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

6,378 篇 会议
161 册 图书
46 篇 期刊文献

馆藏范围

6,585 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,749 篇 工学
- 4,176 篇 计算机科学与技术...
- 3,369 篇 软件工程
- 1,157 篇 信息与通信工程
- 762 篇 生物工程
- 563 篇 生物医学工程（可授...
- 497 篇 控制科学与工程
- 420 篇 电气工程
- 326 篇 动力工程及工程热...
- 267 篇 机械工程
- 254 篇 光学工程
- 251 篇 电子科学与技术（可...
- 240 篇 安全科学与工程
- 219 篇 化学工程与技术
- 214 篇 环境科学与工程（可...
2,076 篇 理学
- 942 篇 数学
- 830 篇 生物学
- 413 篇 物理学
- 399 篇 统计学（可授理学、...
- 278 篇 系统科学
- 222 篇 化学
1,415 篇 管理学
- 784 篇 管理科学与工程(可...
- 774 篇 图书情报与档案管...
- 514 篇 工商管理
615 篇 医学
- 580 篇 临床医学
- 555 篇 基础医学(可授医学...
- 331 篇 药学(可授医学、理...
- 302 篇 公共卫生与预防医...
359 篇 法学
- 266 篇 社会学
208 篇 农学
- 199 篇 作物学
197 篇 经济学
- 196 篇 应用经济学
132 篇 教育学
23 篇 军事学
13 篇 文学

主题

278 篇 internet of thin...
262 篇 machine learning
253 篇 cloud computing
230 篇 big data
219 篇 computational mo...
207 篇 deep learning
182 篇 data mining
157 篇 data models
137 篇 predictive model...
135 篇 artificial intel...
133 篇 training
130 篇 feature extracti...
122 篇 real-time system...
119 篇 blockchain
108 篇 support vector m...
107 篇 accuracy
107 篇 machine learning...
102 篇 convolutional ne...
100 篇 forecasting
96 篇 medical services

机构

54 篇 graphic era deem...
44 篇 chitkara univers...
24 篇 department of co...
24 篇 department of co...
21 篇 department of en...
19 篇 school of comput...
19 篇 teerthanker maha...
18 篇 school of inform...
17 篇 jaipur national ...
16 篇 university of ch...
16 篇 uttaranchal inst...
15 篇 fujian provincia...
14 篇 srm institute of...
14 篇 department of co...
14 篇 uttaranchal inst...
13 篇 computer science...
13 篇 school of comput...
11 篇 uttaranchal inst...
10 篇 college of compu...
10 篇 school of manage...

作者

21 篇 pant bhasker
20 篇 chang kuo-chi
13 篇 tripathi vikas
12 篇 kukreja vinay
12 篇 vinay kukreja
11 篇 jacob lija
11 篇 joshi kapil
11 篇 gangodkar durgap...
10 篇 iwendi celestine
10 篇 lourens melanie
10 篇 chu kai-chun
10 篇 sujithra m.
10 篇 alanya-beltran j...
9 篇 rajeswari d.
9 篇 chang fu-hsiang
9 篇 singh rajesh
8 篇 kapil joshi
8 篇 kapila dhiraj
8 篇 pavithra g.
8 篇 sanjay misra

语言

6,395 篇 英文
184 篇 其他
15 篇 中文

检索条件"任意字段=International Conference on Advances in Data Science and Computing Technologies, ASDC 2022"

共 6585 条记录，以下是81-90 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：

Adversarial Artifact Removal: A GAN-Based Framework for Enhanced Image Quality and Reliability 5

Adversarial Artifact Removal: A GAN-Based Framework for Enha...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Pande, Pournima Misba, M. Gupta, Deepak Rani, V.Kanpur Ahmed, Hassan Safi Balakumar, A. Yeshwantrao Chavan College of Engineering Department of Applied Chemistry Nagpur India Tamil Nadu Chennai India Graphic Era Hill University Department of Mechanical Engineering Uttarakhand Dehradun India Graphic Era Deemed to be University Department of Mechanical Engineering Uttarakhand Dehradun India Hindustan Institute of Technology and Science Department of Eee Chennai India Al-Farahidi University Department of Biomedical Engineering Baghdad Iraq K.Ramakrishnan College of Engineering Department of Ece Trichy India

