检索结果-内蒙古大学图书馆

Personalized Consumer Federated Recommender System Using Fine-grained Transformation and Hybrid Information Sharing

IEEE Transactions on Consumer Electronics 2025年

作者： Di, Yicheng Wang, Xiaoming Shi, Hongjian Fan, Chongsheng Zhou, Rong Ma, Ruhui Liu, Yuan The School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China The Beijing Institute of Tracking and Telecommunications Technology Beijing100094 China The Shanghai Aerospace Equipment Manufacturer Co. Ltd Shanghai200245 China The School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China

Electronic shopping’s convenience and efficiency make it essential in modern life. In trustworthy personalized consumer recommender scenarios, diverse consumer interests lead to various interactions. Existing methods struggle to capture complex behavior dependencies and shared information across behaviors by exploring multi-behavior interaction sequences. To address this, we propose the Personalized Consumer Federated Recommender System Using Fine-grained Transformation and Hybrid Information Sharing (PCFedRec). Our contributions are as follows: Firstly, we employ the Fine-grained Transformation Module to capture fine-grained heterogeneous dependencies of consumer behaviors and model the behavior semantics of interest. Secondly, we use the Weight Correction Mechanism to reduce suboptimal position encoding and noisy input. Finally, we design the Hybrid Information Sharing Module to learn general consumer interests by leveraging common information across different behaviors. The Normalized Discounted Cumulative Gain is used to evaluate the performance of the recommender systems by considering both the relevance and rank order of the top 10 recommended items. The PCFedRec improves performance by 6.20%, 8.08%, 9.16%, and 7.14% on this metric. © 1975-2011 IEEE.

关键词： Information hiding

来源：评论

学校读者我要写书评

暂无评论

A grouping matching algorithm for large-scale Message-Oriented Middleware with Pub/Sub model on TT&C computer

A grouping matching algorithm for large-scale Message-Orient...

引用

2014 IEEE 7th Joint International Information technology and Artificial Intelligence Conference

作者： WANG Chongnan WANG Zongtao Xing Hongwei Computer deparment Beijing Institute of Tracking and Telecommunications Technology

According to the Problems that predicate counting algorithm used for Message-oriented with Publish/Subscribe model on TT&C computer has incomplete preprocessing and complex counting when processing large-scale information exchange. A grouping matching algorithm was put forward, it grouped subscription by binary tree according to message name and deleted subscription group whose message name set was not subset of the event. As for remaining subscription group, it constructed different index structure according to covered relationship between different predicates and filtered corresponding attributes. The result show that time efficiency of grouping matching algorithm is higher than traditional predicate counting algorithm.

关键词： Pub/Sub Message-Oriented Middleware Matching algorithm Group

来源：评论

学校读者我要写书评

暂无评论

MicroBTC:Efficient,Flexible and Fair Micropayment for Bitcoin Using Hash Chains

引用

Journal of computer Science & technology 2019年第2期34卷 403-415页

作者： Zhi-Guo Wan Robert H.Deng David Lee Ying Li School of Computer Science and Technology Shandong University Qingdao 266237 China School of Information Systems Singapore Management University Singapore 188065 Singapore School of Business Singapore University of Social Sciences Singapore 599494 Singapore Beijing Institute of Tracking and Telecommunications Technology Beijing 100094 China

While Bitcoin gains increasing popularity in different payment scenarios,the transaction fees make it difficult to be applied to *** the wide applicability of micropayment,it is crucial for all cryptocurrencies including Bitcoin to provide effective support *** light of this,a number of low-cost micropayment schemes for Bitcoin have been proposed recently to reduce micropayment *** schemes,however,suffer from drawbacks such as high computation cost,inflexible payment value,and possibly unfair *** paper proposes two new micropayment schemes,namely the basic MicroBTC and the advanced MicroBTC,for Bitcoin by integrating the hash chain technique into cryptocurrency *** basic MicroBTC realizes micropayment by exposing hash pre-images on the hash chain one by one,and it can also make arbitrary micropayments by exposing multiple hash *** further design the advanced MicroBTC to achieve non-interactive refund and efficient hash chain *** analyze the complexity and security of the both MicroBTC schemes and implement them using the Bitcoin source *** experiments were conducted to validate their performance,and the result showed that a micropayment session can be processed within about 18 ms for the basic MicroBTC and 9 ms for the advanced MicroBTC on a *** schemes enjoy great efficiency in computation and flexibility in micropayments,and they also achieve fairness for both the payer and the payee.

关键词： blockchain micropayment cryptocurrency hash chain Bitcion

来源：评论

学校读者我要写书评

暂无评论

System level design of address allocation for a private IP network

System level design of address allocation for a private IP n...

