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

817 篇 会议
301 篇 期刊文献
13 册 图书

馆藏范围

1,131 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

595 篇 工学
- 465 篇 计算机科学与技术...
- 393 篇 软件工程
- 161 篇 信息与通信工程
- 100 篇 生物工程
- 83 篇 控制科学与工程
- 61 篇 生物医学工程（可授...
- 60 篇 光学工程
- 54 篇 电气工程
- 42 篇 电子科学与技术（可...
- 31 篇 网络空间安全
- 30 篇 安全科学与工程
- 26 篇 交通运输工程
- 25 篇 动力工程及工程热...
- 24 篇 机械工程
- 21 篇 建筑学
- 18 篇 土木工程
322 篇 理学
- 167 篇 数学
- 106 篇 生物学
- 84 篇 物理学
- 70 篇 统计学（可授理学、...
- 27 篇 系统科学
181 篇 管理学
- 103 篇 图书情报与档案管...
- 90 篇 管理科学与工程(可...
- 59 篇 工商管理
66 篇 医学
- 51 篇 临床医学
- 50 篇 基础医学(可授医学...
- 36 篇 公共卫生与预防医...
- 32 篇 药学(可授医学、理...
38 篇 法学
- 33 篇 社会学
22 篇 经济学
- 22 篇 应用经济学
13 篇 农学
6 篇 教育学
6 篇 文学
2 篇 军事学

主题

92 篇 accuracy
54 篇 computational mo...
54 篇 real-time system...
51 篇 machine learning
43 篇 deep learning
36 篇 training
31 篇 predictive model...
31 篇 feature extracti...
30 篇 machine learning...
29 篇 artificial intel...
27 篇 analytical model...
27 篇 data models
27 篇 convolutional ne...
21 篇 reliability
21 篇 security
21 篇 technological in...
20 篇 support vector m...
20 篇 visualization
19 篇 forecasting
18 篇 adaptation model...

机构

13 篇 center for data ...
13 篇 dept. of linguis...
11 篇 dept. of compute...
11 篇 computer science...
11 篇 dept. of compute...
10 篇 smart data & kno...
8 篇 center for data ...
8 篇 school of data s...
7 篇 dept. of compute...
7 篇 center for data ...
7 篇 deepwise ai lab
6 篇 kalinga universi...
6 篇 fraunhofer insti...
6 篇 data science and...
6 篇 dept. of compute...
6 篇 dept. of compute...
5 篇 university of th...
5 篇 artificial intel...
5 篇 graphic era hill...
5 篇 dept. of informa...

作者

21 篇 bowman samuel r.
13 篇 ashwini kodipall...
13 篇 günnemann stepha...
12 篇 dengel andreas
12 篇 schröder markus
12 篇 jilek christian
11 篇 kodipalli ashwin...
10 篇 ravindran balara...
7 篇 phang jason
7 篇 htut phu mon
7 篇 deepak upadhyay
7 篇 nookala venu
7 篇 wang yizhou
6 篇 shoeibi afshin
6 篇 vijayan priyesh
6 篇 seth pratinav
6 篇 farnadi golnoosh
6 篇 rao trupthi
6 篇 alizadehsani roo...
6 篇 yuyun

语言

916 篇 英文
213 篇 其他
1 篇 朝鲜文
1 篇 中文

检索条件"机构=Dept. of Computer and Data Science"

共 1131 条记录，以下是181-190 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：

Third Generation Security System for Face Detection in ATM Machine Using computer Vision 1

Third Generation Security System for Face Detection in ATM M...

引用

1st International Conference on computer, Power and Communications, ICCPC 2022

作者： Sridevi, S. Monica, K.M. Senthil, G.A. Prabha, R. Sathya, A. Ramya, J. Sri Ramachandra Engineering and Technology Dept. of Computer Science and Engineering Chennai India Vit Chennai Campus Dept. of Computer Science and Engineering Chennai India Agni College of Technology Dept. of Information Technology Chennai India Sri Sai Ram Institute of Technology Dept. of Electronics and Communication Engineering Chennai India Sri Sai Ram Institute of Technology Dept. of Artificial Intelligence and Data Science Chennai India Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397840

