With the wide application of graphs in various fields, graph query languages have attracted more and more attention. Existing graph query languages, such as GraphQL and SoQL, mostly have similar expressive power as th...
详细信息
With the wide application of graphs in various fields, graph query languages have attracted more and more attention. Existing graph query languages, such as GraphQL and SoQL, mostly have similar expressive power as the first-order logic or its extended versions, and are limited when used to express various queries. In this paper, since the graph data model is the base of the graph query language, we propose a new graph data model with the expressive power of monadic second-order logic (abbr. MSOL), and then present a more expressive SQL-like declarative graph query language named SOGQL to support more common queries efficiently. Specifically, a new graph calculus is first proposed based on MSOL for attributed graphs. Then, the new graph data model is proposed. Its graph algebra, which operates on graph sets, has seven fundamental operators such as union, filter, map, and reduce. Next, the graph query language SOGQL is proposed based on the graph data model. Since the graph algebra has the same expressive power as the graph calculus, SOGQL has the expressive power of MSOL, and can express queries with constraints on subgraphs. Moreover, applied with SOGQL, a prototype system named SOGD B is implemented. SOGD B is applied with SOGQL, and the experimental results show its efficiency.
With the development of deep learning in EEG-related tasks, the complexity of learning models has gradually increased. These complex models often result in long inference times, high energy consumption, and an increas...
详细信息
Deep Reinforcement Learning has been successfully applied in various applications and achieved impressive performance compared with previous traditional methods but suffers from high computation cost and long training...
详细信息
Deep Reinforcement Learning has been successfully applied in various applications and achieved impressive performance compared with previous traditional methods but suffers from high computation cost and long training time. MLPerf takes deep reinforcement learning as one of the benchmark tracks and provides a single node training version of MiniGo as a reference. A key challenge is to achieve efficient MiniGo training on a large-scale computing system. According to the training computation pattern in MiniGo and the characteristics of our large-scale heterogeneous computing system, we propose a MultiLevel parallel strategy, MLPs, including task-level parallelism between nodes, CPU-DSP heterogeneous parallelism, and DSP multi-core parallelism. The proposed method reduces the overall execution time from 43 hours to 16 hours while scaling the node size from 1067 to 4139. The scaling efficiency is 69.1%. According to our fitting method, the scaling efficiency is 46.5% when scaling to 8235 nodes. The experimental results show that the proposed method achieves the efficient training of MiniGo on the largescale heterogeneous computing system.
Scene text recognition (STR) is a challenging task that aims to automatically localize and recognize text in varied natural scenes. Although the performance of STR methods has been significantly improved, the STR prob...
详细信息
In this paper, we present a novel method to enhance the sum-rate effectiveness in full-duplex unmanned aerial vehicle (UAV)-assisted communication networks. Existing approaches often couple uplink and downlink associa...
详细信息
In this paper, we present a novel method to enhance the sum-rate effectiveness in full-duplex unmanned aerial vehicle (UAV)-assisted communication networks. Existing approaches often couple uplink and downlink associations, resulting in suboptimal performance, particularly in dynamic environments where user demands and network conditions are unpredictable. To overcome these limitations, we propose a decoupling of uplink and downlink associations for ground-based users (GBUs), significantly improving network efficiency. We formulate a comprehensive optimization problem that integrates UAV trajectory design and user association, aiming to maximize the overall sum-rate efficiency of the network. Due to the problem's non-convexity, we reformulate it as a Partially Observable Markov Decision Process (POMDP), enabling UAVs to make real-time decisions based on local observations without requiring complete global information. Our framework employs multi-agent deep reinforcement learning (MADRL), specifically the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, which balances centralized training with distributed execution. This allows UAVs to efficiently learn optimal user associations and trajectory controls while dynamically adapting to local conditions. The proposed solution is particularly suited for critical applications such as disaster response and search and rescue missions, highlighting the practical significance of utilizing UAVs for rapid network deployment in emergencies. By addressing the limitations of existing centralized and distributed solutions, our hybrid model combines the benefits of centralized training with the adaptability of distributed inference, ensuring optimal UAV operations in real-time scenarios.
