- autoencoders --- radar data --- generalization error --- recurrent neural networks --- machine learning --- model predictive control --- nonlinear systems --- neural networks --- low power --- quantization --- CNN architecture --- multi-objective optimization --- genetic algorithms --- evolutionary computation --- swarm intelligence --- Heating, Ventilation and Air Conditioning (HVAC) --- metaheuristics search --- bio-inspired algorithms --- smart building --- soft computing --- training --- evolution of weights --- artificial intelligence --- deep neural networks --- convolutional neural network --- deep compression --- DNN --- ReLU --- floating-point numbers --- hardware acceleration --- energy dissipation --- FLOW-3D --- hydraulic jumps --- bed roughness --- sensitivity analysis --- feature selection --- evolutionary algorithms --- nature inspired algorithms --- meta-heuristic optimization --- computational intelligence

Choose an application

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

The ongoing digitalization of the energy sector, which will make a large amount of data available, should not be viewed as a passive ICT application for energy technology or a threat to thermodynamics and fluid dynamics, in the light of the competition triggered by data mining and machine learning techniques. These new technologies must be posed on solid bases for the representation of energy systems and fluid machinery. Therefore, mathematical modelling is still relevant and its importance cannot be underestimated. The aim of this Special Issue was to collect contributions about mathematical modelling of energy systems and fluid machinery in order to build and consolidate the base of this knowledge.

Technology: general issues --- centrifugal pump --- double hidden layer --- Levenberg–Marquardt algorithm --- performance prediction --- thermal energy storage --- stratification --- dynamic simulation --- heating --- double-channel sewage pump --- critical wall roughness --- numerical calculation --- external characteristics --- axial-flow pump --- impeller --- approximation model --- optimization design --- multi-disciplinary --- blade slot --- orthogonal test --- numerical simulation --- Francis turbine --- anti-cavity fins --- draft tube --- vortex rope --- low flow rates --- internal flow characteristics --- unsteady pressure --- energy recovery --- turboexpander --- throttling valves --- CFD --- modelling techniques --- Kaplan turbine --- draft tube optimization --- CFD analysis --- DOE --- response surface --- single-channel pump --- CFD-DEM coupling method --- particle features and behaviors --- solid-liquid two-phase flows --- computational fluid dynamics (CFD) --- artificial neural network (ANN) --- subcooled boiling flows --- uncertainty quantification (UQ) --- Monte Carlo dropout --- deep ensemble --- deep neural network (DNN) --- intake structures --- physical hydraulic model --- free surface flow --- free surface vortices --- vertical pump --- design considerations --- magnetocaloric effect --- coefficient of performance --- refrigeration --- capacity --- mathematical modelling --- energy systems

Choose an application

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

The ongoing digitalization of the energy sector, which will make a large amount of data available, should not be viewed as a passive ICT application for energy technology or a threat to thermodynamics and fluid dynamics, in the light of the competition triggered by data mining and machine learning techniques. These new technologies must be posed on solid bases for the representation of energy systems and fluid machinery. Therefore, mathematical modelling is still relevant and its importance cannot be underestimated. The aim of this Special Issue was to collect contributions about mathematical modelling of energy systems and fluid machinery in order to build and consolidate the base of this knowledge.

Technology: general issues --- centrifugal pump --- double hidden layer --- Levenberg–Marquardt algorithm --- performance prediction --- thermal energy storage --- stratification --- dynamic simulation --- heating --- double-channel sewage pump --- critical wall roughness --- numerical calculation --- external characteristics --- axial-flow pump --- impeller --- approximation model --- optimization design --- multi-disciplinary --- blade slot --- orthogonal test --- numerical simulation --- Francis turbine --- anti-cavity fins --- draft tube --- vortex rope --- low flow rates --- internal flow characteristics --- unsteady pressure --- energy recovery --- turboexpander --- throttling valves --- CFD --- modelling techniques --- Kaplan turbine --- draft tube optimization --- CFD analysis --- DOE --- response surface --- single-channel pump --- CFD-DEM coupling method --- particle features and behaviors --- solid-liquid two-phase flows --- computational fluid dynamics (CFD) --- artificial neural network (ANN) --- subcooled boiling flows --- uncertainty quantification (UQ) --- Monte Carlo dropout --- deep ensemble --- deep neural network (DNN) --- intake structures --- physical hydraulic model --- free surface flow --- free surface vortices --- vertical pump --- design considerations --- magnetocaloric effect --- coefficient of performance --- refrigeration --- capacity --- mathematical modelling --- energy systems --- centrifugal pump --- double hidden layer --- Levenberg–Marquardt algorithm --- performance prediction --- thermal energy storage --- stratification --- dynamic simulation --- heating --- double-channel sewage pump --- critical wall roughness --- numerical calculation --- external characteristics --- axial-flow pump --- impeller --- approximation model --- optimization design --- multi-disciplinary --- blade slot --- orthogonal test --- numerical simulation --- Francis turbine --- anti-cavity fins --- draft tube --- vortex rope --- low flow rates --- internal flow characteristics --- unsteady pressure --- energy recovery --- turboexpander --- throttling valves --- CFD --- modelling techniques --- Kaplan turbine --- draft tube optimization --- CFD analysis --- DOE --- response surface --- single-channel pump --- CFD-DEM coupling method --- particle features and behaviors --- solid-liquid two-phase flows --- computational fluid dynamics (CFD) --- artificial neural network (ANN) --- subcooled boiling flows --- uncertainty quantification (UQ) --- Monte Carlo dropout --- deep ensemble --- deep neural network (DNN) --- intake structures --- physical hydraulic model --- free surface flow --- free surface vortices --- vertical pump --- design considerations --- magnetocaloric effect --- coefficient of performance --- refrigeration --- capacity --- mathematical modelling --- energy systems