Proceedings of the 4th International Conference on Advanced Information Science and System最新文献_第5页

Urban Path Planning Based on Improved Model-based Reinforcement Learning Algorithm 基于改进模型强化学习算法的城市路径规划

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574534

Huimin Wang, Dong Liang, Yuliang Xi

{"title":"Urban Path Planning Based on Improved Model-based Reinforcement Learning Algorithm","authors":"Huimin Wang, Dong Liang, Yuliang Xi","doi":"10.1145/3573834.3574534","DOIUrl":"https://doi.org/10.1145/3573834.3574534","url":null,"abstract":"With the development of the urban economy, and the continuous expansion of vehicle scale, trafﬁc congestion has become the most serious problem affecting contemporary urban development. Using advanced road network information perception and transmission technologies, path planning under real-time road conditions has become an important means to solve this problem. Previously, our proposed model-based reinforcement learning multipath planning algorithm realized the rapid response of the path planning result, alleviating congestion drift to a certain extent. However, further research shows that the model performs poorly in extreme road network environments (the road network trafﬁc pressure is 0) and cannot explore the complete path, the main reason is that the effect of model hyperparameters on the convergence of the algorithm was ignored. to solve this problems, we explore the hyperparameters in detail, especially discuss the discount factor γ and the finalReward to the model convergence by using Shenzhen road network data. the results show that when the discount factor γ and the finalReward value satisfy certain conditions, which is obtained in this study, the improved model-based method can guarantee the convergence stability of the algorithm under extreme road network environments. This paper reveals the importance of the design of hyperparameters γ and finalReward as well as their interrelationship on the convergence of reinforcement learning algorithms and we hope to give some insights in the field which explore hyperparameters of reinforcement learning algorithm.","PeriodicalId":345434,"journal":{"name":"Proceedings of the 4th International Conference on Advanced Information Science and System","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122787369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hierarchical Federated Learning with Gaussian Differential Privacy 基于高斯差分隐私的分层联邦学习

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574544

Tao Zhou

{"title":"Hierarchical Federated Learning with Gaussian Differential Privacy","authors":"Tao Zhou","doi":"10.1145/3573834.3574544","DOIUrl":"https://doi.org/10.1145/3573834.3574544","url":null,"abstract":"Federated learning is a privacy preserving machine learning technology. Each participant can build the model without disclosing the underlying data, and only shares the weight update and gradient information of the model with the server. However, a lot of work shows that the attackers can easily obtain the client’s contributions and the relevant privacy training data from the public shared gradient, so the gradient exchange is no longer safe. In order to ensure the security of Federated learning, in the differential privacy method, noise is added to the model update to obscure the contribution of the client, thereby resisting member reasoning attacks, preventing malicious clients from knowing other client information, and ensuring private output. This paper proposes a new differential privacy aggregation scheme, which adopts a more fine-grained hierarchy update strategy. For the first time, the f-differential privacy (f-DP) method is used for the privacy analysis of federated aggregation. Adding Gaussian noise disturbance model update in order to protect the privacy of the client level. We prove that the f-DP differential privacy method improves the previous privacy analysis by experiments. It accurately captures the loss of privacy at every communication round in federal training, and overcome the problem of ensuring privacy at the cost of reducing model utility in most previous work. At the same time, it provides a federal model updating scheme with wider applicability and better utility. When enough users participate in federated learning, the client-level privacy guarantee is achieved while minimizing model loss.","PeriodicalId":345434,"journal":{"name":"Proceedings of the 4th International Conference on Advanced Information Science and System","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130165179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

RPSigmoid: A Randomized Parameterization for a Sigmoidal Activation Function s型激活函数的随机参数化

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574486

Yi-Hsien Lin

引用次数: 0

Traceability of Product Supply Chain Based on Hyperledger Fabric 基于超级账本结构的产品供应链可追溯性研究

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574546

Shiyang Song, Jiadong Lu, Hanxu Zhao, Wennan Wang, Chiyu Shi, Ruijie Luo

{"title":"Traceability of Product Supply Chain Based on Hyperledger Fabric","authors":"Shiyang Song, Jiadong Lu, Hanxu Zhao, Wennan Wang, Chiyu Shi, Ruijie Luo","doi":"10.1145/3573834.3574546","DOIUrl":"https://doi.org/10.1145/3573834.3574546","url":null,"abstract":"Abstract: At present, more and more consumers and manufacturers are aware of the importance of product traceability, so it is very important to strengthen the traceability in the supply chain. The existing centralized database system has isolated data storage, and many parties involved in data query lack mutual trust. Based on the distributed ledger of the blockchain, this paper attempts to solve this problem by transforming the traceability information of physical goods into the digital of the blockchain, so as to realize the collaborative traceability of entities in the supply chain. At present, the relationship between components and products in manufacturing process cannot be captured, which limits the ability to track the source of products. This paper proposes a supply chain traceability model based on blockchain, which uses smart contracts to complete multi-party agreements on the chain. In the contract, the products produced by the manufacturer are transferred in the specified alliance chain entity, and in each transfer process, the products will be marked with new traceability information in the form of digital authentication. This mechanism retains the possibility of products being traced. The model is tested under the framework of hyperledger fabric. By building a blockchain network, the entity objects participating in the supply chain can be authenticated to ensure the closed-loop circulation of goods. It also indirectly proves the feasibility of commodity traceability application based on blockchain technology.","PeriodicalId":345434,"journal":{"name":"Proceedings of the 4th International Conference on Advanced Information Science and System","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134101233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Point Cloud Classification Method for Transmission Towers based on CAA-PointNet 基于CAA-PointNet的输电塔点云分类方法

