检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,861 篇 会议
868 篇 期刊文献
8 册 图书

馆藏范围

2,737 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,548 篇 工学
- 1,209 篇 计算机科学与技术...
- 1,034 篇 软件工程
- 332 篇 信息与通信工程
- 305 篇 控制科学与工程
- 233 篇 生物工程
- 184 篇 生物医学工程（可授...
- 169 篇 电气工程
- 148 篇 光学工程
- 101 篇 电子科学与技术（可...
- 93 篇 机械工程
- 88 篇 安全科学与工程
- 88 篇 网络空间安全
- 81 篇 化学工程与技术
- 76 篇 交通运输工程
- 66 篇 仪器科学与技术
872 篇 理学
- 454 篇 数学
- 268 篇 生物学
- 217 篇 物理学
- 186 篇 统计学（可授理学、...
- 105 篇 化学
- 78 篇 系统科学
485 篇 管理学
- 292 篇 管理科学与工程(可...
- 220 篇 图书情报与档案管...
- 139 篇 工商管理
189 篇 医学
- 149 篇 临床医学
- 145 篇 基础医学(可授医学...
- 110 篇 公共卫生与预防医...
- 81 篇 药学(可授医学、理...
78 篇 法学
- 67 篇 社会学
59 篇 经济学
- 59 篇 应用经济学
59 篇 农学
34 篇 教育学
16 篇 文学
3 篇 哲学
2 篇 历史学
2 篇 艺术学
1 篇 军事学

主题

233 篇 accuracy
169 篇 deep learning
133 篇 machine learning
130 篇 training
122 篇 real-time system...
102 篇 convolutional ne...
98 篇 feature extracti...
89 篇 predictive model...
79 篇 computational mo...
73 篇 support vector m...
68 篇 medical services
66 篇 machine learning...
64 篇 data models
59 篇 optimization
57 篇 internet of thin...
55 篇 semantics
54 篇 artificial intel...
49 篇 reliability
43 篇 image segmentati...
42 篇 reviews

机构

47 篇 college of compu...
40 篇 nitte meenakshi ...
39 篇 lamarr institute...
37 篇 department of ar...
32 篇 school of comput...
27 篇 lovely professio...
25 篇 engineering rese...
24 篇 department of co...
24 篇 division of arti...
23 篇 department of ar...
23 篇 key lab. of mach...
22 篇 center for machi...
21 篇 school of artifi...
20 篇 the lamarr insti...
20 篇 key laboratory o...
20 篇 machine learning...
19 篇 east west instit...
19 篇 department of co...
19 篇 school of comput...
19 篇 hubei provincial...

作者

38 篇 pareek piyush ku...
37 篇 piyush kumar par...
36 篇 prateek verma
36 篇 mohsen guizani
30 篇 lv jiancheng
27 篇 stachniss cyrill
24 篇 verma prateek
23 篇 behnke sven
23 篇 müller klaus-rob...
22 篇 li zengyang
22 篇 guizani mohsen
20 篇 liang peng
20 篇 zhang kun
19 篇 behley jens
18 篇 von lilienfeld o...
18 篇 wang liwei
17 篇 samek wojciech
17 篇 cyrill stachniss
16 篇 liu yang
16 篇 kersting kristia...

语言

2,029 篇 英文
704 篇 其他
9 篇 中文
1 篇 德文
1 篇 斯洛文尼亚文

检索条件"机构=Computer Science with Artificial Intelligence and Machine Learning"

共 2737 条记录，以下是461-470 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks 38

Rethinking the Membrane Dynamics and Optimization Objectives...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shen, Hangchi Zheng, Qian Wang, Huamin Pan, Gang College of Artificial Intelligence Southwest University China Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips China The State Key Lab of Brain-Machine Intelligence Zhejiang University China College of Computer Science and Technology Zhejiang University China

Despite spiking neural networks (SNNs) have demonstrated notable energy efficiency across various fields, the limited firing patterns of spiking neurons within fixed time steps restrict the expression of information, which impedes further improvement of SNN performance. In addition, current implementations of SNNs typically consider the firing rate or average membrane potential of the last layer as the output, lacking exploration of other possibilities. In this paper, we identify that the limited spike patterns of spiking neurons stem from the initial membrane potential (IMP), which is set to 0. By adjusting the IMP, the spiking neurons can generate additional firing patterns and pattern mappings. Furthermore, we find that in static tasks, the accuracy of SNNs at each time step increases as the membrane potential evolves from zero. This observation inspires us to propose a learnable IMP, which can accelerate the evolution of membrane potential and enables higher performance within a limited number of time steps. Additionally, we introduce the last time step (LTS) approach to accelerate convergence in static tasks, and we propose a label smooth temporal efficient training (TET) loss to mitigate the conflicts between optimization objective and regularization term in the vanilla TET. Our methods improve the accuracy by 4.05% on ImageNet compared to baseline and achieve state-of-the-art performance of 87.80% on CIFAR10-DVS and 87.86% on N-Caltech101. The code is available at https://***/StephenTaylor1998/IMP-SNN. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Aspect Sentiment Analysis with Triplet Extraction for E-Commerce