A workflow is proposed for the detection of unauthorized persons in an ATM. Certain assumptions, including the context of identification are made by training their features and storing the datasets. However, not every individual will be a suspect. Suspicious activity on ATMs that are located in remote areas and to reduce the risk of fraudulent transactions. such as using another person's card to withdraw money etc., Various video survey and image processing have been discussed in relation to surveillance methods. It discusses the various processes, preprocessing, classification, feature extraction and the corresponding video processing methods. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Grey Wolf Optimizer and Deep Neural Network based Feature Selection and Classification in Medical Image Analysis 18

Grey Wolf Optimizer and Deep Neural Network based Feature Se...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Chandrashekhar, Katha Leela, P. Madhavi, K. Reddy Avanija, J. Tangudu, Naresh Indur Institute of Engineering and Technology Computer Science and Engineering Siddipet India Mohan Babu University School of Computing Dept. of Data Science Tirupati India Mohan Babu University School of Computing Tirupati India Aditya Institute of Technology and Management Tekkali India

ISBN: (纸本)9789380544519

Accurate and efficient medical image analysis is required for modern healthcare applications, facilitating timely disease diagnosis and treatment. Considering the importance of optimization algorithms and deep learning methodologies, this work presents a novel approach, Grey Wolf Optimizer-Assisted Deep Neural Networks (GWO-DNN), for feature selection and classification in medical image analysis. The proposed framework utilizes the power of the Grey Wolf Optimizer to intelligently select the most relevant features from complex medical images. The selected features are then integrated into Deep Neural Networks, to create accurate models for medical image classification tasks. This integrated approach is designed to improve diagnostic accuracy and enhance patient care. The experimentation and evaluation, reveal that the proposed GWO-DNN based model for image analysis is more efficient than the existing methods. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Deep Neural Networks (DNN) Disease Classification Feature Selection Grey Wolf Optimization (GWO) Medical Image Analysis

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Smart Lighting System using Yolov8 and ESP32

Self-Adaptive Smart Lighting System using Yolov8 and ESP32

引用

International Conference on Electrical Energy Systems (ICEES)

作者： Virum Ranka Dwisha Shah Devam Shah Pradnya Saval Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350353778

ISBN: (纸本)9798350353785

In the pursuit of sustainable living and enhanced user comfort, the integration of smart technologies into everyday devices has become paramount. This paper highlights the importance of dynamic lighting control in improving energy efficiency and the overall quality of life. Traditional lighting systems often fail to account for the dynamic nature of human activities, resulting in unnecessary energy wastage and suboptimal lighting conditions. The proposed system seeks to bridge the gap between existing lighting systems and the evolving needs of modern indoor spaces, with its focus on adaptability, efficiency, and user-centricity, promoting a more comfortable and nurturing environment. Although earlier studies have explored various aspects of smart lighting technologies, there remains a paucity of comprehensive solutions that integrate machine learning with sensor technologies to create truly adaptive environments. Novel algorithms have been utilized to optimize both visual comfort and energy efficiency. This system achieves up to 45-70% energy savings compared to existing lighting systems, making it a promising solution for both environmental and economic concerns.

关键词： Visualization Machine learning algorithms Energy conservation Smart homes Activity recognition Energy efficiency Real-time systems Trajectory Sensors Smart lighting

来源：评论

学校读者我要写书评

暂无评论

Detecting Feet's Bending Patterns With Smart Insoles

Detecting Feet's Bending Patterns With Smart Insoles

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Yuchen Zhong Qijun Ying Xiaohui Cai dept. of Computer Science and Technology University of Science and Technology of China (USTC) Hefei China dept. of Data Science University of Science and Technology of China (USTC) Hefei China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

Foot bending is a basic component of walking. Although bending is important for foot-ground interaction and ensures the speed and balance of the whole walking cycle, there is still no practical method for recording and analyzing foot bending under everyday scenarios. In this study we propose to use a smart insole, with two embedded Inertial Measurement Units, to acquire the movements of the fore-foot and the hind-foot and deduce the bending, represented by the bending point's position. We use the deep learning approach to estimate the bending position and its changes during different walking patterns. On the dataset containing 8 test subjects and 6 walking patterns, our method can achieve an overall mean absolute error accuracy of 2.58 cm. The smart insole can be with the subject all the day, bring in a new method for continuous foot bending monitoring.

