检索结果-内蒙古大学图书馆

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Santosh, Kathari Kholmukhamedov, Timur Kumar, M. Sandeep Aarif, Mohd Muda, Iskandar Bala, B Kiran Cmr Institute of Technology Bengaluru Department of Mba Bengaluru India Turin Polytechnic University In Tashkent Automatic Control and Computer Engineering Department Tashkent Uzbekistan Publishing Global Research Network Noida India Universitas Sumatera Utara Medan Indonesia K.Ramakrishnan College of Engineering Department of Artificial Intelligence and Data Science Trichy India

ISBN: (纸本)9798350353068

In the realm of e-commerce customer support, the adoption of chatbots is on the rise, driven by a quest for heightened user interactions. This study introduces an inventive approach harnessing the advanced capabilities of GPT-4 to construct chatbot interfaces that are both context-aware and personalized. The main aim of this work is to revolutionize ecommerce customer support by developing intelligent and adaptable chatbot interfaces that are context-aware, personalized, and significantly enhance user experiences. Existing chatbot models struggle with context retention and personalization, limiting effectiveness in dynamic e-commerce environments despite the promise of automation. This innovative approach leverages GPT-4's robust language processing, integrating it with user profiling systems for personalized responses grounded in user preferences and historical interactions. The method gives, diverse e-commerce dataset undergoes collection and pre-processing, followed by fine-tuning GPT-4 with an emphasis on context-awareness and personalized responses. The model is seamlessly integrated with e-commerce backend systems for real-time information, multimodal input support caters to varied user preferences. Results exhibit a significant 95% accuracy improvement, affirming the chatbot's enhanced ability to comprehend user queries. By integrating personalization and advanced context retention, this study enhances user engagement, paving way for revolutionary intelligent and adaptable chatbot interfaces in ecommerce customer support. © 2024 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective 41

Rethinking Guidance Information to Utilize Unlabeled Samples...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yulong Yao, Yuan Chen, Shuhao Jin, Pengrong Zhang, Yu Jin, Jian Lu, Jiangang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China College of Control Science and Engineering Zhejiang University Hangzhou China Beijing Teleinfo Technology Company Ltd. China Academy of Information and Communications Technology Beijing China Research Institute of Industrial Internet of Things China Academy of Information and Communications Technology Beijing China

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples.A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their ***, EntMin emphasizes prediction discriminability while neglecting prediction *** alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled *** analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label *** by this finding, we propose a Label-Encoding Risk Minimization (LERM).It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label *** a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a ***, we analyze the relationships between LERM and ERM as well as ***, we verify the superiority of the LERM under several label insufficient *** codes are available at https://***/zhangyl660/LERM. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

ScCADE: A Superior Tool for Predicting Perturbation Responses in Single-Cell Gene Expression Using Contrastive Learning and Attention Mechanisms

ScCADE: A Superior Tool for Predicting Perturbation Response...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ou, Jingfeng Li, Jiawei Xia, Zhiliang Dai, Shurui Ding, Yulian Guo, Yan Jiang, Limin Tang, Jijun Southern University of Science and Technology College of Engineering Shenzhen518055 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Miami Department of Public Health Sciences MiamiFL33136 United States

ISBN: (纸本)9798350386226

The advent of single-cell transcriptomics has revolutionized our ability to analyze cellular heterogeneity and dynamics at a fine resolution, yet covering the vast array of potential perturbations remains challenging due to biological variability. To address this, we propose scCADE, a novel computational approach utilizing contrastive learning and an attention mechanism to decouple gene expression signatures and predict cellular responses to perturbations. scCADE excels in predicting responses in cells to perturbations observed in other cells but not yet seen in the target cells. Through rigorous ablation studies and validation across three datasets involving drug and gene editing perturbations, scCADE consistently outperformed existing methods, underscoring its efficacy and potential to advance genomics and personalized medicine by accurately forecasting responses to novel perturbations. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Spatial data intelligence and city metaverse: A review

引用

Fundamental Research 2025年第3期5卷 1169-1193页

作者： Meng, Xiaofeng Li, Yong Liu, Ke Liu, Yu Yang, Bin Song, Xuan Liao, Guoqiong Wang, Senzhang Yu, Ziqiang Chen, Longbiao Pan, Xiao Lin, Yuming School of Information Renmin University of China Beijing 100872 China Department of Electronic Engineering Tsinghua University Beijing 100084 China Department of Information Sciences National Natural Science Foundation of China Beijing 100085 China Institute of Remote Sensing and Geographic Information Systems School of Earth and Space Sciences Peking University Beijing 100871 China School of Data Science and Engineering East China Normal University Shanghai 200062 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen 518055 China School of Information Management Jiangxi University of Finance and Economics Nanchang 330013 China School of Computer Science and Engineering Central South University Changsha 410017 China School of Computer and Control Engineering Yantai University Yantai 264005 China Department of Computer Science Xiamen University Xiamen 361000 China College of Information Science and Technology Shijiazhuang Tiedao University Shijiazhuang 050043 China

