检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Cheng, Dongdong Zhang, Cheng Li, Ya Xia, Shuyin Wang, Guoyin Huang, Jinlong Zhang, Sulan Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing408100 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

DBSCAN algorithm identifies high-density connected areas as clusters, so that it has advantages in discovering arbitrary-shaped clusters. However, it has difficulty in adjusting parameters and its time complexity is O(n2). Granular-ball (GB) is a coarse grained representation of data. It is on the basis of the assumption that an object and its local neighbors have similar distribution and they have high possibility of belonging to the same class. Inspired by the idea of granular-ball, we introduce it into unsupervised learning and use it to improve the efficiency of DBSCAN, called GB-DBSCAN. Firstly, we use k-nearest neighbor (KNN) to generate granular-balls, which is a bottom-up strategy, and describe granular-balls according to their centers and radius. Then, the granular-balls are divided into Core-GB and Non-Core-GB according to their density. After that, the Core-GBs are merged into clusters according to the idea of DBSCAN and the Non-Core-GBs are assigned to appropriate clusters. Since the granular-balls' number is much smaller than the size of the objects in a data, the running time of DBSCAN is greatly reduced. By comparing with state-of-the-art clustering algorithms, the proposed algorithm can get similar or better clustering result in much less running time. © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Framework for Delivery Capacity Scheduling with Vehicle Constraints 20

Reinforcement Learning Framework for Delivery Capacity Sched...

引用

20th IEEE International Conference on e-Business Engineering, ICEBE 2024

作者： Ma, Zhongneng Qin, Zhuorui Shi, Shuxia Wu, Qingyao South China University of Technology Guangzhou China School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Guangzhou Henll Electronics Equipment Co. Ltd Guangzhou China Peng Cheng Laboratory China

ISBN: (纸本)9798350365856

Improving the risk prevention capability of grid operations is a crucial requirement for smart resilient grids, where efficient dispatch and scheduling of delivery capacity play a pivotal role in enhancing grid resilience. Therefore, it is necessary to develop targeted intelligent dispatch algorithms based on operational data. To address this issue, this paper proposes a framework with inherent constraints and utilizes reinforcement learning using recursive neural networks. A constraint module is designed to identify available vehicle combinations based on de-livery capacity, allocate goods considering vehicle number, load, and size constraints, and generate delivery routes sequentially. Additionally, a reinforcement learning model is introduced, using negative trip length as a reward signal, optimizing parameters of the recursive neural network through policy gradient methods to automatically improve strategies for selecting optimal deliv-ery routes with improved vehicle combinations. To validate the effectiveness of this algorithm, extensive experiments were conducted using both real-world application validation data and the TSPLIB public dataset. Within a limited computational budget, the proposed algorithm outperforms several mature methods in terms of effectiveness and real-time performance, achieving near-optimal results in Euclidean graphs with nearly 100 nodes. These results demonstrate that this approach effectively addresses the intelligent scheduling of delivery capacity in digital twin systems for power storage © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Research on Collaborative Storage of data Based on IPFS and Blockchain

Research on Collaborative Storage of Data Based on IPFS and ...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Boyuan Han Zhihong Liang Yuxiang Huang Mingming Qin Fei Xiong School of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data Southwest Forestry University

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

The advent of the digital economy has necessitated secure and efficient storage solutions for large-scale data. Blockchain technology, characterized by its decentralization and immutability, offers unique advantages for protecting data privacy. However, as the scale of on-chain data processing expands, blockchain faces significant challenges in terms of storage costs and efficiency. This research introduces the IPFS-BC system, a novel collaborative storage solution that integrates the InterPlanetary File System (IPFS) with blockchain. This system harnesses IPFS’ s capability to manage large-scale data and employs blockchain smart contracts to facilitate automated interactions between the IPFS and blockchain systems, thereby ensuring data integrity and security. The IPFS-BC system combines the blockchain's transaction record layer with IPFS's storage solution to achieve decentralized data storage and enhanced efficiency. Experimental validation demonstrates that this system effectively reduces the storage load on the blockchain, improves storage performance, and maintains data security and integrity. This study not only provides a new solution for large-scale data storage but also lays a practical foundation for further integration and interaction between blockchain and IPFS.