关键词： Legged locomotion Measurement units Three-dimensional displays Machine learning algorithms Measurement uncertainty Inertial navigation Bending Recording Monitoring Foot

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Classical and Quantum Algorithms for Portfolio Optimization: Enhancing Financial Decision-Making Through Quantum Computing

Empirical Analysis of Classical and Quantum Algorithms for P...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Krish Valecha Anuradha Yeole Atharv Salian Shruti Mathur Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

This research investigates the efficacy of quantum and classical algorithms in the context of portfolio optimization, focusing on a dataset comprising 20 equities from India's National Stock Exchange over a duration of three years. The study employs quantum methodologies such as the Quantum Approxi-mate Optimization Algorithm (QAOA), the Variational Quantum Eigensolver (VQE), and the Exact Minimum Eigen Solver, alongside conventional strategies including Mean-Variance Op-timization, Genetic Algorithms, and Simulated Annealing. The methodology for this study includes data preprocessing, issue designing, and performance evaluation based on metrics such as MSE, RMSE, and Mean Absolute Error. The results obtained show quantum algorithms exhibit better performance over the classical methods regarding prediction accuracy and risk-return profiles, especially the Exact Minimum Eigen hSolver and QAOA. The Exact Minimum Eigen Solver and QAOA had the lowest MSE values (0.006 and 0.005, respectively), whereas the best-performing classical technique, the Genetic Algorithm, had an MSE of 0.0105. These findings imply that quantum algorithms provide significant advantages in portfolio optimization problems, with the potential to revolutionize financial optimization tactics. The research can be further unfolded into avenues for future inquiry, including expansion of the choice of assets, alternative data sources integration, as well as hybrid quantum-classical models to efficiently enhance portfolio management strategies.

关键词： Quantum algorithm Accuracy Soft sensors Simulated annealing Transforms Prediction algorithms Stock markets Optimization Portfolios Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Directed Adversarial Training for Comprehensive Robustification of CNNs

Directed Adversarial Training for Comprehensive Robustificat...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Bhuvi Ghosh Harsh Shetye Atharv Salian Nilesh Marathe Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Deep convolutional neural networks (CNNs), renowned for their high accuracy on clean datasets, remain notably vulnerable to adversarial attacks. This study assesses how the VGG16 and ResNet50 models withstand various white-box attacks when used for traffic sign classification. Despite their impressive standard accuracy, our findings reveal that these accuracies do not predict robustness against attacks. Techniques such as the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) substantially lowered model accuracy, while DeepFool and Carlini & Wagner (C&W) attacks were even more disruptive. In particular, ResNet50 was more prone to these attacks, with its accuracy dropping to as low as $\mathbf{1 2. 8 5 \%}$ under DeepFool and $\mathbf{1 7. 4 2 \%}$ under C&W at specific confidence levels. Retraining models with adversarial examples did enhance their resilience to certain attacks but at the expense of reduced effectiveness on clean data. These results highlight the critical need for developing more robust defense mechanisms that protect CNNs against a wide array of adversarial threats without compromising performance on standard inputs.

关键词： Training Accuracy Noise Robustness data models Iterative methods Standards Residual neural networks Glass box Resilience

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Hybrid Quantum-Classical Convolutional Neural Networks for Audio Classification

Performance Analysis of Hybrid Quantum-Classical Convolution...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Yash Thakar Bhuvi Ghosh Vishma Adeshra Kriti Srivastava Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Audio signals being high-dimensional and complex pose challenges for classical machine learning techniques in terms of computation and generalization on real-world data. This paper evaluates the use of hybrid quantum-classical convolutional neural networks (QC-CNN) that leverage quantum effects like superposition and entanglement for audio classification using mel-spectrograms obtained from audio data. Evaluated on both small-sized and large-sized datasets, the proposed QC-CNN model gave comparable training accuracy with classical CNN (Convolutional Neural Network) on the smaller dataset but outperformed classical CNN on test accuracy ($\mathbf{95.04 \%}$ vs $\mathbf{92.88 \%}$) for a larger birdsong dataset and reduced overfitting, thus highlighting the potential advantages of QC-CNNs for audio data. The QC-CNN exhibited higher cross-entropy loss in case of the small-sized dataset which was further significantly reduced when evaluated on the large-sized birdsong dataset. The work demonstrates the application of QC-CNN for audio classification.