引用

26th Conference of Spacecraft TT and C technology in China

作者： Huang, Yalin Zhao, Zongyin Liu, Yan Yao, Xu Beijing Institute of Tracking and Telecommunications Technology Beijing 100094 China School of Computer and Communications Engineering University of Science and Technology Beijing Beijing 100083 China

ISBN: (纸本)9783642336621

IP address allocation is very important to data routing, inter-networking and OAM of large IP networks. In this paper, the high level architecture of a private IP network is presented firstly. Then its uniqueness is summarized as large scale multilayer network architectures, independent dual transferring routing of WAN, dual transferring planes of MAN/LAN, support of special requirement such as multicast and external networking. Various address allocation requirements from the above mentioned features are analyzed. Consequently, address spaces are divided according to the network type, routing, devices, and special application requirements. After that, each address space and its future evolution path is presented in details. Finally high level design and analysis of each allocation scheme is presented in sections according to the sequence of MAN, LAN, WAN, multicast and external networking. Field deployment result in the past 2 years has proved the success of the proposed address allocation plan. © 2013 Tsinghua University Press, and Springer-Verlag.

关键词： Wide area networks

来源：评论

学校读者我要写书评

暂无评论

Reducing redundancy of skills in hierarchical reinforcement learning with offline data 3

Reducing redundancy of skills in hierarchical reinforcement ...

引用

3rd International Conference on Electronic Information Engineering and Data Processing, EIEDP 2024

作者： Zhou, Yuhao Wang, Xiaoming Wang, Xinzhi Xie, Shaorong Zhang, Zhenyu College of Computer Engineering and Science Shanghai University Shanghai200444 China Beijing Institute of Tracking and Telecommunications Technology Beijing100094 China

ISBN: (纸本)9781510680531

In highly sparse reward composite tasks, agents often face a lack of reward feedback within fixed time steps, leading to getting trapped in local optima and compromising their ability to effectively explore superior strategies. Skill learning is one approach to increase the density of reward signals, enabling adaptation to multi-stage tasks and expediting the learning process. However, contemporary methods for skill acquisition heavily rely on online asynchronous training. Although certain intrinsic motivation approaches excel at addressing sparse reward challenges, they suffer from issues of low sampling efficiency and limited interpretability of skills. These challenges hinder the speed of model learning and severely impede the reusability of skill policies. In this study, we employ expert demonstration data to facilitate the learning of skill policies, aiming to accelerate the convergence of the model while increasing the utilization of sample data. Subsequently, we engage in interactive learning with the environment. Additionally, we define an evaluation criterion for skill redundancy to encourage the selection of the most cost-effective skill strategy among similar skill policies that manifest between initial and final states. This process helps the agent efficiently and effectively accomplish complex tasks. Our objective is to minimize ineffective and redundant exploration and learning during the skill acquisition process. We evaluate our approach in the simulated UGV-Pyramid and simulated UGV-Hallway tasks, both implemented using Unity3D modeling. The results demonstrate the superiority of our algorithm compared to previous skill learning methods. © 2024 SPIE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

State-only imitation learning via generative adversarial and inverse dynamics model 3

State-only imitation learning via generative adversarial and...

引用

3rd International Conference on Electronic Information Engineering and Data Processing, EIEDP 2024

作者： Zhou, Zhen Wang, Xiaoming Li, Yang Luo, Xiangfeng Wang, Tao College of Computer Engineering and Science Shanghai University Shanghai200444 China Beijing Institute of Tracking and Telecommunications Technology Beijing100094 China

ISBN: (纸本)9781510680531

Imitation learning aims to learn policy from the demonstrations of experts. Compared to reinforcement learning, which learns by trial and error, imitation learning is not limited and affected by reward functions. Therefore, more and more research is focusing on using imitation learning to help agents explore and learn, especially in reward-sparse environments. Most existing work in this area assumes that expert demonstrations include both state and action information. However, in many cases we are only provided with state-only demonstrations, which can affect policy performance. In this paper, we use a state-only demonstrations to guide agents learning in a reward-sparse environment. We propose a policy optimization from observation (POfO) method. First, we reshape the rewards by forcing occupancy measure matching between the current policy and the demonstrations, which can effectively guide agent learning. Second, we train an inverse dynamics model(IDM) for inferring and completing the missing actions in state-only demonstrations. Finally, we accelerate policy learning based on demonstrations that have been complemented by IDM. According to the experimental results, the performance of our method is comparable to that of the method using the complete demonstrations and is significantly better than other methods of the same type. © 2024 SPIE.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Research on the Influence of Network Condition to Network Covert Timing Channels

Research on the Influence of Network Condition to Network Co...

