检索结果-内蒙古大学图书馆

Bring the Intelligent Tutoring Robots to Education: A Systematic Literature Review

IEEE Transactions on Learning Technologies 2024年 1-21页

作者： Zhang, Xinyue Zhu, Fangqing Wang, Kun Cao, Guitao Xue, Yaofeng Liu, Mingzhuo MoE Engineering Research Center of SW/HW Co-design Technology and Application China Shanghai Engineering Research Center of Digital Education Equipment East China Normal University Shanghai China School of Open Learning and Education East China Normal University Shanghai China

Advances in artificial intelligence technologies have given rise to traditional robotics. Intelligent tutoring robots, supported by artificial intelligence technologies and hardware design, have sparked a new revolution in all walks of traditional education. Despite the growing number of research papers published on intelligent tutoring robots, and a few limited reviews focusing on specific technologies or theoretical aspects, there is still no wide-ranging review work that systematically summarizes the studies from the perspectives of theoretical level and practical implications concluded in experiments. To address this challenge and promote a common understanding of the concept of intelligent tutoring robot, we conducted a systematic literature review of papers published between 2016 and 2023. We investigated the construction of intelligent tutoring robots, the advanced artificial intelligence technologies employed, and intelligent tutoring robots' applications in educational contexts. From a total of 1751 publications, we selected and analyzed 105 main studies to identify and address three research questions: 1) How does the construction of intelligent tutoring robots affect education? 2) What artificial intelligence technologies enable intelligent tutoring robots to be “intelligent”? 3) How are intelligent tutoring robots applied in educational contexts? Additionally, we discuss the challenges of current research and provide an outlook on future development trends to provide guidelines for participators and researchers in the fields of intelligent tutoring robots. IEEE

关键词： Educational robots

来源：评论

学校读者我要写书评

暂无评论

A verification framework for spatio-temporal consistency language with CCSL as a specification language

引用

Frontiers of computer Science 2020年第1期14卷 105-129页

作者： Yuanrui ZHANG Frédéric MALLET Yixiang CHEN MoE Engineering Research Center for Software/Hardware Co-design Technology and Application East China Normal UniversityShanghai 200062China University Nice Sophia Antipolis I3SUMR 7271 CNRSINRIA06900 Sophia AntipolisFrance

The Spatio-Temporal consistency Language(STeC)is a high-level modeling language that deals natively with spatio-temporal behaviour,i.e.,behaviour relating to certain locations and *** restriction by both locations and time is of first importance for some types of real-time *** is a formal specification language based on logical *** is used to describe some crucial safety properties for real-time systems,due to its powerful expressiveness of logical and chronometric time *** consider a novel verification framework combining STeC and CCSL,with the advantages of addressing spatio-temporal consistency of system behaviour and easily expressing some crucial time *** propose a theory combining these two languages and a method verifying CCSL properties in STeC *** adopt UPPAAL as the model checking tool and give a simple example to illustrate how to carry out verification in our framework.

关键词： spatio-temporal consistency real-time systems spatio-temporal systems high-level modelling language clock constraint specification model checking verification framework

来源：评论

学校读者我要写书评

暂无评论

Intrusion detection using a combination of one-dimensional convolution and GRU

Intrusion detection using a combination of one-dimensional c...

引用

2020 International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2020

作者： Wang, Xiaojuan Xiao, Bo MOE Research Center for Software Hardware Co-Design Engineering and Application Software Engineering Institute East China Normal University Shanghai China

Intrusion detection plays an important role in ensuring network information security. Traditional machine learning technology does not work well enough with massive data and various intrusion classes, and detection accuracy turns unsatisfied with unknown intrusions. This paper proposes a new network intrusion detection model (conv1d-GRU) that combines one-dimensional convolution and GRU for multi-class intrusion detection scenarios, and improves data imbalance by weighting the samples of each category. NSL-KDD as an improved version of the KDD CUP99 dataset is selected for our intrusion detection system. Experimental results on this dataset show that the proposed deep learning method is superior to present intrusion detection methods based on machine learning and deep learning, and has better feature representation learning and classification capabilities. © Published under licence by IOP Publishing Ltd.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Practical privacy-preserving mixing protocol for Bitcoin

