Object detection in low-light environments poses a challenging task. Existing work involving visible and infrared light primarily focuses on fusion enhancements across multiple scales of the backbone network. This paper proposes and constructs the Prior Difference Interleaved Network (PDIN), a dual-stream detector based on the YOLOv11n framework. Its core innovation lies in the interleaved deep fusion strategy combining CPCA and SDI. Specifically, the model introduces a Channel-Prior Convolutional Attention (CPCA) module before fusion to pre-enhance and reduce redundancy in dual-modal features. Subsequently, a Semantic Difference Interaction (SDI) module is designed and proposed, whose core lies in converting semantic differences between modalities into dynamic weight signals that guide fusion, achieving difference-driven adaptive integration. By first optimizing feature quality and then performing dynamic difference-driven integration, PDIN significantly enhances model robustness. Extensive results on the VEDAI dataset demonstrate PDIN's effectiveness, ultimately improving the mAP50 performance metric from the baseline 47.2% to 52.3%. This study robustly validates the efficacy of explicitly leveraging modal differences and performing feature quality pre-enhancement in bimodal deep learning fusion.
To address the issues of low efficiency in manual modeling of virtual scenes and the high engineering threshold of existing AI generation technologies, an offline automatic virtual scene generation framework based on Generative Adversarial Networks (GAN) and the Unity engine is proposed. With the Pix2Pix conditional generation model as its core, this framework enables the automatic generation of indoor scene layouts. It completes the reconstruction from layouts to 3D scenes through the Unity parsing-generation module and adopts an "offline file collaboration" mode to reduce the cross-domain technical coupling. Experiments are conducted based on the SUNCG indoor dataset. The average Intersection over Union (IoU) between the layouts generated by the trained Pix2Pix model and the real layouts reaches 0.78. In a general PC environment, the Unity scene reconstruction module takes no more than 1.2 seconds to generate a 10×10m indoor scene, which improves the efficiency by over 99% compared with manual modeling. User experience tests show that this framework has a low operation threshold, and the generated scenes receive an average score of 4.1/5 in terms of layout rationality and practicality, which can meet the rapid development needs of scenarios such as game prototype design and educational virtual simulation.
Polar codes and their CRC-assisted derivatives have become important facilitators of ultra-reliable low-latency communication (URLLC) in 5G wireless networks, especially in the cases of applications where short packets have to be transmitted, and error rates must be nearly zero, such as autonomous vehicles, remote medical treatments, and automation of industrial devices. Although the dependability has been proved to be beneficial when the incorporation of codes of CRC-Polar is performed previously, the studies frequently analyze the qualities of the reliability and latency separately without taking into account the trade-offs inherent to 6G URLLC. This paper fills this gap by coming up with a single analytical model that explicitly characterizes the dependence of blocklength, their CRC length, and successive cancellation list size (size of successive cancellation) on the block error rate and the decoding latency. The it is a methodology that incorporates the finite-blocklength information theory, channel polarization principles and the analysis of instruments of CRC errors detection and is confirmed and validated over extensive simulation over realistic 6G parameters. The findings reveal that list decoding with the aid of CRC yields a significant reliability improvement in short packet cases, and the increases in decodinglatency with larger lists are nearly linear, although there is a large gain in reliability with a considerable like impact of CRC length. The paper defines limited optimum areas of the parameters under which URLLC requirements are met, the significance of co-designing of parameters. In general, the framework suggested will give viable considerations towards realizing hybrid codes of CRC-Polar mechanisms to reach ultra-high reliability without breaking the sub-milliseconds delay limitations in future 6G networks.
