A5012888844- Semantic Web and Ontologies
- Multimodal Machine Learning Applications
- Video Analysis and Summarization
- Advanced Image and Video Retrieval Techniques
- Context-Aware Activity Recognition Systems
- Public Relations and Crisis Communication
- Advanced Database Systems and Queries
- Data Quality and Management
- Complex Network Analysis Techniques
- Service-Oriented Architecture and Web Services
- Flood Risk Assessment and Management
- Image Retrieval and Classification Techniques
- Topic Modeling
- Seismology and Earthquake Studies
- Advanced Text Analysis Techniques
- IoT and Edge/Fog Computing
- Dementia and Cognitive Impairment Research
- Infrastructure Maintenance and Monitoring
- Web Data Mining and Analysis
- Geographic Information Systems Studies
- Natural Language Processing Techniques
- Remote-Sensing Image Classification
- Mobile Health and mHealth Applications
- Technology Use by Older Adults
- Data-Driven Disease Surveillance
Centre for Research and Technology Hellas
2015-2024
Information Technologies Institute
2015-2024
Hella (Germany)
2016
Aristotle University of Thessaloniki
2014-2015
Stress is a common problem that affects most people with dementia and their caregivers. symptoms for are often measured by answering checklist of questions the clinical staff who work closely person dementia. This process requires lot effort continuous observation over long term. article investigates effectiveness using straightforward method, based on single wristband sensor to classify events "Stressed" "Not stressed" The presented system calculates stress level as an integer value from...
This paper provides an overview of the tasks submitted to TRECVID 2011 by ITI-CERTH. ITICERTH participated in Known-item search (KIS) as well Semantic Indexing (SIN) and Event Detection Internet Multimedia (MED) tasks. In SIN task, techniques are developed, which combine motion information with existing well-performing descriptors such SURF, Random Forests Bag-of-Words for shot representation. MED trained concept detectors task used represent video sources model vector sequences, then a...
Social media play an important role in the daily life of people around globe and users have emerged as active part news distribution well production. The threatening pandemic COVID-19 has been lead subject online discussions posts, resulting to large amounts related social data, which can be utilised reinforce crisis management several ways. Towards this direction, we propose a novel framework collect, analyse, visualise Twitter tailored specifically monitor virus spread severely affected...
Accurate and objective pain evaluation is crucial in developing effective management protocols, aiming to alleviate distress prevent patients from experiencing decreased functionality. A multimodal automatic assessment framework for acute utilizing video heart rate signals introduced this study. The proposed comprises four pivotal modules: the Spatial Module , responsible extracting embeddings videos; Heart Rate Encoder tasked with mapping into a higher dimensional space; AugmNet designed...
Interactive smart home systems are particularly useful for people with cognitive impairment.To investigate the long-term effects of Assistive Technology (AT) combined tailored non-pharmacological interventions impairment.18 participants (12 mild impairment and 6 Alzheimer's disease) took part in study that we evenly allocated one three groups: 1) experimental group (EG), 2) control 1 (CG1), 3) 2 (CG2). EG received system installed at 4 to 12 months, during which they according observations....
This paper discusses the importance of detecting breaking events in real time to help emergency response workers, and how social media can be used process large amounts data quickly. Most event detection techniques have focused on either images or text, but combining two improve performance. The authors present lessons learned from Flood-related multimedia task MediaEval2020, provide a dataset for reproducibility, propose new multimodal fusion method that uses Graph Neural Networks combine...
This work aims to advance Web Service retrieval, also known as Matching, in two directions. First, it introduces a matching algorithm for SAWSDL, which adapts and extends concepts with novel strategies. Effective logic-based syntactic strategies are introduced combined hybrid strategy, targeting an envisioned well-defined, real-world scenario matching. The is evaluated universal environment algorithms, SME2, objective, reproducible manner. Evaluation ranks Tomaco high amongst state of the...
This paper presents the HealthMon framework towards accessible mobile health. Following emergence of wearables with rich sensing capabilities in market, repurposes an affordable, retail wristband to clinical monitoring scenarios for conditions that impair independence e.g. dementia, Parkinson's or ageing. Multiple sensor modalities, such as physical activity levels, posture and heart rate, are unanimously stored interpreted produce real-time alerts, using Semantic Web technologies....
Recent developments in remote sensing have shown that snow depth can be estimated accurately on a global scale using satellite images through cross-polarization and copolarization backscatter measurements. This method does, however, some limitations low-land areas with dense forest coverage shallow snow, which are often found nearby urban areas. In these areas, citizen observations fused satellite-based estimations to deliver more accurate solutions. To end, we use snow-related tweets been...
Disaster monitoring based on social media posts has raised a lot of interest in the domain computer science last decade, mainly due to wide area applications public safety and security pervasiveness not solely daily communication but also life-threating situations. Social can be used as valuable source for producing early warnings eminent disasters. This paper presents framework analyse multimodal content, order decide if content is relevant flooding. very important since it enhances crisis...
Research in sensor technology has provided the scientific community with advanced sensors higher speed and lower costs, promoting manufacturing of more efficient, comfortable affordable wearable devices coupled pervasive smartphone app usage. A prominent use wearables apps is to leverage built-in accelerometers estimate user's steps as a measure physical activity an eHealth well-being context. This study aims evaluate accuracy, reliability user preferences nine trial 33 healthy adults,...
The increase of social media use in recent years has shown potential also for the identification specific trends data that could be used to locate earthquakes. In this work, we implemented a pipeline uses Twitter identify locations earthquakes and information trigger EO analysis. We tested almost year over Japan, an area where earthquake events are frequent, as well population. Here, show results discuss development such procedures. future, considering rapid satellite constellations aimed at...