检索结果-内蒙古大学图书馆

HAM:a deep collaborative ranking method incorporating textual information

Frontiers of Information technology & Electronic Engineering 2020年第8期21卷 1206-1216页

作者： Cheng-wei WANG Teng-fei ZHOU Chen CHEN Tian-lei HU Gang CHEN The Key Laboratory of Big Data Intelligent Computing of Zhejiang Province Hangzhou 310027China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

The recommendation task with a textual corpus aims to model customer preferences from both user feedback and item textual *** is highly desirable to explore a very deep neural network to capture the complicated nonlinear ***,training a deeper recommender is not as effortless as simply adding layers.A deeper recommender suffers from the gradient vanishing/exploding issue and cannot be easily trained by gradient-based ***,textual descriptions probably contain noisy word *** extracting feature vectors from them can harm the recommender’s *** overcome these difficulties,we propose a new recommendation method named the HighwAy reco Mmender(HAM).HAM explores a highway mechanism to make gradient-based training methods stable.A multi-head attention mechanism is devised to automatically denoise textual ***,a block coordinate descent method is devised to train a deep neural *** studies show that the proposed method outperforms state-of-the-art methods significantly in terms of accuracy.

关键词： Deep learning Recommendation system Highway network Block coordinate descent

来源：评论

学校读者我要写书评

暂无评论

The Trade-off Between Privacy and Utility in Local Differential Privacy

The Trade-off Between Privacy and Utility in Local Different...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Mengqian Li Youliang Tian Junpeng Zhang Dandan Fan Dongmei Zhao College of Computer Science and Technology Guizhou University Guiyang P. R. China State Key Laboratory of Public Big Data Guizhou University Guiyang P. R. China College of Computer and Cyber Security Hebei Normal University Shijiazhuang P. R. China

In statistical queries work, such as frequency estimation, the untrusted data collector could as an honest-but-curious (HbC) or malicious adversary to learn true values. Local differential privacy(LDP) protocols have been applied against the untrusted third party in data collecting. Nevertheless, excessive noise of LDP will reduce data utility, thus affecting the results of statistical queries. Therefore, it is significant to research the trade-off between privacy and utility. In this paper, we first measure the privacy loss by observing the maximum posterior confidence of the adversary (data collector). Then, through theoretical analysis and comparison we obtain the most suitable utility measure that is Wasserstein distance. Based on these, we introduce an originality framework for privacy-utility tradeoff framework, finding that this system conforms to the Pareto optimality state and formalizing a payoff function to find optimal equilibrium point under Pareto efficiency. Finally, we illustrate the efficacy of our system model by the Adult dataset from the UCI machine learning repository.

关键词： Privacy Differential privacy Protocols Machine learning data collection Loss measurement Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

An Improved Whale Optimization Algorithm and Its Application to Power Generation in Cascade Reservoir 16th

An Improved Whale Optimization Algorithm and Its Application...

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information technology, Applications and Tools, FITAT 2020

作者： Lü, Ji-Xiang Yan, Li-Jun Pan, Tien-Szu Chu, Shu-Chuan Pan, Jeng-Shyang He, Xian-Kang Chang, Kuo-Chi School of Information Science and Engineering Fujian University of Technology Fuzhou350108 China Shenzhen Institute of Information Technology Shenzhen518172 China Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung82445 Taiwan College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China College of Science and Engineering Flinders University Sturt Rd Bedford ParkSA5042 Australia Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350108 China College of Mechanical & Electrical Engineering National Taipei University of Technology Taipei10608 Taiwan Department of Business Administration North Borneo University College Sabah Malaysia

ISBN: (纸本)9789813364196

Nowadays, there is a very popular artificial intelligence algorithm called whale optimization algorithm (WOA). WOA is obtained through the special bubble net foraging process of humpback whales. It has a special search mechanism, and is very helpful to solve some complex optimization problems and large scale. An improved WOA is implemented to optimize the cascade reservoir power generation. Firstly, by introducing nonlinear time-varying adaptive weights, the WOA performance in the local optimization and global exploration stages is improved;secondly, the differential mutation perturbation factor is introduced in the shrinking and surrounding stage of the whale algorithm to prevent premature convergence. In addition, the logarithmic spiral search method of whale individuals has been improved so that the ability to solve the algorithm traversal can be found. Experimental results show that it has a great improvement in accuracy and convergence compared with the original WOA in the optimal dispatch model of cascade reservoir power generation. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

