Artificial intelligence advances for cashew fruit maturity and quality detection: a systematic review on models, sensors, and farming applications

Agriculture 4.0 represents the transformation of traditional farming into a data-driven, intelligent system, with fruit cultivation playing an essential part in food security, nutrition, and economic growth. Fruits are a vital part of a healthy diet, offering essential vitamins, minerals, and fibre that support overall well-being and chronic disease prevention. Given their high market value and sensitivity to environmental conditions, ensuring optimal ripeness and quality is a top priority in modern agriculture. Accurate monitoring of ripening stages, texture, colour, sweetness, and overall fruit health is essential to meet consumer expectations, reduce post-harvest losses, and improve marketability. The evaluation of fruit quality has become more accurate and timelier with the use of smart sensors, imaging technologies, and Artificial Intelligence (AI). However, identifying and interpreting multiple influencing factors—such as environmental stress, nutrient imbalance, and disease symptoms- remains a complex challenge. This research has focused on single-parameter analysis, providing a clear understanding of fruit quality. This study does a systematic literature review using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology to address the need for a systematic approach. It investigates topics like feature extraction, sensor selection, data collection, and AI-based classification methods for fruit quality monitoring. By identifying key research gaps and technical challenges, the review highlights how AI can offer robust and scalable solutions. This paper also emphasizes how big data frameworks provide scalable, real-time evaluation of fruit quality by combining several multimodal inputs from image and sensor technologies to aid precision farming.