检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Xu, Yang Xu, Xiaolong Xiao, Fu Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

Few-shot text classification aims to learn transferable knowledge from a limited dataset to perform classification tasks in unseen domains. Recently, metric-based meta-learning methods have demonstrated their advantages in few-shot text classification. However, the influence of randomly sampling support set on prototype quality has often been overlooked by these methods. In this paper, we propose a label-Guided Contrastive Capsule Network (LGCCN) to address this issue. LGCCN leverages label information to guide supervised contrastive learning, using labels as anchors to enhance the clustering process, resulting in higher-quality sentence vectors. Furthermore, LGCCN employs label-guided dynamic routing process to iteratively generate a prototype, significantly mitigating the impact of random support set sampling. We conducted extensive experiments on four datasets, comparing LGCCN with recent methods. The results reveal that LGCCN, compared to the recent best work, has achieved an improvement of 10.1% and 2.1% in classification accuracy for 1-shot and 5-shot tasks, respectively. Additionally, ablation studies validate the effectiveness of each module in our approach. © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Lightweight EEG Classification Model Based on EEG-sensor with Few Channels

Lightweight EEG Classification Model Based on EEG-sensor wit...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Haoyan Xu Xiaolong Xu Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

In the traditional work, based on EEG Sensors monitoring the physiological and emotional state of humans, the time-frequency analysis method is usually used to extract the characteristics of the signal, and then analyzed by SVM, KNN and other methods. However, the recognition accuracy of such methods is not ideal. Deep learning methods such as CNN and RNN have become the research hotspots in the field of EEG analysis. However, due to the high structural risk of the deep learning model, the model is prone to poor generalization ability, long training time, over-fitting, and poor real-time performance. In addition, current EEG data acquisition devices generally require dozens of signal channels to provide a data foundation for accurate analysis of subsequent brain signals, which not only brings high hardware costs, but also is not portable enough to be popularized in daily life. However, due to the weak and susceptible interference of the EEG signal, reducing the number of signal channels under the premise of using the above method may further lead to a worse analysis effect. In order to solve these problems, we propose a new lightweight EEG classification model based on a small number of channel EEG sensors, called Armaiti. Armaiti first uses the 5-channel EEG signal collected by the portable EEG acquisition device to perform blind source signal separation to obtain data from multiple sources, including noise signals such as EOG. Instead of identifying and screening these signals, we use a combination of EEG, EOG and other signals. Then Armaiti performs wavelet packet transform on each signal source, decomposes the signal into different frequency bands, and then inputs it into the lightweight convolutional neural network model designed in this paper to obtain five classifiers. Finally, Armaiti uses the ensemble learning to get the final classification results. In order to verify the performance and practicability of the model, from September 2018 to June 2019, we use

关键词： Electroencephalography Brain modeling Electrooculography Computational modeling Analytical models Fatigue Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Variance Minimization Approach to Temporal-Difference Learning

arXiv

引用

arXiv 2024年

作者： Chen, Xingguo Gong, Yu Yang, Shangdong Wang, Wenhao Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China College of Electronic Engineering National University of Defense Technology China

Fast-converging algorithms are a contemporary requirement in reinforcement learning. In the context of linear function approximation, the magnitude of the smallest eigenvalue of the key matrix is a major factor reflecting the convergence speed. Traditional value-based RL algorithms focus on minimizing errors. This paper introduces a variance minimization (VM) approach for value-based RL instead of error minimization. Based on this approach, we proposed two objectives, the Variance of Bellman Error (VBE) and the Variance of Projected Bellman Error (VPBE), and derived the VMTD, VMTDC, and VMETD algorithms. We provided proofs of their convergence and optimal policy invariance of the variance minimization. Experimental studies validate the effectiveness of the proposed algorithms. © 2024, CC BY-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

TSC-ECFA:A Trusted Service Composition Scheme for Edge Cloud

TSC-ECFA:A Trusted Service Composition Scheme for Edge Cloud

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Jiang Xiaolong Xu Kunda Lin Weihua Duan Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781665408790

In order to select a composition scheme that meets user's needs and high performance from large-scale web services in the edge cloud, this paper proposes a trusted service composition optimization scheme called TSC-ECFA for edge cloud, which applies the predation strategy to the firefly algorithm (FA) and divides the services with the same input and output into one category, reducing the number of combinations to search for feasible solutions. The cotangent chaos theory is used to generate the initial firefly population and disturb the location of the individual to improve the overall search efficiency of FA. This paper also improves the step factor and attractiveness formula of FA to give full play to the detection ability of the step factor in the early stage of the algorithm, and balance the local search and the global search. Considering that the QoS attribute values of the service are vulnerable to be tampered with, the blockchain is used to store the QoS attribute values to ensure the tamper-proof and reliability of the QoS attribute value. Finally, simulation experiments compare the number of iterations and optimization of the three algorithms. The experimental results show that the comprehensive performance of TSC-ECFA is better than other algorithms.