The escalating global mental health crisis has high- lighted a critical shortage of accessible therapeutic resources. While digital health interventions exist, many rely on static jour- naling or rudimentary rule-based chatbots that fail to capture the semantic nuance of complex human emotions. This paper presents the design, development, and evaluation of “Apricity,” a comprehensive AI-powered mental health companion application. Grounded in the principles of Cognitive Behavioral Therapy (CBT), the system provides users with an empathetic platform to track emotions and journal thoughts. The application is engineered as a scalable full-stack solution using the MERN stack (MongoDB, Express, React, Node.js) integrated with an asynchronous Python microservice for heavy inference tasks. A central contribution of this work is the implementation of a high-fidelity emotion recognition model. We fine-tuned the DeBERTa-v3 (Decoding-enhanced BERT with Disentangled Attention) architecture on the GoEmotions dataset, implementing a novel mapping strategy to aggregate 27 fine-grained labels into 5 core emotional categories (Joy, Sadness, Fear, Anger, Surprise). Experimental results demonstrate that our approach achieves a validation accuracy of 92.5% and a weighted F1-score of 0.83, significantly outperforming baseline models including BERT, RoBERTa, and traditional SVM classifiers. Furthermore, the system addresses the challenge of deploying large language models in consumer applications by utilizing a Job Queue architecture, ensuring real-time responsiveness.
To enhance the robustness of small object detection in UAV aerial imagery, this paper proposes an improved detection method based on the YOLOv11 architecture. Initially, to mitigate the occlusion of small-target features by surrounding background clutter, a Multi-scale Edge Information Enhancement module is introduced to amplify fine-grained local details. Subsequently, an efficient feature fusion architecture is constructed to achieve comprehensive integration of global contextual semantics with small-object feature representations. Furthermore, a Task-Dynamic Aligned Head (TDAH) based on shared convolutions is proposed to mitigate the inconsistency between the classification and regression tasks. Finally, a loss function named WSIoU, which incorporates dynamic focusing and shape-aware constraints, is introduced to reduce the interference of low-quality samples during model optimization. Experimental results on the VisDrone2019 dataset confirm that the proposed method not only achieves a 4.72% improvement in mAP@0.5 but also provides a practical and viable enhancement strategy for small object detection from a drone perspective.
In response to the critical issues of link saturation and excessive latency stemming from inter-cluster coordination within partitioned Vehicular Ad-hoc Networks (VANETs), this research develops a Hybrid Genetic-Ant Colony Multipath Routing scheme (GAAC) designed for congestion-free data dissemination. By synthesizing node buffer occupancy, relative mobility patterns, and temporal constraints into a comprehensive assessment framework, the routing selection is reformulated as a multi-constrained optimization challenge. The methodology integrates Genetic Algorithm (GA) operations to conduct a broad-spectrum exploration of the solution space, thereby seeding the Ant Colony Optimization (ACO) process with superior initial pheromone distributions to bypass the traditional pitfalls of erratic searching and sluggish convergence. To further refine path acquisition, the transition rule is augmented with composite heuristic cues, while an adaptive link restoration and proactive failover protocol is implemented to uphold session persistence amidst volatile topology shifts. Performance evaluations indicate that the GAAC framework stabilizes within approximately 34 iterations, exhibiting superior convergence efficiency over decoupled GA or ACO implementations. Compared to the baseline GA configurations, the integrated approach yields a 3.66% enhancement in delivery success, shortens latency by 0.094s, and expands throughput by 73.589 Kbps. Notably, the maintenance of a 200 ms delay profile at high-velocity mobility (80 km/h) underscores the algorithm's suitability for time-sensitive vehicular multimedia applications.
Most traditional SLAM algorithms suffer severe performance degradation in complex outdoor scenes with pedestrians and moving vehicles, leading to blurred and deformed environmental maps. This paper proposes FE-LIM, a mapping algorithm fusing multi-line LiDAR and IMU. The algorithm judges dynamic points via inter-frame point offset differential analysis, clusters dynamic outliers by DBSCAN and removes them. LiDAR and IMU timestamps are strictly aligned, and EKF is used for sensor fusion to reduce cumulative drift. An adaptive parameter adjustment mechanism is introduced for point cloud feature extraction according to the previous frame information. Tested on three groups of real urban scenes from the KITTI dataset, the algorithm thoroughly filters out dynamic point clutter, the reconstructed trajectory presents small three-axis and angular offset, and the generated 3D point cloud clearly restores complete outlines of roads, buildings and parking lots. Experimental results verify that the proposed method can effectively eliminate dynamic points and produce high-quality static environment maps.
