A5081780209- Context-Aware Activity Recognition Systems
- Non-Invasive Vital Sign Monitoring
- IoT and Edge/Fog Computing
- Misinformation and Its Impacts
- Human Pose and Action Recognition
- Topic Modeling
- Hand Gesture Recognition Systems
- Anomaly Detection Techniques and Applications
- Microwave Imaging and Scattering Analysis
- Heart Rate Variability and Autonomic Control
- Gait Recognition and Analysis
- Human Mobility and Location-Based Analysis
- Generative Adversarial Networks and Image Synthesis
- Spam and Phishing Detection
- Privacy, Security, and Data Protection
- Obstructive Sleep Apnea Research
- EEG and Brain-Computer Interfaces
- Geophysical Methods and Applications
- Mobile Crowdsensing and Crowdsourcing
- Music Technology and Sound Studies
- Privacy-Preserving Technologies in Data
- Music and Audio Processing
- Public Spaces through Art
- Digital Mental Health Interventions
- Advanced SAR Imaging Techniques
University of West Attica
2018-2024
Polytechnic University of Turin
2023
National Technical University of Athens
2015-2017
Fog Computing is an emerging paradigm, suitable to serve the particular needs of IoT networks. It includes deployment computational devices at edge network facilitating faster real-time processing time-sensitive data. In this article, we present a architecture, which diverges from traditional hierarchical and centralized model, adopts cooperative allows for federation Edge our proposal, tasks that nodes are called complete, characterized according their nature subsequently allocated...
Search and Rescue (SaR) dogs are important assets in the hands of first responders, as they have ability to locate victim even cases where vision or sound is limited, due their inherent talents olfactory auditory senses. In this work, we propose a deep-learning-assisted implementation incorporating wearable device, base station, mobile application, cloud-based infrastructure that can monitor real-time activity, audio signals, location SaR dog, second, recognize alert rescuing team whenever...
During the last decade, new technological tools have emerged to provide first responders with augmented senses in emergency and disaster situations. Some of these focus on providing extra information about their surroundings. However, despite augmenting responders’ capabilities, quantity way that this is presented can affect cognitive load. This manuscript presents an integrated framework allows real-time biosignals monitoring analyze physical constants correlate them subjective load tests....
The existence of low-cost and accurate tools that can equip the First Responders (FRs) to detect trapped victims provide insights about their health condition in aftermath a disaster, is imperative. To address problem detecting behind walls or debris, we have developed tool exploits an Ultra-Wide Band (UWB) radar sensor for data collection Machine Learning (ML) algorithms analysis. evaluate efficacy our approach, collected from nine humans, both standing lying down positions. Next, applied...
In this paper, a proposal on the evolution of Internet Things towards Social Network's inspired environment (Social Things-SIoT) is presented. An architecture for supporting SIoT based use agents, which enable device to and human "social" communication, presented, along with simulator (ASSIST) enables visualization way proposed works. The rules in our comes communication operation agents basis needs services, while case demonstrating create links between Agents that assist them discover...
Monitoring the behavior of animals (e.g., eating habits) can lead to conclusions regarding animal's welfare. To achieve this, remote monitoring animal activity with aid inertial sensors and use machine learning algorithms over collected data be used. However, these rely on handcrafted features extracted by statistical or heuristic functions raw motion data. this purpose, we employ deep Convolutional Neural Networks (ConvNets) for recognition livestock animals, such as goats horses. We...
The widespread use of social networks has brought to the foreground a very important issue, veracity information circulating within them. Many natural language processing methods have been proposed in past assess post’s content with respect its reliability; however, end-to-end approaches are not comparable ability human beings. To overcome this, this paper, we propose more modular approach that produces indicators about subjectivity and stance provided by replies it received date, letting...
Recent advances in IoT and pervasive computing have led to the introduction of a plethora devices, featuring enhanced intelligence sensing, understanding context reacting situations. In case smart home environment, result is smart, connected domotic intelligence. combination with capabilities for controlling automatic, power these devices can be further exploited by use semantic connection layer that facilitate goal-oriented collaboration between meaningful interaction humans. This paper...
We present the technologies and theoretical background of an intelligent interconnected infrastructure for public security safety. The innovation framework lies in combination devices human information towards situational awareness, so as to provide a protection environment citizens. is currently being used support visitors spaces events, by creating appropriate address set urgent situations, such health-related problems missing children overcrowded environments, supporting smart links...
Situational and context awareness are becoming more important on the road toward intelligent machines devices that can offer a comprehensive toolset for improving quality of life. The increased computational capacity personal smart devices, their constantly increasing capabilities sensing, allow large amount collected data to be stored, processed, transmitted over mobile networks. Consequently, fast processing analysis this is big challenge. In article, authors present common context-aware...
Cultural heritage sites, apart from being the tangible link to a country’s history and culture, actively contribute national economy, offering foundation upon which cultural tourism can develop. This importance at economic level, advocates for need preservation of sites future generations. To this end, advanced monitoring systems harnessing power sensors are deployed near collect data fuel processes aimed protection preservation. In paper we present use acoustic safeguarding located in rural...
The rapidly increasing number of health monitoring devices, mainly wearables, will let users monitor their and habitual parameters in a simple easy way. However, the diversity available platforms calls for simplified, standard solutions that can offer integrated tools to users--that is, patients, professionals, practitioners. authors present idea avatar that's used as electronic equivalent human features dynamic life profile corresponding owner's physical status, living conditions, habits....
We show that the combination of machine learning methods and analytical expressions can enhance OSNIR estimation an optical link up to 2 dB compared with use expression alone. For this purpose, we exploit seven algorithms examine their improvement for 3,000 different operational cases.
Ultra-Wideband (UWB) radars are a cost-effective and accurate solution for recognizing human movements various purposes that span from activity recognition to vital signs monitoring, (i.e. breathing heart beating). In this work, we introduce convenient use, lightweight portable exploits an UWB radar sensor as well analysis tool tailored search rescue operations. particular, the proposed method works in real-time with main aim find trapped victims via their torso movement during breathing. To...
Situational and context awareness are becoming more important on the road toward intelligent machines devices that can offer a comprehensive toolset for improving quality of life. The increased computational capacity personal smart devices, their constantly increasing capabilities sensing, allow large amount collected data to be stored, processed, transmitted over mobile networks. Consequently, fast processing analysis this is big challenge. In article, authors present common context-aware...
With the capabilities and autonomy of smart watches constantly increasing, there is need for introducing applications which can exploit their full potential, establishing use in our daily routine. The field personal safety security provides an excellent basis over be developed, enabling wrist worn devices as tools easy, discreet efficient reporting incidents or suspicious behavior. However, current practices report creation using rely on methods interfaces, such taking pictures writing text,...
Efficient and quick remote communication in search rescue operations can be life-saving for the first responders. However, while operating on field means of based text, image audio are not suitable several disaster scenarios. In this paper, we present a smartwatch-based application, which utilizes Deep Learning (DL) model, to recognize set predefined arm gestures, maps them into Morse code via vibrations enabling amongst The model performance was evaluated by training it using 4,200 gestures...