Lead (Pb) is a common contaminant that causes serious health and environmental problems. Thus, appropriate environmentally friendly and efficient techniques must be developed to remediate Pb in soils. Biochar (BC) has shown promise as an effective strategy to mitigate Pb toxicity. Trehalose (Tre) is a promising sugar that has been shown to effectively improve plant tolerance to abiotic stresses. Nonetheless, its role in alleviating Pb toxicity is unknown. The study investigated the impacts of BC and Tre co-application in alleviating Pb toxicity in rice crops. The study included the following treatments: control, Pb stress (250 mg kg⁻¹), Pb stress (250 mg kg⁻¹) + BC (2.5%), Pb stress (250 mg kg⁻¹) + Tre (30 mM), and Pb stress (250 mg kg⁻¹) + BC (2.5%) + Tre (30 mM). Results showed that Pb toxicity reduced rice yield by decreasing chlorophyll synthesis and relative water content (RWC), by increasing malondialdehyde (MDA) and hydrogen peroxide (H₂O₂) contents, Pb accumulation in roots and shoots, soil available Pb concentration, and by decreasing the availability of soil nutrients. BC and Tre application mitigated the adverse impacts of Pb; however, more promising results were obtained with the co-application of BC and Tre. The results indicated that co-application of BC and Tre increased the rice yield by increasing photosynthetic pigments (46–96.42%), leaf water contents (16.67%), proline and soluble protein synthesis (35.13% and 24.96%), and antioxidant activities (12.07–31.67%), by decreasing root (59.72%), shoot (76.47%), and soil (57.14%) Pb concentrations, and the Pb translocation factor (15.08%). These findings suggested that co-application of BC and Tre can be a practical approach for reducing Pb toxicity, availability, and uptake, which improves rice productivity in Pb-polluted soil.

This study proposes an edge computing-based facial expression recognition system that is low cost, low power, and privacy preserving. It utilizes a minimally obtrusive cap-based system designed for the continuous and real-time monitoring of a user’s facial expressions. The proposed method focuses on detecting facial skin deformations accompanying changes in facial expressions. A multi-zone time-of-flight (ToF) depth sensor VL53L5CX, featuring an 8 × 8 depth image, is integrated into the front brim of the cap to measure the distance between the sensor and the user’s facial skin surface. The distance values corresponding to seven universal facial expressions (neutral, happy, disgust, anger, surprise, fear, and sad) are transmitted to a low-power STM32F476 microcontroller (MCU) as an edge device for data preprocessing and facial expression classification tasks utilizing an on-device pre-trained deep learning model. Performance evaluation of the system is conducted through experiments utilizing data collected from 20 subjects. Four deep learning algorithms, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNN), are assessed. These algorithms demonstrate high accuracy, with CNN yielding the best result, achieving an accuracy of 89.20% at a frame rate of 15 frames per second (fps) and a maximum latency of 2 ms.

Rose leaf diseases severely reduce yield and product quality, and traditional disease monitoring relies on manual visual inspection by experts, which is inefficient for large-scale cultivation. However, deploying accurate and lightweight detectors in field environments remains challenging due to two main obstacles. First, models trained under controlled laboratory conditions suffer performance degradation due to domain shift when deployed in complex field environments. Second, the computational capacity of hardware deployable in the field is often limited. To address these problems, this study proposes a practical knowledge distillation approach based on transferable feature representations from a pre-trained teacher model, rather than on complex distillation architecture. A high-capacity YOLOv12-L teacher, pre-trained on laboratory images, guided the training of a compact YOLOv12-N student using field images. The distilled YOLOv12-N student model achieved an mAP@50 of 81.1% on field test set, representing a 3.5% improvement over the baseline YOLOv12-N model, while maintaining a highly efficient architecture of only 2.56 million parameters and 6.3 GFLOPs. Several ablation studies confirm the core contribution of this work, namely that the performance gains in lightweight detection stem primarily from the transfer of the teacher model’s feature representations, rather than from modifications to the distillation algorithm or student model’s architecture, thus clarifying the importance of high quality feature transfer in cross-domain agricultural vision tasks. This approach provides a generalizable and efficient solution for real-time rose leaf disease detection in precision agriculture.