Interpretable Hybrid Deep Q-Learning Framework for IoT-Based Food Spoilage Prediction with Synthetic Data Generation and Hardware Validation

TL;DR

This paper introduces an interpretable hybrid deep reinforcement learning framework combining LSTM and RNN for accurate, real-time food spoilage prediction in IoT systems, validated through synthetic and hardware data.

Contribution

It presents a novel hybrid RL architecture with interpretability features, improving spoilage prediction accuracy and decision transparency in IoT-based food monitoring.

Findings

Outperforms alternative RL approaches in prediction accuracy

Maintains interpretability through rule-based labeling and metrics

Effective on both simulated and real hardware data

Abstract

The need for an intelligent, real-time spoilage prediction system has become critical in modern IoT-driven food supply chains, where perishable goods are highly susceptible to environmental conditions. Existing methods often lack adaptability to dynamic conditions and fail to optimize decision making in real time. To address these challenges, we propose a hybrid reinforcement learning framework integrating Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) for enhanced spoilage prediction. This hybrid architecture captures temporal dependencies within sensor data, enabling robust and adaptive decision making. In alignment with interpretable artificial intelligence principles, a rule-based classifier environment is employed to provide transparent ground truth labeling of spoilage levels based on domain-specific thresholds. This structured design allows the agent to operate within clearly defined semantic boundaries, supporting traceable and interpretable decisions. Model behavior is monitored using interpretability-driven metrics, including spoilage accuracy, reward-to-step ratio, loss reduction rate, and exploration decay. These metrics provide both quantitative performance evaluation and insights into learning dynamics. A class-wise spoilage distribution visualization is used to analyze the agents decision profile and policy behavior. Extensive evaluations on simulated and real-time hardware data demonstrate that the LSTM and RNN based agent outperforms alternative reinforcement learning approaches in prediction accuracy and decision efficiency while maintaining interpretability. The results highlight the potential of hybrid deep reinforcement learning with integrated interpretability for scalable IoT-based food monitoring systems.