Aspect Sentiment Analysis with Triplet Extraction for E-Comm...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Meenakshi Sundaram A P Joyce Beryl Princess Division of Computer Science and Engineering Karunya Institute of Technology and Science Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Science Coimbatore India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

In the age of e-commerce, it is critical for companies to comprehend the thoughts and feelings of their customers in order to enhance their goods and services. A powerful method for deriving insights from consumer feedback is the combination of aspect sentiment analysis and triplet extraction. The objective of this method is to recognize the characteristics or facets of a good or service under discussion, gather feedback on each component, and create connections between the components, feedback, and viewpoints. Businesses can gain important insights into customer feelings towards certain features like design, usability, price, and customer service by examining customer reviews, comments, and ratings. Opinion sources (experts, customers, etc.), sentiment expressions (positive, negative, or neutral), and opinion targets (aspects) are all identified from the text as part of the triplet extraction process. This gives companies a comprehensive grasp of the thoughts and preferences of their customers, which helps them design products, set prices, and provide customer service with more focus and eventually increase customer happiness.

关键词： Sentiment analysis Reviews Customer services Face recognition Companies Feature extraction Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

Indian Sign Language Recognition Using Scale-Invariant Feature Transform by Depth Sensor 5

Indian Sign Language Recognition Using Scale-Invariant Featu...

引用

5th IEEE International Conference on Cybernetics, Cognition and machine learning Applications, ICCCMLA 2023

作者： Gangrade, Jayesh Gangrade, Shweta Mishra, Ashish Kumar, Gautam Gunjan, Vinit Kumar Manipal University Jaipur Dept. of Artificial Intelligence & Machine Learning Jaipur India Manipal University Jaipur Dept of Information Technology Jaipur India Jaypee Institute of Information Technology Dept of Computer Science & Engineering Noida India CMR Institute of Technology Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350338287

Deaf and hard of hearing people in the Indian community now have a way to communicate with society because to Indian Sign Language (ISL). The hand is accorded significant importance in the framework of the ISL. ISL is composed of both static and dynamic sign hand gestures. Both static and dynamic signs are made up of three components: hand movement, hand orientation, and hand position. The proposed method can recognize static ISL signs. The technique that was suggested makes use of the Microsoft Kinect sensor to locate and separate a hand from its background in a complex scene. SIFT, which stands for 'scale-invariant feature transform,' was used to extract the feature. The SIFT algorithm is invariant under changes in perspective, orientation, and lighting. Recognize the 10 ISL digit movements with an accuracy of 94.9% using a multi support vector machine (MSVM). © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Digital Evidence Management: Modern Techniques in Digital Forensics 3

Digital Evidence Management: Modern Techniques in Digital Fo...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Venkataramanan, N. Jayalakshmi, V. Anitha, S. Ganesan, R. Jenifer, V. Drbccc Hindu College Department of Computer Applications Pattabiram Chennai600072 India Department of Computer Science and Applications Ramapuram600089 India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai600119 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai600062 India Department of Computer Science and Applications Ramapuram Campus 600089 India

ISBN: (纸本)9798331509675

This research study reviews the significance of digital forensic analysis in modern criminal investigations, highlighting the way it complements conventional methods of inquiry and the difficulties it encounters in the information era. To solve crimes effectively, investigators must combine digital knowledge with traditional forensic techniques. This will enable them to use evidence from many different types of digital and physical sources. The specific intricacies of digital crime scenes need specialized methods for the proper storage and analysis of digital evidence to identify criminal intent and patterns of conduct. To propose Modern Techniques for Digital Evidence Management [MT-DEM] based Digital Forensics Service. Multidisciplinary teams and cutting-edge technology are becoming necessities in digital forensic investigation as the field adjusts to new threats like data encryption and massive amounts of data. The admissibility of evidence in the legal world depends on digital forensic procedures being transparent and adhering to set criteria. Digital forensic analysis has become an indispensable tool for contemporary investigators with the rise of digital evidence. © 2025 IEEE.

关键词： Forensic science

来源：评论

学校读者我要写书评

暂无评论

An Effective Method for Distributing Workloads in Smart City using Sensor Networks Enabled by Fog

An Effective Method for Distributing Workloads in Smart City...

