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

552 篇 会议
4 册 图书
4 篇 期刊文献

馆藏范围

560 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

330 篇 工学
- 302 篇 计算机科学与技术...
- 222 篇 软件工程
- 66 篇 信息与通信工程
- 55 篇 控制科学与工程
- 41 篇 生物工程
- 36 篇 生物医学工程（可授...
- 33 篇 电气工程
- 26 篇 电子科学与技术（可...
- 24 篇 动力工程及工程热...
- 21 篇 机械工程
- 20 篇 网络空间安全
- 19 篇 光学工程
- 12 篇 化学工程与技术
- 12 篇 安全科学与工程
- 10 篇 仪器科学与技术
- 8 篇 交通运输工程
115 篇 理学
- 47 篇 数学
- 45 篇 物理学
- 45 篇 生物学
- 25 篇 统计学（可授理学、...
- 12 篇 化学
95 篇 管理学
- 60 篇 管理科学与工程(可...
- 34 篇 图书情报与档案管...
- 19 篇 工商管理
29 篇 医学
- 28 篇 临床医学
- 23 篇 基础医学(可授医学...
- 12 篇 药学(可授医学、理...
- 9 篇 公共卫生与预防医...
16 篇 教育学
- 15 篇 教育学
13 篇 法学
- 12 篇 社会学
6 篇 农学
4 篇 经济学
2 篇 文学

主题

95 篇 machine learning
72 篇 human computer i...
70 篇 accuracy
57 篇 deep learning
35 篇 feature extracti...
31 篇 training
29 篇 convolutional ne...
28 篇 emotion recognit...
27 篇 computational mo...
27 篇 predictive model...
27 篇 machine learning...
21 篇 adversarial mach...
19 篇 real-time system...
18 篇 computer vision
18 篇 data models
17 篇 support vector m...
17 篇 artificial intel...
15 篇 reliability
14 篇 face recognition
14 篇 prediction algor...

机构

4 篇 school of materi...
3 篇 school of comput...
3 篇 school of inform...
3 篇 graphic era deem...
3 篇 new york univers...
2 篇 department of co...
2 篇 saveetha institu...
2 篇 school of comput...
2 篇 school of xiamen...
2 篇 singapore univer...
2 篇 dept. of compute...
2 篇 wuhan digital en...
2 篇 dept. of softwar...
2 篇 dept. of electro...
2 篇 chitkara univers...
2 篇 south china univ...
2 篇 school of comput...
2 篇 school of comput...
2 篇 department of in...
2 篇 dept. of compute...

作者

3 篇 surendran r.
3 篇 ggaliwango marvi...
2 篇 zhou jing
2 篇 r surendran
2 篇 julian anitha
2 篇 wenle bai
2 篇 qingle quan
2 篇 hanqing sun
2 篇 sharma ajay
2 篇 jac fredo agasti...
2 篇 jing zhou
2 篇 kulkarni hrishik...
2 篇 wu kai
2 篇 shahade makarand
2 篇 bharti
2 篇 sharma shamneesh
2 篇 bingyao liu
2 篇 nakayiza hellen
2 篇 vishalakshmi
2 篇 schiller dominik

语言

442 篇 英文
118 篇 其他
8 篇 中文

检索条件"任意字段=5th International Conference on Machine Learning and Human-Computer Interaction, MLHMI 2024"

共 560 条记录，以下是451-460 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：

An Emotion Recognition Using Electrocardiogram Signals 25

An Emotion Recognition Using Electrocardiogram Signals

引用

2025 5th international conference on Bioinformatics and Intelligent Computing, BIC 2025

作者： Guo, Wei Teng, Fei Lin, Yongzhong Zhao, Wenzhi Liu, Wenlong School of Information and Communication Engineering Dalian University of Technology Liaoning Dalian China Central Hospital of Dalian University of Technology Liaoning Dalian China The Second Affiliated Hospital of Dalian Medical University Liaoning Dalian China Dalian Key Laboratory of Artificial Intelligence DUT Artificial Intelligence Institute Liaoning Dalian China