ISBN: (纸本)9798350356236

Artifacts in images are significant challenges in many fields and degrade the quality and reliability of data analysis. Existing methods for artifact removal face a problem of complex and diverse artifacts, limiting their effectiveness. Traditional techniques for removing artifacts have a problem with low adaptability to different types of artifacts and can sometimes delete important features of an image. The artifact removal method takes the concept of GANs into use to remove artifacts within the adversarial training model from images. It rectifies the issues stated previously through the proposed approach based on training a GAN. The G learns artifact-free versions of the images and the D tells them clean or corrupted ones while the G continues its progression towards artifact removal guided by D. Once it was trained, G had completely removed artifacts in novel unseen images. Results prove the superiority of this proposed artifact removal compared with existing approaches across a spectrum of datasets including different forms of artifacts: noise compression, and occlusion results of removing such different kinds of artifacts without sacrificing much the image quality along with preserving other critical features that need removal. Adversarial removal artifacts can be taken as one such error value 112.31 solution in making an improved version of enhancing quality as well as reliability of the image while making applications over the range. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Technique for Fingerprint-Based Blood Group Identification 5

Non-Invasive Technique for Fingerprint-Based Blood Group Ide...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Thakre, Devyani Panpatte, Manswi Khandelwal, Richa Shri Ramdeobaba College of Engineering And Management Electronics and Computer Science Department Nagpur India Ramdeobaba University Department of Electronics Engineering Nagpur India

ISBN: (纸本)9798350356236

This work delves into the development of a novel, non-invasive method for determining blood groups using finger-print analysis. Traditional blood group testing methods, such as blood sampling, are invasive, time-consuming, and require specialized equipment. In contrast, our approach utilizes image processing techniques to analyze the unique patterns present in fingerprints, aiming to accurately predict an individual's blood type without the need for direct blood contact. The methodology begins with the acquisition of high-resolution fingerprint images, which are then processed through a series of image enhancement and normalization steps to ensure consistent quality. Feature extraction techniques are employed to identify distinctive patterns and characteristics in the fingerprints that correlate with specific blood groups. These extracted features are subsequently fed into advanced classification algorithms, such as Convolutional Neural Networks (CNNs), which are trained to recognize and classify the fingerprint data into one of the primary blood groups: A, B, AB, and O, with both positive and negative Rh factors. Through extensive training and validation, the classification model achieved a training accuracy of 99.47% and a validation accuracy of 80%, demonstrating its robustness and reliability. Additionally, the model achieves high F1-scores across most blood groups, with an average F1-score of 0.83, highlighting its precision and recall balance. Compared to traditional blood testing methods, this approach offers a faster, cost-effective, and painless alternative, achieving comparable accuracy while significantly reducing time and costs. This work leverages state-of-the-art machine learning and image processing methods, optimizing accuracy and reliability by utilizing a large dataset of labeled fingerprint images. By eliminating the need for invasive procedures, this work aims to enhance patient comfort, reduce the risk of infection, and streamline the process of

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Improving Automated Assessment of English Spoken Discourse Using Transfer Learning Models-Wav2Vec 2.0 5

Improving Automated Assessment of English Spoken Discourse U...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Hameed, N. Sheik Vijayakumar, S. Rajaraman, K. Kumar, V. Vinod Tamilarasan, P. Faizal, M. K. Mohamed B. S Abdur Rahman Crescent Institute of Science and Technology Department of English Chennai India Annamalai University Department of English Tamil Nadu Chidambaram India Bharathidasan University Department of English Tiruchirappalli India Srm University Department of English Chennai India K.Ramakrishnan College of Engineering Department of Ai & Ds Tamil Nadu Trichy India

ISBN: (纸本)9798350356236

Automated Assessment of English Spoken Discourse is invaluable tool used in the process of learning foreign languages, teaching and communication as it is capable of delivering a large number of assessments of spoken language without significant human interferences. However, common approaches may yield some issues in terms of accuracy, methods' applicability to a variety of accents and languages, and the scalability of the techniques. Conventional techniques including HMM-GMM and contemporary DL techniques like the CNN-RNN triangulate unsatisfactory results due to the inability to capture more intricate spoken discourse since they are unable to pick tune from the din. In response to these difficulties, this research proposal presents the following framework using Wav2Vec 2.0, a self-supervised learning model involved in speech signals. The proposed method makes use of Wav2Vec 2.0 to capture rich representations directly from the raw input data to minimize dependence on labelled data and improve robustness to different patterns of speech. Applicable in Python, the model is fine-tuned in spoken discourse datasets and is assessed based on primary metrics of performance;test performance: 99.1%. These results are much better than traditional and baseline methods and clearly demonstrate the high stability and potential of the model. This way, the study that addresses prior limitations and offers a stable solution contributes to the development of the automated speech assessment. Further work that could be suggested is the selection of multimodal integration approaches and real time as a way to increase more the scores of the different models and the flexibility of the system that has been proposes in education and work environments. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing for Sentiment Analysis in ESL Writing: Understanding Emotional Tone in Learner Essays 5