Practical privacy-preserving mixing protocol for Bitcoin

引用

International conference on computer Supported cooperative Work in design

作者： Qianqian Chang Lin Xu Lei Zhang Shanghai Key Laboratory of Trustworthy Computing East China Normal University China Science and Technology on Communication Security Laboratory Chengdu China Ministry of Education Engineering Research Center of Software/Hardware Co-Design Technology and Application China

The privacy of Cryptocurrencies are of great concern in various fields. researches has shown that pseudonyms, which are used in Bitcoin, only provide weak privacy. The privacy of users may be put at risk under deanonymization attacks. The exisiting schemes typically require a trusted-third party to achieve anonymity, however this usually faces a single-point fault. In addition, existing schemes suffer from high communication complexity and impracticality. This paper proposes a practical privacy-preserving mixing protocol for Bitcoin to achieve unlink-ability of input and output address of transactions. compared to existing schemes, our protocol improves practicality. The communication complexity of our protocol is linearly related to the number of peers. Moreover, our protocol is scalable as it works not only for Bitcoin, but also for other cryptocurrencies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Verifiable Asynchronous Federated Learning 3

Privacy-Preserving Verifiable Asynchronous Federated Learnin...

引用

3rd International conference on software engineering and Development, ICSED 2021

作者： Gao, Yuanyuan Wang, Lulu Zhang, Lei Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education East China Normal University China Guangxi Key Laboratory of Cryptography and Information Security China Software Engineering Institute East China Normal University China

ISBN: (纸本)9781450385213

Federated learning (FL) is a recently proposed technique to cope with growing data and break the barriers among datasets, which enables nodes to train machine learning models without sharing their local datasets. However, the data privacy and model performance concerns in asynchronous federated learning hinder its deployment in practical applications, especially in dynamic scenarios. To address these problems, we propose a verifiable asynchronous federated learning with a peer-to-peer network based on local dataset test and cosine value examination to improve the model performance. We also design a privacy-preserving scheme by using the local differential privacy (LDP) to protect data privacy. We evaluate our scheme on the model accuracy and convergence performance. Numerical results show the high accuracy and efficiency of our proposed scheme while protecting privacy. © 2021 ACM.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Federated Linear Bandit Learning via Over-the-air computation

Federated Linear Bandit Learning via Over-the-air Computatio...

引用

IEEE conference on Global communications (GLOBEcoM)

作者： Jiali Wang Yuning Jiang Xin Liu Ting Wang Yuanming Shi MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China School of Information Science and Technology (SIST) ShanghaiTech University China Automatic Control Laboratory Ecole Polytechnique Fédérale de Lausanne (EPFL) Switzerland

In this paper, we investigate federated contextual linear bandit learning within a wireless system that comprises a server and multiple devices. Each device interacts with the environment, selects an action based on the received reward, and sends model updates to the server. The primary objective is to minimize cumulative regret across all devices within a finite time horizon. To reduce the communication overhead, devices communicate with the server via over-the-air computation (Aircomp) over noisy fading channels, where the channel noise may distort the signals. In this context, we propose a customized federated linear bandits scheme, where each device transmits an analog signal, and the server receives a superposition of these signals distorted by channel noise. A rigorous mathematical analysis is conducted to determine the regret bound of the proposed scheme. Both theoretical analysis and numerical experiments demonstrate the competitive performance of our proposed scheme in terms of regret bounds in various settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Scheduling Algorithm for Distributed Heterogeneous Systems with Task Duplication Allowed

An Efficient Scheduling Algorithm for Distributed Heterogene...

引用

IEEE International conference on Big Data and Cloud computing (BdCloud)

作者： Hao Shi Yixiang Chen Jinyi Xu Software Engineering Institute East China Normal University Shanghai China MOE Engineering Research Center for Software/Hardware Co-Design Technology and Application Shanghai China

Due to the restriction of data transmission speed and bandwidth between processing units, communication delays are significantly impacting the complete time of applications in distributed heterogeneous systems. Most of the existing methods considering communication delays are approximate. The performance of solutions given by these heuristic methods are depends on the input instance. Another common choice is optimization methods, such as genetic algorithms and branch-and-bound search. However, these algorithms solve general situations with low efficiency. This paper proposes an efficient scheduling algorithm with task duplication allowed, called DHSA. Task duplication allows tasks executing multiple times to trade extra computation for communication delays, which is widely used in parallel system scheduling approximately. To address the complexity explosion caused by allowing all-task duplication, we decompose the scheduling into allocation and ordering stages and optimize them separately with solving optimization model and slack-interval aware ordering approach. Extensive experiments show that DHSA gives more optimal solutions within feasible time comparing to two state-of-the-art methods, particularly for applications with medium to high communication load.

