A5001926243- Education and Digital Technologies
- Smart Agriculture and AI
- Innovative Energy Harvesting Technologies
- Energy Harvesting in Wireless Networks
- Wireless Power Transfer Systems
- Experimental Learning in Engineering
- Education and Technology Integration
- Horticultural and Viticultural Research
- Online and Blended Learning
- Image and Signal Denoising Methods
- Education and Public Policy
- Sensor Technology and Measurement Systems
- Innovative Teaching and Learning Methods
- Spectroscopy and Chemometric Analyses
- Advanced Sensor and Energy Harvesting Materials
- Energy Efficient Wireless Sensor Networks
- Biomedical and Engineering Education
- Advanced MEMS and NEMS Technologies
- Child Development and Digital Technology
- Fuel Cells and Related Materials
- Emotion and Mood Recognition
- Power Quality and Harmonics
- Image Processing Techniques and Applications
- ECG Monitoring and Analysis
- Food Supply Chain Traceability
University of Trás-os-Montes and Alto Douro
2016-2025
University of Aveiro
2010-2025
Instituto de Telecomunicações
2013
Frequently, the vineyards in Douro Region present multiple grape varieties per parcel and even row. An automatic algorithm for variety identification as an integrated software component was proposed that can be applied, example, to a robotic harvesting system. However, some issues constraints its development were highlighted, namely, images captured natural environment, low volume of images, high similarity among different varieties, leaf senescence, significant changes on grapevine bunch...
A recent study by the Food and Agriculture Organization (FAO) reveals that approximately 40% of India’s food production is wasted each year due to inefficient fragmented supply chain management. An effective essential ensure efficient use resources maximize profitability. platform required enhance communication, facilitate contract agreements, streamline collaboration among stakeholders reach their target destinations. In some cases, suppliers raw materials often struggle find buyers, which...
The need for safe and healthy air quality has become critical as urbanization industrialization increase, leading to health risks environmental concerns. Gas leaks, particularly of gases like carbon monoxide, methane, liquefied petroleum gas (LPG), pose significant dangers due their flammability toxicity. LPG, widely used in residential industrial settings, is especially hazardous because it colorless, odorless, highly flammable, making undetected leaks an explosion risk. To mitigate these...
The rapid expansion of 5G networks and edge computing has amplified security challenges in Internet Things (IoT) environments, including unauthorized access, data tampering, DDoS attacks. This paper introduces EdgeChainGuard, a hybrid blockchain-based authentication framework designed to secure 5G-enabled IoT systems through decentralized identity management, smart contract-based access control, AI-driven anomaly detection. By combining permissioned permissionless blockchain layers with...
The increasing adoption of smart home technologies has intensified the demand for real-time anomaly detection to improve security, energy efficiency, and device reliability. Traditional cloud-based approaches introduce latency, privacy concerns, network dependency, making Edge AI a compelling alternative low-latency, on-device processing. This paper presents an AI-based framework that combines Isolation Forest (IF) Long Short-Term Memory Autoencoder (LSTM-AE) models identify anomalies in IoT...
The increasing complexity of urban mobility systems demands innovative solutions to address challenges such as traffic congestion, energy inefficiency, and environmental sustainability. This paper proposes an IoT AI-driven framework for secure sustainable green mobility, leveraging multimodal data fusion enhance management, efficiency, emissions reduction. Using publicly available datasets, including METR-LA flow OpenWeatherMap context, the integrates machine learning models congestion...
The validation of security protocols remains a complex and critical task in the cybersecurity landscape, often relying on labor-intensive testing or formal verification techniques with limited scalability. In this paper, we explore property-based (PBT) as powerful yet underutilized methodology for automated protocols. PBT enables generation large diverse input spaces guided by declarative properties, making it well-suited to uncover subtle vulnerabilities protocol logic, state transitions,...
A simple method is described for constructing functions that superoscillate at an arbitrarily chosen wavelength scale. Our based on the technique of oversampled signal reconstruction. This allows us to explicitly demonstrate observed fragility superoscillating wavefunctions indeed mathematically closely connected what in communication theory community known as instability reconstruction, confirming a previous conjecture. potential interest, example, concerning understanding practical...
Background One of the most mentioned problems web accessibility, as recognized in several different studies, is related to difficulty regarding perception what or not clickable a page. In particular, key problem recognition hyperlinks by specific group people, namely those with intellectual disabilities. Materials and Methods This experiment investigated methodology based on direct observation, video recording, interview data obtained an eye tracker device. Ten participants took part this...
With the increase of distance learning, in general, and e-learning, particular, having a system capable determining engagement students is primordial importance, one biggest challenges, both for teachers, researchers policy makers. Here, we present to detect level students. It uses only information provided by typical built-in web-camera laptop computer, was designed work real time. We combine about movements eyes head, facial emotions produce concentration index with three classes...