检索结果-内蒙古大学图书馆

Plausible Proxy Mining With Credibility for Unsupervised Person Re-Identification

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第7期33卷 3308-3318页

作者： Zheng, Dingyuan Xiao, Jimin Sun, Mingjie Bai, Huihui Hou, Junhui Northwestern Polytech Univ Sch Microelect Xian 710072 Peoples R China Univ Liverpool Liverpool L69 3BX England Xian Jiaotong Liverpool Univ Sch Adv Technol Suzhou 215123 Peoples R China Univ Liverpool Dept Elect Engn & Elect Liverpool L69 3BX England Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

One effective way to address unsupervised person re-identification is to use a clustering-based contrastive learning approach. Existing state-of-the-art methods adopt clustering algorithms (e.g., DBSCAN) and camera ID information to divide all person images into several camera-aware proxies. Then, for each person image, the extracted feature representation is pulled closer to the centroids of its pseudo-positive proxies (the proxies that share the same pseudo-identity label with this image) and pushed away from the centroids of other pseudo-negative proxies (the proxies that share the different pseudo-identity label with this image). However, the quality of the proxy centroid is significantly affected by the proxy impurity issue and thus deteriorates the learned feature representations. On the premise that we cannot introduce superior supervision signals by thoroughly solving the proxy impurity issue, for a person image, identifying its plausible proxies: the pseudo-negative proxies which potentially include its wrongly-clustered instances (the instances with the same ground-truth identity with this image), and further fixing the resulted incorrect supervision signals become an urgent and challenging problem. This paper proposes a simple yet effective approach to address this problem. With a given image, our method can effectively locate its plausible proxies. Then we introduce credibility to measure how much we should treat the centroid of each mined plausible proxy as a positive supervision signal rather than entirely negative. Extensive experiments on three widely-used person re-ID datasets validate the effectiveness of our proposed approach. Codes will be available at: https://***/Dingyuan-Zheng/PPCL.

关键词： Person re-identification clustering algorithm proxy impurity issue contrastive learning plausible proxy super-vision signals

来源：评论

学校读者我要写书评

暂无评论

Video object segmentation through semantic visual words matching

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第13期82卷 19591-19605页

作者： Hao, Chuanyan Chen, Yadang Wu, Weimin Yang, Zhi-Xin Wu, Enhua Nanjing Univ Posts & Telecommun Sch Educ Sci & Technol Nanjing Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Jiangsu Peoples R China Univ Macao Dept Electromech Engn State Key Lab Internet Things Smart City Taipa Macau Peoples R China Univ Chinese Acad Sci Inst Software State Key Lab Comp Sci Beijing Peoples R China

Video object segmentation (VOS) has been widely used in the fields of computer vision. However, existing VOS algorithms have drawbacks, such as difficulty with object deformation, occlusion, and fast motion. We therefore propose an effective VOS algorithm based on semantic visual words matching. Specifically, given the support frame and its corresponding mask, the frame is firstly input to the encoder with an embedding layer, and then a clustering algorithm is followed to generate a group of semantic visual words according to its mask. For a query frame to be segmented, a matching operation is performed against words generated from the support frame. In this manner, each pixel on query frame can be classified into different object categories by the obtained similarity. What's more, a self-attention mechanism is applied to enhance the embedding features in order to capture the global dependencies before the words matching. For further handling the object changing and global mismatch problems, an online update and correction mechanism are also employed in our method. Experiments show that our proposed method achieved competitive results on the DAVIS 2016 and DAVIS 2017 datasets. J&F-mean, the mean value between regional similarity and contour accuracy, reached 83.2% and 72.3% on DAVIS 2016 and DAVIS 2017, respectively.

关键词： Video object segmentation clustering algorithm Visual words Self-attention Online update mechanism

来源：评论

学校读者我要写书评

暂无评论

Topic Modeling-Based Framework for Extracting Marketing Information From E-Commerce Reviews

引用

IEEE ACCESS 2023年 11卷 135049-135060页

作者： An, Yusung Kim, Dongju Lee, Juyeon Oh, Hayoung Lee, Joo-Sik Jeong, Donghwa Sungkyunkwan Univ Seoul 03063 South Korea Sungkyunkwan Univ Coll Comp & Informat Seoul 03063 South Korea MechaSolut Daegu 41024 South Korea

Reviews left by consumers on e-commerce platforms provide crucial marketing information as they are a publicly available source of information providing insight into consumers' thoughts and opinions. However, it is physically impossible to read hundreds of reviews per product. Therefore, algorithmically extracting the necessary insights from a large volume of review data can provide more advanced information while reducing time and costs. This study aims to automate the process of extracting related products, pros and cons of products, and trend forecasting from review data using clustering algorithms. The review dataset for pros and cons of products and related products was constructed by selecting 17 products on the Naver Shopping platform and crawling them and the product keyword and search volume dataset for trend forecasting was constructed by crawling the data from Itemscout and Naver datalab platform. Various clustering-based algorithms such as Deep clustering Network, BERTopic, and a Transformer-based forecasting model were used to conduct the research. It is expected that this will allow for a more accurate understanding of consumer thoughts, which can be utilized in marketing for various products and services.