关键词： Chaos Web services Conferences Sociology Quality of service Reliability theory Blockchains

来源：评论

学校读者我要写书评

暂无评论

RPSBPT: A Route Planning Scheme with Best Profit for Taxi

RPSBPT: A Route Planning Scheme with Best Profit for Taxi

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Yuhua Qiu Xiaolong Xu Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781728105499;9781728105482

Reasonable route planning for taxi can not only improve quality of customer experience, but also maximize the benefit of taxi drivers. Most current taxi planning schemes are designed to achieve the shortest route or the shortest time, not to achieve the best profit. In this paper, we propose a route planning scheme with best profit for taxi (RPSBPT). First, we define the optimal profit point and the profit per unit time function. Second, we design the workflow of data cleaning, sampling and partitioning for preprocessing the dataset of taxi trajectory. Then, we integrate the DBSCAN algorithm and the K-means algorithm to obtain the optimal profit points. Finally, the simulate anneal Algorithm (SA), the genetic algorithm (GA), and the ant colony optimization algorithm (ACO) are adopted respectively to plan route for taxi. We constructed the taxi route planning prototype system and applied the proposed route planning scheme to the system. Based on the system and the collected taxi trajectory data at the Jinjiang district of the Chengdu city, we performed a series of experiments to compare the performance of three heuristic algorithms, including optimal route length, algorithm stability, total profit and profitability per unit time. Experimental results show that ACO has the best performance.

关键词： Public transportation Planning Trajectory Clustering algorithms Genetic algorithms Urban areas Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparison and Analysis on Typical Network Representation Learning Algorithms

Comparison and Analysis on Typical Network Representation Le...

引用

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Yang Wang Xiaolong Xu Yun Li Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781538676738;9781538676721

Large-scale complex networks show complex nonlinear relationships among objects, such as the social relationships in the real world, the citation relationship among papers and the interactions among proteins in biology. The analysis of complex network systems make it possible to reveal network structures, information disseminating laws, and communication patterns. Network representation learning (NRL) algorithms focus on mapping the original network structure information to a low-dimensional vector space through a series of operations under the premise of maximally retaining the network structure. In order to analyze current representative NRL algorithms effectively to provide valuable references for other researchers, we built an experimental platform to perform and test the NRL algorithms based on matrix factorization, the NRL algorithms based on shallow neural network and the NRL algorithms based on deep neural network, with datasets on Collaboration Network, Social Network and Citation Network. We implemented a series of comprehensive experiments, based on metrics include precision@k, micro-F1 and macro-F1. Our experiments include network reconstruction, vertex classification, and link prediction, and show readers principles, performances and applications of typical NRL algorithms.

关键词： Neural networks Prediction algorithms Task analysis Matrix decomposition data visualization Blogs Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Multi-agent game abstraction via graph attention neural network

arXiv

引用

arXiv 2019年

作者： Liu, Yong Wang, Weixun Hu, Yujing Hao, Jianye Chen, Xingguo Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University Tianjin University NetEase Fuxi AI Lab Noah's Ark Lab Huawei Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications

In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent systems, the interactions between agents often happen locally, which means that agents neither need to coordinate with all other agents nor need to coordinate with others all the time. Traditional methods attempt to use pre-defined rules to capture the interaction relationship between agents. However, the methods cannot be directly used in a large-scale environment due to the difficulty of transforming the complex interactions between agents into rules. In this paper, we model the relationship between agents by a complete graph and propose a novel game abstraction mechanism based on two-stage attention network (G2ANet), which can indicate whether there is an interaction between two agents and the importance of the interaction. We integrate this detection mechanism into graph neural network-based multi-agent reinforcement learning for conducting game abstraction and propose two novel learning algorithms GA-Comm and GA-AC. We conduct experiments in Traffic Junction and Predator-Prey. The results indicate that the proposed methods can simplify the learning process and meanwhile get better asymptotic performance compared with state-of-the-art algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Joint Spatial-Temporal Trajectory Clustering Method for Mobile Social Networks