Image super-resolution reconstruction aims to transform low-resolution blurred images into high-resolution images under the same scene. Due to its practical value and theoretical significance, this technology is widely used in computer vision and image processing. In recent years, deep learning-based super-resolution algorithms have shown strong performance. However, most existing deep learning methods suffer from a common issue: when reconstructing images at large magnification factors, the results tend to be overly smooth and lacking in texture, resulting in unrealistic visual perception. Perceptual super-resolution methods based on generative adversarial networks (GANs) can effectively alleviate the oversmoothing problem, which has drawn significant research attention. Nevertheless, GAN-based approaches still have limitations, including single-scale reconstruction, insufficient acquisition of high-frequency information, and a tendency to generate excessive textures in smooth areas, leading to images with noticeable noise, artifacts, and insufficient texture details. To address these shortcomings, this paper proposes a novel network structure that integrates generative adversarial networks with multi-stage gated aggregation and multi-scale feature fusion mechanisms. The goal is to optimize the existing problems in current image super-resolution networks and improve the quality of image reconstruction.Image super-resolution reconstruction aims to transform low-resolution blurred images into high-resolution images under the same scene. Due to its practical value and theoretical significance, this technology is widely used in computer vision and image processing. In recent years, deep learning-based super-resolution algorithms have shown strong performance. However, most existing deep learning methods suffer from a common issue: when reconstructing images at large magnification factors, the results tend to be overly smooth and lacking in texture, resulting in unrealistic visual perception. Perceptual super-resolution methods based on generative adversarial networks (GANs) can effectively alleviate the oversmoothing problem, which has drawn significant research attention. Nevertheless, GAN-based approaches still have limitations, including single-scale reconstruction, insufficient acquisition of high-frequency information, and a tendency to generate excessive textures in smooth areas, leading to images with noticeable noise, artifacts, and insufficient texture details. To address these shortcomings, this paper proposes a novel network structure that integrates generative adversarial networks with multi-stage gated aggregation and multi-scale feature fusion mechanisms. The goal is to optimize the existing problems in current image super-resolution networks and improve the quality of image reconstruction.
To address the issue of overloaded course resources on MOOC platforms and the poor effectiveness of personalized course recommendations for users, this paper proposes a MOOC course recommendation method that integrates reinforcement learning and neural-symbolic reasoning. The method uses neural networks to extract features of user behavior in MOOCs, the neural-symbolic reasoning module to explore paths in the knowledge graph, and reinforcement learning to simulate user-course interactions for recommendation decisions. Experiments conducted on the MOOCCube dataset show that the proposed method integrating reinforcement learning and neural-symbolic reasoning improves the NDCG and HR metrics by 9.96% and 23.5%, respectively.
Traditional product recognition methods are limited by human experience and complex environments, leading to low accuracy and efficiency. The algorithm proposed in this paper significantly enhances the efficiency of retail and warehouse management, addressing these issues. This paper improves upon the YOLOv7 model and proposes a new model, MS-YOLO, to tackle the challenges of small object and occlusion detection. An improved CSPNet backbone network is designed, and the Ghost module is introduced to improve computational efficiency. The feature pyramid network is optimized and the NAM attention mechanism is embedded to enhance the feature fusion of small and occluded objects. A small object detection head branch is added, combined with the lightweight Ghost module, to improve small object detection robustness. Experimental results show that the model performs better in multi-scale object detection, low-light scenarios, and complex backgrounds, with the mAP@0.5 increasing from 87.5% in the original YOLOv7 to 92%, indicating that the model can effectively achieve rapid and accurate object recognition.
