A5056965744- Sleep and Wakefulness Research
- EEG and Brain-Computer Interfaces
- Face and Expression Recognition
- Video Surveillance and Tracking Methods
- Face recognition and analysis
- Neural dynamics and brain function
- Sleep and related disorders
- Functional Brain Connectivity Studies
- Obstructive Sleep Apnea Research
- Context-Aware Activity Recognition Systems
- Hearing Loss and Rehabilitation
- Non-Invasive Vital Sign Monitoring
- Gaze Tracking and Assistive Technology
- ECG Monitoring and Analysis
- Mental Health Research Topics
- Hearing, Cochlea, Tinnitus, Genetics
- Innovative Energy Harvesting Technologies
- Blind Source Separation Techniques
- Speech and Audio Processing
- Advanced Adaptive Filtering Techniques
- Assistive Technology in Communication and Mobility
- Transcranial Magnetic Stimulation Studies
- Circadian rhythm and melatonin
- Phonocardiography and Auscultation Techniques
Aristotle University of Thessaloniki
2015-2025
Johns Hopkins University
2025
University of Bristol
2017
Understanding of the neuroscientific sleep mechanisms is associated with mental/cognitive and physical well-being pathological conditions. A prerequisite for further analysis identification macroarchitecture through manual staging. Several computer-based approaches have been proposed to extract time and/or frequency-domain features accuracy ranging from 80% 95% compared golden standard However, their acceptability by medical community still suboptimal. Recently, utilizing deep learning...
Sleep staging, the process of assigning labels to epochs sleep, depending on stage sleep they belong, is an arduous, time consuming and error prone as initial recordings are quite often polluted by noise from different sources. To properly analyze such data extract clinical knowledge, components must be removed or alleviated. In this paper a pre-processing subsequent staging pipeline for analysis electroencephalographic signals described. Two novel methods functional connectivity estimation...
Dissociating Primary Progressive Aphasia (PPA) from Mild Cognitive Impairment (MCI) is an important, yet challenging task. Given the need for low-cost and time-efficient classification, we used low-density electroencephalography (EEG) recordings to automatically classify PPA, MCI healthy control (HC) individuals. To best of our knowledge, this first attempt individuals these three populations at same time. We collected three-minute EEG with 8-channel system eight MCI, fourteen PPA HC...
This paper focuses on developing a novel approach to automatic sleep stage classification based electroencephalographic (EEG) data. The proposed methodology employs contemporary mathematical tools such as the synchronization likelihood and graph theory metrics applied EEG derived features are then fitted into three different machine learning techniques, namely k-nearest neighbors, support vector machines neural networks. evaluation of their comparative performance is investigated according...
In this paper, we develop a face detection hindering method, as means of preventing the threats to people's privacy, automatic video analysis may pose. Face in images or videos is first step human-centered be followed, e.g. by recognition. Therefore, detection, also render recognition improbable. To end, examine application two methods. First, consider naive approach, i.e., simply use additive impulsive noise input image, until point where cannot automatically detected anymore. Second,...
In this paper, a method is proposed that manipulates images in manner hinders face recognition by automatic algorithms. The purpose of method, to partly degrade image quality, so humans can identify the person or persons scene, while common classification algorithms fail do so. approach used achieve involves use singular value decomposition (SVD). From experiments it be concluded that, reduces percentage correct rate over 90%. addition, final not degraded beyond humans.
A major issue that arises from mass visual media distribution in modern video sharing, social and cloud services, is the of privacy. Malicious users can use these services to track actions certain individuals and/or groups thus violating their As a result need hinder automatic facial image identification images videos arises. In this paper we propose method for de-identifying images. Contrary most de-identification methods, manipulates so humans still recognize individual or an frame, but at...
Sleep is an essential biological function that critical for a healthy and fulfilling life. Available sleep quality assessment tools contain long questionnaires covering period of time, not taking into account daily physical activity patterns individual lifestyles.
From the advent of simple hearing aids to modern cochlear implants attempt restore human sense has shown significant progress. Modern and their coupled speech processors enable recipients with loss regain ability listen world around them. An interesting new feature that is available in newest offered by leading companies connectivity through 2.4 GHz band commonly used Wi-Fi routers Bluetooth devices other wireless applications. In this paper we provide an overview as well functions are use...
In this paper, two face de-identification methods are proposed regarding identification hindering against a deep neural network. Our work focuses on achieving delicate balance, so that the facial images miss-classified by network, while human observer can still identify persons depicted in scene. The based partly degrading image quality order to hinder recognition from networks, maintaining highest possible quality, at same time. To end, we employ singular value decomposition and hypersphere...
Varenicline (VAR) is a drug used for smoking cessation by intervening in nicotinic withdrawal and reward pathways the brain. VAR administration has been reported to affect sleep. The aim of this study was evaluate possible changes sleep architecture polysomnography (PSG) recordings during treatment (SmokeFreeBrain). <b>Methods:</b> 13 healthy smokers were evaluated with PSG (Embletta MPR-Master) before while 20-30 days after at least 5 days. PSGs manually scored according AASM criteria...
In this paper we propose a novel methodology for investigating pathological sleep patterns through network neuroscience approaches. It consists of initial identification statistically significant alterations in cortical functional connectivity patterns. The resulting sub-network is then analyzed by employing graph theory estimating both global performance metrics (integration and specialization) as well the significance specific nodes their hierarchical organization. So, with important role...
In this paper we present the first steps in developing SmartHypnos, an easy to use and user friendly graphical interface, which aims provide polysomngographic data visualization detection classification of sleep related events. Currently SmartHypnos supports EEG, ECG, EOG EMG signals, respiratory signals such as nasal pressure, thermistor, oxygen saturation, thoracic abdominal belt recordings. All these are incorporated into interface that provides quick effortless access mentioned above....
is an open access, peer-reviewed online journal that encompasses all aspects of tobacco use, prevention and cessation can promote a free society.The aim the to foster, disseminate research involving prevention, policy implementation at regional, national or international level, disease development -progression related use impact from cellular level finally treatment attributable through smoking cessation.
<b>Background:</b> Varenicline (VAR) is a drug used for smoking cessation. VAR administration has been reported to affect sleep. The aim of this study was evaluate possible polysomnographic (PSG) changes during treatment (SmokeFreeBrain) in healthy smokers and with obstructive sleep apnea (OSA). Methods: 26 (14 12 OSA) were evaluated PSG (Embletta MPR-Master including electroencephalography (EEG), electrooculography (EOG), electromyography (EMG), electrocardiography (ECG), flow,...