This work proposes a hybrid machining robot RPR/RP + RR + P based on a planar parallel mechanism. Based on the screw theory, the characteristics of the degree of freedom of the hybrid robot are analyzed, and then the ...
详细信息
The explosive growth of social media means portrait editing and retouching are in high *** portraits are commonly captured and stored as raster images,editing raster images is non-trivial and requires the user to be h...
详细信息
The explosive growth of social media means portrait editing and retouching are in high *** portraits are commonly captured and stored as raster images,editing raster images is non-trivial and requires the user to be highly *** at developing intuitive and easy-to-use portrait editing tools,we propose a novel vectorization method that can automatically convert raster images into a 3-tier hierarchical *** base layer consists of a set of sparse diffusion curves(DCs)which characterize salient geometric features and low-frequency colors,providing a means for semantic color transfer and facial expression *** middle level encodes specular highlights and shadows as large,editable Poisson regions(PRs)and allows the user to directly adjust illumination by tuning the strength and changing the shapes of *** top level contains two types of pixel-sized PRs for high-frequency residuals and fine details such as pimples and *** train a deep generative model that can produce high-frequency residuals *** to the inherent meaning in vector primitives,editing portraits becomes easy and *** particular,our method supports color transfer,facial expression editing,highlight and shadow editing,and automatic *** quantitatively evaluate the results,we extend the commonly used FLIP metric(which measures color and feature differences between two images)to consider *** new metric,illumination-sensitive FLIP,can effectively capture salient changes in color transfer results,and is more consistent with human perception than FLIP and other quality measures for portrait *** evaluate our method on the FFHQR dataset and show it to be effective for common portrait editing tasks,such as retouching,light editing,color transfer,and expression editing.
Automated fabric defect detection is crucial for improving quality control, reducing manual labor, and optimizing efficiency in the textile industry. Traditional inspection methods rely heavily on human oversight, whi...
详细信息
Automated fabric defect detection is crucial for improving quality control, reducing manual labor, and optimizing efficiency in the textile industry. Traditional inspection methods rely heavily on human oversight, which makes them prone to subjectivity, inefficiency, and inconsistency in high-speed manufacturing environments. This review systematically examines the evolution of the You Only Look Once (YOLO) object detection framework from YOLO-v1 to YOLO-v11, emphasizing architectural advancements such as attention-based feature refinement and Transformer integration and their impact on fabric defect detection. Unlike prior studies focusing on specific YOLO variants, this work comprehensively compares the entire YOLO family, highlighting key innovations and their practical implications. We also discuss the challenges, including dataset limitations, domain generalization, and computational constraints, proposing future solutions such as synthetic data generation, federated learning, and edge AI deployment. By bridging the gap between academic advancements and industrial applications, this review is a practical guide for selecting and optimizing YOLO models for fabric inspection, paving the way for intelligent quality control systems.
This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations....
详细信息
This paper introduces an advanced and efficient method for distributed drone-based fruit recognition and localization, tailored to satisfy the precision and security requirements of autonomous agricultural operations. Our method incorporates depth information to ensure precise localization and utilizes a streamlined detection network centered on the RepVGG module. This module replaces the traditional C2f module, enhancing detection performance while maintaining speed. To bolster the detection of small, distant fruits in complex settings, we integrate Selective Kernel Attention (SKAttention) and a specialized small-target detection layer. This adaptation allows the system to manage difficult conditions, such as variable lighting and obstructive foliage. To reinforce security, the tasks of recognition and localization are distributed among multiple drones, enhancing resilience against tampering and data manipulation. This distribution also optimizes resource allocation through collaborative processing. The model remains lightweight and is optimized for rapid and accurate detection, which is essential for real-time applications. Our proposed system, validated with a D435 depth camera, achieves a mean Average Precision (mAP) of 0.943 and a frame rate of 169 FPS, which represents a significant improvement over the baseline by 0.039 percentage points and 25 FPS, respectively. Additionally, the average localization error is reduced to 0.82 cm, highlighting the model’s high precision. These enhancements render our system highly effective for secure, autonomous fruit-picking operations, effectively addressing significant performance and cybersecurity challenges in agriculture. This approach establishes a foundation for reliable, efficient, and secure distributed fruit-picking applications, facilitating the advancement of autonomous systems in contemporary agricultural practices.
暂无评论