Intelligent vehicle detection systems have the potential to improve road safety and optimize traffic management. Despite the continuous advancements in AI technology, the detection of different types of vehicles in complex traffic environments remains a persistent challenge. In this paper, an end-to-end solution is proposed. The image enhancement part proposes a super-resolution synthetic image GAN (SSIGAN) to improve detection of small, distant objects in low-resolution (LR) images. An edge enhancer (EE) and a hierarchical self-attention module (HS) are applied to address the loss of high-frequency edge information and texture details in the super-resolved images. The output super-resolution (SR) image is fed into detection part. In the detection part, we introduce a global context-aware network (GCAFormer) for accurate vehicle detection. GCAFormer utilizes a cascade transformer backbone (CT) that enables internal information interaction and generates multi-scale feature maps. This approach effectively addresses the challenge of varying vehicle scales, ensuring robust detection performance. We also built in a cross-scale aggregation feature (CSAF) module inside GCAFormer, which fuses low- and high-dimensional semantic information and provides multi-resolution feature maps as input to the detection head, so as to make the network more adaptable to complex traffic environments and realize accurate detection. In addition, we validate the effectiveness of our proposed method on a large number of datasets, reaching 89.12% mAP on the KITTI dataset, 90.62% on the IITM-hetra, 86.83% on the Pascal VOC and 93.33% on the BDD-100k. The results were compared to SOTA and demonstrated the competitive advantages of our proposed method for Vehicle Detection in complex traffic environments.

Colonic endoscopy is the gold standard for detecting rectal polyps and rectal cancer. In which polyps are a major predisposing factor for colorectal cancer, the precise diagnosis of polyps within colorectal endoscopy is highly dependent on a physician of professional level. With the development of deep learning, some semantic segmentation methods have recently been applied to polyp detection, but there are problems with insufficient accuracy and segmentation speed. To this end, we propose a precision adaptive global context network (AGCNet) based on real-time colon endoscopy. Firstly, in order to adapt to the problem of large-scale variation of polyps, we designed a multi-scale semantic fusion module (MSFM), which enhances the representation capability by varieties of filters to collect contextual information at different scales, thus adapting to the problem of large variation of polyp size, especially smaller polyps. In addition, modelling long-range dependence by simply using complex spatial pixels tends to introduce more background noise and increase the computational effort. To this end, a context-aware pyramid aggregation module (CPAM) was designed, which internally includes a novel dual attention mechanism whereby the CPAM aggregates feature information across different regions to boost the network’s ability to utilize global context and model long-range dependency through dual attention to further reinforce the features information of important regions and efficiently suppress features in non-important regions, Thereby achieving precise polyp segmentation and taking real-time into account. Our proposed AGCNet performed extensive experimental studies on datasets Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB and ETIS-LaribPolypDB. Specifically, AGCNet achieved an IoU of 87.40% and a Dice score of 92.63% on the Kvasir dataset, achieving accurate segmentation results faster than many current state-of-the-art models.

Agriculture is pivotal in national economies, with pest classification significantly influencing food quality and quantity. In recent years, pest classification methods based on deep learning have made progress. However, there are two problems with these methods. One is that there are few multi-scale pest detection algorithms, and they often lack effective global information integration and discriminative feature representation. The other is the lack of high-quality agricultural pest datasets, leading to insufficient training samples. To overcome these two limitations, we propose two methods called RS Transformer (a two-stage region proposal using Swin Transformer) and the Randomly Generated Stable Diffusion Dataset (RGSDD). Firstly, we found that the diffusion model can generate high-resolution images, so we developed a training strategy called the RGSDD, which was used to generate agricultural pest images and was mixed with real datasets for training. Secondly, RS Transformer uses Swin Transformer as the backbone to enhance the ability to extract global features, while reducing the computational burden of the previous Transformer. Finally, we added a region proposal network and ROI Align to form a two-stage training mode. The experimental results on the datasets show that RS Transformer has a better performance than the other models do. The RGSDD helps to improve the training accuracy of the model. Compared with methods of the same type, RS Transformer achieves up to 4.62% of improvement.

Transcranial magnetic stimulation (TMS) is a noninvasive neuromodulation technique for treating various neurological disorders. The geometry of the TMS coil determines the focality, stimulation field strength, and stimulation depth of the induced electric field. In this paper, we introduce a novel coil, named the eccentric folding coil (EFC). We used Sim4Life, a three-dimensional human tissue medical electromagnetic simulation software, and the brain models of the subjects from the population head model repository to conduct finite element simulations of the eccentric folding coil, circular coil, and figure-eight coil, implying that the largest EFC has a focal area of 19.5 cm2 less than the smallest circular coil, and the EFC of any size has a smaller focal area than the figure-8 coil of the same size. Furthermore, we stimulated the model from three directions with the coil and measured the electric field responses of the model, confirming that stimulation varied in different directions. Additionally, we applied EFC to four representative human models and found that the electric field in different subjects’ brains differed by 3.03 mm in stimulation depth and 12.9 cm2 in focal area, suggesting that personalized human head modeling and electromagnetic analysis are essential for TMS treatment. In the future, we will explore using different types of TMS devices for patients with different conditions to achieve more precise and customized treatment.

Transcranial magnetic stimulation (TMS) is a physical technique that modulates the human brain nervous system and can be used as a non-invasive treatment for neurological diseases. To address the problem of poor focusing performance of TMS coils, this study first designs a new coil geometry, Double Square Semicircle (DSS) coil, based on traditional coil stimulation characteristics. Second, this study uses the Sim4Life finite element simulation software to compare the stimulation characteristics of DSS coil and six traditional coils under the head model, proving that the induced electric field generated by DSS coil has high-focusing performance. Third, this paper explores the effects of four physical parameters - the distance between the human brain model and the coil, different stimulation directions, coil size and coil bending angle - on the spatial distribution of the induced electric field. After the above simulation experiments, the optimal design scheme of DSS coil is found. Experimental results show that, compared with several traditional coils, the focusing effect can be improved by up to 77.49%, proving that DSS is a high-focusing performance TMS coil, which is suitable for future TMS high-precision treatment needs.

Agriculture is pivotal in national economies, with pest detection significantly influencing food quality and quantity. Pest classification remains challenging in automated agriculture monitoring systems, exacerbated by the non-uniform pest scales and the scarcity of high-quality datasets. In this study, we constructed a pest dataset by acquiring domain-agnostic images from the Internet and resizing them to a standardized 299x299 pixel format. Additionally, we employed diffusion models to generate supplementary data. While Convolutional Neural Networks (CNNs) are prevalent for prediction and classification, they often lack effective global information integration and discriminative feature representation. To address these limitations, we propose the RS Transformer, an innovative model that combines elements like the Region Proposal Network, Swin Transformer, and ROI Align. Additionally, we introduce the Randomly Generated Stable Diffusion Dataset (RGSDD) to augment the availability of high-quality pest datasets. Extensive experimental evaluations demonstrate the superiority of our approach compared to both two-stage models (SSD and Faster R-CNN) and one-stage models (YOLOv3, YOLOv4, YOLOv5m, YOLOv8, and DETR). We rigorously assess performance using metrics such as mean Average Precision (mAP), F1Score, Recall, and mean Detection Time (mDT). Our research contributes to advancing pest detection methodologies in automated agriculture systems, promising improved food production and quality.