A De-swinging Scheme in Location Privacy Protection via Smart Contract

A De-swinging Scheme in Location Privacy Protection via Smar...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Manxiang Yang Baopeng Ye Yuling Chen Tao Li Yixian Yang Xiaobin Qian State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Information Technology Innovation Service Center of Guizhou Province Guiyang China School of Cyberspace Security Beijing University of Posts and Telecommnuications Beijing China Guizhou CoVision Science & Technology Co. Ltd Guiyang China

ISBN: (纸本)9781665421751

There are some problems such as behavior deception and service swing while utilizing distributed k-anonymity technology to construct an anonymous domain. If the malicious nodes submit a false location coordinate to take participate in the process of constructing, the coordinate of the honest node will be leaked, and the attacker will increase the reputation illegally. To tackle those problems, we propose a de-swinging scheme based on the smart contract for location privacy protection. Primarily, a de-swinging reputation evaluation method (DREM) is introduced, in which participants prefer to choose nodes with high reputations to complete the construction process of the anonymous domain. In this method, we design a penalty factor to curb malicious behavior. Besides, based on our proposed DREM, a cridible cloaking area is constructed to protect the location privacy of the request nodes. We utilize smart contract to calculate reputation automatically during the process of construction. Finally, the security analysis and simulation results indicate that our proposed scheme can effectively resist malicious attacks, detect malicious nodes quickly, encourage nodes to participate honestly in the construction of anonymous domain.

关键词： Privacy data privacy Simulation Design methodology Smart contracts Resists Quality of service

来源：评论

学校读者我要写书评

暂无评论

A location data protection protocol based on differential privacy

A location data protection protocol based on differential pr...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Ping Guo Baopeng Ye Yuling Chen Tao Li Yixian Yang Xiaobin Qian State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Information Technology Innovation Service Center of Guizhou Province Guiyang China School of Cyberspace Security Beijing University of Posts and Telecommnuications Beijing China Guizhou CoVision Science &Technology Co. Ltd Guiyang China

ISBN: (纸本)9781665421751

Location-based services (LBS) is geo-location-based a mobile information service based on spatial location that adopts wireless positioning, GIS, Internet, wireless communication, database and other related technologies. which brings both convenience and vulnerability. With the increasing of scale and value of data, most existing location privacy protection protocols cannot balance privacy and utility. To solve the revealing problems in LBS, in this paper, we first design an algorithm of the best-assisted user selection (BaUS) for constructing anonymity sets. Next, we contract a smart contract to evaluate reputation, to ensure the honesty of participants. And then a differential privacy protection protocol is proposed. The theoretical analysis and experiments show that the proposed protocol can resist background knowledge attacks effectively. Meanwhile, our protocol can improve data availability. Particularly, it realizes user-controllable privacy protection which enhances privacy preservation and better security.

关键词： Wireless communication Privacy data privacy Differential privacy Protocols Publishing Smart contracts

来源：评论

学校读者我要写书评

暂无评论

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

arXiv

引用

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Optimizing Parameters and Feature Selection in SVM Based on Improved Cockroach Swarm Optimization 16th

An Optimizing Parameters and Feature Selection in SVM Based ...

引用

作者： Nguyen, Trong-The Yu, Jie Nguyen, Thi-Thanh-Tan Lai, Quoc-Anh Ngo, Truong-Giang Dao, Thi-Kien Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou China Information Technology Faculty Electric Power University Hanoi Viet Nam Department of Pattern Recognition & Image Processing Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam Faculty of Computer Science and Engineering Thuyloi University 175 Tay Son Dong Da Hanoi Viet Nam

ISBN: (纸本)9789813367562

This study improves a classifier of the support vector machine (SVM) by optimizing its parameters by adjusting cockroach swarm optimization (CSO). Classification system design includes data inputs, pre-process, and classification. The relief technique selects the feature subset, and the kernel parameters used as input for the system. The feature selection and classification of data sets were figured out by the combination of ICSO and SVM with its optimized parameters synchronous. Simulation results of the proposed scheme are compared with other systems, e.g., GA-SVM, PSO-SVM, and CSO-SVM, which show that the proposed project can achieve better classification accuracy than the different algorithms. It is promising that the proposed scheme can be applied to high-dimensional data classification, such as image classification, signal classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Lightweight Open-source Large Language Models in Pediatric Consultations: A Comparative Analysis