关键词： Topic modeling clustering algorithm trend forecasting BERT e-commerce marketing

来源：评论

学校读者我要写书评

暂无评论

A higher satisfaction product customization method for different customer groups

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第12期83卷 36571-36601页

作者： Wang, Zhengyu Dai, Mingzhi Sun, Xin Zhou, Meiyu East China Univ Sci & Technol Sch Art Design & Media Meilong Rd 130 Shanghai 200237 Peoples R China East China Univ Sci & Technol Sch Informat Sci & Engn Meilong Rd 130 Shanghai 200237 Peoples R China Qinghai Univ Sch Mech Engn Ningda Rd 251 Xining 810016 Qinghai Peoples R China

Product customization in response to the widely varying perceptual expectations of different customers is an effective means to obtain customer satisfaction. Rapidly optimizing products to meet the personalized needs of different customers while controlling costs and improving design efficiency remains a challenge. In the present paper, a higher satisfaction product customization model was proposed with aim of efficiently reducing the number of target research customers and rapidly generating customer-oriented product design. In this model, a clustering algorithm based on emotional preference and migratory behavior (EPMC) was combined with a coupled model of interactive genetic algorithm with hesitancy-based interval individual fitness (IGA-HIIF) and Kansei Engineering (KE) method. This is the first implementation of EPMC in the customer research field, and the output content is optimized, which makes it capable of quickly dividing the multi-dimensional customer data space constructed in this study and accurately identifying different types of representative customers (RCs). And then, coupled the IGA-HIIF and KE model was adopted to establish a customer-oriented product evolution design system (PEDS). Finally, the most satisfactory products were auto-generated by PEDS with the participation of the RCs. The proposed method was applied to a case of social robot design. The result verifies that the approach could reduce the number of target research customers effectively without reducing diversity, allow direct customer involvement in the design process, and accurately extracts customers' personalized emotional implicit information and preference differences.

关键词： Product customization clustering algorithm Interactive genetic algorithm Kansei engineering Customers satisfaction diversity

来源：评论

学校读者我要写书评

暂无评论

An intelligent routing algorithm for energy prediction of 6G-powered wireless sensor networks

引用

ALEXANDRIA ENGINEERING JOURNAL 2023年 76卷 35-49页

作者： Zhang, Tantong Henan Univ Anim Husb & Econ Sch Software Dept Informat Engn Zhengzhou 450053 Peoples R China

With the rapid development of the Internet and computers, large-scale network applications have become a research hotspot in the communication industry, engineering and other fields. Building a new wireless sensor network and intelligent communication transmission system can promote the further upgrading and improvement of the capability industry, which is also a subject that the current network academia and communication academia are trying to explore. Based on the above background environment, this paper proposes the research on energy prediction and intelligent routing algorithm of wireless sensor networks in the development of sixth generation (6G) networks. A node coverage and scheduling algorithm based on energy prediction is proposed for the overlap and non-uniformity of regions in network transmission. Secondly, the problem of energy efficient utilization in wireless sensor networks is solved, and the clustering algorithm is used to predict the use process. The working state model of network sensor is established, and the energy parameters are added to the actual prediction calculation as influencing factors. Finally, in the intelligent routing mechanism, clustering mechanism and particle swarm optimization algorithm are used to improve the path selection, so as to improve the fault tolerance of wireless network transmission in the face of large amounts of dynamic data. The research results show that the optimization and intelligent routing algorithm based on energy prediction for wireless sensor networks can prolong the service life cycle and ensure the network transmission efficiency and coverage in a long work cycle. It can ensure the energy supply of the sensor and prolong the service time through the balanced node scheduling.& COPY;2023 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University This is an open access article under the CC BY-NC-ND license (http://***/ licenses/by-nc-nd/4.0/).