Natural Language Processing for Sentiment Analysis in ESL Wr...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Kumar, M. Vinoth Ansari, Subuhi Kashif Gupta, Deepak Kavitha, P. Kumar, G.M. Prem Bala, B. Kiran Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Technology Department of English Avadi Chennai India Jazan University College of Engineering & Computer Science Jazan Saudi Arabia Graphic Era Hill University Department of Mechanical Engineering Uttarakhand Dehradun India Graphic Era Deemed to be University Department of Mechanical Engineering Uttarakhand Dehradun India Department of English Erode India Ddgd Vaishnav College University of Madras Pg Department of English Tamil Nadu Chennai India K. Ramakrishnan College of Engineering Department of Ai & Ds Trichy India

ISBN: (纸本)9798350356236

In recent years, the significance of sentiment analysis in educational contexts has gained considerable attention, particularly in understanding the emotional expressions of English as a Second Language (ESL) learners. Accurately capturing these sentiments is essential for providing targeted support and feedback to enhance student writing skills. This study presents an advanced natural language processing (NLP) framework for sentiment analysis in ESL writing, specifically focusing on understanding emotional tones in learner essays. Utilizing a dataset sourced from Kaggle, which categorizes tweets based on emoticons, the methodology incorporates rigorous data preprocessing techniques, including text cleaning, tokenization, and error correction to enhance data quality. A comprehensive feature extraction process captures linguistic, syntactic, and sentiment-related features using dependency parsing and word embeddings, such as Word2Vec and BERT. The proposed model, implemented in Python, demonstrates a remarkable accuracy of 98.5%, significantly surpassing existing methods like Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), which achieved accuracies of 95.12% and 96.97%, respectively. This enhanced performance highlights the model's ability to effectively capture nuanced emotional expressions in ESL writing. The validation of the model's predictions against human evaluations ensures the reliability and accuracy of the findings. This research not only contributes to the field of sentiment analysis but also informs educational practices, offering targeted interventions to support ESL learners in improving their emotional expression and writing skills. Ultimately, the proposed NLP framework serves as a robust tool for enhancing understanding and assessment of emotional tone in educational contexts. © 2025 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Deep CNN Self-Attention Model for Multidimensional Speech Quality Prediction Using Crowdsourced datasets 5

A Deep CNN Self-Attention Model for Multidimensional Speech ...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Gummadi, Annapurna Kaur, Chamandeep Gupta, Deepak Rao, Vuda Sreenivasa Tripurana, Santosh Nagaraj, P. Hyderabad India Jazan University Computer Science & Information Technology Department Jazan Saudi Arabia Graphic Era Hill University Department of Mechanical Engineering Uttarakhand Dehradun India Graphic Era Deemed to be University Department of Mechanical Engineering Uttarakhand Dehradun India Koneru Lakshmaiah Education Foundation Department of Cse A.P. Vaddeswaram India Vignan's Institute of Engineering for Women Dept of Ece Andhra Pradesh Visakhapatnam India K. Ramakrishnan College of Engineering Department of Ai & Ml Tamil nadu Trichy India

ISBN: (纸本)9798350356236

Predicting voice quality is critical for improving communication systems and the user experience. In this article, we offer a unique technique to multidimensional speech quality prediction using a Deep Convolutional Neural Network (CNN) enriched with self-attention techniques and crowdsourced datasets. The proposed model incorporates both spatial and temporal information from speech signals via numerous convolutional layers, enabling it to accurately represent the intricate patterns and features seen in speech data. Furthermore, self-attention methods are used to let the algorithm to focus on relevant parts of the input data, increasing its discriminative capacity and tolerance to interference. Transfer learning is utilized to leverage pre-trained representations from large-scale speech datasets, enabling the model to generalize well to diverse speech characteristics and environments. By fine-tuning the pre-trained model on the specific crowdsourced dataset, we adapt it to the task of speech quality prediction while mitigating the need for large annotated datasets, which are often costly and time-consuming to obtain. Experimental results demonstrate the effectiveness of the proposed approach, achieving state-of-the-art performance on various metrics for multidimensional speech quality prediction tasks. Furthermore, extensive ablation studies are conducted to analyze the contributions of different components of the model, highlighting the importance of both the CNN architecture and self-attention mechanisms. Overall, our findings suggest that the proposed deep CNN self-attention model, combined with transfer learning from crowdsourced datasets, presents a promising approach for accurate and efficient speech quality prediction in diverse real-world scenarios © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Real-Time Threat Detection with YOLOv8 and LSTM Integration for Intelligent Surveillance Systems 5

