Gastric cancer is a highly prevalent disease that poses a serious threat to public health. In clinical practice, gastroscopy is frequently used by medical practitioners to screen for gastric cancer. However, the symptoms of gastric cancer at different stages of advancement vary significantly, particularly in the case of early gastric cancer (EGC). The manifestations of EGC are often indistinct, leading to a detection rate of less than 10%. In recent years, researchers have focused on leveraging deep learning algorithms to assist medical professionals in detecting EGC and thereby improve detection rates. To enhance the ability of deep learning to detect EGC and segment lesions in gastroscopic images, an Improved Mask R-CNN (IMR-CNN) model was proposed. This model incorporates a “Bi-directional feature extraction and fusion module” and a “Purification module for feature channel and space” based on the Mask R-CNN (MR-CNN). Our study includes a dataset of 1120 images of EGC for training and validation of the models. The experimental results indicate that the IMR-CNN model outperforms the original MR-CNN model, with Precision, Recall, Accuracy, Specificity and F1-Score values of 92.9%, 95.3%, 93.9%, 92.5% and 94.1%, respectively. Therefore, our proposed IMR-CNN model has superior detection and lesion segmentation capabilities and can effectively aid doctors in diagnosing EGC from gastroscopic images.

Today, the development of unmanned aerial vehicles (UAVs) has attracted significant attention in both civil and military fields due to their flight flexibility in complex and dangerous environments. However, due to energy constraints, UAVs can only finish a few tasks in a limited time. The problem of finding the best flight path while balancing the task completion time and the coverage rate needs to be resolved urgently. Therefore, this paper proposes a UAV path coverage algorithm base on the greedy strategy and ant colony optimization. Firstly, this paper introduces a secondary advantage judgment and optimizes it using an ant colony optimization algorithm to reach the goal of minimum time and maximum coverage. Simulations are performed for different numbers of mission points and UAVs, respectively. The results illustrate that the proposed algorithm achieves a 2.8% reduction in task completion time while achieving a 4.4% improvement in coverage rate compared to several previous works.

Most approaches to action recognition based on pseudo-images involve encoding skeletal data into RGB-like image representations. This approach cannot fully exploit the kinematic features and structural information of human poses, and convolutional neural network (CNN) models that process pseudo-images lack a global field of view and cannot completely extract action features from pseudo-images. In this paper, we propose a novel pose-based action representation method called Optical Flow Pose Image (OFPI) in order to fully capitalize on the spatial and temporal information of skeletal data. Specifically, in the proposed method, an advanced pose estimator collects skeletal data before locating the target person and then extracts skeletal data utilizing a human tracking algorithm. The OFPI representation is obtained by aggregating these skeletal data over time. To test the superiority of OFPI and investigate the significance of the model having a global field of view, we trained a simple CNN model and a transformer-based model, respectively. Both models achieved superior outcomes. Because of the global field of view, especially in the transformer-based model, the OFPI-based representation achieved 98.3% and 94.2% accuracy on the KTH and JHMDB datasets, respectively. Compared with other advanced pose representation methods and multi-stream methods, OFPI achieved state-of-the-art performance on the JHMDB dataset, indicating the utility and potential of this algorithm for skeleton-based action recognition research.

The diversity and complexity of the agricultural environment pose significant challenges for the collection of pest and disease data. Additionally, pest and disease datasets often suffer from uneven distribution in quantity and inconsistent annotation standards. Enhancing the accuracy of pest and disease recognition remains a challenge for existing models. We constructed a representative agricultural pest and disease dataset, FIP6Set, through a combination of field photography and web scraping. This dataset encapsulates key issues encountered in existing agricultural pest and disease datasets. Referencing existing bounding box regression (BBR) loss functions, we reconsidered their geometric features and proposed a novel bounding box similarity comparison metric, DDRIoU, suited to the characteristics of agricultural pest and disease datasets. By integrating the focal loss concept with the DDRIoU loss, we derived a new loss function, namely Focal-DDRIoU loss. Furthermore, we modified the network structure of YOLOV7 by embedding the MobileViTv3 module. Consequently, we introduced a model specifically designed for agricultural pest and disease detection in precision agriculture. We conducted performance evaluations on the FIP6Set dataset using mAP75 as the evaluation metric. Experimental results demonstrate that the Focal-DDRIoU loss achieves improvements of 1.12%, 1.24%, 1.04%, and 1.50% compared to the GIoU, DIoU, CIoU, and EIoU losses, respectively. When employing the GIoU, DIoU, CIoU, EIoU, and Focal-DDRIoU loss functions, the adjusted network structure showed enhancements of 0.68%, 0.68%, 0.78%, 0.60%, and 0.56%, respectively, compared to the original YOLOv7. Furthermore, the proposed model outperformed the mainstream YOLOv7 and YOLOv5 models by 1.86% and 1.60%, respectively. The superior performance of the proposed model in detecting agricultural pests and diseases directly contributes to reducing pesticide misuse, preventing large-scale pest and disease outbreaks, and ultimately enhancing crop yields. These outcomes strongly support the promotion of sustainable agricultural development.

To enhance the overall communication rate and capacity of mobile networks, a real-time application (RTA)-classification vertical handover (Ac-VHO) scheme is presented for indoor visible light communication (VLC) heterogeneous networks. The scheme considers user mobility, optical link instability, and the variability of real-time applications. It incorporates VLC line-of-sight (LOS) blocking and MT entry into co-channel interference (CCI) areas as triggers, while also providing differentiated delay tolerance intervals and optimized handover dwell time calculations for various RTAs, including video, audio (VoIP), and web/text. A simulation and comparative analysis demonstrate the superior performance of Ac-VHO in terms of signaling cost, and its average rate compared to other methods (hybrid application-aware VHO, dynamic time-dwelling VHO, and static time-dwelling VHO). In addition, it maintains a consistent and relatively high overall quality of user experience (QoE) for different RTA types.