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Nithiyanandam Velvizhi, R. Priyadharshini, S.P. Poongavanam, N. SRM Institute of Science and Technology Kattankulathur Campus Department of Computing Technologies Chengalpattu Kattankulathur India Sathyabama Institute of Science and Technology OMR Department of Computer Science and Engineering Chennai India St' Joseph College of Engineering OMR Department of Artificial Intelligence and Machine Learning Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331522988

By linking sensor nodes to fog nodes in critical locations, the Distributing Workloads in Fog Enabled Smart City (DW-FESC) technique efficiently handles the problem of distribution of workloads in smart cities. To get over the processing limits of IoT devices, this setup makes sure that complicated tasks are sent off to neighbouring fog nodes. The plan uses a load balancer and an updated greedy algorithm to evenly distribute work, which speeds up execution and keeps loads from becoming too heavy. Additionally, it has a deadline-based task execution mechanism that makes sure the most important jobs are done on time. The simulation results show that DW-FESC keeps the variance from the mean execution times to a minimum while considerably improving task execution times in comparison to other methods. With the use of fog computing, DW-FESC improves the dependability, efficiency, and responsiveness of smart city applications, leading to greener city life. © 2024 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation System Using Hybrid Based Method

Movie Recommendation System Using Hybrid Based Method

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Khushi Kamble Pradnyanand Bhadarge Shreejit Bhakte Omkaresh Kulkarni Rutuja Kadam Latika Pinjarkar Computer Science and Engineering - Artificial Intelligence and Machine Learning Department Vishwakarma Institute of Information Technology Pune India Department of CSE (Artificial Intelligence and Machine Learning) Vishwakarma Institute of Information Technology Pune Maharashtra Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

The rise of digital platforms has increased user engagement and satisfaction through personalized recommendation systems. The research paper presents a hybrid approach to movie recommendation, which uses content-based filtering and collaborative filtering techniques to mitigate the cold start problem, data sparsity, and scalability issues. The proposed system will utilize methodologies from machine learning, such as cosine similarity and vectorization, and the K-Nearest Neighbors (KNN) algorithm, for recommending movies based on their precise and personalized values. The dataset TMDB5000 will then be used for two datasets involving movie features, cast, and crew information while preprocessing techniques in cleaning, feature extraction, and merging are undertaken to ensure robust foundation for the model building. The hybrid model uses the bag-of-words technique to vectorize and compute cosine similarity to determine movies' relationships in a multidimensional space. The KNN algorithm then refines the collaborative filtering process by the clustering of user preferences and makes recommendations using nearest-neighbor analysis. Our current approach overcomes these weaknesses by combining both content-based and collaborative methods, resulting in a system which handles diverse user preferences while maintaining high recommendation accuracy. As the evaluation of precision, recall, F1-score, and mean squared errors further validates that this system performance is good and also scalable and efficient for processing large datasets for which it explains some practical aspects related to implementation in real time. The future work includes deep learning models like neural collaborative filtering to further improve semantic understanding and recommendation accuracy. This paper addresses the current system's limitations by proposing a novel, efficient, and user-centric hybrid approach, which can be extended to other domains, such as e-commerce, music, and book recommendati

关键词： Deep learning Accuracy Filtering Collaborative filtering Scalability Semantics Nearest neighbor methods Motion pictures Real-time systems Recommender systems

来源：评论

学校读者我要写书评

暂无评论

MediGlove: Integrating IoT and machine learning for Personalized Remote Health Care 2

MediGlove: Integrating IoT and Machine Learning for Personal...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Nanda, K.V. Keerthan Kumar, T.G. Achyutha Prasad, N. Raviprakash, M.L. Anand Babu, J. Naveen Kumar, M.R. Sri Siddhartha Institute Of Technology Master Of Computer Applications Tumkur India Siddaganga Institute Of Technology Information Science And Engineering Tumkur India East West Institute Of Technology Computer Science And Engineering Bangalore India Kalpataru Institute Of Technology Artificial Intelligence And Machine Learning Tiptur India Malnad College Of Engineering Information Science And Engineering Hassan India Vidyavardhaka College Of Engineering Information Science And Engineering Mysore India

