Choose an application

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

Smart, wearables devices on a miniature scale are becoming increasingly widely available, typically in the form of smart watches and other connected devices. Consequently, devices to assist in measurements such as electroencephalography (EEG), electrocardiogram (ECG), electromyography (EMG), blood pressure (BP), photoplethysmography (PPG), heart rhythm, respiration rate, apnoea, and motion detection are becoming more available, and play a significant role in healthcare monitoring. The industry is placing great emphasis on making these devices and technologies available on smart devices such as phones and watches. Such measurements are clinically and scientifically useful for real-time monitoring, long-term care, and diagnosis and therapeutic techniques. However, a pertaining issue is that recorded data are usually noisy, contain many artefacts, and are affected by external factors such as movements and physical conditions. In order to obtain accurate and meaningful indicators, the signal has to be processed and conditioned such that the measurements are accurate and free from noise and disturbances. In this context, many researchers have utilized recent technological advances in wearable sensors and signal processing to develop smart and accurate wearable devices for clinical applications. The processing and analysis of physiological signals is a key issue for these smart wearable devices. Consequently, ongoing work in this field of study includes research on filtration, quality checking, signal transformation and decomposition, feature extraction and, most recently, machine learning-based methods.

Technology: general issues --- History of engineering & technology --- automated dietary monitoring --- eating detection --- eating timing error analysis --- biomedical signal processing --- smart eyeglasses --- wearable health monitoring --- artificial neural network --- joint moment prediction --- extreme learning machine --- Hill muscle model --- online input variables --- Review --- ECG --- Signal Processing --- Machine Learning --- Cardiovascular Disease --- Anomaly Detection --- photoplethysmography --- motion artifact --- independent component analysis --- multi-wavelength --- continuous arterial blood pressure --- systolic blood pressure --- diastolic blood pressure --- deep convolutional autoencoder --- genetic algorithm --- electrocardiography --- vectorcardiography --- myocardial infarction --- long short-term memory --- spline --- multilayer perceptron --- pain detection --- stress detection --- wearable sensor --- physiological signals --- behavioral signals --- non-invasive system --- hemodynamics --- arterial blood pressure --- central venous pressure --- pulmonary arterial pressure --- intracranial pressure --- heart rate measurement --- remote HR --- remote PPG --- remote BCG --- blind source separation --- drowsiness detection --- EEG --- frequency-domain features --- multicriteria optimization --- machine learning --- n/a

Choose an application

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

Smart, wearables devices on a miniature scale are becoming increasingly widely available, typically in the form of smart watches and other connected devices. Consequently, devices to assist in measurements such as electroencephalography (EEG), electrocardiogram (ECG), electromyography (EMG), blood pressure (BP), photoplethysmography (PPG), heart rhythm, respiration rate, apnoea, and motion detection are becoming more available, and play a significant role in healthcare monitoring. The industry is placing great emphasis on making these devices and technologies available on smart devices such as phones and watches. Such measurements are clinically and scientifically useful for real-time monitoring, long-term care, and diagnosis and therapeutic techniques. However, a pertaining issue is that recorded data are usually noisy, contain many artefacts, and are affected by external factors such as movements and physical conditions. In order to obtain accurate and meaningful indicators, the signal has to be processed and conditioned such that the measurements are accurate and free from noise and disturbances. In this context, many researchers have utilized recent technological advances in wearable sensors and signal processing to develop smart and accurate wearable devices for clinical applications. The processing and analysis of physiological signals is a key issue for these smart wearable devices. Consequently, ongoing work in this field of study includes research on filtration, quality checking, signal transformation and decomposition, feature extraction and, most recently, machine learning-based methods.

Technology: general issues --- History of engineering & technology --- automated dietary monitoring --- eating detection --- eating timing error analysis --- biomedical signal processing --- smart eyeglasses --- wearable health monitoring --- artificial neural network --- joint moment prediction --- extreme learning machine --- Hill muscle model --- online input variables --- Review --- ECG --- Signal Processing --- Machine Learning --- Cardiovascular Disease --- Anomaly Detection --- photoplethysmography --- motion artifact --- independent component analysis --- multi-wavelength --- continuous arterial blood pressure --- systolic blood pressure --- diastolic blood pressure --- deep convolutional autoencoder --- genetic algorithm --- electrocardiography --- vectorcardiography --- myocardial infarction --- long short-term memory --- spline --- multilayer perceptron --- pain detection --- stress detection --- wearable sensor --- physiological signals --- behavioral signals --- non-invasive system --- hemodynamics --- arterial blood pressure --- central venous pressure --- pulmonary arterial pressure --- intracranial pressure --- heart rate measurement --- remote HR --- remote PPG --- remote BCG --- blind source separation --- drowsiness detection --- EEG --- frequency-domain features --- multicriteria optimization --- machine learning

