检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Du, Xin Cai, Weihong Liu, Jianquan Yu, Ding Xu, Kai Li, Wei Department of Computer Science College of Engineering Shantou University China Big Data Research Institute Tong Xing Technology Corporation China System Platform Research Laboratories NEC Corporation Japan Graduate School of Science and Engineering Hosei University Japan

Determining the value of basketball players through analyzing the players’ behavior is important for the managers of modern basketball teams. However, conventional methods always utilize isolated statistical data, leading to ineffective and inaccurate evaluations. Existing models based on dynamic network theory offer major improvements to the results of such evaluations, but said models remain imprecise because they focus merely on evaluating the values of individual players rather than considering them within their current teams. To solve this problem, we propose an analysis and evaluation model based on networks and a hidden Markov model. To the best of our knowledge, we are the first to combine a network form representing the players who are playing with the use of a hidden Markov model to mine the network and generate the desired results. Applying our approach to SportVU data collected from the National Basketball Association shows that this analysis and evaluation model can effectively analyze the performance of each player in a game and provides an assistive tool for team managers. Copyright © 2020, The Authors. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Binary neural networks: A survey

arXiv

引用

arXiv 2020年

作者： Qin, Haotong Gong, Ruihao Liu, Xianglong Bai, Xiao Song, Jingkuan Sebe, Nicu State Key Lab of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Valid Bug Reports Determination and Explanation

Deep Learning Based Valid Bug Reports Determination and Expl...

引用

International Symposium on software Reliability engineering (ISSRE)

作者： Jianjun He Ling Xu Yuanrui Fan Zhou Xu Meng Yan Yan Lei Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9781728198705

ISBN: (纸本)9781728198712

Bug reports are widely used by developers to fix bugs. Due to the lack of experience, reporters may submit numerous invalid bug reports. Manually determining valid bug reports is a laborious task. Automatically identifying valid bug reports can save time and effort for bug analysis. In this paper, we propose a deep learning-based approach to determine and explain valid bug reports using only textual information i.e., summaries and descriptions of bug reports. Convolutional neural network (CNN) is applied to capture their contextual and semantic features. Moreover, by analyzing the spatial structure of CNN, we backtrack the trained CNN model to get phrases that can explain valid bug reports determination. After inspecting the phrases manually, we summarize some valid bug report patterns. We evaluate our approach on five large-scale open-source projects containing a total of 540491 bug reports. On average, across the five projects, our approach achieves 0.85, 0.80, 0.69 and improves the state-of-the-art approach by 8.97%, 9.59%, 9.52% in terms of AUC, F1-score for valid bug reports, and F1-score for invalid bug reports, respectively. From the summarized patterns, we can find that determining valid bug reports is mainly due to three categories of patterns: Attachment, Environment, and Reproduce.

关键词： Fans computer bugs Semantics Feature extraction software reliability Task analysis Open source software

来源：评论

学校读者我要写书评

暂无评论

Correction to: Framework for automatically suggesting remedial actions to help students at risk based on explainable ML and rulebased models

引用

International Journal of Educational Technology in Higher Education 2022年第1期19卷 1-1页

作者： Albreiki, Balqis Habuza, Tetiana Zaki, Nazar Department of Computer Science and Software Engineering College of Information Technology UAE University Al Ain UAE Office of Institutional Effectiveness UAE University Al Ain UAE Big Data Analytics Center (BIDAC) UAE University Al Ain UAE

来源：评论

学校读者我要写书评

暂无评论

A privacy-preserving access control protocol for 6G supported intelligent UAV networks

引用

Vehicular Communications 2025年 54卷

作者： Mahmood, Khalid Shamshad, Salman Anisi, Mohammad Hossein Brighente, Alessandro Saleem, Muhammad Asad Das, Ashok Kumar School of Engineering and Computing University of Lancashire Preston PR1 2HE United Kingdom of Intelligent Data Science National Yunlin University of Science and Technology Douliu 64002 Taiwan Department of Software Engineering The University of Lahore Lahore 54590 Pakistan School of Computer Science and Electronic Engineering University of Essex Colchester CO4 3SQ United Kingdom Department of Mathematics and HIT research center Univ. of Padova Italy School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 611731 China Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad 500032 India Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 South Korea

