Timely and accurate identification of tea tree pests is critical for effective tea tree pest control. We collected image data sets of eight common tea tree pests to accurately represent the true appearance of various aspects of tea tree pests. The dataset contains 782 images, each containing 1~5 different pest species randomly distributed. Based on this dataset, a tea garden pest detection and recognition model was designed using the Yolov7-tiny network target detection algorithm, which incorporates deformable convolution, the Biformer dynamic attention mechanism, a non-maximal suppression algorithm module, and a new implicit decoupling head. Ablation experiments were conducted to compare the performance of the models, and the new model achieved an average accuracy of 93.23%. To ensure the validity of the model, it was compared to seven common detection models, including Efficientdet, Faster Rcnn, Retinanet, DetNet, Yolov5s, YoloR, and Yolov6. Additionally, feature visualization of the images was performed. The results demonstrated that the Improved Yolov7-tiny model developed was able to better capture the characteristics of tea tree pests. The pest detection model proposed has promising application prospects and has the potential to reduce the time and economic cost of pest control in tea plantations.

The emergence of consumer electronic Unmanned Aerial Vehicle (UAV) systems has brought innovation to the field of ship inspection. Traditional ship detection is carried out through traditional target recognition methods, but the efficiency and accuracy cannot meet the requirements. With the major breakthrough in the resolution of remote sensing images, it has become possible to use UAV to capture remote sensing images to detect ships. In this paper, object detection technology based on deep learning is used to improve the current detection methods and achieve accurate ship target detection. We propose an anchor-free detection method based on FCOS to reduce model hyperparameters. Meanwhile, a positive and negative sample selection method is put forth based on attention mechanism feature fusion and self-adaptation to enhance the fusion expression of features and improve the efficiency of sample selection, therefore improving the accuracy of the model. Experiments demonstrate notable progress in the detection accuracy from the proposed method, especially when small ship targets are concerned. Compared with Faster R-CNN and R3Det, the method introduced in this paper needs fewer hyperparameters, while achieving higher detection accuracy, with AP50 reaching 83.90%.

As consumer electronics become more ubiquitous and Generative Artificial Intelligence (GenAI) technologies advance rapidly, processing and analyzing semantic information collected from users to enhance their experiences becomes especially important. Traditionally, monitoring students' educational and psychological health has relied primarily on teachers, a method that is both inefficient and inadequate for comprehensively grasping students' needs. Therefore, the application of artificial intelligence is particularly critical. GenAI has the capability to gather semantic information from consumer electronics commonly used by students, such as smartphones, wearable devices, and tablets, and perform in-depth analysis. By analyzing curriculum schedules, GenAI can personalize learning paths and predict students' psychological states through examining individual mental health and media usage data. This paper explores how GenAI processes this information to intervene in students' education and psychological health, and discusses the analysis of adolescent mental health test data collected in recent years as well. Evidence suggests that students enrolled in high schools suffer from the highest rates of depression and major depressive disorder compared to other stages, at 40% and 12.5% respectively, underscoring the importance of using GenAI for educational and psychological health monitoring. The article summarizes the relevant technologies and models, highlighting the potential of GenAI in enhancing student well-being and academic performance.

Consumer electronics products are widely used in the agricultural field, but traditional consumer electronics products are limited to specific environmental applications and are susceptible to external attacks. The next generation of imaging technology is driving the widespread application of electronic consumer products. We propose a novel multi-source visual data fusion insect recognition algorithm called SE-SANet, which has high anti-interference capability and robustness to cope with various attacks in practical applications. Specifically, first, a deep residual contraction network is used to set different thresholds for different samples. Second, a spatial attention mechanism is introduced to assist the model in recognizing image features. When the feature data is input into the attention mechanism, the model filters the features based on their contribution values in spatial locations and ultimately produces the recognition result. The model shows excellent anti-interference ability on our collected dataset of 30 different insects, with a recognition correctness of 93.25%, which is higher than that of the traditional methods Inception-V4, Vgg16, Googlenet, Alexnet, 3.68%, 4.97%, 3.22% and 3.69%, respectively. We propose that the SE-SA model has important research implications in improving the robustness of insect recognition techniques and enhancing the model’s anti-interference capability.

Detection of lung nodules is key in the treatment of early-stage lung cancer. Computed tomography (CT) scanning technology is an essential contactless tool. However, stray radiation caused by a patient's slight movements and equipment operation can impair CT images, hindering accurate lung nodule detection. To address these issues, this study proposes an artificial intelligence-based anti-interference lung nodule detection method, which is primarily structured with Yolov8 and combines the modules of adaptive gating sparse attention (AGSA) and haar wavelet downsampling (HWD), referred to as Yolov8-AH. This model aimed to improve the accuracy of lung nodule detection in lung CT images under interference conditions. AGSA focuses on key areas of the image, promoting detection stability even when CT images are disturbed. Furthermore, HWD prioritizes the frequency components corresponding to the size and shape of the nodules, enhancing their visibility for easier detection and analysis. HWD effectively reduces image noise without significantly blurring the lung nodule edges, emphasizing them prominently within the lung tissue. Furthermore, when combined with the Yolov8 deep learning model driven by artificial intelligence, the model could accurately detect lung nodules, significantly aiding in early diagnosis and treatment. The effectiveness of the Yolov8-AH detection model was verified through ablation experiments, experiments under varying noise intensities, and experiments under different noise application ratios. The experimental results demonstrate that, compared to existing lung nodule detection models, the Yolov8-AH model achieves a 24% improvement in mAP50 and an 8.2% improvement in precision.

Implementing internal tree hollow detection using the Internet of Things (IoT) technology is a crucial method for forestry conservation. Current methodologies primarily rely on stress wave sensors for such inspections. However, the inherently low signal acquisition density of these sensors leads to significant discrepancies between reconstructed wave velocity tomography and conventional optical imaging principles. This sparse signal distribution severely limits the ability of existing image processing algorithms to resolve internal hollow features, creating a bottleneck of insufficient precision in hollow localization and dimensional estimation for detection systems. To address the aforementioned problems, the research team independently developed a sensor for detecting internal tree defects and proposed a transformer-based model (RCE-DETR) for internal tree hollow detection. The sensor comprises three core modules: stress wave signal detection probes, a signal processor, and a display module. The proposed model in this study is deployed in the signal processor. By replacing the original convolution in the transformer framework with receptive-field attention convolution (RFAConv), the model retains important feature information, effectively fuses signal features, and further improves the accuracy of defect detection. Additionally, the model incorporates cascaded group attention (CGA) and efficient multiscale attention (EMA) to address the difficulty that the existing methods have in precisely determining the size of internal tree defects. Experimental results demonstrate that compared with the existing models, the RCE-DETR model increases the mean average precision (mAP) by 10.5%, 10.9%, 5.2%, and 6.3%, respectively, when compared to the commonly used YOLOv11, YOLOv8, EfficientDet, and CenterNet++ models.