引用

2015 6th IEEE International Conference on Software Engineering and Service Science(ICSESS 2015)

作者： Peng Yang Hui zhao Zhonggui Bao Computer department Beijing Institute of Tracking and Telecommunications Technology

Interest of covert timing channels is increasing rapidly.A lot of exploitation has been done on the construction of covert timing channels over the internet. But the construction work of covert timing channels is always in laboratory environment. In the real network environment, delay and packet loss influence the transmission quality of covert messages. In this thesis, we introduce evaluation criterion of network condition as a reference of network covert timing channel. Then we do an experiment to verify the influence of network condition to network covert timing *** the network condition is busy, there are some letters wrong and lost among covert messages. When network condition is free,the covert messages transmit successfully. From this experiment result, we can see that network condition influences the transmission of covert timing channels deeply. This result has certain significance for the future construction work of network covert timing channel in the real network environment.

关键词： covert timing channel network condition influence evaluation criterion

来源：评论

学校读者我要写书评

暂无评论

A Probability-Model-Based Approach to Detect Covert Timing Channel

A Probability-Model-Based Approach to Detect Covert Timing C...

引用

IEEE International Conference on Information and Automation

作者： Peng Yang Hui Zhao Zhonggui Bao Computer department Beijing Institute of Tracking and Telecommunications Technology

ISBN: (纸本)9781467391054

Interest of detecting covert timing channels is increasing rapidly. A lot of exploitation has been done on the construction and detection of covert timing channels over the internet. But the detection of covert timing channels is a challenging task because legitimate network traffic is so various that it's hard to detect and distinguish. The existing detection approaches are not so effective to detect the variety of covert timing channels known to security community. In this paper, we first review some typical detection methods of covert timing channels and then evaluate every approach. After that we introduce a new model-based approach to detecting various covert timing channels. Our new approach is based on the probability model that covert timing channels have different distribution from the legitimate channels. At last, we do an experiment to confirm the effectiveness of our model-based approach. The experiment result shows that our model-based approach is sensitive to the current timing channels, and is capable of detecting them in an accurate manner.

关键词： Covert timing channel Detection Probability-model-based

来源：评论

学校读者我要写书评

暂无评论

Research on the influence of network condition to network covert timing channels

Research on the influence of network condition to network co...

引用

IEEE International Conference on Software Engineering and Service Sciences (ICSESS)

作者： Peng Yang Hui Zhao Zhonggui Bao Computer department Beijing Institute of Tracking and Telecommunications Technology Beijing China

ISBN: (纸本)9781479983544

Interest of covert timing channels is increasing rapidly. A lot of exploitation has been done on the construction of covert timing channels over the internet. But the construction work of covert timing channels is always in laboratory environment. In the real network environment, delay and packet loss influence the transmission quality of covert messages. In this thesis, we introduce evaluation criterion of network condition as a reference of network covert timing channel. Then we do an experiment to verify the influence of network condition to network covert timing channels. When the network condition is busy, there are some letters wrong and lost among covert messages. When network condition is free, the covert messages transmit successfully. From this experiment result, we can see that network condition influences the transmission of covert timing channels deeply. This result has certain significance for the future construction work of network covert timing channel in the real network environment.

关键词： Delays Receivers Packet loss Synchronization computers

来源：评论

学校读者我要写书评

暂无评论

Dynamic Replica Selection Using Improved Kernel Density Estimation

Dynamic Replica Selection Using Improved Kernel Density Esti...

引用

International Symposium on Intelligent Information technology and Security Informatics, IITSI

作者： Yin Pang Kan Li Xin Sun Kaili Bu Beijing Key Laboratory of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing China Beijing Institute of Tracking and Telecommunications Technology Beijing China Beijing Aerospace Control Center Beijing China

ISBN: (纸本)9781424467303;9780769540207

Replication service in Distributed Systems can reduce access latency and bandwidth consumption. When different nodes hold replicas accessed, there will be a significant benefit by selecting the best replica. Most of the existed replication strategies deal with the prediction of the response time. However, these strategies do not take fully into account the network dynamic and access locality. To solve this problem, a dynamic replica selection strategy using improved Kernel Density Estimation (KDE) is presented. Firstly, it distinguishes old replicas from new ones. Then, it predicts the network load and available bandwidth to choose the best replica. The improved KDE can select accurately the best accessed replica with only a little history data, which is very useful in a dynamic network. Simulation results demonstrate the efficiency and effectiveness of improved KDE in comparison with other approaches.

关键词： Kernel Delay Aerodynamics History Bandwidth Information technology Predictive models computer security Information security Informatics

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：