关键词： 6G network Energy prediction Wireless sensor network Intelligent routing algorithm clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent algorithms in privacy-preserving authentication schemes and traceability with accuracy in VANETs for smart transportation

引用

SOFT COMPUTING 2023年第23期28卷 1-10页

作者： Shikka, Rishi Kamalraj, R. Shah, Pradeep Kumar Sutariya, Kamal Anwar, Syed Rashid Kumar, Arvind Sanskriti Univ Dept Elect Mathura Uttar Pradesh India Jain Deemed Univ Sch Comp Sci & Informat Technol Bangalore India Teerthanker Mahaveer Univ Coll Comp Sci & IT Moradabad Uttar Pradesh India Parul Univ Parul Inst Engn & Technol Dept Comp Sci & Engn Vadodara Gujarat India Arka Jain Univ Dept Comp Sci & IT Jamshedpur Jharkhand India Galgotias Univ Sch Comp Sci & Engn Greater Noida Uttar Pradesh India

Vehicle ad hoc network is used on the road where vehicles serve as mobile nodes. VANET's primary uses include intelligent transportation and active security. The framework for intelligent transportation systems relies heavily on VANETs. Intelligent transportation networks are sometimes used to refer to VANETs. In VANETs, however, authentication and user privacy remain crucial issues. This study proposes a novel method for privacy-based authentication algorithms that improve the accuracy of data transmission for smart VANET transportation. Here, a lightweight hybrid authentication-based privacy-preserving algorithm is used to improve privacy. Then, an effective congestion-based clustering algorithm is used to send the data. Throughput, QoS, latency, computational cost, and data transmission rate are the focus of the experimental analysis. Throughput, QoS, latency, computational cost, and data transmission rate were all achieved using the proposed method. The proposed method makes use of lightweight, efficient pseudonyms that can be used for both message authentication and as a trapdoor to provide conditional anonymity. The proposed method's ability to withstand a variety of security and privacy threats is demonstrated by the various attack scenarios and the proposed technique attained throughput 93%, QoS 55%, latency 62%, computational cost 63%, and data transmission rate 69%.

关键词： Privacy-based authentication Data transmission accuracy Smart transportation VANET Efficient congestion clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Scenario-Transformation-Based Optimal Sizing of Hybrid Hydrogen-Battery Storage for Multi-Timescale Islanded Microgrids

引用

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY 2023年第3期14卷 1784-1795页

作者： Jiang, Sheng Wen, Shuli Zhu, Miao Huang, Yuqing Ye, Huili Shanghai Jiao Tong Univ Key Lab Control Power Transmiss & Convers Minist Educ Shanghai 200240 Peoples R China Shanghai Marine Equipment Res Inst Dept Technol Manage Shanghai 200031 Peoples R China

The increasing penetration of volatile renewable energy poses a significant challenge for islanded microgrids in maintaining the seasonal power balance on a long-term timescale. To support renewable integration, seasonal energy storage techniques are expected to coordinate with short-term storage systems to compensate for power mismatches on multiple timescales. However, hybrid storage sizing is often hindered by the coupling of different timescales, which will lead to a large number of variables and greater computational complexity. Thus, in this article, a novel optimal sizing framework is proposed for a hybrid hydrogen-battery storage system, considering a year-round time horizon. To ensure reliable planning of hydrogen storage, a "seasonal-trend decomposition based on LOESS (STL)" technique is applied to preserve long-term power fluctuation characteristics during scenario clustering. Moreover, a least-squares-based scenario approximation method is developed to improve the accuracy of the clustering results. On this basis, a scenario-transformation solution method is proposed to avoid a large number of variables due to year-round hourly operation. The case studies verify the advantages and efficiency of the proposed method.

关键词： clustering algorithm hydrogen-battery energy storage multiple-timescale operation optimal sizing scenario transformation seasonal imbalance STL decomposition

来源：评论

学校读者我要写书评

暂无评论

Minimum cost consensus model with loss aversion based large-scale group decision making

引用

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY 2023年第7期74卷 1712-1729页

作者： Liang, Yingying Ju, Yanbing Qin, Jindong Pedrycz, Witold Dong, Peiwu Beijing Inst Technol Sch Management & Econ Beijing 100081 Peoples R China Wuhan Univ Technol Sch Management Wuhan Hubei Peoples R China Wuhan Univ Technol Res Ctr Data Sci & Intelligent Decis Making Wuhan Hubei Peoples R China Wuhan Univ Technol Res Inst Digital Governance & Management Decis In Wuhan Hubei Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB Canada