ISBN: (纸本)9798400712203

With the increasing focus on mental health, emotion recognition based on Electrocardiogram (ECG) shows great potential in applications such as human-computer interaction and the treatment of emotion-related diseases. Deep learning has advantages over traditional machine learning methods for automatic feature extraction. However, overcoming individual differences and achieving highly accurate emotion recognition on lightweight models remains a major challenge. To address this issue, this paper proposes an emotion recognition method based on an improved residual network (ResNet) architecture, which aims to improve the representation of ECG signals on different time scales. In addition, the proposed method combines Squeeze-and-Excitation Networks (SENet) to dynamically assign weights to ECG features from different channels, effectively accounting for individual differences. Deeply separable convolution (DWConv) is also employed to reduce computational complexity, enabling its use on portable devices. Validation on three publicly available datasets shows that the proposed method identifies valence, arousal and explicitness with 94.7%, 92.9% and 94.6% accuracy in the SWELL dataset for valence, 92.9% and 94.6% respectively, and 98.6% in the WESAD dataset for emotional states, and correctly identifies value and arousal with 78.5% and 83.8% in the CASE dataset. the results show that the method has significant advantages in multi-class emotion recognition tasks. © 2025 Copyright held by the owner/author(s).

关键词： Attention mechanisms Deep learning ECG Emotion classification

来源：评论

学校读者我要写书评

暂无评论

Design of Intelligent Question-Answering System Based on Large Language Model

Design of Intelligent Question-Answering System Based on Lar...

引用

5th international conference on machine learning and Big Data Analytics for IoT Security and Privacy, SPIoT 2024

作者： Li, Xueqin Teaching and Research Institute of Foreign Languages Bohai University Jinzhou China

the progress of deep learning and natural language processing technology has promoted the question answering system into a new era, which can understand complex questions more accurately, support multi-source knowledge expression and multi-round interaction, and realize intelligence. As a pre-trained language generation model, LLM can better handle the task of understanding and generating natural language, so as to effectively reduce the development cost of intelligent question answering system and improve its accuracy. In this paper, the BERT model has the characteristics of multi-layer bidirectional Transformer coding structure, and the LLM for intelligent problems is constructed, and the weight clipping optimization method is studied. By deleting neurons with zero weight value in the model, the number of parameters in the model is reduced. Finally, the experimental environment is set up, simulation experiments are carried out, and the original model is compared with the optimized model, which verifies the scientific nature of the optimized model. the LLM studied in this paper improves the accuracy of intelligent problem and provides a new idea for constructing intelligent problem system. © 2025 the Authors. Published by Elsevier B.V.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Audio Deepfakes: Feature Extraction and Model Evaluation for Detection

Audio Deepfakes: Feature Extraction and Model Evaluation for...

引用

Emerging Technology (INCET), international conference for

作者： Ramesh K Bhukya Aditya Raj Danish N Raja Department of Electronics and Communication Engineering Indian Institute of Information Technology Allahabad Prayagraj Uttar Pradesh India Department of Computer Science Islamic University of Science and Technology Awantipora Pulwama Jammu and Kashmir India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Cutting-edge AI-driven tools are currently employed for replicating human voices, leading to the emergence of audio deepfakes. Initially designed to enhance experiences like audio-books, the potential misuse of audio deepfakes poses significant risks to public safety. Despite advancements in detecting video deepfakes, identifying audio deepfakes remains challenging. We employ methods to extract features such as Mel-frequency cepstral coefficients, chromagrams, spectral contrast, tonnetz, and Mel-spectrograms from audio samples. the extracted deep features are concatenated together and then employed in machine learning and deep learning models to evaluate the ASVspoof2021 dataset to categorize it into bonafide and spoofed speech utterances. the experimental results reveal that the multilayer perceptron model achieves the highest accuracy rate of 96.073%, while SVM, k-NN, XGBoost, and RF produce accuracy rates of 93.58%, 94.58%, 93.544%, and 93.58%, respectively. Additionally, DL models, including CNN, achieve an accuracy rate of 98.2%, DNN of 97.6%, and LSTM of 97.7%, showcasing the superiority of CNN in identifying deepfake audio amidst the evolving landscape of synthetic media.

