In recent years, agricultural landscapes have increasingly suffered from severe fire incidents, posing significant threats to crop production, economic stability, and environmental sustainability. Timely and precise detection of fires, especially at their incipient stages, remains crucial to mitigate damage and prevent ecological degradation. However, conventional detection methods frequently fall short in accurately identifying small-scale fire outbreaks due to limitations in sensitivity and response speed. Addressing these challenges, this research proposes an advanced fire detection model based on a modified Detection Transformer (DETR) architecture. The proposed framework incorporates an optimized ConvNeXt backbone combined with a novel Feature Enhancement Block (FEB), specifically designed to refine spatial and contextual feature representation for improved detection performance. Extensive evaluations conducted on a carefully curated agricultural fire dataset demonstrate the effectiveness of the proposed model, achieving precision, recall, mean Average Precision (mAP), and F1-score of 89.67%, 86.74%, 85.13%, and 92.43%, respectively, thereby surpassing existing state-of-the-art detection frameworks. These results validate the proposed architecture’s capability for reliable, real-time identification, offering substantial potential for enhancing agricultural resilience and sustainability through improved preventive strategies.

Early detection of cotton diseases is critical for safeguarding crop yield and minimizing agrochemical usage. However, most state-of-the-art systems rely on multispectral or hyperspectral sensors, which are costly and inaccessible to smallholder farmers. This paper introduces CottoNet, a lightweight and efficient deep learning framework for detecting early-stage cotton diseases using only RGB images captured by unmanned aerial vehicles (UAVs). The proposed model integrates an EfficientNetV2-S backbone with a Dual-Attention Feature Pyramid Network (DA-FPN) and a novel Early Symptom Emphasis Module (ESEM) to enhance sensitivity to subtle visual cues such as chlorosis, minor lesions, and texture irregularities. A custom-labeled dataset was collected from cotton fields in Uzbekistan to evaluate the model under realistic agricultural conditions. CottoNet achieved a mean average precision (mAP@50) of 89.7%, an F1 score of 88.2%, and an early detection accuracy (EDA) of 91.5%, outperforming existing lightweight models while maintaining real-time inference speed on embedded devices. The results demonstrate that CottoNet offers a scalable, accurate, and field-ready solution for precision agriculture in resource-limited settings.

To prevent crop damage from harmful birds, various repelling methods have been studied. However, harmful birds are still causing damage in the orchard by adapting to the repelling device according to their biological characteristics. This paper proposes a method called Anti-adaptive Harmful Birds Repelling (AHBR) that uses the model-free learning idea of the Reinforcement Learning (RL) approach to repell harmful birds that can effectively prevent bird adaptation problems. To prevent adaptation, the AHBR method uses a method of learning the bird’s reaction to the available threat sounds and playing them in patterns that are difficult to adapt through the RL approach. We also proposed the Long-term and Short-term (LaS) policy to meet the Markov assumptions that make RL difficult to implement in the real world. The LaS policy enable learning of the actual bird’s reaction to the sound of a threat. The performance of the AHBR method was evaluated in a closed environment to experiment real harmful bird such as Brown-eared Bulbul, Great Tit, and Eurasian Magpie captured in orchards. Results obtained from the experiment showed that the AHBR method was on average 43.5% better than the threat sound patterns(One, Sequential, Reverse Sequential, Random) used in commercial products.

Breast cancer continues to be a leading cause of cancer death in women globally

The purpose of this study is to develop an optimized system for predicting Knee Adduction Moment (KAM) using wearable Inertial Measurement Unit (IMU) sensors and Long Short-Term Memory (LSTM) RNN. Traditional KAM measurement methods are limited by the need for complex laboratory equipment and significant time and cost investments. This study proposes two systems for predicting Knee Adduction Moment based on wearable IMU sensor data and gait patterns: the Multi-model Gait-based KAM Prediction System and the Single-model KAM Prediction System. The Multi-model system pre-classifies different gait patterns and uses specific prediction models tailored for each pattern, while the Single-model system handles all gait patterns with one unified model. Both systems were evaluated using IMU sensor data and GRF data collected from participants in a controlled laboratory environment. The overall performance of the Multi-model Gait-based KAM Prediction System showed an approximately 20% improvement over the Single-model KAM Prediction System. Specifically, the RMSE for the Multi-model system was 6.84 $\mathrm{N}·\mathrm{m}$, which is lower than the 8.82 $\mathrm{N}·\mathrm{m}$ of the Single-model system, indicating a better predictive accuracy. The Multi-model system also achieved a MAPE of 8.47%, compared with 12.95% for the Single-model system, further demonstrating its superior performance.

Background/Objectives: The accurate identification of insect bites from images of skin is daunting due to the fine gradations among diverse bite types, variability in human skin response, and inconsistencies in image quality. Methods: For this work, we introduce DeepBiteNet, a new ensemble-based deep learning model designed to perform robust multiclass classification of insect bites from RGB images. Our model aggregates three semantically diverse convolutional neural networks—DenseNet121, EfficientNet-B0, and MobileNetV3-Small—using a stacked meta-classifier designed to aggregate their predicted outcomes into an integrated, discriminatively strong output. Our technique balances heterogeneous feature representation with suppression of individual model biases. Our model was trained and evaluated on a hand-collected set of 1932 labeled images representing eight classes, consisting of common bites such as mosquito, flea, and tick bites, and unaffected skin. Our domain-specific augmentation pipeline imputed practical variability in lighting, occlusion, and skin tone, thereby boosting generalizability. Results: Our model, DeepBiteNet, achieved a training accuracy of 89.7%, validation accuracy of 85.1%, and test accuracy of 84.6%, and surpassed fifteen benchmark CNN architectures on all key indicators, viz., precision (0.880), recall (0.870), and F1-score (0.875). Our model, optimized for mobile deployment with quantization and TensorFlow Lite, enables rapid on-client computation and eliminates reliance on cloud-based processing. Conclusions: Our work shows how ensemble learning, when carefully designed and combined with realistic data augmentation, can boost the reliability and usability of automatic insect bite diagnosis. Our model, DeepBiteNet, forms a promising foundation for future integration with mobile health (mHealth) solutions and may complement early diagnosis and triage in dermatologically underserved regions.