检索结果-内蒙古大学图书馆

Combining permissioned blockchain and Bayesian best-worst method for transparent supplier selection in supply chain management

引用

Science China(Technological Sciences) 2024年第8期67卷 2579-2593页

作者： LIU JiaJun ZHANG Jie LENG JieWu Shanghai Engineering Research Center of Industrial Big Data and Intelligent System Institute of Artificial IntelligenceDonghua UniversityShanghai 201620China State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment Guangdong University of TechnologyGuangzhou 510006China

Supplier selection is an important business activity in order to realize the purchasing function in supply chain *** supplier selection process includes four stages,i.e.,bidding inviting,bidding,group decision-making,and results disclosure,involving the participation of manufacturing service demanders(MSDs),manufacturing service suppliers(MSSs),and ***,all the participants have raised concerns about the increased transparency in supplier ***,this study proposes a transparent supplier selection method by considering the engagement of *** this method,the Bayesian best-worst method(Bayesian BWM)is used to aggregate decision-makers'preferences into the overall optimal weights of the alternative MSSs,and the MSS with the largest weight is considered the suitable MSS for ***,blockchain is introduced to record the decision-making process information about supplier selection through a customized smart contract,where MSSs act as supervisors to supervise the decision-making process through the distributed consensus mechanism rather than directly participate in the decision-making ***,a case study of supplier selection in purchasing vibration acceleration sensors is *** result shows that the proposed method can support MSDs in selecting suitable MSS from alternative MSSs by aggregating decision-makers'preferences,and blockchain can provide credible information about the supplier selection process for MSSs,MSDs,and *** this way,the transparency of supplier selection is enhanced.

关键词： blockchain supplier selection supply chain transparency Bayesian BWM group decision-making

来源：评论

学校读者我要写书评

暂无评论

Psychological Counseling with Integration of Knowledge Graph and Multi-Agent Collaboration

引用

Journal of shanghai Jiaotong University (Science) 2025年 1-13页

作者： Liu, Xi Zheng, Xiaohu Cui, Weiwei College of Information Science and Technology Donghua University Shanghai201620 China Institute of artificial Intelligence Donghua University Shanghai201620 China Shanghai Engineering Center of Industrial Big Data and Intelligent System Shanghai201620 China Management College Wuzhou University Guangxi Wuzhou543003 China

Applying large language models (LLMs) to psychological counseling can reduce costs and lower barriers to access. However, issues inherent to LLMs, such as output hallucinations, knowledge lags, and response biases, limit the quality of counseling services. To address these challenges, we propose a psychological counseling method that integrates a knowledge graph (KG) and multi-agent collaboration (MAC). First, we design an ontology model and use an improved convolution residual network (CRN) to extract relational triples for constructing a psychological medicine KG. Second, we perform low-rank adaptation (LoRA) on Qwen1.5-7B-chat using the Text2Cypher training set. Finally, we design MAC prompts based on the characteristics of the retrieval-based question-answering (QA) process to facilitate the collaborative implementation of psychological medicine knowledge QA and updates. The experiments showed that the improved CRN achieved an extraction accuracy of 80%. The mean squared error of the general-domain capability of the LLM before and after LoRA was only 0.738, with a Text2Cypher score of 99.8 after LoRA. The results generated after prompting received a 70.44% approval rate compared to other methods. Thus, the proposed method can effectively enhance the intelligence, accuracy, and controllability of psychological counseling. © shanghai Jiao Tong University 2024.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Feature Fusion and Advanced Representation Learning for Multi Label Image Classification

引用

Computers, Materials & Continua 2025年第3期82卷 5285-5306页

作者： Naikang Zhong Xiao Lin Wen Du Jin Shi Institute of Artificial Intelligence on Education Research College of InformationMechanical and Electrical EngineeringShanghai Normal UniversityShanghai200234China Lab for Educational Big Data and Policymaking Ministry of EducationShanghai Normal UniversityShanghai200234China Shanghai Intelligent Education Big Data Engineering Technology Research Center Shanghai Normal UniversityShanghai200234China Shanghai Online Education Research Base for Primary and Secondary Schools Shanghai200234China DS Information Technology Co. Ltd.Shanghai200032China Faculty of Innovation Engineering Macao university of Science and TechnologyMacao999078China

Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in *** class-specific precise representations at different scales is a key aspect of feature ***,existing methods often rely on the single-scale deep feature,neglecting shallow and deeper layer features,which poses challenges when predicting objects of varying scales within the same *** some studies have explored multi-scale features,they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different *** address these issues,we propose a two-stage,three-branch Transformer-based *** first stage incorporates multi-scale image feature extraction and hierarchical scale *** design enables the model to consider objects at various scales while enhancing the flow of information across different feature scales,improving the model’s generalization to diverse object *** second stage includes a global feature enhancement module and a region selection *** global feature enhancement module strengthens interconnections between different image regions,mitigating the issue of incomplete represen-tations,while the region selection module models the cross-modal relationships between image features and ***,these components enable the efficient acquisition of class-specific precise feature *** experiments on public datasets,including COCO2014,VOC2007,and VOC2012,demonstrate the effectiveness of our proposed *** approach achieves consistent performance gains of 0.3%,0.4%,and 0.2%over state-of-the-art methods on the three datasets,*** results validate the reliability and superiority of our approach for multi-label image classification.

关键词： Image classification multi-label multi scale attention mechanisms feature fusion

来源：评论

学校读者我要写书评

暂无评论

Modeling of Micropores Drilling Force for Printed Circuit Board Micro-holes Based on Energy Method

引用

Journal of Donghua University(English Edition) 2023年第5期40卷 525-530页

作者：郑小虎阮浩陈宏博刘骁佳刘正好 Institute of Artificial Intelligence Donghua UniversityShanghai 201620China Shanghai Industrial Big Data and Intelligent Systems Engineering Technology Center Shanghai 201620China College of Mechanical Engineering Donghua UniversityShanghai 201620China Shanghai Institute of Aerospace Precision Machinery Shanghai 201600China

The quality of printed circuit board(PCB)micro-hole processing directly determines the stability of the inner and outer circuit ***-hole drilling technology is a typical method for PCB micro-hole *** problem of optimal control of its drilling force is one of the main factors affecting the quality of micro-hole *** address this problem,the thrust forces and torques in PCB drilling were first modeled and analyzed,and the corresponding prediction models were *** drilling force analysis was carried out through the micro-hole drilling experiment,the specific cutting energy under different feed rates was calculated,the influence of the size effect was clarified,and the accuracy of the prediction model was *** result shows that during the drilling of glass fiber cloth,changes in the material removal mechanism are induced as the feed per revolution is *** the feed per revolution is less than the tool edge radius,the glass fiber is not cut by the main cutting edge,but is crushed and *** the feed per revolution is greater than the radius of the tool edge,the glass fiber is cut by the main cutting *** the same time,the established analytical model can accurately reflect the influence of the size effect on the drilling torque in PCB micro-hole drilling,and the error is within 10%.This method has certain practical application value in controlling PCB micro hole processing quality.

关键词： printed circuit board(PCB) micro-hole drilling predictive model size effect multi-layer material

来源：评论

学校读者我要写书评

暂无评论

ViGT: proposal-free video grounding with a learnable token in the transformer

引用

Science China(Information Sciences) 2023年第10期66卷 196-212页

作者： Kun LI Dan GUO Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province Institute of Artificial Intelligence Hefei Comprehensive National Science Center

The video grounding(VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in the complex interaction between video and query, overemphasizing cross-modal feature fusion and feature correlation for VG. In this paper, we propose a novel boundary regression paradigm that performs regression token learning in a transformer. Particularly, we present a simple but effective proposal-free framework, namely video grounding transformer(ViGT), which predicts the temporal boundary using a learnable regression token rather than multi-modal or cross-modal features. In ViGT, the benefits of a learnable token are manifested as follows.(1) The token is unrelated to the video or the query and avoids data bias toward the original video and query.(2) The token simultaneously performs global context aggregation from video and query ***, we employed a sharing feature encoder to project both video and query into a joint feature space before performing cross-modal co-attention(i.e., video-to-query attention and query-to-video attention) to highlight discriminative features in each modality. Furthermore, we concatenated a learnable regression token [REG] with the video and query features as the input of a vision-language transformer. Finally, we utilized the token [REG] to predict the target moment and visual features to constrain the foreground and background probabilities at each timestamp. The proposed ViGT performed well on three public datasets:ANet-Captions, TACoS, and YouCookⅡ. Extensive ablation studies and qualitative analysis further validated the interpretability of ViGT.