Spatial Data Intelligence (SDI) encompasses acquiring, storing, analyzing, mining, and visualizing spatial data to gain insights into the physical world and uncover valuable knowledge. These understandings and knowledge play a crucial role in connecting physical and virtual realms, such as in developing a City Metaverse (CM) aimed at enhancing and optimizing modern urban environments. The advancement of CM holds immense potential to benefit urban dwellers, making research on SDI an increasingly prominent area of focus. This paper contributes significantly by organizing the relevant research and technologies within a coherent framework. Firstly, we identify SDI technologies capable of collecting real-world information to construct a virtual CM. Subsequently, we delve into the technologies that can be compositely integrated with SDI to facilitate interaction with and management of actual cities from the virtual perspective. Additionally, we emphasize the effectiveness and potential of these methods in practical applications. Lastly, we conclude our survey by discussing emerging challenges associated with technological progress, the industrial chain, legal and regulatory aspects, and ethical and moral considerations. © 2024

关键词： Application prospect City metaverse Smart city Spatial data intelligence Virtual-real interaction

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

arXiv

引用

arXiv 2024年

作者： Dong, Wei Zhang, Xing Chen, Bihui Yan, Dawei Lin, Zhijun Yan, Qingsen Wang, Peng Yang, Yang School of Computer Science and Engineering University of Electronic Science and Technology of China China College of information and control engineering Xi'an University of Architecture and Technology China School of Computer Science Northwestern Polytechnical University China

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pretrained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pretrained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at https://***/zstarN70/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

An Erasure-Coded Data Update Method for Distributed Storage Clusters

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2022年第11期59卷 2451-2466页

作者： Zhang, Zilin Liu, Duo Tan, Yujuan Wu, Yu Luo, Longpan Wang, Weilüe Qiao, Lei College of Computer Science Chongqing University Chongqing400044 China Beijing Institute of Control Engineering Beijing100080 China

Erasure coding is widely deployed in distributed storage clusters to provide data reliability, but the disk I/O overhead becomes a performance bottleneck when data updates are intensive. On the one hand, traditional data update strategies need to read the original data chunk, and then write new data when updating the data chunk. In the case of intensive updates, frequent write-after-read seriously affects the write performance of the storage clusters. On the other hand, the operations of updating the parity chunk include reading the increments randomly distributed in the log file and merging them with the data file, which also introduces additional disk seek overhead. In this paper, a data updating method, named PARD (parity logging with reserved space and data delta), is proposed to solve these problems. The main idea of PARD is to use the linear calculations of erasure coding to reduce write-after-read, and take advantage of the disk characteristics to reduce the disk seek overhead. PARD comprises three key design features: 1) Adopting in-place data updates and log-based parity updates. 2) Taking advantage of the linear calculations of erasure coding to construct the log based on data increments. For a series of write requests to the same data chunk, only the first update needs to read the original data chunk, and the subsequent update executes the pure write, which remarkably reduces the write-after-read. 3) According to the characteristics of disk, reserving space for the log at the end of data file to reduce the disk seek overhead of reading and writing log. Experiments show that when the chunk size is 4 MB, PARD gains at least, 30.4%, 47.0% and 82.0% improvements in update throughput compared with PLR, PARIX, and FO, respectively. © 2022, Science Press. All right reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A public data-set for synchronous motor electrical faults diagnosis with CNN and LSTM reference classifiers

引用

Energy and AI 2023年第4期14卷 221-237页

作者： Zhenglong Sun Ram Machlev Qianchao Wang Juri Belikov Yoash Levron Dmitry Baimel Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology Ministry of Education(Northeast Electric Power University)JilinChina The Andrew and Erna Viterbi Faculty of Electrical&Computer Engineering Technion-Israel Institute of TechnologyHaifa 3200003Israel Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing210096China Department of Software Science Tallinn University of TechnologyAkadeemia tee 15a12618 TallinnEstonia Department of Electrical and Electronics Engineering Sami Shamoon College of EngineeringBeer-Sheva84100Israel

In the last two decades,motor operation monitoring tools have become a necessity,and many studies focus on the detection and diagnosis of motor electrical ***,at present,a core obstacle that prevents the direct comparison of such classification techniques is the lack of a standard database that can be used as a *** view of this,we offer here a public experimental data-set that has beendesigned specifically for the comparison of synchronous motor electrical fault *** data-set comprises five types of motor electrical faults:open phase between inverter and motor;short circuit/leakage current between two phases;short circuit/leakage current in phase-to-neutral;rotor excitation voltage disconnection;and variation of rotor excitation *** addition,each fault has been recorded as a four-dimensional signal:three phase voltages;three phase currents;motor speed;and motor *** package includes two deep-learning reference classifiers that are based on a convolutional neural network(CNN)and long short term memory(LSTM).Due to the good performance of these classifiers,we suggest that they can be used by the community as benchmarks for the development of new and better motor electrical fault classification *** database and the reference classifiers are examined and insights regarding different combinations of features and lengths of recording points are *** developed code is available online,and is free to use.

