International Journal of Advanced Network, Monitoring and Controls

As the technologies of virtual reality and augmented reality rapidly advance, the demand for high-quality 3D models has been growing exponentially. However, the Multi-View Stereo Network (MVSNet) for 3D reconstruction has faced issues with the inaccurate extraction of global image information and depth cues. In response to these challenges, this paper presents enhancements to MVSNet. First, the self-attention mechanism is introduced to enhance MVSNet's ability to capture global information in images. Second, a residual structure is added to mitigate the accuracy loss caused by the downsampling and upsampling of feature maps during the regularization process of cost volume, thus ensuring the integrity of information and transmission efficiency. Experimental results indicate that, in comparison with the original MVSNet, the SelfRes-MVSNet reduces the error rate by 1.3% in terms of overall accuracy and completeness, thereby improving the reconstruction effect from 2D images to 3D models.

To address the challenges of low reconstruction accuracy and insufficient model generalization in image super-resolution (ISR) under complex degradation scenarios, this paper proposes an improved method that integrates generative adversarial networks (GAN) and vision transformers (ViT). First, in the generator module of Real-ESRGAN, some residual-in-residual dense blocks (RRDB) are replaced with ViT modules, leveraging the self-attention mechanism to enhance global feature modeling. This enables the model to better capture global information while preserving local details in complex scenes. Experimental results demonstrate that the improved model achieves PSNR gains of 0.59dB/0.45dB and SSIM improvements of 0.018/0.056 in ×2/×4 upscaling tasks on the Urban100 dataset, while also exhibiting excellent performance on benchmark datasets such as Set14. This method significantly enhances image reconstruction quality under complex degradation conditions, providing an effective technical solution for practical applications such as security surveillance, remote sensing monitoring, and target reconnaissance.

This research investigates the development of a custom hybrid operating system (OS) for a Mars rover experimental prototype using the Raspberry Pi platform. Focusing on operating system optimization, the work enhances computational efficiency, real-time responsiveness, and AI integration. Key innovations include overclocking (boosting CPU performance by 28%), custom threading (reducing task scheduling latency by 22%), and networking improvements for stable remote operation. Codec refinements and framework adaptations improved real-time video analysis throughput by 30%. Integration of a Power-over-Ethernet (PoE) HAT enhanced thermal regulation and stabilized system runtime. Experimental results show the customized OS effectively supports intensive tasks such as image processing, sensor data acquisition, and edge AI workloads. The findings demonstrate a scalable, modular OS framework for real-time vision systems and intelligent robotics in resource-constrained environments.

It’s highly crucial to divide up medical photos correctly in order to make diagnoses and plan treatments. Convolutional Neural Networks (CNNs) are very good at picking up local information, but they have problems with long-range dependencies. On the other side, Vision Transformers (ViTs) are good at modeling global context, but they need a lot of computer power and labeled data. To get surrounding these difficulties, we establish PSwinUNet, a hybrid CNN-Transformer system based on a partially supervised learning the structure. Adding a SwinTransformer block to a U-shaped structure makes PSwinUNet better at learning internationally semantics and up-sampling. It also uses a polarized self-attention mechanism in skip connections to keep spatial information from getting lost when the image is downsampled. PSwinUNet does a better job than the best gets closer that are currently accessible when tested on the BUSI, DRIVE, and CVC-ClinicDB datasets. For instance, it earned Dice Similarity Coefficient (DSC) scores of 0.781, 0.896, and 0.960 based on the BUSI data set with 1/8, 1/2, and entire labeled information, respectively. These scores are substantially better than those of the old UNet and UNet++ models.

This study investigates the optimization of broadband communication channel capacity through an integrative information-theoretic framework. Leveraging Shannon’s theory, it examines fundamental constraints such as bandwidth limitations, channel noise, modulation techniques, error correction mechanisms, and adaptive systems. A comprehensive literature review of 118 articles identified 18 critical enablers, which were evaluated by domain experts. The Fuzzy DEMATEL method was employed to prioritize enablers based on interdependencies and influence. Results indicate that Security Considerations, Channel Access Protocols, and Propagation Characteristics exert the most significant impact on capacity optimization. The findings offer a structured decision-making model for stakeholders, enabling efficient allocation of technological, infrastructural, and human resources. By bridging theoretical principles with practical implementation, this research provides actionable insights for academic researchers and industry practitioners in designing robust, high-capacity broadband systems. The integrative modeling approach advances the application of information theory in modern communication networks, supporting informed technology adoption and system integration.

Image inpainting represents a sophisticated methodology within the domain of computer vision, whose core objective is to programmatically restore occluded regions or eliminate undesired elements from digital imagery. This process endeavors to reconstruct visual continuity such that the resulting image exhibits both perceptual naturalness and structural completeness. Image inpainting has gradually become a hot field in computer vision. It is used in film processing, watermark removal, photo processing, and other fields. Traditional image inpainting methods use adjacent pixels of the missing area for filling, which not only incur high computational costs but also suffer from ghost artifacts and blur. With the emergence of large-scale datasets, deep learning-based image inpainting methods have been successively proposed, significantly improving restoration quality. However, the current state-of-the-art methodologies continue to demonstrate suboptimal performance when confronted with images featuring extensive occluded domains. Additionally, technological advancements in related image fields bring new opportunities and challenges to image inpainting. This paper discusses three aspects: (1) a review of relevant datasets for image inpainting, (2) a detailed description and summary of state-of-the-art methods, and (3) an introduction of evaluation metrics with performance comparisons of representative approaches. Finally, we address existing challenges and future opportunities in this field.