In minimum cost consensus problems, to accomplish the group consensus, decision makers accommodate their initial discrepant opinions based on the unit adjustment costs. During this process, decision makers may exhibit loss aversion, which results in extra expenses when participants feel loss in contrast to their reference opinion adjustments. Existing minimum cost consensus models pay little attention to the loss-averse preference. Hence, to fill up this gap, a minimum cost consensus model with loss aversion (MCCM-LA) is established and the desired properties are analyzed. To manage large-scale group decision making problems, we first propose an integrated opinion similarity, connectivity similarity and behavior similarity clustering algorithm to divide decision makers into multiple subgroups. Balancing the individual adjustment willingness and consensus reaching efficiency, a two-stage consensus reaching mechanism is further designed based on MCCM-LA to realize the accordant opinion. Finally, the effectiveness and feasibility of the proposed method are demonstrated by sensitivity and comparative analyses with an illustrative example.

关键词： Minimum cost consensus model loss aversion large-scale group decision making consensus reaching mechanism clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

V2V Communications Performance Enhancement

引用

WIRELESS PERSONAL COMMUNICATIONS 2023年第4期129卷 2387-2401页

作者： Hamarsheh, Qadri Daoud, Omar Al-Akaidi, Marwan Damati, Ahlam Philadelphia Univ Fac Engn & Technol Dept Commun & Elect Engn Amman Jordan Al Farahidi Univ Baghdad Iraq Philadelphia Univ Fac Engn & Technol Dept Renewable Engn Amman Jordan Amer Int Univ Elect & Comp Engn Al Jahraa Kuwait

During the last decade, vehicle communications gained a huge interest and considered as emerging technologies. It makes transportation easier and safer. However, it has a serious concern with respect to the issue of sharing the information. Some crucial data must be transferred between the vehicles, such as orientation, positions, and any urgent road data. Accordingly, the system reliability and feasibility must be *** this work, a robust vehicular communications benchmark is proposed to enhance the efficiency for such systems. It is based on enhancing the orthogonal frequency division multiplexing structure by imposing the fast frequency hopping structure. Hence, some of the channel impairments such as the effect of the Doppler spread is mitigated. The proposed benchmark is divided into two processing stages: adaptive re-clustering stage and the multiparalell one. These two stages lead to modifying the VANET standard;IEEE 802.11p physical layer. For enhancing the system's throughput, another modification will be made to have Multiple Input Multiple Output antennas as *** results show a noticeable stability compared to our previously published work. Since it improves the BER at 8 dB SNR from 3.10(- 2) to be 7.10(- 4) when using our proposition bases 2.2 MIMO. Another 30% improvement has been attained after increasing the number of antennas to be four. Another enhancement has been derived from the results comparing to the literature Lower-ID DCA technique;that they are exceed its performance from the communication's point of view of either for peed or for the range.

关键词： clustering algorithm Doppler Spread Fast Frequency Hopping MIMO OFDM V2V

来源：评论

学校读者我要写书评

暂无评论

Data Integration Method of Multi-source Feedback Evaluation for Remote Teaching Quality (Aug, 10.1007/s11036-023-02189-5, 2023)

引用

MOBILE NETWORKS & APPLICATIONS 2023年第3期28卷 935-935页

作者： Chen, Lili Baza, Mohamed Alshahrani, Hani Jilin Univ Architecture & Technol Dev & Planning Off Changhun 130114 Peoples R China Coll Charleston Dept Comp Sci Charleston SC 29414 USA Najran Univ Coll Comp Sci & Informat Syst Dept Comp Sci Najran 61441 Saudi Arabia

Distance teaching is a teaching method widely concerned and used in the current education field, and accurate evaluation of the quality of distance teaching is the key to improve the effect of distance teaching. Therefore, a multi-source feedback evaluation data integration method for the quality of distance teaching is proposed. The remote teaching of organic chemistry experiment was taked as the research object, the initial multi-source feedback evaluation index system is constructed through the research of experts and scholars. After the initial evaluation index is standardized, the K means clustering is used to reduce the initial evaluation index and determine the final evaluation index system. Then the final used evaluation index data are checked and coded to determine whether the final used evaluation index data set matches the actual data. In this way, artificial intelligence (AI) is used to realize the integration of multi-source feedback evaluation data of distance teaching quality. The experimental results show that the information contribution rate of the evaluation index system constructed in this method is 90.93%, the correlation coefficient value with the actual results is 0.982, and the evaluation accuracy is as high as 99.48%.

关键词： Analytic Hierarchy Process clustering algorithm Distance Teaching Quality Multi-source Feedback Evaluation Organic Chemistry Experiment

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：