关键词： File systems data integrity Smart contracts Memory Collaboration data processing Blockchains InterPlanetary File System Information technology Secure storage

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-AGVs dynamic scheduling based on deep reinforcement learning 19

Research on Multi-AGVs dynamic scheduling based on deep rein...

引用

19th IEEE International Conference on e-Business Engineering, ICEBE 2023

作者： Qin, Zhuorui Wu, Xiaoqian Zheng, Yimin Wu, Qingyao South China University of Technology School of Software Engineering Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Shenzhen Bangqi Technology Intelligent Development Co. Ltd Shenzhen China Pazhou Lab Guangzhou China

ISBN: (纸本)9798350325553

Driven by the latest advances in industrial artificial intelligence, automatic guided vehicles (AGVs) have been widely used for material handling in flexible workshops. In the pursuit of agile and flexible production transportation planning, the ability to handle unpredictable and dynamic events is becoming increasingly important. In order to achieve this real-time dynamic control, this study proposes a distributed multi-agent architecture to solve the dynamic Multi-AGVs scheduling problem. Double Deep Q-Network algorithm is used to train the scheduling agent, capture the relationship between production transportation operation information and scheduling goals, and make real-time scheduling decisions for flexible jobs with constant arrival intervals. Specialized state, action, and reward representations are proposed to handle variable specifications of dynamic scheduling problems. The performance of this method under different scene scales was verified through simulation studies. Numerical results show that compared with existing traditional heuristic scheduling strategies, this method not only has superior performance, but also its advantages persist even if the manufacturing system job scale changes. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Belief Propagation Cooperative Localization Algorithm in GNSS-Loss Environments 3

A Belief Propagation Cooperative Localization Algorithm in G...

引用

3rd International Conference on Digital Signal and Computer Communications, DSCC 2023

作者： Ma, Fei Tan, Guoping Zhou, Siyuan Hu, Hexuan College of Computer and Information Hohai University Jiangsu Intelligent Transportation and Intelligent Driving Research Institute Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University College of Computer and Information Hohai University Nanjing China

ISBN: (数字)9781510666566

ISBN: (纸本)9781510666559

When vehicles are in driving environments such as urban roads and tunnels, the global navigation satellite system (GNSS) signal can fail to achieve positioning due to occlusion. Cooperative positioning can effectively improve the accuracy and coverage of vehicle positioning. In this paper, we address the vehicle localization issue in GNSS-Loss driving environments and with random packet loss due to wireless communications. We propose an improved cooperative localization algorithm based on belief propagation, which first linearizes the measurement model of distance by statistical linear regression method, then performs belief propagation based on the linearized model, and solves the packet loss problem by expanding the dimension of the vehicle state. From the simulation results, the algorithm can effectively reduce the impact of packet loss and improve the vehicle localization accuracy. © 2023 SPIE.

关键词： Belief propagation

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

IEEE Symposium on High-Performance Computer Architecture

作者： Siling Yang Shuibing He Wenjiong Wang Yanlong Yin Tong Wu Weijian Chen Xuechen Zhang Xian-He Sun Dan Feng The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Lab Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver Illinois Institute of Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work.

关键词： Training Accuracy Graph convolutional networks Pipelines Energy conservation Computer architecture Machine learning Parallel processing Optimization

来源：评论

学校读者我要写书评

暂无评论

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framework using Adaptive Gabor convolution 43

DGN-MEF: A DenseNet-Based Multi-Exposure Image Fusion Framew...