Aiming at the significant deficiencies of traditional traffic signal control algorithms in multi-intersection collaboration, unexpected event response and system generalization ability, this paper proposes an intelligent traffic signal control method that integrates a bidirectional gated recurrent unit BGRU with deep reinforcement learning DRL. The method adopts BGRU to model the historical traffic flow data in time sequence and accurately predict the traffic state; and based on this, it constructs deep Q-network intelligences to dynamically optimize the multi-intersection signal timing strategy. The experimental validation on SUMO simulation platform shows that the proposed method effectively improves the control performance. Compared with the traditional fixed-cycle control and adaptive control methods, the proposed method reduces the average vehicle waiting time by 58.8% and 42.2%, and improves the intersection access efficiency by 83.8% and 52.4%, respectively. The study provides new ideas for building an efficient and intelligent urban traffic management system.

In UAV-captured images, the high density of objects and the large proportion of small targets pose significant challenges to YOLO-based object detection algorithms. This study presents an enhanced object detection framework derived from the YOLOv10s architecture, aiming to achieve superior detection accuracy. First, an Adaptive Progressive Feature Unification (APFU) module is proposed to effectively integrate multi-level feature representations, ensuring a balanced fusion of high-level semantic information from low-resolution features and fine-grained spatial details from high-resolution features. Second, a Feature Enhancement and Attention (FEA) module is introduced to adaptively recalibrate feature responses, emphasizing informative features while suppressing irrelevant noise and interference. Finally, based on these modules, the APFU-YOLOv10 network is built to effectively improve the network's perception ability of objects at different scales. Experimental results on the VisDrone dataset demonstrate the superior performance of the proposed algorithm: mAP@0.5 increased from 42.6% to 43.5%, a relative improvement of approximately 2.11%; mAP@0.5:0.95 improved from 25.4% to 26.2%, a relative increase of about 3.15%; recall improved from 0.410 to 0.416, further reducing missed detections and enhancing object coverage. The method achieves significant improvements in detection accuracy under medium to high IoU thresholds, validating the effectiveness of multi-scale feature fusion and adaptive attention mechanisms in small object detection for UAV imagery.

Satellite communication has served as the foundation for television, radio, and telephone transmission for more than a century. These communications function at extremely high frequencies, primarily 6 GHz for uplink and 4 GHz for downlink. Satellite antennas installed on residences convert these high-frequency signals downward to make more efficient use of them. Frequency down-converters are commercially known as Low-Noise Blocks (LNBs). LNBs are responsible for receiving, amplifying, and then down-converting these microwave signals to a lower range of intermediate frequencies. This down-conversion is essential as it enables the signal to be transmitted through relatively inexpensive coaxial cables, in contrast to the costly and impractical waveguides that would be necessary for transmitting the original microwave signals. This paper addresses the design of the three primary components that constitute a frequency down-converter: the Low Noise Amplifier (LNA), the Local Oscillator (LO), and the Frequency Mixer. The intermediate frequencies required for satellite applications typically range from 75 MHz to 900 MHz. This study designs a frequency down-converter that generates an intermediate frequency of 100 MHz. For an input radio frequency of 1 GHz, the oscillator will be designed to operate at a center frequency of 0.9 GHz.

Uncertainty in decision-making processes presents a critical challenge for autonomous agents, often leading to suboptimal or erroneous policies. This paper addresses two prevalent yet distinct types of uncertainty that significantly degrade agent performance: fuzzy uncertainty, stemming from ambiguous task boundaries, and gray uncertainty, arising from noisy or incomplete state observations. To tackle these challenges, we propose the Dual-Task-State Inference (DTS-Infer) method, a novel framework that leverages variational inference within an off-policy reinforcement learning structure. DTS-Infer utilizes a dual-network architecture to explicitly disentangle and resolve these uncertainties: (1) a task inference network learns a latent distribution over tasks from historical data to disambiguate task goals, thereby solving the fuzzy uncertainty problem ; and (2) a state inference network captures robust latent features of the current state to overcome corrupted sensory input, thus addressing gray uncertainty. Extensive experiments on continuous control benchmarks demonstrate that DTS-Infer significantly outperforms state-of-the-art algorithms. For instance, in the Half-Cheetah-Fwd-Back environment, DTS-Infer achieved a final average reward of 1612.61, representing an 18.9% improvement over the PEARL algorithm. Furthermore, ablation studies confirmed that our inference modules contribute to an 80% increase in average reward over a standard TD3 baseline, highlighting the method's effectiveness in enhancing the robustness and adaptability of intelligent agents.