A5072772953- Phonocardiography and Auscultation Techniques
- EEG and Brain-Computer Interfaces
- Emotion and Mood Recognition
- ECG Monitoring and Analysis
- Music and Audio Processing
- Heart Rate Variability and Autonomic Control
- Parkinson's Disease Mechanisms and Treatments
- Neural dynamics and brain function
- Innovative Teaching and Learning Methods
- Blind Source Separation Techniques
- Neurological disorders and treatments
- Online Learning and Analytics
- Online and Blended Learning
- Non-Invasive Vital Sign Monitoring
- Structural Health Monitoring Techniques
- Functional Brain Connectivity Studies
- Speech and Audio Processing
- Machine Fault Diagnosis Techniques
- Gastrointestinal Bleeding Diagnosis and Treatment
- Flow Measurement and Analysis
- Noise Effects and Management
- Neuroscience and Music Perception
- Educational Games and Gamification
- Autism Spectrum Disorder Research
- Image and Signal Denoising Methods
Khalifa University of Science and Technology
2016-2025
Aristotle University of Thessaloniki
2016-2025
University of Lisbon
2022-2023
University of Oxford
2023
Universiti of Malaysia Sabah
2023
AHEPA University Hospital
2020
Papageorgiou General Hospital
2020
Hellenic Agency for Local Development and Local Government
2020
Centre for Research and Technology Hellas
2017
Information Technologies Institute
2017
Abstract In the past few decades, analysis of heart sound signals (i.e. phonocardiogram or PCG), especially for automated segmentation and classification, has been widely studied reported to have potential value detect pathology accurately in clinical applications. However, comparative analyses algorithms literature hindered by lack high-quality, rigorously validated, standardized open databases recordings. This paper describes a public database, assembled an international competition,...
Electroencephalogram (EEG)-based emotion recognition is a relatively new field in the affective computing area with challenging issues regarding induction of emotional states and extraction features order to achieve optimum classification performance. In this paper, novel evocation EEG-based feature technique presented. particular, mirror neuron system concept was adapted efficiently foster by process imitation. addition, higher crossings (HOC) analysis employed for scheme robust method,...
This paper aims at providing a new feature extraction method for user-independent emotion recognition system, namely, HAF-HOC, from electroencephalograms (EEGs). A novel filtering procedure, Hybrid Adaptive Filtering (HAF), an efficient of the emotion-related EEG-characteristics was developed by applying Genetic Algorithms to Empirical Mode Decomposition-based representation EEG signals. In addition, Higher Order Crossings (HOCs) analysis employed realization HAF-filtered The introduced...
Affective phenomena, as reflected through brain activity, could constitute an effective index for the detection of music preference. In this vein, paper focuses on discrimination between subjects' electroencephalogram (EEG) responses to self-assessed liked or disliked music, acquired during experimental procedure, by evaluating different feature extraction approaches and classifiers end. Feature is based time-frequency (TF) analysis implementing three TF techniques, i.e., spectrogram,...
The automatic and accurate P phase arrival identification is a fundamental problem for seismologists worldwide. Several approaches have been reported in the literature, but most of them only selectively deal with are severely affected by noise presence. In this paper, new approach based on higher-order statistics (HOS) introduced that overcomes subjectivity human intervention eliminates factor. By using skewness kurtosis, two algorithms formed, namely, Phase Arrival...
This paper aims at providing a novel method for evaluating the emotion elicitation procedures in an electroencephalogram (EEG)-based recognition setup. By employing frontal brain asymmetry theory, index, namely Index (AsI), is introduced, order to evaluate this asymmetry. accomplished by multidimensional directed information analysis between different EEG sites from two opposite hemispheres. The proposed approach was applied three-channel (Fp1, Fp2, and F3/F4 10/20 sites) recordings drawn 16...
An efficient heart sound segmentation (HSS) method that automatically detects the location of first ( S <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> ) and second xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> extracts them from auscultatory raw data is presented here. The phonocardiogram analyzed by employing ensemble empirical mode decomposition (EEMD) combined with kurtosis features to locate presence , extract recorded data,...
Recognizing emotions during social interactions has many potential applications with the popularization of low-cost mobile sensors, but a challenge remains lack naturalistic affective interaction data. Most existing emotion datasets do not support studying idiosyncratic arising in wild as they were collected constrained environments. Therefore, context requires novel dataset, and K-EmoCon is such multimodal dataset comprehensive annotations continuous conversations. The contains...
This paper focuses on detecting and localizing anomalous events in videos of crowded scenes, i.e., divergences from a dominant pattern. Both motion appearance information are considered, so as to robustly distinguish different kinds anomalies, for wide range scenarios. A newly introduced concept based swarm theory, histograms oriented swarms (HOS), is applied capture the dynamics environments. HOS, together with well-known gradients, combined build descriptor that effectively characterizes...
Abstract Coronavirus (Covid-19) pandemic has imposed a complete shut-down of face-to-face teaching to universities and schools, forcing crash course for online learning plans technology students faculty. In the midst this unprecedented crisis, video conferencing platforms (e.g., Zoom, WebEx, MS Teams) management systems (LMSs), like Moodle, Blackboard Google Classroom, are being adopted heavily used as environments (OLEs). However, such media solely provide platform e-interaction, effective...
Abstract Depressive disorder (DD) is a mental illness affecting more than 300 million people worldwide, whereas social stigma and subtle, variant symptoms impede diagnosis. Psychomotor retardation common component of DD with negative impact on motor function, usually reflected patients’ routine activities, including, nowadays, their interaction mobile devices. Therefore, such interactions constitute an enticing source information towards unsupervised screening for in daily life. In this...
Freezing of Gait (FoG) is a movement disorder that mostly appears in the late stages Parkinson’s Disease (PD). It causes incapability walking, despite PD patient’s intention, resulting loss coordination increases risk falls and injuries severely affects quality life. Stress, emotional stimulus, multitasking have been encountered to be associated with appearance FoG episodes, while functionality self-confidence are constantly deteriorating. This study suggests non-invasive method for...
Alzheimer's Disease (AD) is the most common form of dementia. It usually manifests through progressive loss cognitive function and memory, subsequently impairing person's ability to live without assistance causing a tremendous impact on affected individuals society. Currently, AD diagnosis relies tests, blood behavior assessments, brain imaging, medical history analysis. However, these procedures are subjective inconsistent, making an accurate prediction for early stages difficult. This...
An efficient technique for detecting explosive lung sounds (LS) (fine/coarse crackles and squawks) or bowel (BS) in clinical auscultative recordings is presented. The based on a fractal-dimension (FD) analysis of the recorded LS BS obtained from controls patients with pulmonary pathology, respectively. Experimental results demonstrate efficiency proposed method, since it clearly detects time location duration BS, despite their variation either and/or amplitude. A noise stress test justifies...
The separation of pathological discontinuous adventitious sounds (DAS) from vesicular (VS) is great importance to the analysis lung sounds, since DAS are related certain pulmonary pathologies. An automated way revealing diagnostic character by isolating them VS, based on their nonstationarity, presented in this paper. proposed algorithm combines multiresolution with hard thresholding order compose a wavelet transform-based stationary-nonstationary filter (WTST-NST). Applying WTST-NST...
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> Sign language forms a communication channel among the deaf; however, automated gesture recognition could further expand their with hearers. In this work, data from five-channel surface electromyogram and 3-D accelerometer signer's dominant hand were analyzed using intrinsic-mode entropy (IMEn) for of Greek sign (GSL) isolated signs. Discriminant analysis was used to identify effective scales...