A5004481552- Smart Grid Energy Management
- Green IT and Sustainability
- Building Energy and Comfort Optimization
- Energy Efficiency and Management
- Recommender Systems and Techniques
- Human Mobility and Location-Based Analysis
- IoT and Edge/Fog Computing
- Data Management and Algorithms
- Anomaly Detection Techniques and Applications
- Caching and Content Delivery
- Autonomous Vehicle Technology and Safety
- Environmental Education and Sustainability
- Blockchain Technology Applications and Security
- Advanced Graph Neural Networks
- Digital Transformation in Industry
- Topic Modeling
- Context-Aware Activity Recognition Systems
- Human-Automation Interaction and Safety
- Explainable Artificial Intelligence (XAI)
- Economic and Technological Systems Analysis
- Cloud Computing and Resource Management
- Web Data Mining and Analysis
- Sentiment Analysis and Opinion Mining
- Energy Load and Power Forecasting
- Advanced Text Analysis Techniques
Harokopio University of Athens
2016-2025
Athens University of Economics and Business
2016
National and Kapodistrian University of Athens
2014
Recommender systems have significantly developed in recent years parallel with the witnessed advancements both internet of things (IoT) and artificial intelligence (AI) technologies. Accordingly, as a consequence IoT AI, multiple forms data are incorporated these systems, e.g. social, implicit, local personal information, which can help improving recommender systems' performance widen their applicability to traverse different disciplines. On other side, energy efficiency building sector is...
Recommender systems have been widely used in different application domains including energy-preservation, e-commerce, healthcare, social media, etc. Such applications require the analysis and mining of massive amounts various types user data, demographics, preferences, interactions, order to develop accurate precise recommender systems. datasets often include sensitive information, yet most are focusing on models' accuracy ignore issues related security users' privacy. Despite efforts...
The recent advances in artificial intelligence namely machine learning and deep learning, have boosted the performance of intelligent systems several ways. This gave rise to human expectations, but also created need for a deeper understanding how think decide. concept explainability appeared, extent explaining internal system mechanics terms. Recommendation are that support decision making, as such, they be explainable order increase user trust improve acceptance recommendations. In this...
Argument extraction is the task of identifying arguments, along with their components in text. Arguments can be usually decomposed into a claim and one or more premises justifying it. The proposed approach tries to identify segments that represent argument elements (claims premises) on social Web texts (mainly news blogs) Greek language, for small set thematic domains, including articles politics, economics, culture, various issues, sports. exploits distributed representations words,...
Among the large number of efforts that study role technology in energy saving, there exists, first, frameworks for monitoring and controlling consumption households, second, systems suggest best practices to users providers, third, findings focus on motivations trigger a behavioral change toward efficiency. However, is still no work builds habitual behavior individuals use this purpose. In paper, we survey literature aims at understanding consumers then changing it by recommending...
Excessive domestic energy usage is an impediment towards efficiency. Developing countries are expected to witness unprecedented rise in electricity the forthcoming decades. A large amount of research has been directed behavioral change for Thus, it prudent develop intelligent system that combines proper use technology with behavior order sustainably transform end-user at a scale. This paper presents overview our AI-based efficiency framework applications and explains how micro-moments can...
Recommender systems are one of the fields information filtering that have attracted great research interest during past several decades and been utilized in a large variety applications, from commercial e-shops to social networks product review sites. Since applicability these applications is constantly increasing, size graphs represent their users support functionality increases too. Over last years, different approaches proposed deal with problem scalability recommender systems’...
Domestic user behavior is a crucial factor guiding overall power consumption, necessitating the development of systems that analyze and help shape energy-efficient behavior. Therefore, most important step in process collection understanding highly detailed domestic consumption data. This article presents an appliance-based energy data analysis system for efficiency applications. It leverages concept micro-moments, which are short-timed energy-based events form end user. The comprises sensing...
The crossing of the Mediterranean by refugees has turned to be an extremely perilous activity. Human operators that handle Search and Rescue (SAR) missions need all help they can muster in order timely discover assist coordination operations. In this work we present a tool automatically detects SAR sea, employing Automatic Identification System (AIS) data streams. approach defines three steps taken: a) trajectory compression for affordable real time analysis presence big data; b) detection...
This paper discusses the perspective of H2020 TEACHING project on next generation autonomous applications running in a distributed and highly heterogeneous environment comprising both virtual physical resources spanning edge-cloud continuum. puts forward human-centred vision leveraging physiological, emotional, cognitive state users as driver for adaptation optimization applications. It does so by building distributed, embedded federated learning system complemented methods tools to enforce...
Energy efficiency based on behavioral change has attracted increasing interest in recent years, although, solutions this area lack much needed techno-economic analysis. That is due to the absence of both prospective studies and consumer awareness. To close such gap, paper proposes first assessment a change-based building energy solution, best authors’ knowledge. From one hand, technical conducted through (i) introducing novel edge-based solution; (ii) analyzing data using machine learning...
Since electricity consumption of households in developing countries is dramatically increasing every year, it now more prudent than ever to utilize technology-based solutions that assist energy end-users improve efficiency without affecting quality life. User behavior the most important factor influences household and recommender systems can be technology enabler for shaping users’ towards efficiency. The current literature mostly focuses on usage monitoring home automation fails engage...
When designing a large scale IoT ecosystem, it is important to provide economical solutions at all levels, from sensors and actuators the software used for analytics orchestration. It of equal importance non-intrusive that do not violate users' privacy, but above all, guarantee accuracy integrity provided solution. In this work, we present research prototype solution has been developed as part an ongoing project called (EM)3. The involves actuators, realtime data modules cutting edge...
The increased consumption of energy worldwide has boosted the interest people for energy-efficient solutions at every level daily life, from goods production and transportation to use household office appliances. This gave rise monitoring applications that monitor user interaction with electrical electronic appliances, detect unnecessary or extensive usage recommend corrective actions. In this direction, work presents anatomy Consumer Engagement Towards Energy Saving Behavior by means...
This paper introduces a novel approach to job recommendation systems by incorporating personality traits evaluated through the Gallup CliftonStrengths assessment, aiming enhance traditional matching process beyond skills and qualifications. Unlike broad models like Big Five, Gallup’s assesses 34 specific talents (e.g., ‘Analytical’, ‘Empathy’), enabling finer-grained, actionable matches. While existing focus primarily on hard skills, this argues that traits—such as those measured test—play...