关键词： Motor faults Synchronous motors Public data-set Classification Deep-learning CNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Distributed Bilevel Optimization via Adaptive Penalization with Time-Scale Separation

arXiv

引用

arXiv 2024年

作者： Niu, Youcheng Xu, Jinming Sun, Ying Chai, Li Chen, Jiming State Key Laboratory of Industrial Control Technology The College of Control Science and Engineering Zhejiang University Hangzhou310027 China School of Electrical Engineering and Computer Science Pennsylvania State University PA16802 United States

This paper studies a class of distributed bilevel optimization (DBO) problems with a coupled inner-level subproblem. Existing approaches typically rely on hypergradient estimations involving computationally expensive Hessian information. To address this, we propose an equivalent constrained reformulation by treating the inner-level subproblem as an inequality constraint, and introduce an adaptive penalty function to properly penalize both inequality and consensus constraints based on subproblem properties. Moreover, we propose a loopless distributed algorithm, AHEAD, that employs multiple-timescale updates to solve each subproblem asymptotically without requiring Hessian information. Theoretically, we establish convergence κ4 rates of O((1−ρ)2K1/3 ) for nonconvex-strongly-convex cases and κ2 O((1−ρ)2K2/3 ) for distributed min-max problems. Our analysis shows the clear dependence of convergence performance on bilevel heterogeneity, the adaptive penalty parameter, and network connectivity, with a weaker assumption on heterogeneity requiring only bounded first-order heterogeneity at the optimum. Numerical experiments validate our theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

High Efficiency Crypto-Watermarking System Based on Clifford-Multiwavelet for 3D Meshes Security

引用

computers, Materials & Continua 2022年第11期73卷 4329-4347页

作者： Wajdi Elhamzi Malika Jallouli Yassine Bouteraa Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Engineering and Sciences Higher School of Sciences and Technology of Hammam SousseUniversity of SousseSousse4011Tunisia LATIS Laboratory of Advanced Technology and Intelligent Systems University of SousseSousse4023Tunisie Control and Energy Management Laboratory(CEM Lab.) Ecole Nationale d Ingenieurs de Sfax(ENIS)Institut Superieur de Biotechnologie de Sfax(ISBS)University of SfaxSfax3038Tunisia

Since 3D mesh security has become intellectual property,3D watermarking algorithms have continued to appear to secure 3D meshes shared by remote users and saved in distant multimedia *** novelty of our approach is that it uses a new Clifford-multiwavelet transform to insert copyright data in a multiresolution domain,allowing us to greatly expand the size of the *** that,our method does two rounds of insertion,each applying a different type of Clifford-wavelet *** being placed into the Clifford-multiwavelet coefficients,the watermark,which is a mixture of the mesh description,source mesh signature(produced using SHA512),and a logo encrypted using the RSA(Ronald Shamir Adleman)technique,is encoded using *** the Least Significant Bit method steps,data embedding involves modulation and insertion ***,the watermarked mesh is reconstructed using the inverse Cliffordmultiwavelet *** to the utilization of a hybrid insertion domain,our technique has demonstrated a very high insertion rate while retaining mesh *** mesh is watermarked,and the extracted data is acquired in *** approach is also resistant to the most common types of *** findings reveal that the current approach improves on previous efforts.

关键词： Digital watermarking Clifford-multiwavelet transform Multiwavelet entropy LSB method RSA algorithm RSA algorithm Turbocode 3D multiresolution meshes

来源：评论

学校读者我要写书评

暂无评论

Traffic Pattern Classification in Smart Cities Using Deep Recurrent Neural Network

arXiv

引用

arXiv 2024年

作者： Ismaeel, Ayad Ghany Krishnadas, J. Manishankar, S. Natarajan, Yuvaraj Mahmood, Sarmad Nozad Alani, Sameer Shather, Akram H. Computer Technology Engineering College of Engineering Technology Al-Kitab University Kirkuk36001 Iraq Department of Computer Science and Engineering Sahrdaya College of Engineering and Technology Thrissur Kodakara680684 India Department of Computer Science and Engineering Sri Shakthi Institute of Engineering and Technology Coimbatore641062 India Electronic and Control Engineering Techniques Technical Engineering College Northern Technical University Kirkuk36001 Iraq Computer Center University of Anbar Ramadi55431 Iraq Department of Computer Engineering Technology Al-Kitab University Altun Kopru Kirkuk36001 Iraq

This paper examines the use of deep recurrent neural networks to classify traffic patterns in smart cities. We propose a novel approach to traffic pattern classification based on deep recurrent neural networks, which can effectively capture traffic patterns' dynamic and sequential features. The proposed model combines convolutional and recurrent layers to extract features from traffic pattern data and a SoftMax layer to classify traffic patterns. Experimental results show that the proposed model outperforms existing methods regarding accuracy, precision, recall, and F1 score. Furthermore, we provide an in-depth analysis of the results and discuss the implications of the proposed model for smart cities. The results show that the proposed model can accurately classify traffic patterns in smart cities with a precision of as high as 95%. The proposed model is evaluated on a real-world traffic pattern dataset and compared with existing classification methods. © 2024, CC BY-NC-ND.

关键词： Classification (of information)

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：