Due to their autonomous operation, high mobility, and real-time communication capabilities, 6G-supported Unmanned Aerial Vehicles (6G-UAVs) (i.e., drones) are increasingly being utilized to enhance data collection and management in Intelligent Transportation Systems (ITSs). Despite their manifold benefits, 6G-supported UAV-based ITS (6G-U-ITS) faces unique security challenges beyond conventional cyber and physical threats. These include real-time authentication, impersonation attacks, physical tampering or cloning and protection against identity spoofing in highly dynamic environments. For instance, an attacker may steal a drone and use its identity to send authenticated malicious messages to the ITS, causing road accidents. Therefore, a secure authentication scheme must ensure resilience against UAV identity theft and unauthorized access while maintaining low-latency and computational efficiency to support the stringent real-time security requirements of 6G-U-ITS. Existing authentication schemes are not specifically designed to address these challenges, making it imperative to develop a lightweight and robust authentication mechanism tailored for 6G-U-ITS. Moreover, most of the existing protocols are vulnerable to physical tampering and impersonation attacks and also require high computation overhead. In this paper, to mitigate these limitations and satisfy the aforementioned requirements, we propose a secure access control protocol for 6G-U-ITS. To the best of our knowledge, this is the first security solution in the literature that can achieve security against UAVs physical attacks. Furthermore, we justify the robustness of the designed protocol against potential attacks through detailed formal and informal security assessment. Via testbed experiments, we show that our protocol achieves 20.66% and 22.82% higher efficiency on communication and computation overhead, respectively, compared to other contemporary competing protocols. © 2025 Elsevier Inc.

关键词： Authentication protocol Intelligent transport systems Key agreement Security protocol UAV

来源：评论

学校读者我要写书评

暂无评论

Development of an Artificial Intelligence Model for Individualized FSH Daily Dosage Guidance During Ovulation Stimulation

SSRN

引用

SSRN 2023年

作者： Duan, Liyan Xia, Yu Mei, Jie Zhang, Hui Zhu, YingChun Huang, ChenYnag Yan, Guijun Kong, Na Li, Wujun Sun, Haixiang Center for Reproductive Medicine and Obstetrics and Gynecology Drum Tower Clinic Medical College Nanjing Medical University Nanjing210008 China Center for Molecular Reproductive Medicine Nanjing University Nanjing210008 China National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing210008 China National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China Center for Medical Big Data Nanjing Drum Tower Hospital Affifiliated Drum Tower Hospital Medical School of Nanjing University Jiangsu Nanjing210008 China State Key Laboratory of Reproductive Medicine China International Joint Research Center on Environment and Human Health Center for Global Health School of Public Health Nanjing Medical University Nanjing211166 China Department of Reproductive Medicine Center Nanjing Drum Tower Hospital State Key Laboratory of Pharmaceutical Biotechnology Nanjing University Nanjing210023 China

Background: We aim to develop a real-time, interpretable artificial intelligence (AI) system, using an algorithm for estimating follicle stimulating hormone (FSH) daily dose in individualized controlled ovarian stimulation (COS).Methods: Between January 2018 and December 2020, a total of 13,788 cycles of GnRHa long-protocol ovulation stimulation cycles were included from the Reproductive Medicine Centre of Nanjing Drum Tower Hospital. We used a method of cross-temporal and cross-feature joint encoding to learn the time series information X=X1, X2,..., XN of the N days to get its hidden layer representation H. Then, we applied K-nearest neighbors (KNN) with the hidden layer representation H to obtain the ***: Our proposed CTFE model obtained Accuracy and Weighted-F1 metrics of 0.737 and 0.733, to predict the daily FSH dose respectively, which are the highest among other popular models for processing time series data. On days 1 and 5, Lasso regression predicted the FSH daily dosage with an accuracy of 0.696 and 0.522, respectively, whereas our technique predicted it with 0.834 and 0.819. The introduction of a sliding window mechanism after 13 days helps to maintain good performance, although accuracy drops due to insufficient ***: Our study demonstrated that the CTFE model can be used to calculate the daily FSH dose with high accuracy. This model may be easily applied in daily clinical practice by ***: This work was supported by the National Natural science Foundation of China (NO.82030040), Scientific research project of Jiangsu Province Association of Maternal and Child Health (No. FYX202203).Declaration of Interest: HX S, WJ L,GJ Y, N K, J M, LY D and Y X are listed as inventors of patents relating to this work. The authors affirm that they have no known financial or interpersonal conflicts that would have seemed to have an impact on the research presented in this *** Approval: The study had ethical approval fro

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

A Deep Concept-aware Model for predicting and explaining restaurant future status

A Deep Concept-aware Model for predicting and explaining res...

引用

IEEE International Conference on Web Services (ICWS)

作者： Hao Liao Xiaojie Zhang Xin Li Mingyang Zhou Alexandre Vidmer Rui Mao Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Guangdong Province Engineering Center of China-made High Performance Data Computing System Shenzhen City Key Laboratory of Service Computing and Application Shenzhen China Institute of Big Data Intelligent Management and Decision Shenzhen University Shenzhen China

ISBN: (数字)9781728187860

ISBN: (纸本)9781728187877

Nowadays, with the development of web services, the survival of online service has captured public attention significantly. Future prediction of business is crucial to the shopkeepers. Predicting how the business will develop and explaining what key factors are leading to it are two most important tasks. Existing literatures usually tackle only one of these two tasks, ignoring that they are two closely related tasks and complement each other. In this paper, we propose a review-based neural model, named Deep Concept-aware Model (DCA), to predict restaurants' future status and provide explainable sentences simultaneously in an end2end framework. Specifically, we use co-attention to select concepts and implement prediction and explanation tasks through Factorization Machine and Gated Recurrent Unit, respectively. We conduct extensive experiments on three Chinese cities' datasets. The proposed joint model outperforms the state-of-the-art baseline methods for both prediction (average 40.96% improvement in AUC) and explanation (average 9.72% improvement in BLEU and 86.05% in Precision metric of ROUGE).