关键词： Support vector machines Radio frequency Voice activity detection Deepfakes Accuracy Transfer learning Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

BioSegNet: Pioneering Convolutional Approaches in Medical Imaging

BioSegNet: Pioneering Convolutional Approaches in Medical Im...

引用

international conference on Circuits, Communication, Control and Computing

作者： Swathika R Akshatha P S Sheela S S M Dilip Kumar Department of Engineering Dr. APJ Abdul Kalam School of Engineering Garden City University Bengaluru India Department of AIML New Horizon College of Engineering Bengaluru India Department of Computer Science Siddaganga Institute of Technology Tumakuru India Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore University Bengaluru India

ISBN: (数字)9798331528539

ISBN: (纸本)9798331528546

the integration of machine learning in biomedical imaging has significantly advanced the detection of tumors in brain using MRI scans. While traditional manual methods are effective, they often suffer from human error, inefficiency, and variability in diagnostic accuracy. BioSegNet addresses these challenges by introducing a CNN-based approach for automated detection of tumor in brain, segmentation, and classification of different types of tumors in MRI scans. this system reduces reliance on subjective interpretation and minimizes delays associ-ated with manual analysis. Built with TensorFlow Lite, BioSegNet ensures efficient deployment on edge devices and cloud platforms, making it versatile and accessible. Its user-friendly Streamlit-based web interface caters to users with varying technical expertise, enhancing its practical application in clinical settings. Extensive testing shows BioSegNet's ability to deliver accurate, real-time tumor analysis, offering a valuable tool for improving diagnostic accuracy and reducing errors. By optimizing for edge and cloud deployment, BioSegNet makes advanced diagnostic tools more accessible to medical professionals globally, contributing to better patient outcomes and timely treatments.

关键词： Accuracy Magnetic resonance imaging Image edge detection Biological system modeling Manuals machine learning Streaming media Real-time systems Tumors Testing

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Visual Tracker Based on Deformable Attention

Spatiotemporal Visual Tracker Based on Deformable Attention

引用

Pattern Recognition and machine learning (PRML), IEEE international conference on

作者： Zhuo Wu Askar Hamdulla Yucheng Huang School of Computer Science and Technology(School of Cyberspace Security) Xinjiang University Urumqi China School of Intelligence Science and Technology(School of Future Technology) Xinjiang University Urumqi China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

At present, the visual tracking method based on Transformer has made significant progress, and has shown excellent performance on various data sets. However, the traditional Transformer tracker pays too much attention to global features, and its intensive attention calculation will increase the space-time complexity of the tracking algorithm. And the features of the relevant region will be affected by the features of the non-relevant region, resulting in a decrease in tracking accuracy. In addition, the Transformer tracker lacks the ability to utilize the spatiotemporal information between frames, which further hinders the improvement of its tracking performance. To solve these problems, this paper proposes a new tracker SVT-DA based on deformable attention. the tracker captures local and global important features through CNN and deformable attention. In addition, it uses a cross-attention module nested with self-attention to achieve deep semantic information interaction between template features and search features. In order to verify the effectiveness of the proposed method, we conduct experiments on LaSOT, GOT-10K, OTB100 and VAU123 datasets. the result indicators are 4%~5% higher than the baseline method. the experimental results show that our method improves the tracking performance while reducing the number of model parameters, and is highly competitive with other state-of-the-art methods.

关键词： Visualization Target tracking Semantics Transformers Feature extraction Spatiotemporal phenomena Pattern recognition Convolutional neural networks Information exchange Resilience

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of machine learning Algorithms in threat Detection and Mitigation in Cyberspace: A Systematic Review

Effectiveness of Machine Learning Algorithms in Threat Detec...

