A5020552918- Explainable Artificial Intelligence (XAI)
- Cloud Computing and Resource Management
- Statistical and Computational Modeling
- Service-Oriented Architecture and Web Services
- Service and Product Innovation
- Digital Marketing and Social Media
- Complex Network Analysis Techniques
- Blockchain Technology Applications and Security
- Web Data Mining and Analysis
- Green IT and Sustainability
- Big Data and Business Intelligence
- Semantic Web and Ontologies
- Anomaly Detection Techniques and Applications
- Sentiment Analysis and Opinion Mining
- Collaboration in agile enterprises
- Maritime Navigation and Safety
- Impact of AI and Big Data on Business and Society
- Smart Grid Security and Resilience
- Open Source Software Innovations
- Crime Patterns and Interventions
- Forecasting Techniques and Applications
- Consumer Market Behavior and Pricing
- Personal Information Management and User Behavior
- Data-Driven Disease Surveillance
- Maritime Ports and Logistics
Tecnológico de Monterrey
2023
University of Applied Sciences Landshut
2023
Limassol General Hospital
2020
National Technical University of Athens
2014-2018
Explainable Artificial Intelligence (XAI) has gained significant attention as a means to address the transparency and interpretability challenges posed by black box AI models. In context of manufacturing industry, where complex problems decision-making processes are widespread, XMANAI platform emerges solution enable transparent trustworthy collaboration between humans machines. By leveraging advancements in XAI catering prompt data scientists domain experts, enables construction...
In this paper we attempt to define the major trade routes which vessels of follow when travelling across globe in a scalable, data-driven unsupervised way. For this, exploit large volume historical AIS data, so as estimate location and connections routes, with minimal reliance on other sources information. We address challenges posed due data by leveraging distributed computing techniques present novel MapReduce based algorithmic approach, capable handling skewed nonuniform geospatial data....
Today, a new age of engagement and collaboration has emerged with the proliferation usergenerated content in social networks generally Web 2.0, rendering it particularly difficult for enterprises to monitor act upon all following conventional data mining methodologies. In this paper, we present our approach Future Internet enabler (FITMAN Anlzer) that provides automated, analytics aims at assisting becoming more tuned their customer needs gaining insights into current future trends early...
In the case of Product-Service Systems (PSS), design phase is characterized by a demand for intensive exchange knowledge between stakeholders from different domains. Thus, comprehensive approach sharing would support integrated development PSS. Existing attempts are however mainly focusing on using explicit service product and operations only. Knowledge domains, including tacit sentiment, products services have received less attention. The objective this paper to present initial results...
Public safety and personal security organizations need to achieve maintain high levels of service, while managing the expectations citizens, mandates legislation, impacts new forms technology, including mobile IoT communications. In this context, Big Linked Data analysis is expected play a key role in domain Safety Personal industries. The paper presents challenges achieving efficient secure big data domain, view current state-of-the-art linked technologies, proposes framework that brings...
Abstract As the confidentiality and integrity of modern health infrastructures is threatened by intrusions real-time attacks related to privacy cyber-security, there a need for proposing novel methodologies predict future incidents identify new threat patterns. The main scope this article propose an advanced extension current Intrusion Detection System (IDS) solutions, which (i) harvests knowledge out data sources or network monitoring construct models patterns (ii) encompasses methods...
Over the past decade, way people communicate, share content and eventually conduct business has been disrupted by social networking platforms. By bringing together pervasive computing with under a common modelling methodology rules based on human activities in accordance Activity Theory, our work aims at contributing to standardisation of Social Web that is independent from proprietary solutions, interoperable semantically rich for applications beyond networking. The concept Agent introduced...
Over the past couple of years, implementations Artificial Intelligence (AI) have significantly risen in numerous platforms, tools and applications around world, impacting a broad range industries such as manufacturing towards Smart Factories Industry 4.0, general. Nevertheless, despite industrial AI being driving force for smart factories, there is strong reluctance its adoption by manufacturers due to lack transparency black-box models trust behind decisions taken, well awareness where how...
The electricity networks in Europe are facing new challenges due to changing geopolitical conditions at the EC level (as highlighted by recently implemented REPowerEU regulation) as well widespread use of renewable energy sources (RES). To address these challenges, it is necessary develop solutions that optimize local systems, allowing for integration distributed generation and demand, coordinating flexibility resources. Such should combine generation, storage, electric vehicles,...
Although customers become more and vocal in expressing their experiences, demands needs various social networks, companies of any size typically fail to effectively gain insights from such data eventually catch the market realm. This paper introduces Anlzer analytics engine that aims at leveraging "social" deluge help quest for deeper understanding products' perceptions as well emerging trends order early embed them into product design phase. The proposed approach brings together polarity...
Lack of understanding for machine learning models' inner workings by business users inevitably leads to lack trust, particularly in critical operations. Recent advancements artificial intelligence include the development explainability methods and tools deep models. These explainable AI (XAI) techniques can significantly reduce black box effect that often hinders direct inclusion automated integration ML outputs decision making. The manufacturing sector is gradually increasing its adoption...