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574515

Letan Zhang, G. Lan, Xiaoyong Shi, Xinghui Duanmu, Kan Chen

引用次数: 0

A Biped Robot Learning to Walk like Human by Reinforcement Learning 通过强化学习学习像人一样走路的两足机器人

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574484

Yi Liu, Honglei An, Hongxu Ma

引用次数: 0

Automatic identification system of aircraft cockpit indicators based on machine vision 基于机器视觉的飞机座舱指示器自动识别系统

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574549

Jiaqing Yao, Renwen Chen, Yijun Huang

{"title":"Automatic identification system of aircraft cockpit indicators based on machine vision","authors":"Jiaqing Yao, Renwen Chen, Yijun Huang","doi":"10.1145/3573834.3574549","DOIUrl":"https://doi.org/10.1145/3573834.3574549","url":null,"abstract":"Aiming at the problem that the test of civil aircraft is greatly affected by human factors in the batch manufacturing process, the automatic identification system of aircraft cockpit indicators based on machine vision is researched. Firstly, the slant screen images are automatically corrected and segmented by image processing technology. Secondly,different methods are used to identify different regions according to the specificity of different regions in the images. YOLOv5 algorithm is used for target detection of unconventional indicators; EasyOCR algorithm is used for character recognition, especially in decimal recognition, this research improved EasyOCR, in which using the projection of the legal decimal point position and cover at the data input end, modify the initial characteristics, to avoid the wrong identification interference of the decimal point. At the output end, the correct decimal point is reset between digits. The accuracy is improved by 27.65% and the average accuracy is 96.60%; Other general indicators recognition, using common image processing techniques, such as Hough transform, HSV color matching, etc. Experimental results show that the average error rate of identification results of various indicators is only 1.96%, the speed of machine recognition is 4.8 times that of manual test. Compared with manual test, it can effectively solve the problems of misjudgment, heavy workload and inefficient, and improve the degree of automation in the batch production process of civil aircraft.","PeriodicalId":345434,"journal":{"name":"Proceedings of the 4th International Conference on Advanced Information Science and System","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122266140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Machine Reading Comprehension Based on SpanBERT and Dynamic Convolutional Attention 基于SpanBERT和动态卷积注意的机器阅读理解

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574512

Chun-Ye Wu, Li Li, Zhigui Liu, Xiaoqian Zhang

引用次数: 0

Extracting Process Instances from User Interaction Logs 从用户交互日志中提取流程实例

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574538

Lars Kornahrens, Sebastian Kritzler, Dirk Werth

{"title":"Extracting Process Instances from User Interaction Logs","authors":"Lars Kornahrens, Sebastian Kritzler, Dirk Werth","doi":"10.1145/3573834.3574538","DOIUrl":"https://doi.org/10.1145/3573834.3574538","url":null,"abstract":"Thoroughly documenting digital business processes in a company is a crucial and necessary, yet cumbersome task. However, having detailed documentation of one's processes in a modelling language like Business Process Model and Notation (BPMN) can prove very useful regarding process optimization or automation, employee training and on- and offboarding. Process and task mining frameworks try to ease the creation of process documentation by automatically generating it based on transaction or user interaction data with the system. These approaches often have the disadvantage of not covering the whole process due to a variety of possible execution paths and their habit of not continuously recording process data. We propose an extension to the task mining tool Desktop Activity Mining (DAM) which allows to capture data continuously over several hours and therefore not miss any important cases that might not occur very often. This approach also limits the influence of human errors when recording process data with certain frameworks for documentation purposes and provide the possibility of an improved degree of automation. We evaluate the approach on real-world data to show its feasibility and application in practice. We used a combination of already existing algorithms and created our own. By classifying 332 unique user interactions, we end up with 76 different equivalence classes. Evaluating the algorithm, we achieved a classification correctness of 70% in two datasets.","PeriodicalId":345434,"journal":{"name":"Proceedings of the 4th International Conference on Advanced Information Science and System","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129662814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Layer-wise based Adabelief Optimization Algorithm for Deep Learning 面向深度学习的分层自适应优化算法

Proceedings of the 4th International Conference on Advanced Information Science and System Pub Date : 2022-11-25 DOI: 10.1145/3573834.3574539

Zhiyong Qiu, Zhenhua Guo, Li Wang, Yaqian Zhao, Rengang Li

引用次数: 0