引用

IEEE international conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Mathew Akwu Adaji Francis Sunday Bakpo Modesta E. Ezema Emmanuel Etuh Caleb Markus Samuel Owoicho Olofu Buhari Isa Sambo Department of Computer Science University of Nigeria Nsukka Nigeria Department of Mathematics/Statistics and Computer Science Kwararafa University Wukari Nigeria Department of Computer Science Federal Polytechnic Ohodo Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

the rapid digitalization and proliferation of internet-connected devices have not only revolutionized our daily lives but also exponentially expanded the attack surface for cybercriminals, creating an increasingly complex and treacherous cybersecurity landscape. this review critically examines the effectiveness of machine learning (ML) algorithms in cyber threat detection and mitigation, addressing the need for advanced cybersecurity measures in our interconnected digital landscape. Following Kitchenham's guidelines and utilizing the PRISMA model, the study analyzed 907 initial records from Science Direct, Google Scholar, IEEE Xplore, Springer, and ACM Digital Library, ultimately including only 15 studies that met stringent criteria. the thematic analysis revealed varying effectiveness of supervised learning (SVM and Random Forests) with accuracy rates of 85-90%, but with moderate false positive rates (15-20%). Unsupervised learning techniques (like K-means and DBSCAN) demonstrated lower accuracy (70-75%) yet excelled in detecting novel threats, albeit with higher false positive rates (25-30%). Reinforcement learning showcased adaptive defense capabilities but suffered from lower accuracy (65-70%) due to adversarial manipulation. Deep learning methods achieved high accuracy (up to 99%) in specific tasks, yet faced challenges related to resource demands and limited interpretability. the study highlights data quality difficulties, high false positive and negative rates, and complex model interpretability issues. ML can automate incident response and security orchestration, but the evaluation stresses the need for a balanced approach with human experience. Increasing model interpretability and defending against adversarial attacks are research gaps. the paper emphasises the need of hybrid approaches and explainable AI techniques for cyber threat identification and mitigation using ML. this thorough study lays the groundwork for ML-based cybersecurity in a complex threa

关键词： Support vector machines Accuracy machine learning algorithms Prevention and mitigation Supervised learning Reinforcement learning threat assessment Unsupervised learning Stress Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Multi-disaster Emergency Response Decision Support Based on Reinforcement learning Algorithm

Multi-disaster Emergency Response Decision Support Based on ...

引用

5th international conference on machine learning and Big Data Analytics for IoT Security and Privacy, SPIoT 2024

作者： Lei, Yu Liu, Jiabao Ke, Yuqiang Officers College of PAP Sichuan Chengdu610213 China

With the acceleration of global climate change and urbanization, the frequency and intensity of natural disasters and emergencies continue to increase, posing severe challenges to social security and stability. Traditional emergency response research often focuses on a single type of disaster, relying on static models and historical data, and lacking in-depth analysis of the interaction between multiple disasters. this article investigated a multi disaster emergency response decision support system based on reinforcement learning. the system combined real-time data with reinforcement learning algorithms by constructing a dynamic environment model, achieving adaptive decision-making of intelligent agents in disaster scenarios. In terms of specific methods, this article designed state, action, and reward mechanisms to optimize emergency response strategies, and evaluated the performance of the system through simulation experiments. the experimental results showed that the decision support system based on reinforcement learning significantly improved decision efficiency (Max: 89.4%) and resource utilization (Max: 91.4%) in multi disaster emergency response. this study not only provides a new solution for multi disaster emergency response, but also lays the foundation for the intelligent development of future emergency management. © 2025 the Authors. Published by Elsevier B.V.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent System to Analysis of Plant Diseases using machine learning Techniques 23

Intelligent System to Analysis of Plant Diseases using Machi...

引用

Proceedings of the 5th international conference on Information Management & machine Intelligence

作者： Prachi A Bainalwar Shubhangi M Borkar Shubhangi S Shambharkar Pradnya S Moon Computer Technology Yeshwantrao chavan College of Engineering India

ISBN: (纸本)9798400709418

For the efficient monitoring and control of crop health, the timely and precise diagnosis of plant diseases is essential. Traditional techniques of disease diagnosis rely on visual examination by human experts, which can be laborious, arbitrary, and liable to mistakes. machine learning approaches have recently shown promise as intelligent and automated solutions for analysing plant diseases. In this paper, we offer an intelligent system for the investigation and identification of plant diseases that makes use of machine learning methods. the method uses a large library of plant photos that includes both healthy and diseased plants in various states of health. Pre-processing is done on the dataset to extract pertinent properties including colour, texture, and shape. In order to effectively identify and categorise the ailments of the plant and support decision-making in real time, a system was developed that makes use of a camera sensor module. the SVM), CNN, with a linear nucleus, and the Support Vector machine with a polysomic nucleus are three machine learning techniques that are highlighted in the paper. the recommended intelligent system performs a very accurate and efficient analysis of plant diseases. By accepting photos of plant samples taken using different technologies, such as cell-phones or drones, it offers real-time disease detection. By effectively identifying and managing plant diseases, the system can be used in agricultural settings, enabling farmers and agricultural specialists to reduce crop losses and maximise agricultural productivity.