Joint Spatial-Temporal Trajectory Clustering Method for Mobi...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Ji Tang Linfeng Liu Jiagao Wu Jian Zhou Yang Xiang School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781728125848

As an important issue in the trajectory mining task, the trajectory clustering technique has attracted lots of the attention in the field of data mining. Trajectory clustering technique identifies the similar trajectories (or trajectory segments) and classifies them into the several clusters which can reveal the potential movement behaviors of nodes. At present, most of the existing trajectory clustering methods focus on some spatial properties of trajectories (such as geographic locations, movement directions), while the spatial-temporal properties (especially the combination of spatial distances and semantic distances) are ignored, and thus some vital information regarding the movement behaviors of nodes is probably lost in the trajectory clustering results. In this paper, we propose a Joint Spatial-Temporal Trajectory Clustering Method (JSTTCM), where some spatialtemporal properties of the trajectories are exploited to cluster the trajectory segments. Finally, the number of clusters and the silhouette coefficient are observed through simulations, and the results show that JSTTCM can cluster the trajectory segments appropriately.

关键词： Trajectory clustering Spatial-temporal properties Spatial distances Semantic distances trajectory Social Networks Clustering methods Social Media Ganglia

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimension Training Scheme to Improve the Innovation Capacity of Postgraduate and Undergraduate Students Collaboratively

Multi-Dimension Training Scheme to Improve the Innovation Ca...

引用

Frontiers in Education (FIE) Conference

作者： Xiaolong Xu Jianhua Shen Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781538611753;9781538611746

This Innovative Practice Work in Progress Paper presents a multi-dimension training scheme to improve the innovation capacity of postgraduate and undergraduate students collaboratively. The current training of postgraduate and undergraduate education schemes cannot form a mutually beneficial relation, not suitable for the training of innovation capacity on postgraduate and undergraduate students collaboratively. There are various problems that need to be addressed. The main strategy of the proposed scheme is utilizing real research programs to establish an integrated team mixed with both postgraduate and undergraduate students, focusing on stimulating their innovation capacity in scientific research. In the scheme, we designed a multi-level joint training mechanism based on the mixed pedagogy, the collaborative resource pool platform, the multi-role and team-based innovation talent incubation mechanism, and the preparatory postgraduate student selection and training goal achievement evaluation mechanism. We applied the scheme to the training process of postgraduate students from the majors of Software Engineering, Computer Software and Theory, Computer Application, Computer Technology and Electronic Information Engineering, and undergraduate students from the majors of Computer Science and Technology, Information security and Communication Engineering in Nanjing University of Posts and Telecommunications. The training results approve the feasibility and effectiveness of the scheme.

关键词： Training Technological innovation Collaboration Software Telecommunications Business

来源：评论

学校读者我要写书评

暂无评论

Sybil-Proof Online Incentive Mechanisms for Crowdsensing

Sybil-Proof Online Incentive Mechanisms for Crowdsensing

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Jian Lin Ming Li Dejun Yang Guoliang Xue Colorado School of Mines Golden CO USA Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu China Arizona State University Tempe AZ USA

ISBN: (纸本)9781538641293

Crowdsensing leverages the rapid growth of sensor-embedded smartphones and human mobility for pervasive information collection. To incentivize smartphone users to participate in crowdsensing, many auction-based incentive mechanisms have been proposed for both offline and online scenarios. It has been demonstrated that the Sybil attack may undermine these mechanisms. In a Sybil attack, a user illegitimately pretends multiple identities to gain benefits. Sybil-proof incentive mechanisms have been proposed for the offline scenario. However, the problem of designing Sybil-proof online incentive mechanisms for crowdsensing is still open. Compared to the offline scenario, the online scenario provides users one more dimension of flexibility, i.e., active time, to conduct Sybil attacks, which makes this problem more challenging. In this paper, we design Sybil-proof online incentive mechanisms to deter the Sybil attack for crowdsensing. Depending on users' flexibility on performing their tasks, we investigate both single-minded and multi-minded cases and propose SOS and SOM, respectively. SOS achieves computational efficiency, individual rationality, truthfulness, and Sybil-proofness. SOM achieves individual rationality, truthfulness, and Sybil-proofness. Through extensive simulations, we evaluate the performance of SOS and SOM.

关键词： Task analysis Smart phones Sensors Microsoft Windows Conferences Privacy Cost function

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：