关键词： video grounding temporal sentence grounding boundary regression token learning proposal-free

来源：评论

学校读者我要写书评

暂无评论

Leverage Learning Behaviour data for Students' Learning Performance Prediction and Influence Factor Analysis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2422-2433页

作者： Ni, Qin Zhu, Yanjin Zhang, Lingying Lu, Xiaochen Zhang, Lei Shanghai International Studies University Key Laboratory of Multilingual Education with AI Shanghai201620 China Donghua University College of Information Science and Technology Shanghai201620 China Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China Shanghai Normal University Shanghai Engineering Research Center of Intelligent Education and Bigdata and Lab for Educational Big Data and Policymaking Shanghai200234 China

Online education has become increasingly significant for university students and faculty, especially in the context of the modern remote education landscape. However, the inherent space-time separation in online education can create communication delays between teachers and students, making it challenging to monitor students' behaviors effectively. In an effort to understand the connection between students' online engagement and their learning performance, data annotation has been implemented to address the issue of accurately representing students' learning behaviors. Taking the online teaching data of shanghai Normal University platform as the research object, the primary online education problem is explored through data mining, which includes correlation analysis, Gini importance ranking, and principal component analysis (PCA). Then, constructing the learning performance prediction model using random forest (RF) based on PCA by comparing various machine learning algorithms. As a consequence, the most influential online learning behaviors are course duration time, document learning time, test average score, and video completion rate. The overall classification accuracy of the learning performance prediction model is 87.45%, and the highest prediction accuracy for a single category is 96.52%. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Lightweight Human Pose Estimation Based on Multi-Attention Mechanism

引用

Journal of shanghai Jiaotong University (Science) 2024年 1-12页

作者： Lin, Xiao Lu, Meichen Gao, Mufeng Li, Yan Institute of Artificial Intelligence on Education Research College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai200234 China Shanghai Intelligent Education Big Data Engineering Technology Research Center Shanghai Normal University Shanghai200234 China Shanghai Online Education Research Base for Primary and Secondary Schools Shanghai200234 China School of Physical Education Shanghai Normal University Shanghai200234 China

Human pose estimation has received much attention from the research community because of its wide range of applications. However, current research for pose estimation is usually complex and computationally intensive, especially the feature loss problems in the feature fusion process. To address the above problems, we propose a lightweight human pose estimation network based on multi-attention mechanism (LMANet). In our method, network parameters can be significantly reduced by lightweighting the bottleneck blocks with depth-wise separable convolution on the high-resolution networks. After that, we also introduce a multi-attention mechanism to improve the model prediction accuracy, and the channel attention module is added in the initial stage of the network to enhance the local cross-channel information interaction. More importantly, we inject spatial cross-awareness module in the multi-scale feature fusion stage to reduce the spatial information loss during feature extraction. Extensive experiments on COCO2017 dataset and MPII dataset show that LMANet can guarantee a higher prediction accuracy with fewer network parameters and computational effort. Compared with the high-resolution network HRNet, the number of parameters and the computational complexity of the network are reduced by 67% and 73%, respectively. © 2023, shanghai Jiao Tong University.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Forecasting the yield of wafer by using improved genetic algorithm, high dimensional alternating feature selection and SVM with uneven distribution and high-dimensional data

引用

Autonomous intelligent systems 2022年第1期2卷 1-16页

作者： Xu, Qiuhao Xu, Chuqiao Wang, Junliang Institute of Artificial Intelligence Donghua University Shanghai201620 China College of Mechanical Engineering Donghua University Shanghai201620 China School of Mechanical Engineering Shanghai Jiaotong University Shanghai200240 China Shanghai Engineering Research Center of Industrial Big Data and Intelligent System Shanghai201512 China

