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

4,122 篇 会议
38 册 图书
6 篇 期刊文献

馆藏范围

4,166 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,726 篇 工学
- 2,455 篇 计算机科学与技术...
- 2,045 篇 软件工程
- 616 篇 生物工程
- 581 篇 信息与通信工程
- 362 篇 生物医学工程（可授...
- 266 篇 控制科学与工程
- 212 篇 光学工程
- 212 篇 电气工程
- 148 篇 安全科学与工程
- 137 篇 机械工程
- 124 篇 电子科学与技术（可...
- 119 篇 化学工程与技术
- 106 篇 交通运输工程
- 92 篇 动力工程及工程热...
1,369 篇 理学
- 675 篇 数学
- 646 篇 生物学
- 332 篇 统计学（可授理学、...
- 307 篇 物理学
- 197 篇 系统科学
- 127 篇 化学
722 篇 管理学
- 395 篇 管理科学与工程(可...
- 388 篇 图书情报与档案管...
- 239 篇 工商管理
340 篇 医学
- 315 篇 临床医学
- 308 篇 基础医学(可授医学...
- 221 篇 药学(可授医学、理...
- 125 篇 公共卫生与预防医...
160 篇 法学
- 138 篇 社会学
156 篇 教育学
- 154 篇 教育学
142 篇 农学
- 141 篇 作物学
91 篇 经济学
9 篇 军事学
5 篇 文学

主题

517 篇 machine learning
240 篇 deep learning
118 篇 support vector m...
99 篇 adversarial mach...
92 篇 accuracy
92 篇 machine learning...
82 篇 forecasting
74 篇 convolutional ne...
70 篇 predictive model...
69 篇 feature extracti...
56 篇 artificial intel...
53 篇 students
51 篇 learning systems
48 篇 decision trees
48 篇 training
47 篇 reinforcement le...
47 篇 computational mo...
47 篇 computer vision
46 篇 internet of thin...
41 篇 sentiment analys...

机构

46 篇 chitkara univers...
15 篇 graphic era hill...
10 篇 college of manag...
9 篇 graphic era deem...
8 篇 computer science...
8 篇 beijing universi...
7 篇 school of comput...
7 篇 school of comput...
7 篇 school of comput...
7 篇 department of in...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 computer science...
6 篇 lovely professio...
6 篇 in2p3 lpc campus...
6 篇 kkr and ksr inst...
6 篇 institut univers...
6 篇 national centre ...
6 篇 greater bay area...

作者

18 篇 kukreja vinay
15 篇 mehta shiva
10 篇 william p.
8 篇 sharma vikrant
7 篇 mahamudul hasan
7 篇 shiva mehta
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.
6 篇 huang f.

语言

4,020 篇 英文
145 篇 其他
34 篇 中文

检索条件"任意字段=Proceedings of the 2023 4th International Conference on Machine Learning and Computer Application"

共 4166 条记录，以下是161-170 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：

application of NLP and Deep learning in Enhancing the Resilience of Cross border E-commerce Supply Chain for Agricultural Products 25

Application of NLP and Deep Learning in Enhancing the Resili...

引用

proceedings of the 2025 4th international conference on Big Data, Information and computer Network

作者： Xiaomei Zou Yan Peng Hunan Biological and Electromechanical Polytechnic Changsha Hunan China Guangxi Transport Vocational and Technical College Nanning Guangxi China

ISBN: (纸本)9798400712425

Agricultural products have time constraints and logistics transportation cost constraints, which reduce the elasticity of the supply chain. In order to combine market trends, reasonably control supply volume, and improve supply efficiency, an application method of NLP and deep learning is proposed to enhance the elasticity of the cross-border e-commerce supply chain for agricultural products. Using deep learning algorithm BP neural network to predict market demand for agricultural cross-border e-commerce; Using NLP technology to monitor and analyze textual information in the cross-border e-commerce supply chain of agricultural products, and utilizing deep learning models to identify potential risk factors that may affect the supply chain; Apply the word frequency inverse document frequency algorithm and Word2Vec algorithm from NLP technology to multi feature extraction of logistics transportation text. A logistics transportation optimization model for agricultural cross-border e-commerce supply chain considering potential risk factors was constructed by combining deep learning. Adopting enhanced particle swarm optimization algorithm to solve the model, matching multiple features, and achieving optimization of agricultural cross-border e-commerce supply chain logistics transportation. the experimental results show that this method has a lower frequency of supply chain interruptions and a lower error rate in supply chain demand forecasting after application. By integrating NLP and deep learning methods, logistics transportation costs can be effectively reduced, supply chain resilience can be enhanced, and it has good practical application effects.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Research on Relationship Between Aging Population Distribution and Real Estate Market Dynamics based on Neural Networks 25

Research on Relationship Between Aging Population Distributi...

