Low Cost and Efficient IoT Trap System for Remote Monitoring of Olive Fruit Fly Attacks

The emergence of new plant diseases and the proliferation of harmful pests have caused substantial damage to the agricultural economy worldwide, threatening both crop productivity and economic sustainability. A primary counter-measure is excessive and indiscriminate pesticide applications, which have led to severe environmental pollution and negative impacts on ecosystems and human health. Consequently, the development and adoption of safe, reliable, and effective monitoring methodologies have become not only desirable but also essential for modern agricultural systems. Pest management represents a critical challenge in precision agriculture, as it plays a fundamental role in improving crop yields and supporting the stability of local and global agricultural economies. From a food safety perspective, accurate and timely pest detection and control are of paramount importance to ensure the production of healthy crops characterized by high-quality, pesticide-free fruits and vegetables. In this context, early identification of pest infestations can significantly reduce the need for chemical treatments, promoting more sustainable and environmentally friendly farming practices. In this paper, an intelligent system for remote in field monitoring of the Bactrocera oleae is implemented. The deep learning-based system has been designed to be fully automated, cost effective, scalable, energy efficient, and accurate