Gamma-ray burst (GRB) detection is crucial for triggering rapid follow-up observations and enabling subsequent multi-wavelength studies, yet traditional methods are limited by their difficulty in modeling long-range temporal dependencies in noisy, non-stationary data. In this work, we propose GRBNet, a self-attention–based neural network for GRB detection from same-source multi-detector time-tagged event (TTE) sequences. GRBNet leverages multi-head self-attention to adaptively aggregate discriminative evidence over the full observation window, explicitly capturing long-term dependencies and multi-pulse structures, and integrates complementary responses from multiple detectors under a unified tokenization scheme to improve robustness against background drift and low SNR in individual instruments. Experiments on real Fermi/GBM observations show strong detection performance (recall=1.00, precision=1.00) under a stringent triggering threshold 0.99, indicating reliable performance for weak and morphologically complex GRB events.
To address the issues of uneven texture distribution, background mis-migration, and training imbalance in traditional CycleGAN for style transfer of non-paired horse and zebra images, this study proposes an improved model integrating dynamic attention mechanisms, semantic segmentation constraints, and adaptive training strategies. By embedding lightweight space-channel hybrid attention modules in generator residual blocks, the model enhances feature extraction in target regions. A lightweight semantic segmentation network is introduced to enforce local style transfer constraints, preventing redundant background migration. A two-stage adaptive loss weight adjustment strategy is designed to improve training stability. Experiments on the horse2zebra dataset using the PyTorch platform demonstrate that the improved model generates zebra stripes that conform to the subject structure, with non-target region pixel changes below 15.8%. Compared to the original CycleGAN, the model achieves an 8.3% SSIM improvement and 1.5dB PSNR enhancement. This model effectively resolves core limitations of traditional methods, providing a superior solution for style transfer of non-paired animal images.
To address the challenges in efficiently modeling and simulating Electromagnetic Compatibility (EMC) for complex electrical and electronic systems, a system-level EMC analysis method based on cascaded multi-port network theory is proposed. According to the topological structure of the system, this method decomposes the complex system into multiple cascaded multi-port network modules, where electromagnetic energy transmission and coupling occur via ports. In this method, the Electromagnetic Interference (EMI) transfer characteristics of each module are described by the impedance matrix of its internal circuitry. The voltage and current coupling relationships at system ports are calculated using the cascaded impedance matrix of the multi-stage network combined with specific boundary conditions, thereby significantly simplifying the modeling and simulation process. Numerical validation performed on a three-stage cascaded system across the 10–100 MHz frequency band demonstrates that the proposed method achieves high fidelity. Compared with full-wave simulations, the maximum absolute error for the current response is limited to 0.7 mA (occurring at 10 MHz), and for the voltage response is merely 0.037 V, with the average current error maintained at approximately 0.1 mA. The relative error for both responses at critical ports consistently remains within 0.2%. Furthermore, both modeling complexity and calculation time are substantially reduced, providing a feasible technical approach for the EMC modeling and simulation of complex systems.
In response to the limitations of traditional obstacle avoidance algorithms for unmanned vehicles in dealing with unknown obstacles and complex dynamic environments, this paper proposes Q Mixing Network and Video Delivery Network reinforcement learning algorithms, specifically for the research of obstacle avoidance decision-making for unmanned vehicles. By constructing a mapping relationship between local function values and global function values, it is possible to guide obstacle avoidance decisions for unmanned vehicles based on the decomposed function values. Experimental verification was conducted on a simulation platform based on ROS+Gazebo, and compared with the Quantile Regression for Reinforcement Learning algorithm in the same testing environment. The results showed that QMIX and VDN algorithms were more adaptable to complex map environments during training, with obstacle avoidance success rates increased by 16.9% and 18.1%, respectively, effectively improving the obstacle perception and avoidance capabilities of unmanned vehicles.