引用

proceedings of the 2025 4th international conference on Big Data, Information and computer Network

作者： Yiqiu Tang Shenghan Zhao School of Professional Studies Columbia University New York New York State USA The Department of Economics Cornell University New York New York State USA

ISBN: (纸本)9798400712425

this study aims to analyze the relationship between demographic patterns and real estate market movements. In particular, the study aims to examine the relation with the help of a neural network-based model. Considering that the model in question is using a deep learning approach with, one long short-term memory network enhanced with several optimization techniques, adaptive learning rate methods and data augmentation techniques. Collectively, these strategies provide sufficient means to understand the potential impacts for the dynamics of the housing market, those that run between the population age structure, migration demographics and economic indicators. the model's timeliness is validated through its ability to match market trends tightly, while providing the potential to minimize the impact of an aging population on housing prices from structural angles. the empirical analysis showed that the proposed LSTM model provides more reliable predictions compared to conventional statistical methods. In addition, the model demonstrates excellent generalization for application robustness in different market conditions.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Artificial Intelligence Logic and applications, AILA 2024

4th International Conference on Artificial Intelligence Logi...

引用

4th international conference on Artificial Intelligence Logic and applications, AILA 2024

ISBN: (纸本)9789819603534

the proceedings contain 27 papers. the special focus in this conference is on Artificial Intelligence Logic and applications. the topics include: Lattices for Many-Logics Modal Logic: Constructions and Representations;a Note to the Construction of t-Norms Based on TnM;conditional Distributivity of S-Uninorms and T-Uninorms over Uninorms;fuzzy Integrals Induced From Semi-Quasi-Overlap (Grouping) Functions;the Research on the Multi-agent Argumentation Semantics;an Exercise in Uppaal: Modelling the Circadian Clock of a Cyanobacteria;semi-Quasi-Overlap Functions and their applications in Classifier Ensemble;data and Knowledge Dual-Driven Traffic Sign Recognition Algorithm;Automatic Inspection of Static application Security Testing (SAST) Reports via Large Language Model Reasoning;semantic Abstractions for Multi-label Classification;multi-granularity Semantic Representation and Rule-Based Labeling for Relation Classification;feature Representation learning Based on Graph Curvature-Revised Deep Graph learning;non-negative Tensor Representation and Unsupervised Classification of Object Pose in Continuous Image Sequences;an Optimal Scheduling Algorithm for Intelligent Embedded Heterogeneous Multicore System;kernel Cutset-Type Possibility C-Means Algorithm for Gaussian Granularity;research on Fusion Modeling for Active Magnetic Bearings Based on Mechanism and Data Driven;Multi-objective Waterborne Trash Tracking Based on D-StrongSORT;a Contributor-Based Segmentation Model for Open Source Software Source Code Trustworthiness Measurement;facilitating the Propagation of Oscillatory Signals in Cortical Networks through Mixed Resonance;an Empirical Study for Source Code Incompatibility Between Versions of Java Open-Source Software;exploring Multi-source Mobile applications Association Discovery Based on Representation learning;takagi–Sugeno Target Recognition Algorithm Based on Global Intuitionistic Fuzzy Method;automated Legality Detection on Privacy Policy Based on Deep Learnin

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Federated learning, Deep learning, and Traditional machine learning Techniques for IoT Malware Detection

Comparative Analysis of Federated Learning, Deep Learning, a...

引用

AI in Cybersecurity (ICAIC), international conference on

作者： Rami Darwish Kaushik Roy Department of Computer Science North Carolina A&T State University Greensboro NC USA