Enhancing Real-Time Threat Detection with YOLOv8 and LSTM In...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Behera, Prakash Chandra Rani, V. Kanpur Gupta, Deepak Hamid, Noor Kaylan Rao, Vuda Sreenivasa Dhaaraani, R. St. Claret College Autonomous Department of Science Bangalore India Hindustan Institute of Technology and Science Department of Eee Chennai India Department of Mechanical Engineering Graphic Era Hill University Uttarakhand Dehradun India Department of Mechanical Engineering Graphic Era Deemed to be University Uttarakhand Dehradun India Al Kitab University Department of Computer Education Kirkuk Iraq Koneru Lakshmaiah Education Foundation Department of Cse A.P. Vaddeswaram India K. Ramakrishnan College of Engineering Department of Ai & Ds Trichy India

ISBN: (纸本)9798350356236

In the face of increasing security threats, efficient surveillance systems are crucial for timely threat detection and response. This study presents a comprehensive approach that integrates the YOLOv8 object detection framework with Long Short-Term Memory (LSTM) networks to enhance real-time threat detection capabilities. The UCF-Crime dataset, which encompasses a variety of crime-related scenarios, was utilized to evaluate the proposed model's effectiveness. Traditional methods often struggle with accurately detecting objects and understanding complex behavioral patterns in dynamic environments. The existing methods primarily rely on conventional object detection techniques that lack the ability to capture temporal dependencies, leading to limitations in anomaly detection. In contrast, our proposed YOLOv8-LSTM model combines fast and accurate object detection with advanced sequential analysis, enabling the identification of unusual activities such as loitering or aggressive behavior over time. Performance metrics, including precision, recall, and accuracy, were employed to assess both object detection and anomaly recognition capabilities, demonstrating significant improvements in real-time threat detection. The results indicate that the integrated model not only enhances the reliability of surveillance systems but also opens pathways for future enhancements, such as incorporating multimodal data and optimizing the model for edge device deployment. This research highlights the potential of advanced deep learning techniques to improve security measures in public spaces, ultimately contributing to safer communities. The successful integration of YOLOv8 and LSTM marks a significant advancement in the development of intelligent surveillance systems, addressing modern security challenges effectively. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Soccer Match Prediction with Deep Convolutional Neural Networks and Grey Wolf Optimization 5

Optimizing Soccer Match Prediction with Deep Convolutional N...

引用

5th IEEE international conference on advances in Electrical, computing, Communication and Sustainable technologies, ICAECT 2025

作者： Shukla, Tushar Dhar Rani, V.Kanpur Kumar, Indrajeet Hussein, Omar Mohsen Banu, Shaik Balkhis Bhavani, P. University Institute of Physical Education & Sports Chandigarh University Mohali India Hindustan Institute of Technology and Science Department of Eee Chennai India Department of Cse Graphic Era Hill University Uttarakhand Dehradun India Graphic Era Deemed to be University Uttarakhand Dehradun India Al-Farahidi University Department of Biomedical Engineering Baghdad Iraq Fatima College of Health Sciences Department of Physiotherapy Al Ain United Arab Emirates K. Ramakrishnan college of Engineering Dept of Ai & Ds Trichy India

ISBN: (纸本)9798350356236

Predicting soccer match outcomes has become an essential area of interest in sports analytics, yet many existing studies rely on traditional machine learning methods that may not adequately capture the complex dynamics inherent in the sport. This study aims to address these limitations by proposing a novel approach utilizing a Deep Convolutional Neural Network (DCNN) optimized through Grey Wolf Optimization (GWO) to significantly enhance prediction accuracy. The methodology leverages a comprehensive dataset from the European Soccer database, gathered from Kaggle, which includes detailed match statistics, player attributes, and betting odds, allowing for a richer analysis. The results of the study indicate that the proposed DCNN model outperforms several baseline models, achieving notable improvements in accuracy, precision, and F1-scores, thereby showcasing its ability to learn complex patterns and relationships within the data effectively. Despite these promising findings, the study acknowledges certain limitations, such as the potential for further enhancement through the integration of additional features like spatiotemporal tracking data and more detailed player performance metrics. The outcomes suggest that the combination of advanced deep learning techniques with effective optimization strategies can yield substantial improvements in predictive analytics in sports. In conclusion, this research contributes significantly to the field by demonstrating the potential of deep learning in the accurate prediction of soccer match outcomes. It encourages future exploration of diverse datasets and methodologies to further refine predictive capabilities, ultimately supporting more informed decision-making processes for teams and coaches within the competitive landscape of soccer. Overall, the study underscores the transformative potential of machine learning in sports analytics. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrated Energy System for an Integrated Park of Cloud Pipe Edge Device Based on Carbon Emission Flow: System Framework, Key technologies and Prospects

Integrated Energy System for an Integrated Park of Cloud Pip...

