- Data Management and Algorithms
- Maritime Navigation and Safety
- Geographic Information Systems Studies
- Human Mobility and Location-Based Analysis
- Context-Aware Activity Recognition Systems
- Transportation Planning and Optimization
- Maritime Security and History
- Mobile Agent-Based Network Management
- Advanced Database Systems and Queries
- 3D Modeling in Geospatial Applications
- Transportation and Mobility Innovations
- Usability and User Interface Design
- Marine and fisheries research
- Traffic Prediction and Management Techniques
- Network Security and Intrusion Detection
- Speech and dialogue systems
- Semantic Web and Ontologies
- Indoor and Outdoor Localization Technologies
- Simulation Techniques and Applications
- Bayesian Modeling and Causal Inference
- Automated Road and Building Extraction
- Web Data Mining and Analysis
- Underwater Vehicles and Communication Systems
- Recommender Systems and Techniques
- Data Visualization and Analytics
Augusta University Health
2024
Institut de Recherche de l’École Navale
2013-2022
Arts et Métiers
2019-2022
École Navale
2010-2020
ParisTech
2016-2020
University of Piraeus
2017
Dalhousie University
2013
Guangzhou Institute of Geochemistry
2009
Chinese Academy of Sciences
2009
Swiss Finance Institute
2008
The study presented in this paper explores people perception of robots, with a particular focus on domestic use. We addressed issues related to positive and negative attitudes toward needs for robots as well preferences terms appearance interaction modalities. used combined qualitative quantitative approach using interviews questionnaires. In total, 240 participated our survey. Results indicate that large proportion participants have very attitude towards robots. They expect concrete help...
This paper surveys indoor spatial models developed for research fields ranging from mobile robot mapping, to location-based services (LBS), and most recently context-aware navigation applied environments. Over the past few years, several studies have evaluated potential of ubiquitous computing. In this we take a slightly different perspective, considering not only underlying properties those models, but also which degree notion context can be taken into account when delivering in Some...
In almost all digital data processing machine applications, the input made available to are result of some prior processing. This is done manually in many applications. Thus, such inputs as punched cards, magnetic tape, and paper tape often a manual operation which human being required inspect visually an array printed characters describe these form capable processed by machine. recognition importance automating operations, investigations have been undertaken devise automatic character...
Facing an ever-increasing amount of traffic at sea, many research centres, international organisations, and industrials have favoured developed sensors together with detection techniques for the monitoring, analysis, visualisation sea movements. The Automatic Identification System (AIS) is one electronic systems that enable ships to broadcast their position nominative information via radio communication. In addition these systems, understanding maritime activities impact on environment also...
The Automatic Identification System (AIS) was initially designed for safety and security of navigation purposes. However it progressively also used other objectives, such as surveillance, thus led to the discovery behaviors falsification AIS messages by people that have been carrying out illegal activities will keep their up in an hidden way. In addition, contain erroneous data undergo spoofing attacks. paper introduces quality dimensions shall be a assessment messages, order point dubious...
High resolution estimates of bottom towed fishing gears are needed to provide relevant information for natural resource management, impact assessment and maritime spatial planning. The use satellite-based vessel monitoring system (VMS) data is constrained by access restrictions as well rather coarse resolution. This study focuses on mapping dredge gear grounds using effort at the métier level based automatic identification (AIS) data. performance approach was evaluated in terms correct...
The correlated exploitation of heterogeneous data sources offering very large historical as well streaming is important to increasing the accuracy computations when analysing and predicting future states moving entities. This particularly critical in maritime domain, where online tracking, early recognition events, real-time forecast anticipated trajectories vessels are crucial safety operations at sea. objective this paper review current research challenges trends tied integration,...
Maritime monitoring systems support safe shipping as they allow for the real-time detection of dangerous, suspicious and illegal vessel activities. We present such a system using Run-Time Event Calculus, composite event recognition with formal, declarative semantics. For effective recognition, we developed library maritime patterns in close collaboration domain experts. thorough evaluation both terms predictive accuracy computational efficiency, real-world datasets position streams...
INTRODUCTION: Peripartum cardiomyopathy (PPCM) incidence varies widely based on maternal health factors such as hypertension and advanced age, race, access to routine obstetric care. Nearly 50% of PPCM patients are Black, more than 38% live in the least advantaged, first quartile, around 48% South. There is limited understanding left ventricle ejection fraction (LVEF) recovery rates stratified according Area Deprivation Index (ADI) residence quartile. We hypothesized lower living areas worse...
Crossroads of international issues, maritime domain is facing growing human activities (fishing, transportation, boating...) involving a large spectrum ships from small sailing boats to super tankers. This increase mobilities has favored the appearance and generalization position report systems for keeping track movements. Amongst these systems, cooperative reports using devices such as Automatic Identification System (AIS) have been widely deployed used. Recent works shown that...
Accurate emotion understanding from multimodal signals has become a pivotal research area, especially given its relevance in enhancing human-computer interaction systems. However, the inherent complexity of emotional expression across modalities, coupled with scarcity high-quality annotated data, poses significant barriers to progress. In this work, we present MUSE, novel multigranular unified synthesis encoder framework, designed seamlessly integrate fine-grained representations and global...
We introduce the concept of time mask, which is a type temporal filter suitable for selection multiple disjoint intervals in some query conditions fulfil. Such can be applied to time-referenced objects, such as events and trajectories, selecting those objects or segments trajectories that fit one selected intervals. The subsets are dynamically summarized various ways, summaries represented visually on maps and/or other displays enable exploration. mask filtering especially helpful analysis...
With continuous increase of available online spatial data, requirements for the adaptation content to user's context becomes increasingly important. Location-based services (LBS) deliver user information specific a given location preferably using mobile devices. Personalizing provided take into account her/his preferences and current location, problem inundating with irrelevant is avoided. The research presented in this paper introduces an approach which implicitly monitors activity...
Continuous location-dependent queries can be considered as key elements for the development of different categories location-based and context-aware services. However, most work on query processing has been mainly oriented towards outdoor environments. This paper studies over moving objects in indoor environments (e.g., houses, commercial malls, etc.), with a special focus navigation-related (i.e., path search range queries). A hierarchical context-dependent spatial data model is firstly...
The notion of context has been recently recognised as a key element in the development context-aware information systems. Context varies according to application constraints, but also integrates way users act environment and interfaces they use interact. Amongst many applications, indoor navigation systems strongly rely on context-based adapt their services accordingly. Still, these need design flexible dynamic spatial data models that will be able provide appropriate mobile acting...