关键词： Web services Urban areas Predictive models Prediction algorithms data models Task analysis Business

来源：评论

学校读者我要写书评

暂无评论

Efficient Contact Tracing for pandemics using blockchain

引用

Informatics in Medicine Unlocked 2021年 26卷

作者： Bari, Nida Qamar, Usman Khalid, Ayesha Knowledge & Data Science Research Centre Computer & Software Engineering Department College of Electrical and Mechanical Engineering National University of Sciences and Technology (NUST) Islamabad Pakistan The Centre for Secure Information Technologies (CSIT) ECIT Institute Queen's University of Belfast Belfast BT7 1NN United Kingdom

Blockchain technologies have been benefiting many industries by being decentralized, secure and confidential. They offer great potential in pandemic impacted scenarios as well. Contact tracing helps to mitigate the transmission of disease by alerting people who may have been exposed so they can act on time to protect themselves. Contact tracing systems face some challenges related to issues of medical privacy, data security and transparency. Multiple researches show concern that contact tracing discourages people to seek medication because of the fear of loss of data, subsequent stigma, discrimination, or abuse. In this paper, we discuss how contact tracing can be improved using blockchain technology and could be able to solve these issues. The aim of our proposed system would be to reduce the impact of pandemic, to implement this merger of the blockchains and the Contact tracing app and to ensure user privacy and avoid data misuse by incorporating a symmetric key cryptographic mechanism. To tackle the scalability related issues of Blockchain this framework uses IPFS, a distributed file storage system also known as Interplanetary File System. This blockchain based solution system will enhance contact tracing by making it more stable, secure, performant, highly useable and above all effective in the fight against any pandemic. © 2021 The Authors

关键词： And pandemic Blockchain Contact tracing COVID-19 Distributed system Interplanetary file system

来源：评论

学校读者我要写书评

暂无评论

Adaptive gradient methods with dynamic bound of learning rate 7

Adaptive gradient methods with dynamic bound of learning rat...

引用

7th International Conference on Learning Representations, ICLR 2019

作者： Luo, Liangchen Xiong, Yuanhao Liu, Yan Sun, Xu MOE Key Lab of Computational Linguistics School of EECS Peking University China College of Information Science and Electronic Engineering Zhejiang University China Department of Computer Science University of Southern California United States Center for Data Science Beijing Institute of Big Data Research Peking University China

Adaptive optimization methods such as ADAGRAD, RMSPROP and ADAM have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGRAD to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of ADAM and AMSGRAD, called ADABOUND and AMSBOUND respectively, which employ dynamic bounds on learning rates to achieve a gradual and smooth transition from adaptive methods to SGD and give a theoretical proof of convergence. We further conduct experiments on various popular tasks and models, which is often insufficient in previous work. Experimental results show that new variants can eliminate the generalization gap between adaptive methods and SGD and maintain higher learning speed early in training at the same time. Moreover, they can bring significant improvement over their prototypes, especially on complex deep networks. The implementation of the algorithm can be found at https://***/Luolc/AdaBound. © 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Improved small gain conditions for input-to-state stability with respect to measurement functions: Discrete time networked system

Improved small gain conditions for input-to-state stability ...

引用

IEEE Conference on Decision and Control

作者： Yuanqiu Mo Changbin Yu Soura Dasgupta Westlake Institute for Advanced Study Westlake University Hangzhou China College of Artificial Intelligence and Big Data Shandong First Medical University & Shandong Academy of Medical Sciences Jinan China Institute for Intelligent Robots Fudan University Shanghai China Shandong Computer Science Center Shandong Provincial Key Laboratory of Computer Networks China Faculty of Engineering & the Built Environment University of Johannes-Burg Johannesburg South Africa University of Iowa Iowa City Iowa USA

ISBN: (纸本)9781665436601

In this paper we study input-to-state stability with respect to measurement functions for discrete time networked systems. In such a networked system, the trajectory of each subsystem is affected by another in each time step, and this constraining system may change from step to step. We derive small gain conditions of input-to-state stability with respect to measurement functions for this type of discrete time networked system relying on the construction of dissipative-form finite time Lyapunov function. These conditions loosen those presented in [1] and [2]. Finally, we demonstrate the applicability of our results by applying them to the stability analysis of a distributed graph algorithm which does not satisfy the conditions of [1] and [2].

关键词： Network topology Conferences Gain measurement Stability analysis Time measurement Trajectory Topology

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：