Wafer yield prediction, as the basis of quality control, is dedicated to predicting quality indices of the wafer manufacturing process. In recent years, data-driven machine learning methods have received a lot of attention due to their accuracy, robustness, and convenience for the prediction of quality indices. However, the existing studies mainly focus on the model level to improve the accuracy of yield prediction does not consider the impact of data characteristics on yield prediction. To tackle the above issues, a novel wafer yield prediction method is proposed, in which the improved genetic algorithm (IGA) is an under-sampling method, which is used to solve the problem of data overlap between finished products and defective products caused by the similarity of manufacturing processes between finished products and defective products in the wafer manufacturing process, and the problem of data imbalance caused by too few defective samples, that is, the problem of uneven distribution of data. In addition, the high-dimensional alternating feature selection method (HAFS) is used to select key influencing processes, that is, key parameters to avoid overfitting in the prediction model caused by many input parameters. Finally, SVM is used to predict the yield. Furthermore, experiments are conducted on a public wafer yield prediction dataset collected from an actual wafer manufacturing system. IGA-HAFS-SVM achieves state-of-art results on this dataset, which confirms the effectiveness of IGA-HAFS-SVM. Additionally, on this dataset, the proposed method improves the AUC score, G-Mean and F1-score by 21.6%, 34.6% and 0.6% respectively compared with the conventional method. Moreover, the experimental results prove the influence of data characteristics on wafer yield prediction. © 2022, The Author(s).

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin-based Framework of Motion Control and State Monitoring for Pneumatic Muscle

引用

Recent Patents on Mechanical engineering 2023年第3期16卷 203-213页

作者： Xie, Shenglong Liu, Wenyuan Duan, Huiru Chen, Dijian Wan, Yanjian Key Laboratory of Intelligent Manufacturing Quality Big Data Tracking and Analysis of Zhejiang Province China Ji-liang University Zhejiang Hangzhou310018 China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Ma'anshan243032 China

Introduction: The current digital twin systems usually have the drawback of high cost and complex technology, and it is necessary to develop a simple solution to reduce the cost and cycle for the development of digital twin systems, especially for small projects or systems with simple structures. Objective: A low-cost patent technology of digital twin system was proposed by taking the motion control and state monitoring system (MCSMS) of pneumatic muscle as an example. Methods: The MCSMS is developed based on the browser/server architecture. The software of 3ds Max and SolidWorks are used to make the virtual model, *** and JavaScript are applied to build the browser side. data of the physical world is collected and processed on the server side firstly, and then is sent to the browser side through HTTP communication protocol to realize data interchange between the browser and server. Results: In the roaming experiment and the experiment of motion control and state monitoring of pneumatic muscle, the MCSMS can work smoothly without obvious delay and has good real-time performance, which can realize the 3D visual monitoring of the pneumatic muscle very well. Conclusion: The experimental results indicate that the proposed method possesses the ability of good feasibility and effectiveness. © 2023 Bentham Science Publishers.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

A Non-Parametric Scheme for Identifying data Characteristic Based on Curve Similarity Matching

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1424-1437页

作者： Quanbo Ge Yang Cheng Hong Li Ziyi Ye Yi Zhu Gang Yao School of Automation Nanjing University of Information Science&TechnologyJiangsu Provincial University Key Laboratory of Big Data Analysis and Intelligent SystemsNanjing University of Information Science&Technologyand the Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)Nanjing University of Information Science&TechnologyNanjing 210044China School of Department of Logistics Engineering Shanghai Maritime UniversityShanghai 201306China China Classification Society Nantong Office Nantong 226006China Chinese Flight Test Establishment Xi’an 710089China School of Mathematics Tsinghua UniversityBeijing 100084China School of Automation Nanjing University of Information Science&TechnologyNanjing 210044China Department of Logistics Engineering Shanghai Maritime UniversityShanghai 201306China IEEE

For accurately identifying the distribution charac-teristic of Gaussian-like noises in unmanned aerial vehicle(UAV)state estimation,this paper proposes a non-parametric scheme based on curve similarity *** the framework of the pro-posed scheme,a Parzen window(kernel density estimation,KDE)method on sliding window technology is applied for roughly esti-mating the sample probability density,a precise data probability density function(PDF)model is constructed with the least square method on K-fold cross validation,and the testing result based on evaluation method is obtained based on some data characteristic analyses of curve shape,abruptness and *** com-parison simulations with classical methods and UAV flight exper-iment shows that the proposed scheme has higher recognition accuracy than classical methods for some kinds of Gaussian-like data,which provides better reference for the design of Kalman filter(KF)in complex water environment.

关键词： Curve similarity matching Gaussian-like noise non-parametric scheme parzen window.

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：