Temperature and humidity excursions during transport accelerate quality loss in fresh produce. This study develops and validates a self-contained Internet of Things (IoT) platform for in-transit monitoring and energy-aware operation. The battery-powered device operates independently of vehicle power and continuously logs temperature, relative humidity, GPS position, and onboard power draw. Power budgeting combines firmware-level deep-sleep scheduling with a LiFePO₄ battery pack, enabling uninterrupted operation for up to four days. Using ∼10,000 time-stamped observations collected over four consecutive days in a standard dry truck (non-commercial validation), we trained and compared Gradient Boosting Machine (GBM), Random Forest (RF), and Linear Regression (LR) models to predict energy consumption under varying environmental and routing conditions. GBM and LR achieved high explanatory power (R2≈0.88) with a mean absolute error of 0.77 A·h, while RF provided interpretable feature importance data, identifying temperature as the dominant driver, followed by trip duration and humidity. The end-to-end system integrates an EMQX MQTT broker, a Laravel web application, MongoDB storage, and Node-RED flows for real-time dashboards and multi-day historical analytics. The proposed platform supports proactive decision-making in perishable logistics, with the AI analysis validating that the collected time-aligned on-route data can configure sampling/transmit cadence to preserve autonomy under stressful conditions.

Sentiment analysis is a task in natural language processing that focuses on identifying and categorizing emotions expressed in text. Despite the remarkable predictive performance achieved by deep learning models in this domain, their limited interpretability posed a significant challenge. Furthermore, the development of interpretable sentiment analysis models for the Thai language had received inadequate attention. To address this gap, this study proposed a Zero-shot Interpretable Sentiment Analysis Framework, integrating sentiment polarity extraction and leveraging the zero-shot learning with the powerful WangchanBERTa model. Our framework utilized the word selection method from the feeling wheel to represent six primary feelings as sentiment polarities, effectively capturing the subtle emotions expressed in the text. These sentiment polarities played a crucial role as features in training our model, enhancing its interpretability for sentiment analysis tasks. Through the evaluation of three Thai sentiment analysis datasets, we compared the sentiment polarity extraction with two traditional feature extraction methods and ten classification algorithms. The results showed the superiority of the sentiment polarity extraction over Bag of words and its competitive performance compared to TF-IDF in terms of accuracy. To gain insights into the model’s decision-making process, SHAP (SHapley Additive exPlanations) was employed to analyze feature importance. Our findings highlighted the alignment of influential features with the sentiment polarities of the text, providing a crucial understanding of the model’s functionality. Notably, we uncovered a clear relationship between specific feeling features and their corresponding sentiment classes, deepening our comprehension of the model’s performance in sentiment analysis. This study not only contributed to the advancement of sentiment analysis in the Thai language but also bridged the gap between predictive performance and model transparency, yielding a novel and interpretable approach for sentiment analysis.