关键词： Training Accuracy Quantum computing Quantum entanglement Neural networks computer architecture data models Performance analysis Convolutional neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Dynamic Parameter for Video Inpainting Transformer

Semantic-Aware Dynamic Parameter for Video Inpainting Transf...

引用

International Conference on computer Vision (ICCV)

作者： Eunhye Lee Jinsu Yoo Yunjeong Yang Sungyong Baik Tae Hyun Kim Dept. of Computer Science Hanyang University Dept. of Artificial Intelligence Hanyang University Dept. of Data Science Hanyang University

Recent learning-based video inpainting approaches have achieved considerable progress. However, they still cannot fully utilize semantic information within the video frames and predict improper scene layout, failing to restore clear object boundaries for mixed scenes. To mitigate this problem, we introduce a new transformer-based video inpainting technique that can exploit semantic information within the input and considerably improve reconstruction quality. In this study, we use the mixture-of-experts scheme and train multiple experts to handle mixed scenes, including various semantics. We leverage these multiple experts and produce locally (token-wise) different network parameters to achieve semantic-aware inpainting results. Extensive experiments on YouTube-VOS and DAVIS benchmark datasets demonstrate that, compared with existing conventional video inpainting approaches, the proposed method has superior performance in synthesizing visually pleasing videos with much clearer semantic structures and textures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Opportunistic Balancing and Strategic Insights through Deep Reinforcement Learning in Asset Allocation

Opportunistic Balancing and Strategic Insights through Deep ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Harsh Shetye Vaidehi Shah Jay Chotalia Pradnya Saval Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Asset allocation, diversification of investments across various asset classes, presents significant challenges in accurately forecasting expected returns and adapting to dynamic market conditions. This research explores a novel approach, “Opportunistic Balancing and Strategic Insights through Deep Reinforcement Learning in Asset Allocation,” by leveraging Deep Reinforcement Learning (DRL) to optimize dynamic asset allocation strategies. Specifically, we investigate the Advantage Actor-Critic (A2C) Model, renowned for its stability and superior performance with large batch sizes. Our approach aims to capture short to medium-term market trends and anomalies, enabling strategic asset allocation to enhance risk-adjusted returns. We evaluate the DRL models’ performance against traditional benchmarks, including the portfolio index, the naive equal-weight allocation, and the maximum Sharpe strategy (mean-variance optimization). The DRL models exhibit relatively superior performance compared to the mean-variance portfolio during periods preceding 2020, with the A2C model outperforming the benchmark DJIA index across all considered market conditions. Notably, the A2C model demonstrated a Sharpe ratio of 0.733, surpassing the DJIA index’s Sharpe ratio of 0.406. Additionally, during the 2020 market downturn, the A2C model exhibited a faster recovery rate than the benchmark index, regaining positive returns swiftly.

关键词： Analytical models Uncertainty Stability criteria Benchmark testing Deep reinforcement learning Dynamic scheduling Resource management Indexes Portfolios Optimization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Injury Risk Assessment in Athletes Based on Relative Joint Angles

Real-Time Injury Risk Assessment in Athletes Based on Relati...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Atharv Salian Bhuvi Ghosh Harsh Shetye Parth Kapadia Kriti Srivastava Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India

Preventing running injuries is critical for track and field athletes. This work presents a novel machine learning methodology to automatically detect injury risk from videos by analyzing biomechanical technique. Joint angles from anatomical pose estimates serve as descriptive features input to ML classifiers. Statistical tests verified significant distribution differences in angles between injured and non-injured states, evidencing utility as injury markers. Multi-frame analysis integrating temporal context attained 0.735 accuracy on held-out test data using SVM, surpassing single-frame approaches. The scoring function showed no significant statistical drift from training to test, providing evidence of strong generalization. By automating nuanced pose pattern quantification imperceptible to the naked eye, the proposed video screening enables early at-risk athlete identification for targeted preventative intervention before injuries develop.

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114页 << < 15 16 17 18 19 20 21 22 23 24 > >>

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：