ISBN: (纸本)9798350381665

Mobile operating systems have advanced significantly in recent decades, with Android emerging as a widely used open-source platform. Simultaneously, the Internet of Things (IoT) has transformed computer equipment by enabling seamless data transfer over networks without human involvement. This study makes use of intelligent gloves equipped with various sensors, as well as IoT and Android applications, to improve healthcare. In this work, we introduce a pioneering framework that combines IoT and Android technology to revolutionize remote health monitoring called IoT-enabled Smart Gloves for Remote Health Monitoring using an Android-based solution approach (MediGlove). MediGlove uses intelligent smart gloves with robust sensors to continuously collect crucial health data. The solution works with IoT devices to send data quickly to a cloud-based server. The cloud server provides real-time health metric analysis with great precision by utilizing cutting-edge algorithms and machine learning techniques. A simple Android software acts as a dynamic health dashboard, allowing users to track their health in real-time. The framework generates real-time alerts for problematic health markers, allowing prompt medical action. Extensive testing validates the system's efficacy and dependability in health monitoring and the seamless integration of smart gloves with Android applications. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Vortex Search Optimizer based Hybrid Watermarking Scheme for Securing the Medical Images 3

Vortex Search Optimizer based Hybrid Watermarking Scheme for...

引用

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Murthy, G N Keshava Nalini, B.M. Madhura, G.K. Nayana, S.N. Siddaganga Institute of Technology Department of Electronics and Instrumentation Engineering Karnataka Tumakuru India East West Institute of Technology Department of Computer Science and Engineering Bengaluru560091 India Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350340358

Preventing the duplication, modification, and claim of unauthorised ownership of digital content is one of the major issues caused by the growing use of computer capabilities. Watermarking is one way to put a visible or invisible watermark on a digital document in order to later show that the document is legitimate or belongs to its owner. concentrating on security issues in the storage and broadcast of images in the medical info scheme, as well as the special requirements for medical images for the protection of lesion regions. In this study, a hybrid watermarking strategy was presented utilising the Slantlet transform, randomised singular value decomposition, and optimisation methods (Vortex Search algorithm (VSA)) that are modelled after natural processes. The XOR encryption method is used to encrypt the watermark image. Extensive testing demonstrates that our novel approach works better than the current approaches based on the NC, SSIM, and PSNR. The PSNR of the suggested technique is between 58 and 59 dB, suggesting increased performance, and at a scale factor of 0.06, the SSIM and NC standards of the watermarked picture and the extracted watermark are nearly equal to. The recommended method outperforms past studies in the field in terms of usability, robustness, security, and invisibility, as well as its ability to repel local nonlinear geometric attacks. © 2023 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

CAUSAL BALANCING FOR DOMAIN GENERALIZATION 11

CAUSAL BALANCING FOR DOMAIN GENERALIZATION

引用

11th International Conference on learning Representations, ICLR 2023

作者： Wang, Xinyi Saxon, Michael Li, Jiachen Zhang, Hongyang Zhang, Kun Wang, William Yang Department of Computer Science University of California Santa Barbara United States David R. Cheriton School of Computer Science University of Waterloo Canada Department of Philosophy Carnegie Mellon University United States Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

While machine learning models rapidly advance the state-of-the-art on various real-world tasks, out-of-domain (OOD) generalization remains a challenging problem given the vulnerability of these models to spurious correlations. We propose a balanced mini-batch sampling strategy to transform a biased data distribution into a spurious-free balanced distribution, based on the invariance of the underlying causal mechanisms for the data generation process. We argue that the Bayes optimal classifiers trained on such balanced distribution are minimax optimal across a diverse enough environment space. We also provide an identifiability guarantee of the latent variable model of the proposed data generation process, when utilizing enough train environments. Experiments are conducted on DomainBed, demonstrating empirically that our method obtains the best performance across 20 baselines reported on the benchmark. © 2023 11th International Conference on learning Representations, ICLR 2023. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

learning Discrete Latent Variable Structures with Tensor Rank Conditions 38

Learning Discrete Latent Variable Structures with Tensor Ran...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Zhengming Cai, Ruichu Xie, Feng Qiao, Jie Wu, Anpeng Li, Zijian Hao, Zhifeng Zhang, Kun School of Computer Science Guangdong University of Technology China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Department of Applied Statistics Beijing Technology and Business University China Department of Computer Science and Technology Zhejiang University China College of Science Shantou University Guangdong Shantou China Department of Philosophy Carnegie Mellon University United States

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or impose strict constraints on latent structures, which fail to address cases in discrete data involving non-linear relationships or complex latent structures. To achieve this, we explore a tensor rank condition on contingency tables for an observed variable set Xp, showing that the rank is determined by the minimum support of a specific conditional set (not necessary in Xp) that d-separates all variables in Xp. By this, one can locate the latent variable through probing the rank on different observed variables set, and further identify the latent causal structure under some structure assumptions. We present the corresponding identification algorithm and conduct simulated experiments to verify the effectiveness of our method. Our results elegantly expand the application scope of causal discovery with latent variables. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共274页 << < 43 44 45 46 47 48 49 50 51 52 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：