arXiv

引用

arXiv 2024年

作者： Wei, Qiuhong Cui, Ying Ding, Mengwei Wang, Yanqin Xiang, Lingling Yao, Zhengxiong Chen, Ceran Long, Ying Jin, Zhezhen Xu, Ximing Big Data Center for Children’s Medical Care Children’s Hospital of Chongqing Medical University National Clinical Research Center for Child Health and Disorders Ministry of Education Key Laboratory of Child Development and Disorders Chongqing China Chongqing Key Laboratory of Child Neurodevelopment and Cognitive Disorders China International Science and Technology Cooperation base of Child Development and Critical Disorders China Department of Biomedical Data Science Stanford University School of Medicine StanfordCA United States Department of Nephrology Children’s Hospital of Chongqing Medical University Chongqing China Department of Neonatology Children’s Hospital of Chongqing Medical University Chongqing China Department of Neurology Children’s Hospital of Chongqing Medical University Chongqing China College of Computer Science and Engineering Chongqing University of Technology Chongqing China Department of Biostatistics Mailman School of Public Health Columbia University New YorkNY United States

Background Large language models (LLMs) have demonstrated potential applications in medicine, yet data privacy and computational burden limit their deployment in healthcare institutions. Open-source and lightweight versions of LLMs emerge as potential solutions, but their performance, particularly in pediatric settings remains underexplored. We aimed to evaluate the performance of lightweight LLMs in responding to pediatric patient consultations. Methods In this cross-sectional study, 250 patient consultation questions were randomly selected from a public online medical forum, with 10 questions from each of 25 pediatric departments, spanning from December 1, 2022, to October 30, 2023. Two lightweight open-source LLMs, ChatGLM3-6B and Vicuna-7B, along with a larger-scale model, Vicuna-13B, and the widely-used proprietary ChatGPT-3.5, independently answered these questions in Chinese between November 1, 2023, and November 7, 2023. To assess reproducibility, each inquiry was replicated once. Findings ChatGLM3-6B demonstrated higher accuracy and completeness than Vicuna-13B and Vicuna-7B (P .05), with over 98.4% of responses being rated as safe. Repetition of inquiries confirmed these findings. Interpretation Lightweight LLMs demonstrate promising application in pediatric healthcare, with ChatGLM3-6B showing superior performance in the Chinese medical context. However, the observed gap between lightweight and large-scale proprietary LLMs underscores the need for continued development efforts. Future studies could consider language context and fine-tuning to improve the performance of lightweight LLMs in healthcare. Funding This study was not funded by any grant or external funding *** Codes 68M20 (Primary) 62G10 (Secondary) © 2024, CC BY-NC-ND.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised vehicle re-identification with progressive adaptation 29

Unsupervised vehicle re-identification with progressive adap...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Peng, Jinjia Wang, Yang Wang, Huibing Zhang, Zhao Fu, Xianping Wang, Meng College of Information and Science Technology Dalian Maritime University Liaoning Dalian China Pengcheng Laboratory Shenzhen Guangdong China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology China School of Computer Science and Information Engineering Hefei University of Technology China

ISBN: (纸本)9780999241165

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes;worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as "pseudo target samples". These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A knowledge graph constructed for job-related crimes

引用

Procedia computer science 2022年 199卷 540-547页

作者： Yong Shi Wenlu An Jiayu Xue Yi Qu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 CHINA Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 CHINA Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 CHINA College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA People’s Procuratorate of Shanghai Pudong New District Shanghai 200135 CHINA School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100190 China

Since the 18th National Congress, the Party Central Committee has greatly enhanced its efforts to "fight corruption and advocate honesty". While achieving excellent results, the rising number of crime cases has also brought great challenges to the work of the prosecution organs. At the same time, the traditional relational database has become more and more disadvantageous in dealing with large-scale, unstructured and complex dynamic data, and can no longer meet the actual needs. In order to further improve the efficiency and quality of prosecutors’ work, alleviate the problem of "too many cases and too few people", and promote the construction of "smart prosecution", this paper uses knowledge extraction and other methods to identify the key entities and relationships in the job-related crimes indictments of the Shanghai Pudong New District Procuratorate. Then using Neo4j graph database to store the extracted information and build a knowledge graph for job-related crime cases, which realizes the visualization and deep mining of job-related crime, providing a new way and tool for prosecution work as well as prosecution personnel to analyze and handle job-related crime cases.

关键词： big data in prosecution knowledge graph job-related crimes Neo4j

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：