Miguel Molina-Rotger

Miguel Molina-Rotger

Auto-generated profile, based on publicly available information

Miguel Molina-Rotger

Department of Industrial Engineering and Construction, University of the Balearic Islands, Palma, Spain

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 November 2025 in IEEE Transactions on AgriFood Electronics
Verified
Journal Article
Open access
MMMiguel Molina-Rotger
Miguel Molina-Rotger
ACAlejandro Morán Costoya
Alejandro Morán Costoya
MMMiguel Ángel Miranda
Miguel Ángel Miranda
MRMiquel Roca
Miquel Roca
BABartomeu Alorda
Bartomeu Alorda
BioVIEW is a solar-powered, dual-camera Internet of Things (IoT) station designed for long-term, nondestructive biodiversity monitoring in remote habitats. Each station is built from wood and aluminum and integrates two 64-MP cameras, temperature and humidity sensors, programmable LED attractants, and a 30-W photovoltaic power system that powers two Raspberry Pi (RPi) controllers, ensuring months of autonomous operation. The BioVIEW station also provides dual communication options: mobile networks for high-bandwidth image uploads to servers, and LoRaWAN for ultra-low-power telemetry. This setup supports remote management and ensures resilient data delivery. Ten stations deployed across the Balearic Islands (Mallorca, Menorca, Ibiza, Formentera, Cabrera, and Dragonera) are generating a fixed-interval image archive to support supervised learning. In a proof-of-concept study, 62 labeled frames of Bactrocera oleae were used to train a support vector machine, achieving an accuracy of 0.86 and tracking cumulative counts within one specimen of ground truth over two weeks. Energy profiling across RPi models showed inference budgets ranging from 7 J (MobileNet on RPi 4) to 12 J (SVM on RPi 3), demonstrating the feasibility of edge-based analytics under strict power constraints. By combining energy-efficient hardware, event-driven capture, and a flexible classification framework, BioVIEW enables scalable, high-resolution biodiversity monitoring without harming either target or nontarget species.