A5002173556- Urban Planning and Valuation
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- IoT and Edge/Fog Computing
- Bioenergy crop production and management
- Model Reduction and Neural Networks
- Phonocardiography and Auscultation Techniques
- Generative Adversarial Networks and Image Synthesis
- Adversarial Robustness in Machine Learning
- Health, Environment, Cognitive Aging
- Domain Adaptation and Few-Shot Learning
- Face recognition and analysis
- Forest Biomass Utilization and Management
- Advanced Chemical Sensor Technologies
- Water Resources and Management
- Agriculture and Rural Development Research
- Machine Learning in Bioinformatics
- Sustainable Agricultural Systems Analysis
- Intellectual Property and Patents
- Advanced Control Systems Optimization
- Video Surveillance and Tracking Methods
- Diverse academic and cultural studies
- Context-Aware Activity Recognition Systems
- Artificial Intelligence in Healthcare
- Mobile Crowdsensing and Crowdsourcing
University of Bari Aldo Moro
2021-2024
University of Basilicata
2013
The widespread use of artificial intelligence deep neural networks in fields such as medicine and engineering necessitates understanding their decision-making processes. Current explainability methods often produce inconsistent results struggle to highlight essential signals influencing model inferences. This paper introduces the Evolutionary Independent Deterministic Explanation (EVIDENCE) theory, a novel approach offering deterministic, model-independent method for extracting significant...
Deep learning (DL) has been demonstrated to be a valuable tool for analyzing signals such as sounds and images, thanks its capabilities of automatically extracting relevant patterns well end-to-end training properties. When applied tabular structured data, DL exhibited some performance limitations compared shallow techniques. This work presents novel technique data called adaptive multiscale attention deep neural network architecture (also named excited attention). By exploiting parallel...
<abstract> <bold>Abstract. </bold>Woodfire is widely used in Sub-Saharan Africa, even urban areas. The use rate largely exceeds the plants growth rate, and areas close to cities are subject progressive deforestation. To stop this trend a switch other sources of energy necessary. aim present work illustrate how biomass gasification stove has been set up being built Niger, supply chain pellets produced from agricultural residues up, framework European Union development project. equipment for...
This article presents a multi-temporal uncertainty-based method that incor - porates statistical regression model with view to establishing the risk (probabil- ity) of land cover changes as function set environmental and socio-economic driving factors. The morphologic, climatic variables were exam- ined using an Artificial Neural Network (ANN) Multi-Layer Percep- tron (MLP). Following analysis, maps indicating suitability future generated on basis observed transitions. From these two...
<abstract> <bold>Abstract. </bold>Two Centres for the transformation of agricultural products have been set up in Niger framework a European Union development project. The two are located different rural areas, first one municipality Makalondi, close to border with Burkina Faso, and second central part Niger, periphery Agadez. facilities areas that not reached by national electric grid. Energy centres is provided means photovoltaic systems, power 6 kWp each. systems supply AC current at...
This article shows a system performing re-identification and description of people entering different stores the same franchise by means Face Recognition, Gait Analysis, Soft Biometrics techniques. Additionally, an anomaly detection analysis is conducted to identify suspicious behavioral patterns.It has been tested on ad-hoc dataset set pawn shops local franchise.The registered users paths have human labelled as ‘normal’ or ‘abnormal’ achieving precision 100%, recall 72.72%, average accuracy...