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

this paper addresses the challenge of classifying Internet of things (IoT) binary files as either malware or benign using graph-theoretical features derived from Control Flow Graphs (CFGs). We use a dataset of 248,276 IoT binary files, each represented by 23 features. Our analysis presents traditional machine learning (ML) classifiers, including Logistic Regression (LR), K-Nearest Neighbors (KNN), and Random Forest (RF), with deep learning (DL) techniques-a Deep Neural Network (DNN) and a Convolutional Neural Network (CNN). Further developing these techniques, we propose the first application of Federated learning (FL) for IoT binary file classification based on CFG features, which provides a decentralized and privacy-preserving solution to malware detection. FL is simulated with two models, FL-DNN and FL-CNN, under IID (Independent and Identically Distributed) and Non-IID scenarios. IID divides the data equally among clients, while Non-IID causes an imbalance to reflect real-world scenarios where data distribution is significantly varied among the clients. In order to handle the challenges in imbalanced data scenarios, threshold tuning and class weighting have been applied to improve FL performance. Our results showed that, among the machine learning techniques, RF achieved the highest accuracy of $\mathbf{96.06\%}$, followed by KNN at $\mathbf{92.78\%}$, and LR at $\mathbf{74.25\%}$. For DL models, DNN and CNN are competitive, achieving accuracies of $\mathbf{93.55\%}$ and $\mathbf{93.24\%}$, respectively. Within the FL framework, FL-CNN achieved an accuracy of 95.27% under the IID scenario, while FL-CNN and FL-DNN achieved $\mathbf{95.09\%}$ and $\mathbf{94.76\%}$ under the Non-IID scenario. Our findings illustrate the feasibility of applying FL for IoT malware detection based on the analysis of IoT binary files with regard to CFG-based features, which can be extended to broader IoT domains such as health care, industrial IoT, and autonomous vehicles.

关键词： Deep learning Accuracy Federated learning Nearest neighbor methods Feature extraction Malware Convolutional neural networks Tuning Random forests Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Forest Fire Classification with Feature Selection and machine learning Based on PRISMA Hyperspectral Data 4th

Enhancing Forest Fire Classification with Feature Selection ...

引用

4th international conference on Intelligent Systems and Pattern Recognition, ISPR 2024

作者： Meroufel, Hanifi Berrichi, Faouzi Amri, Mohammed Bilel El Amin Larabi, Mohammed Agence Spatiale Algérienne Centre des Techniques Spatiale Arzew Oran Algeria Algerian Space Agency Algiers Algeria

ISBN: (纸本)9783031821554

Forest fires, a significant global threat causing vast annual devastation where each year millions of hectares are destroyed over the world. Burned areas necessitate early and accurate detection for effective response. this study investigates the application of Feature Selection (FS) to address data complexity in forest fire detection utilizing PRISMA hyperspectral imagery (HSI). FS is employed to select the most relevant information, thereby reducing complexity and facilitating the interpretation of results. the effectiveness of Extreme Gradient Boosting (XGBoost), Light Gradient Boosting machine (LGBM), Random Forest (RF), and Support Vector machine (SVM) algorithms is investigated. Analysis reveals that while the raw 229-band data yielded a reasonable accuracy with RF, applying FS through wrapper methods only select 13 bands and improve the performance of LGBM, XGBoost, and SVM. Notably, the best model achieves a classification precision of 94% and recall of 91%, demonstrating the effectiveness of FS in enhancing forest fire detection and mapping. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

FMLM: A federated meta-learning method for learning multimodal data features 25

FMLM: A federated meta-learning method for learning multimod...

引用

proceedings of the 2025 4th international conference on Big Data, Information and computer Network

作者： Meng Yue Weiyun Li College of Safety Science and Engineering Civil Aviation University of China Tianjin China

ISBN: (纸本)9798400712425

Federated meta-learning, which possesses the ability of fast adaptive learning and privacy preservation, has gained great momentum in personalized federated learning. the development of IoT technology has led to more demand for sharing different modal data, and federated meta-learning has a broad application prospect in the field of multimodal data. Many of the existing learning in the context of multimodal data focus on improving the ability of multimodal data fusion, and it is easy to ignore the advantages of unimodal data features in modal data feature extraction. In this paper, we propose a new federated meta-learning approach FMLM to efficiently extract multimodal data features. On the one hand, in local meta-learning, the optimal representation of unimodal modalities is obtained by internal updating, and the fused multimodal model is updated in external updating, and the update results are used for unimodal model parameter updating; on the other hand, in multi-party aggregation of federated learning, a kind of personalized aggregation is considered, and parameter sharing is carried out in only the feature extraction layer, which further improves the model's feature extraction effect and privacy preservation Performance. In a publicly available human action recognition dataset, our method is able to achieve a privacy-preserving accuracy of 69.92%, and in addition, the effectiveness of our proposed method is verified through well-established comparative experiments.

关键词： Federated Meta-learning

来源：评论

学校读者我要写书评

暂无评论

Saudi Stock Market Prediction Using machine learning and Deep learning

Saudi Stock Market Prediction Using Machine Learning and Dee...