关键词： Schedules Scheduling algorithms computational modeling Optimization methods Scheduling Delays complexity theory

来源：评论

学校读者我要写书评

暂无评论

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

arXiv

引用

arXiv 2025年

作者： Li, Nan Wang, Xiaolu Du, Xiao Cai, Puyu Wang, Ting Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education the Shangh ai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China Software Engineering Institute East China Normal University Shanghai200050 China Computer Science Department New York University New YorkNY10012 United States

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they often struggle with high computational and communication overhead. To address these issues, model pruning is introduced as a strategy to streamline computations. However, existing pruning methods, when applied solely based on local data, often produce sub-models that inadequately reflect clients’ specific tasks due to data insufficiency. To overcome these challenges, this paper introduces SAFL (Structure-Aware Federated Learning), a novel framework that enhances personalized federated learning through client-specific clustering and Similar Client Structure Information (SCSI)-guided model pruning. SAFL employs a two-stage process: initially, it groups clients based on data similarities and uses aggregated pruning criteria to guide the pruning process, facilitating the identification of optimal sub-models. Subsequently, clients train these pruned models and engage in server-based aggregation, ensuring tailored and efficient models for each client. This method significantly reduces computational overhead while improving inference accuracy. Extensive experiments demonstrate that SAFL markedly diminishes model size and improves performance, making it highly effective in federated environments characterized by heterogeneous data. copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

VARF: Verifying and Analyzing Robustness of Random Forests 22nd

VARF: Verifying and Analyzing Robustness of Random Forests

引用

22nd International conference on Formal engineering Methods, ICFEM 2020

作者： Nie, Chaoqun Shi, Jianqi Huang, Yanhong Hardware/Software Co-design Technology and Application Engineering Research Center National Trusted Embedded Software Engineering Technology Research Center East China Normal University Shanghai China

ISBN: (纸本)9783030634056

With the large-scale application of machine learning in various fields, the security of models has attracted great attention. Recent studies have shown that tree-based models are vulnerable to adversarial examples. This problem may cause serious security risks. It is important to verify the safety of models. In this paper, we study the robustness verification problem of Random Forests (RF) which is a fundamental machine learning technique. We reduce the verification problem of an RF model into a constraint solving problem solved by modern SMT solvers. Then we present a novel method based on the minimal unsatisfiable core to explain the robustness over a sample. Furthermore, we propose an algorithm for measuring Local Robustness Feature Importance (LRFI). The LRFI builds a link between the features and the robustness. It can identify which features are more important for providing robustness of the model. We have implemented these methods into a tool named VARF. We evaluate VARF on two public datasets, demonstrating its scalability and ability to verify large models. © 2020, Springer Nature Switzerland AG.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Protein Functional Family Classification Based on Multilevel Feature Information

Protein Functional Family Classification Based on Multilevel...

引用

IEEE International conference on Bioinformatics and Biomedicine (BIBM)

作者： Guokai Zhou Weiting Chen MOE Research Center of Software/Hardware Co-Design Engineering Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Next-generation sequencing technologies generated a large number of new sequenced proteins. Classifying these proteins into functional families is an important task in the field of biological protein property research. The high-cost and time-consuming drawbacks of bioassays promote the development of machine learning-based protein classification studies. However, previous work only used single level features, which were not informative enough and had classification bias. In this paper, we propose a new model named PCNM to alleviate the above problems. Different from previous work that extracts only a single level of features, the PCNM model uses a convolutional Neural Network (CNN) module and a Global and Local feature (GL) module to extract feature at three levels: conserved domains, amino acids, and protein sequences. The experimental results of the Phages of orthologous groups dataset (POG) and the G-protein coupled receptor superfamily dataset (GPCR) show that our proposed PCNM outperforms currently available methods in five metrics: accuracy, precision, recall, F1 score, and MCC. PCNM achieves a high accuracy of 85.12% on the GPCR sub-subfamily dataset and 81.42% on the POG dataset. The robustness experiments of PCNM further demonstrate that the model alleviates the classification bias.

关键词： Proteins Sequential analysis Neuroscience Feature extraction Amino acids Robustness convolutional neural 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：