引用

international conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Wang, Yun Ke, Ji Yin, Yaohua Xing, Xueshu College of Energy and Electrical Engineering Chang’an University Shaanxi Xi’an710064 China Power China Guiyang Engineering Co. Ltd Guiyang China

ISBN: (纸本)9789819618637

The "double carbon" strategy has brought attention to the importance of integrated energy system management in parks for improving energy utilization efficiency, reducing energy consumption costs, and achieving intelligent management. This paper introduces an integrated energy system framework for a park that uses cloud-based edge devices and focuses on managing carbon emissions and operational efficiency based on carbon emission flow. This framework aims to enhance data processing and energy management efficiency, decrease carbon emissions, and improve economic performance by utilizing resource pre-allocation through edge computing and centralized management via cloud platforms. The paper summarizes critical technologies associated with this framework, including carbon emission prediction, data security assurance, operational efficiency maintenance, and pressure reduction on energy storage facilities to optimize carbon emission solutions. These technologies support the low-carbon development and optimal resource utilization of integrated energy systems, providing a novel approach to sustainable development and a reference for future technological advancements. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Carbon capture and utilization

来源：评论

学校读者我要写书评

暂无评论

Diabetic Foot Ulcer Classification Using Deep Learning Approach 8th

Diabetic Foot Ulcer Classification Using Deep Learning Appro...

引用

8th IFIP TC 12 international conference on Computer, Communication and Signal Processing, ICCCSP 2024

作者： Sivakamasundari, P. Niranjana, G. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9783031736162

Podiatrist diagnosis and lesion localization are used as current testing approaches for Diabetic Foot ulcers (DFU). Current systems for automation concentrate on either categorization or division. One of the most common metabolic conditions, Diabetes (also called diabetes mellitus), is brought on by the pancreas incapacity to generate sufficient anti hyper-glycemic hormone to control glycemia levels. It may cause "Diabetic Peripheral Neuropathy," a collection of nerve diseases that can develop if the blood glucose level is left uncontrolled and unmanaged. Blood glucose levels may be efficiently maintained by recognising diabetes initially through constant surveillance and screenings. Using image processing methods such as data stretching with Deep Learning, image reduction and improvement, image division, and feature extraction, this paper offers a thorough approach for analysing thermal scans of the diabetic foot. By using these techniques, doctors may assess and track a patient's condition with fewer examinations. In this work, EfficientNetB3 architecture is compared with other Deep Learning models for accuracy in DFU identification. To create a powerful deep learning model, we gathered an extensive collection of 1,775 DFU photos. The basis of belief for this data gathering was created by two medical experts using annotator software to define the DFU region of interest. It took 48 ms to figure out a single image and 57.2 MB to validate the model. EfficientnetB3 got an average mean accuracy of 93%. This work demonstrates the effectiveness of Deep Learning for DFU localization in real-time, which could have improved with the use of a larger data set. © IFIP international Federation for Information Processing 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Knowledge Distillation for Human Activity Recognition 1

Hierarchical Knowledge Distillation for Human Activity Recog...

引用

1st international conference on Intelligent Manufacturing and Cloud computing, ICIMCC 2024

作者： Hu, Di Wu, Xingchen Xiong, Dezhu Department of Optoelectronic Science and Technology Ji Hua Laboratory Foshan China Jiushao Institute of AI Algorithm Ji Hua Laboratory Foshan China Intelligent robot research center Ji Hua Laboratory Foshan China

ISBN: (纸本)9781643685779

The widespread adoption of IoT and mobile devices with a variety of sensors has made it possible to develop applications that combine time-series data from multiple sensor inputs. However, current deep neural network architectures for multimodal fusion struggle with consecutive missing data and noise, common in real-world scenarios. We introduce a Hierarchical Knowledge Distillation Framework (HKDF) designed to address noise and data missingness challenges in Human Activity Recognition (HAR). Specifically, we introduce a cross-sample correlation distillation mechanism, leveraging contrastive learning to capture and transfer holistic semantics across samples, thereby enabling effective feature reconstruction. Additionally, a cross-category variation distillation strategy is proposed to learn inter- and intra- category dynamics based on category prototypes to produce robust joint multimodal representations. The superior performance achieved on both datasets demonstrates the remarkable advantages of HKDF. © 2025 The Authors.

关键词： Contrastive Learning

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500页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：