引用

Computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Raid Mohsen Alhazmi Computer Science University of Tabouk Tabouk KSA

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

the research seeks to apply a particular approach to predicting a company's adjusted closing price in hopes of making an advancement in forecasting of the stock price. this research is significant due to its advantages to individuals, corporations, and governments. Approximating a stock's volatility is challenging for traders, and accurate predictions can help investors reduce portfolio risks. Stock prices do not behave in the linear manner. thus, we suggest the application of artificial intelligence techniques, namely multilayer perceptron (MLP) and long short-term memory (LSTM), to model the changes in Saudi Stock Exchange (Tadawul) index. this research aims at predicting the future of energy, telecommunication, financial, and industrial sectors of the stock exchange. the data was collected from Tadawul for the years 2018–2020 concerning these sectors. the AI algorithms aimed to predict the forthcoming benchmarks for the stock market sectors. the proposed models were tested against actual input data and simulation results, which produced extremely accurate results, demonstrating the effectiveness of the models. In addition, the correlation coefficient (R) of the MLP and LSTM models in predicting the values of Tadawul's four sectors integrated around 0.9950, signifying an exceptional correlation between forecasted and actual results. the forecasts were evaluated using four diverse trials, and between all the algorithms employed, LSTM produced the model's most precise predictions and best-fitting capacity.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Predictive models Prediction algorithms Data models Stock markets Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

Sentiment Analysis and Deep learning (ICSADL), international conference on

作者： Sophia S Getzi Jeba Leelipushpam Paulraj Yuvarajan D Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance; however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. this research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. the proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. the proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios.

关键词： Protocols Heuristic algorithms Clustering algorithms Autonomous aerial vehicles Routing Elliptic curve cryptography Real-time systems Security Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Momentum on Sports Performance: machine learning and Multi-Aspect Analysis 24

Momentum on Sports Performance: Machine Learning and Multi-A...

引用

proceedings of the 2024 4th international conference on Big Data, Artificial Intelligence and Risk Management

作者： Junxiao Li Xin Tan Lanfang Yi Qianting Ma College of Finance Nanjing Agricultural University Nanjing Jiangsu China College of Artificial Intelligence Nanjing Agricultural University Nanjing Jiangsu China

ISBN: (纸本)9798400709753

this study examines the multidimensional influence of momentum on competitive sports performance through a holistic analytical lens. Commencing with the application of the Information Entropy Weight Technique for Order Preference by Similarity to Ideal Solution (IEW-TOPSIS), it meticulously measures momentum by integrating psychological components, scoring trends, and skill indicators. this refined measurement approach enables an exhaustive exploration of athletes' variable performance throughout competitive engagements. Expanding on this groundwork, a Multilayer Perceptron (MLP) model is employed to forecast player performance with notable precision, reinforcing its efficacy as a predictive instrument. the research extends to strategy formulation, leveraging opponents' historical data, athletes' self-reflections, and pivotal momentum transitions to inform tactical strategies, thereby augmenting decision-making acumen. Model generalizability is demonstrated through successful application to additional tennis matches, albeit suggesting calibration with specific match category data for enhanced accuracy. Sensitivity analyses confirm the robustness of the IEW-TOPSIS and MLP models across varied parameters and data distributions, positioning them as valuable tools for coaching and athlete enhancement in diverse competitive scenarios.

关键词： IEW-TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Lane Detection in Autonomous Vehicles Using Unsupervised machine learning and Light Detection and Ranging 4th

Lane Detection in Autonomous Vehicles Using Unsupervised Mac...

引用

4th international conference on Advanced Network Technologies and Intelligent Computing, ANTIC 2024

作者： Singh, Siddharth Sharma, Shruti Singh, Adarsh Dwivedi, Rajendra Kumar Department of ITCA Madan Mohan Malaviya University of Technology Gorakhpur India

ISBN: (纸本)9783031837890

the high growth in the number of automobiles has raised the demand of enhanced driver and passenger safety measures. the goal being effective and efficient application of evolving technology to address the concerns arising with partially or fully autonomous vehicles. Accurate lane positioning and lane change detection is an integral part of Advanced Driver Assistance System which helps in safer trajectory planning. the engineering marvel of Light Detection and Ranging sensors corrects global localization error and provides centimeter-level accuracy but finds its use in restricted domain due to its computational complexity and cost implied. Lane detection is a technique for automatically road markers to ensure that cars stay in their assigned lane and do not collide with vehicles in other lanes. As an alternative, machine learning enabled vision-based lane change detection is highly regarded to provide lane-level localization maintaining high level accuracy. the algorithm design provides polynomial fitting with LiDAR data that helps model perform well in bad lighting conditions and help detect curved lane marking. the technology is well adopted based on the real-world testing scenarios which affirms its real time robustness with average of 89% lane detection accuracy. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Advanced driver assistance systems

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417页 << < 13 14 15 16 17 18 19 20 21 22 > >>

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：