Efficient water management is crucial for sustainable sugarcane farming, particularly in regions with water scarcity. This study investigated the implementation of an AIoT-based water management system designed to optimize irrigation in sugarcane fields. By integrating Artificial Intelligence (AI) with Internet of Things (IoT) technology, the system leverages real-time data from sensors monitoring soil moisture, weather conditions, and plant health. The AI component employs Long Short-Term Memory (LSTM) algorithms to predict optimal irrigation schedules, ensuring precise water delivery tailored to the crop's growth stages. Additionally, the system utilizes solar-powered pumps to enhance sustainability by reducing reliance on non-renewable energy sources. Preliminary results indicated that the AloT system significantly improved water use efficiency, crop yields, and operational cost-effectiveness. This research highlights the potential of AIoT solutions in addressing water management challenges in agriculture, promoting both productivity and environmental conservation.

Rapid and reliable detection of pesticide residues in vegetables is essential for food safety and sustainable agriculture. This work presents a four-port closed-loop ring resonator (CLRR) sensor for quantitative detection of carbamate residues in leafy vegetables. Operating through the S₃₁ transmission path, the sensor enhances electric-field coupling and sensing resolution in the high-field region. Four resonance modes were identified at 1.05, 2.10, 3.12, and 4.11 GHz, with the third mode (3.12 GHz) showing the most stable and linear response. Vegetable extracts of Chinese kale and Choy sum were prepared with carbamate concentrations of 0–8% (w/v). Increasing concentration caused a red-shift in resonance frequency corresponding to a reduction in dielectric constant. Regression analysis revealed a strong linear correlation between frequency shift and concentration (R² = 0.9855–0.9988). The CLRR achieved average normalized sensitivities of 6.39% and 6.54% per unit dielectric variation, outperforming most planar and metamaterial sensors. Fabricated on a single-layer FR-4 substrate, the sensor combines high sensitivity, low cost, and excellent repeatability, offering a practical, label-free, non-destructive tool for on-site monitoring of pesticide contamination in leafy vegetables.

The growing demand for automated postal sorting has increased due to E-commerce and global trade. Traditional manual and barcode-based methods struggle with rising parcel volumes, while Optical Character Recognition (OCR) and image processing offer a label-free alternative. This paper presents an OCR-based postal sorting system that extracts and classifies postal codes from envelope images. The system integrates a high-resolution camera, OCR processing unit, and real-time GUI, employing image acquisition, preprocessing, postal code detection, OCR extraction, and classification. Tests on nine postal codes achieved over $96 \%$ accuracy, with detection times of $0.61-0.84$ seconds. Errors primarily occurred in thin-stroke fonts under 3 mm, such as TH SarabunPSK and Angsana New, whereas larger fonts improved recognition. The system enhances sorting efficiency and reduces manual workload, proving its feasibility in regional logistics centers. Future work will explore deep learning-based OCR enhancements, multilingual postal code support, and integration with hardware-based automation.