Choose an application

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

This book includes impactful chapters which present scientific concepts, frameworks, architectures and ideas on sensing technologies and machine learning techniques. These are relevant in tackling the following challenges: (i) the field readiness and use of intrusive sensor systems and devices for capturing biosignals, including EEG sensor systems, ECG sensor systems and electrodermal activity sensor systems; (ii) the quality assessment and management of sensor data; (iii) data preprocessing, noise filtering and calibration concepts for biosignals; (iv) the field readiness and use of nonintrusive sensor technologies, including visual sensors, acoustic sensors, vibration sensors and piezoelectric sensors; (v) emotion recognition using mobile phones and smartwatches; (vi) body area sensor networks for emotion and stress studies; (vii) the use of experimental datasets in emotion recognition, including dataset generation principles and concepts, quality insurance and emotion elicitation material and concepts; (viii) machine learning techniques for robust emotion recognition, including graphical models, neural network methods, deep learning methods, statistical learning and multivariate empirical mode decomposition; (ix) subject-independent emotion and stress recognition concepts and systems, including facial expression-based systems, speech-based systems, EEG-based systems, ECG-based systems, electrodermal activity-based systems, multimodal recognition systems and sensor fusion concepts and (x) emotion and stress estimation and forecasting from a nonlinear dynamical system perspective.

Technology: general issues --- subject-dependent emotion recognition --- subject-independent emotion recognition --- electrodermal activity (EDA) --- deep learning --- convolutional neural networks --- automatic facial emotion recognition --- intensity of emotion recognition --- behavioral biometrical systems --- machine learning --- artificial intelligence --- driving stress --- electrodermal activity --- road traffic --- road types --- Viola-Jones --- facial emotion recognition --- facial expression recognition --- facial detection --- facial landmarks --- infrared thermal imaging --- homography matrix --- socially assistive robot --- EEG --- arousal detection --- valence detection --- data transformation --- normalization --- mental stress detection --- electrocardiogram --- respiration --- in-ear EEG --- emotion classification --- emotion monitoring --- elderly caring --- outpatient caring --- stress detection --- deep neural network --- convolutional neural network --- wearable sensors --- psychophysiology --- sensor data analysis --- time series analysis --- signal analysis --- similarity measures --- correlation statistics --- quantitative analysis --- benchmarking --- boredom --- emotion --- GSR --- classification --- sensor --- face landmark detection --- fully convolutional DenseNets --- skip-connections --- dilated convolutions --- emotion recognition --- physiological sensing --- multimodal sensing --- flight simulation --- activity recognition --- physiological signals --- thoracic electrical bioimpedance --- smart band --- stress recognition --- physiological signal processing --- long short-term memory recurrent neural networks --- information fusion --- pain recognition --- long-term stress --- electroencephalography --- perceived stress scale --- expert evaluation --- affective corpus --- multimodal sensors --- overload --- underload --- interest --- frustration --- cognitive load --- stress research --- affective computing --- human-computer interaction --- deep convolutional neural network --- transfer learning --- auxiliary loss --- weighted loss --- class center --- stress sensing --- smart insoles --- smart shoes --- unobtrusive sensing --- stress --- center of pressure --- regression --- signal processing --- arousal --- aging adults --- musical genres --- emotion elicitation --- dataset --- emotion representation --- feature selection --- feature extraction --- computer science --- virtual reality --- head-mounted display --- n/a

Choose an application

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

This book includes impactful chapters which present scientific concepts, frameworks, architectures and ideas on sensing technologies and machine learning techniques. These are relevant in tackling the following challenges: (i) the field readiness and use of intrusive sensor systems and devices for capturing biosignals, including EEG sensor systems, ECG sensor systems and electrodermal activity sensor systems; (ii) the quality assessment and management of sensor data; (iii) data preprocessing, noise filtering and calibration concepts for biosignals; (iv) the field readiness and use of nonintrusive sensor technologies, including visual sensors, acoustic sensors, vibration sensors and piezoelectric sensors; (v) emotion recognition using mobile phones and smartwatches; (vi) body area sensor networks for emotion and stress studies; (vii) the use of experimental datasets in emotion recognition, including dataset generation principles and concepts, quality insurance and emotion elicitation material and concepts; (viii) machine learning techniques for robust emotion recognition, including graphical models, neural network methods, deep learning methods, statistical learning and multivariate empirical mode decomposition; (ix) subject-independent emotion and stress recognition concepts and systems, including facial expression-based systems, speech-based systems, EEG-based systems, ECG-based systems, electrodermal activity-based systems, multimodal recognition systems and sensor fusion concepts and (x) emotion and stress estimation and forecasting from a nonlinear dynamical system perspective.