关键词： Convolution Neural Network

来源：评论

学校读者我要写书评

暂无评论

- Statistical and machine learning Tools for Consonance Detection

- Statistical and Machine Learning Tools for Consonance Dete...

引用

Artificial Intelligence, Robotics and Control (AIRC), international conference on

作者： Paolo Barile Aysel Alizada Clara Bassano Computer Science dept. (DI) Università degli Studi di Salerno Salerno Italy Management dept. Sapienza University of Rome Rome Italy Pharmacy dept. (DIFARMA) Università degli Studi di Salerno Salerno Italy

ISBN: (数字)9798350385076

ISBN: (纸本)9798350385083

the study of emotions via Artificial Intelligence (AI) is considered a hot topic as technological development is gradually turning its gaze more and more toward understanding and emulating human beings. Emotion detection, however, runs the risk of being a useless investigative tool if it is not accompanied by solid theoretical foundations to reinterpret AI-detected emotions through a broader perspective. the Viable Systems Approach (ASV) may likely be the missing link between studying the emotional sphere and understanding the social dynamics that characterize human beings during each interaction. the concepts of consonance and resonance, typical of ASV, make it possible to describe patterns of information acquisition and to understand the dynamics underlying each individual's decision-making. the purpose of our study is to demonstrate, through field experimentation, the possibility of detecting consonance within groups of people in an automatic way, using statistical analysis techniques and Facial Expression Recognition (FER) algorithms. the trial was conducted in two phases: In the first one, a structured questionnaire categorized participants into distinct value clusters based on their strong beliefs; in the second one FER techniques were used to gauge the change in the initial level of consonance within the same clusters during a common contextual experience. Results demonstrated the possibility of detecting the initial level of consonance and its context-driven variation (resonance) both qualitatively and (at least partially) quantitatively. Research findings certified the feasibility of conso-nance measurement, opening the way to new usage perspectives for emotion detection tools in AI.

关键词： Emotion recognition Phase measurement Statistical analysis Radar measurements Decision making Turning Solids

来源：评论

学校读者我要写书评

暂无评论

A Deep learning Method for Obfuscated Android Malware Detection 5th

A Deep Learning Method for Obfuscated Android Malware Detec...

引用

5th international conference on machine learning, Image Processing, Network Security, and Data Sciences, MIND 2023

作者： Dasiah, Nitin Benjamin Gain, Ritu Sabarisrinivas, V. Sitara, K. Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli620015 India

ISBN: (纸本)9783031622168

With smartphones becoming increasingly prevalent and irreplaceable parts of modern society and individual life, it opens new windows for cybercriminals into our everyday life. Mobile devices are now at risk of being attacked by adversaries ranging from small-time crooks hoping to make a quick profit scamming people to authoritarian nation-states trying to attack and target journalists and human rights activists Malware programs are codes that are written by these adversaries to perform malicious tasks on the victim’s devices. these tasks can be spying on victims, encrypting all their files and extorting money, or using the computational power of a victim‘s device for illegal purposes. Many anti-malware solutions that exist for Android Smartphones rely on manual analysis and signatures to detect malware. However, most modern malware relies on polymorphic tendencies to change the signatures. Another major way of detecting malware is by using machine learning and Deep learning models for detection and classification. One of the major issues faced by most detectors is Adversarial evasion, where an adversary modifies the malware using various techniques to intentionally induce a misclassification by the detectors to evade it. Another major issue in this area is the selection of features from a large pool. Selecting a large number of features and not selecting enough can both be detrimental to the model’s performance. In this project, we propose a novel robust malware detection mechanism based on Deep learning for Android devices that solves both of the aforementioned challenges and thus creating a secure Android ecosystem. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Deep 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56页 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：