引用

43rd Chinese Control Conference, CCC 2024

作者： Zhang, Mei Jin, Ye Zhu, Jinhui South China University of Technology School of Automation Science and Engineering Guangzhou510641 China South China University of Technology School of Software Engineering Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

ISBN: (纸本)9789887581581

Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules by current deep learning multi-exposure image fusion algorithms, we propose a DenseNet-based framework using adaptive Gabor convolution. Building on the Dense network architecture, we design an adaptive Gabor convolution module, which the parameters of the Gabor filter can be updated along with the network, enhancing the ability of Gabor to extract image features. Additionally, a cross-domain aggregation attention module is proposed, which effectively aggregates and enhances information. Comparing our method with seven advanced methods on the multi-exposure image fusion benchmark dataset, the subjective and objective evaluations outperform the other methods, proving the effectiveness and superiority of our method. The experiments of different exposure images fusion demonstrate the good generalization performance of our method. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

On the Road to Portability: Compressing End-to-End Motion Pl...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Kaituo Feng Changsheng Li Dongchun Ren Ye Yuan Guoren Wang Beijing Institute of Technology ALLRIDE.AI Hebei Province Key Laboratory of Big Data Science and Intelligent Technology

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neu-ral networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference. To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller stu-dent model to learn from a larger teacher model. Neverthe-less, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation frame-work tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy in-formation, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscrim-inately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that as-signs adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time.

关键词： Computer vision Computational modeling Roads Artificial neural networks Planning Trajectory Safety

来源：评论

学校读者我要写书评

暂无评论

Plausible Heterogeneous Graph k-Anonymization for Social Networks

引用

Tsinghua Science and Technology 2022年第6期27卷 912-924页

作者： Kaiyang Li Ling Tian Xu Zheng Bei Hui School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610054China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu 610000China

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods,aiming at learning a continuous vector space for the graph which is amenable to be adopted in traditional machine learning algorithms in favor of vector *** embedding methods build an important bridge between social network analysis and data analytics as social networks naturally generate an unprecedented volume of graph data *** social network data not only bring benefit for public health,disaster response,commercial promotion,and many other applications,but also give birth to threats that jeopardize each individual’s privacy and ***,most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social *** be specific,attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network *** this paper,we propose a novel link-privacy preserved graph embedding framework using adversarial learning,which can reduce adversary’s prediction accuracy on sensitive links while persevering sufficient non-sensitive information such as graph topology and node attributes in graph *** experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

关键词： social network graph embedding privacy preservation adversarial learning

来源：评论

学校读者我要写书评

暂无评论

GNEA: A Novel GCN-based Network Embedding Algorithm for Semantic Social Network 10

GNEA: A Novel GCN-based Network Embedding Algorithm for Sema...

引用

10th International Symposium on System Security, Safety, and Reliability, ISSSR 2024

作者： Zhao, Jinbo He, Jinling Du, Yuanhan Tang, Ming Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing China State Grid Jiangsu Electric Power Company Limited Nanjing China Nanjing University of Posts and Telecommunications School of Computer Science Nanjing China

ISBN: (纸本)9798350362930

With the development of semantic social networks, social networks become more complex and their size expands rapidly, which brings significant challenges to social network analysis. Network Embedding can transform the network from a high-dimensional adjacency matrix to a low-dimensional one, which has excellent foreground in link prediction, vertex classification, and graph visualization. Nowadays, most algorithms are proposed for static networks with little consideration of the dynamic changes in the network. However, most real-world networks change over time. Directly applying static network embedding algorithms to dynamic networks will result in poor stability, flexibility, and efficiency. Because of these shortcomings, we propose a graph convolution-based dynamic network representation learning algorithm (GNEA), which combines Graph Convolutional Network (GCN) with Long Short-Term Memory (LSTM) to train the time series networks. GCN is applied to extract features in the network, and LSTM is utilized to capture temporal information. GNEA can not only perform characterization learning on the network but also obtain more abundant information during the dynamic evolution of the network. GNEA is compared with several typical algorithms on the datasets Stochastic Block Model (SBM), Autonomous Systems (AS), and Digital Bibliography and Library Project (DBLP). The results prove that GNEA has good performance in MAP and precision@k. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：