subject-dependent emotion recognition --- subject-independent emotion recognition --- electrodermal activity (EDA) --- deep learning --- convolutional neural networks --- automatic facial emotion recognition --- intensity of emotion recognition --- behavioral biometrical systems --- machine learning --- artificial intelligence --- driving stress --- electrodermal activity --- road traffic --- road types --- Viola-Jones --- facial emotion recognition --- facial expression recognition --- facial detection --- facial landmarks --- infrared thermal imaging --- homography matrix --- socially assistive robot --- EEG --- arousal detection --- valence detection --- data transformation --- normalization --- mental stress detection --- electrocardiogram --- respiration --- in-ear EEG --- emotion classification --- emotion monitoring --- elderly caring --- outpatient caring --- stress detection --- deep neural network --- convolutional neural network --- wearable sensors --- psychophysiology --- sensor data analysis --- time series analysis --- signal analysis --- similarity measures --- correlation statistics --- quantitative analysis --- benchmarking --- boredom --- emotion --- GSR --- classification --- sensor --- face landmark detection --- fully convolutional DenseNets --- skip-connections --- dilated convolutions --- emotion recognition --- physiological sensing --- multimodal sensing --- flight simulation --- activity recognition --- physiological signals --- thoracic electrical bioimpedance --- smart band --- stress recognition --- physiological signal processing --- long short-term memory recurrent neural networks --- information fusion --- pain recognition --- long-term stress --- electroencephalography --- perceived stress scale --- expert evaluation --- affective corpus --- multimodal sensors --- overload --- underload --- interest --- frustration --- cognitive load --- stress research --- affective computing --- human-computer interaction --- deep convolutional neural network --- transfer learning --- auxiliary loss --- weighted loss --- class center --- stress sensing --- smart insoles --- smart shoes --- unobtrusive sensing --- stress --- center of pressure --- regression --- signal processing --- arousal --- aging adults --- musical genres --- emotion elicitation --- dataset --- emotion representation --- feature selection --- feature extraction --- computer science --- virtual reality --- head-mounted display --- n/a

Choose an application

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

Non-invasive biomedical sensors for monitoring physiological parameters from the human body for potential future therapies and healthcare solutions. Today, a critical factor in providing a cost-effective healthcare system is improving patients' quality of life and mobility, which can be achieved by developing non-invasive sensor systems, which can then be deployed in point of care, used at home or integrated into wearable devices for long-term data collection. Another factor that plays an integral part in a cost-effective healthcare system is the signal processing of the data recorded with non-invasive biomedical sensors. In this book, we aimed to attract researchers who are interested in the application of signal processing methods to different biomedical signals, such as an electroencephalogram (EEG), electromyogram (EMG), functional near-infrared spectroscopy (fNIRS), electrocardiogram (ECG), galvanic skin response, pulse oximetry, photoplethysmogram (PPG), etc. We encouraged new signal processing methods or the use of existing signal processing methods for its novel application in physiological signals to help healthcare providers make better decisions.

Medical equipment & techniques --- movement intention --- brain–computer interface --- movement-related cortical potential --- neurorehabilitation --- phonocardiogram --- machine learning --- empirical mode decomposition --- feature extraction --- mel-frequency cepstral coefficients --- support vector machines --- computer aided diagnosis --- congenital heart disease --- statistical analysis --- convolutional neural network (CNN) --- long short-term memory (LSTM) --- emotion recognition --- EEG --- ECG --- GSR --- deep neural network --- physiological signals --- electroencephalography --- Brain-Computer Interface --- multiscale principal component analysis --- successive decomposition index --- motor imagery --- mental imagery --- classification --- hybrid brain-computer interface (BCI) --- home automation --- electroencephalogram (EEG) --- steady-state visually evoked potential (SSVEP) --- eye blink --- short-time Fourier transform (STFT) --- convolution neural network (CNN) --- human machine interface (HMI) --- rehabilitation --- wheelchair --- quadriplegia --- Raspberry Pi --- image gradient --- AMR voice --- Open-CV --- image processing --- acoustic --- startle --- reaction --- response --- reflex --- blink --- mobile --- sound --- stroke --- EMG --- brain-computer interface --- myoelectric control --- pattern recognition --- functional near-infrared spectroscopy --- z-score method --- channel selection --- region of interest --- channel of interest --- respiratory rate (RR) --- Electrocardiogram (ECG) --- ECG derived respiration (EDR) --- auscultation sites --- pulse plethysmograph --- biomedical signal processing --- feature selection and reduction --- discrete wavelet transform --- hypertension