The optimization problem of the number of mirrors under energy efficiency (EE) maximization for vehicular visible light communication (VVLC) via mirror array-based intelligent reflecting surface (IRS) is investigated. Under considering that the formulated optimization problem is subject to the real and non-negative of the transmitted signal, the maximum power consumption satisfied luminous ability and eye safety, the minimum achievable rate, and the required bit error ratio (BER), EE is proved to be a unimodal function of the number of mirrors. Then, the binary search-conditional iteration (BSCI) algorithm is proposed for quickly finding the optimal number of mirrors with maximum EE. Numerical results demonstrate that fewer mirrors can obtain the maximum EE, and the computational complexity of the BSCI algorithm is reduced by ${10}^5$ orders of magnitude, compared with the Bubble Sort method.

Sign language is a kind of important communication gesture to be studied in the human-computer interaction filed. Kinect is a 3D somatosensory camera launched by Microsoft, which can capture the color, depth and skeleton frames and is helpful to the gesture recognition research. In this paper, a method using the HOG and SVM algorithms with the Kinect software libraries to recognize sign language by recognizing the hand position, hand shape and hand action features is proposed. In order to realize this method, a special 3D sign language dataset contains 72 words is collected with Kinect, and experiments are conducted to evaluate the method. It is shown in the experimental results that the use of the HOG and SVM algorithms significantly increases the recognition accuracy of the Kinect, and is insensitive to background and other factors. The average recognition rate is up to 89.8%, which means the Kinect-based recognition method proposed in this paper can effectively and efficiently recognize sign language, and it has a great significance to the research and promotion of the sign language recognition technology.

Liver tumor segmentation is a critical part in the diagnosis and treatment of liver cancer. While U-shaped convolutional neural networks (UNets) have made significant strides in medical image segmentation, challenges remain in accurately segmenting tumor boundaries and detecting small tumors, resulting in low segmentation accuracy. To improve the segmentation accuracy of liver tumors, this work proposes space pyramid attention (SPA)-UNet, a novel image segmentation network with an encoder-decoder architecture. SPA-UNet consists of four modules: (1) Spatial pyramid convolution block (SPCB), extracting multi-scale features by fusing three sets of dilated convolutions with different rates. (2) Spatial pyramid pooling block (SPPB), performing downsampling to reduce image size. (3) Upsample module, integrating dense positional and semantic information. (4) Residual attention block (RA-Block), enabling precise tumor localization. The encoder incorporates 5 SPCBs and 4 SPPBs to capture contextual information. The decoder consists of the Upsample module and RA-Block, and finally a segmentation head outputs segmented images of liver and liver tumor. Experiments using the liver tumor segmentation dataset demonstrate that SPA-UNet surpasses the traditional UNet model, achieving a 1.0 and 2.0% improvement in intersection over union indicators for liver and tumors, respectively, along with increased recall rates by 1.2 and 1.8%. These advancements provide a dependable foundation for liver cancer diagnosis and treatment.

Drowning constitutes the leading cause of injury-related fatalities among adolescents. In swimming pool environments, traditional manual surveillance exhibits limitations, while existing technologies suffer from poor adaptability of wearable devices. Vision models based on YOLO still face challenges in edge deployment efficiency, robustness in complex water conditions, and multi-scale object detection. To address these issues, we propose YOLO11-LiB, a drowning object detection model based on YOLO11n, featuring three key enhancements. First, we design the Lightweight Feature Extraction Module (LGCBlock), which integrates the Lightweight Attention Encoding Block (LAE) and effectively combines Ghost Convolution (GhostConv) with dynamic convolution (DynamicConv). This optimizes the downsampling structure and the C3k2 module in the YOLO11n backbone network, significantly reducing model parameters and computational complexity. Second, we introduce the Cross-Channel Position-aware Spatial Attention Inverted Residual with Spatial–Channel Separate Attention module (C2PSAiSCSA) into the backbone. This module embeds the Spatial–Channel Separate Attention (SCSA) mechanism within the Inverted Residual Mobile Block (iRMB) framework, enabling more comprehensive and efficient feature extraction. Finally, we redesign the neck structure as the Bidirectional Feature Fusion Network (BiFF-Net), which integrates the Bidirectional Feature Pyramid Network (BiFPN) and Frequency-Aware Feature Fusion (FreqFusion). The enhanced YOLO11-LiB model was validated against mainstream algorithms through comparative experiments, and ablation studies were conducted. Experimental results demonstrate that YOLO11-LiB achieves a drowning class mean average precision (DmAP50) of 94.1%, with merely 2.02 M parameters and a model size of 4.25 MB. This represents an effective balance between accuracy and efficiency, providing a high-performance solution for real-time drowning detection in swimming pool scenarios.

Simple Baseline has become a dominant benchmark in human pose estimation (HPE) due to its excellent performance and simple design. However, its “strong encoder + simple decoder” architectural paradigm suffers from two core limitations: (1) its non-branching, linear deconvolutional path prevents it from leveraging the rich, fine-grained features generated by the encoder at multiple scales and (2) the model lacks explicit prior knowledge of both the absolute positions and structural layout of human keypoints. To address these issues, this paper introduces AFJ-PoseNet, a new architecture that deeply enhances the Simple Baseline framework. First, we restructure Simple Baseline’s original linear decoder into a U-Net-like multi-scale fusion path, introducing intermediate features from the encoder via skip connections. For efficient fusion, we design a novel Attention Fusion Module (AFM), which dynamically gates the flow of incoming detailed features through a context-aware spatial attention mechanism. Second, we propose the Joint-Aware Positional Encoding (JAPE) module, which innovatively combines a fixed global coordinate system with learnable, joint-specific spatial priors. This design injects both absolute position awareness and statistical priors of the human body structure. Our ablation studies on the MPII dataset validate the effectiveness of each proposed enhancement, with our full model achieving a mean PCKh of 88.915, a 0.341 percentage point improvement over our re-implemented baseline. On the more challenging COCO val2017 dataset, our ResNet-50-based AFJ-PoseNet achieves an Average Precision (AP) of 72.6%. While this involves a slight trade-off in Average Recall for higher precision, this result represents a significant 2.2 percentage point improvement over our re-implemented baseline (70.4%) and also outperforms other strong, publicly available models like DARK (72.4%) and SimCC (72.1%) under comparable settings, demonstrating the superiority and competitiveness of our proposed enhancements.

As an emerging type of network architecture, SDN is widespread used and security issues have also received more and more attention. Fingerprint attacks represent one of the most significant threats to network security. Attackers obtain key fingerprint information of the target network, which lays the foundation for subsequent more threatening attacks. Currently, research on domestic and international SDN fingerprint attacks focuses on how to attack, and less research is being done on how to defend against fingerprinting attacks. This paper proposes a mechanism for defending fingerprint attacks that combines dynamic disturbance and information entropy detection. This mechanism adopts the principle of fingerprint attack, combined with a moving average algorithm, Bloom Filter, and packet delay tool, to confuse opponents by disturbing a small number of packets, simultaneously, combined with the information entropy detection to make real-time processing feedback to the network. The experimental results show that this mechanism works effectively to defend SDNs against fingerprint attacks without affecting the normal network communication.