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

4,137 篇 会议
38 册 图书
6 篇 期刊文献

馆藏范围

4,181 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,738 篇 工学
- 2,465 篇 计算机科学与技术...
- 2,042 篇 软件工程
- 616 篇 生物工程
- 587 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
- 216 篇 电气工程
- 211 篇 光学工程
- 148 篇 安全科学与工程
- 136 篇 机械工程
- 124 篇 电子科学与技术（可...
- 118 篇 化学工程与技术
- 107 篇 交通运输工程
- 91 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
720 篇 管理学
- 393 篇 管理科学与工程(可...
- 388 篇 图书情报与档案管...
- 237 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...
159 篇 法学
- 138 篇 社会学
157 篇 教育学
- 155 篇 教育学
141 篇 农学
- 140 篇 作物学
89 篇 经济学
9 篇 军事学
5 篇 文学

主题

526 篇 machine learning
243 篇 deep learning
117 篇 support vector m...
99 篇 adversarial mach...
92 篇 accuracy
92 篇 machine learning...
83 篇 forecasting
75 篇 convolutional ne...
70 篇 predictive model...
69 篇 feature extracti...
58 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 neural networks

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

3,930 篇 英文
250 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 4181 条记录，以下是3451-3460 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 on E-Commerce Knowledge Graph Recommendation Model Integrating Attention Mechanism and Random Features 22

Application on E-Commerce Knowledge Graph Recommendation Mod...

引用

proceedings of the 2022 4th international conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Jin Li Zhejiang Wanli University China

ISBN: (纸本)9781450398343

In order to effectively solve the problem of information overload, different types of models can be constructed for personalized recommendation through the analysis of user commodity interaction information and related auxiliary information in e-commerce. Traditional recommendation methods cannot resolve the complex and diverse connection and transmission relationships between entities, which can be solved to a certain extent by building a knowledge graph between entities. Graph neural network enables the deep learning technology to expand on the graph structure, and further improves the accuracy and interpretability of recommendation based on knowledge graph. Aiming at the problems that the weights of nodes and relationships in the knowledge graph network are adaptive, and some non-isomorphic graphs cannot be identified and learned sufficiently, an attention mechanism is proposed to learn different weights in the network. At the same time, the minimization dominating set problem and the maximization matching problem are efficiently solved by random features. the experimental results show that for three public data sets: Book e-commerce data set Amazon book, music e-commerce data set last FM and catering review e-commerce data set yelp2018; A private data set: a comprehensive e-commerce data set after desensitization of a medium-sized e-commerce enterprise in Zhejiang, including user information, commodity information and interactive information. the performance of the proposed algorithm in recall and normalized impairment cumulative gain (NDCG) exceeds the common recommended algorithms of machine learning, deep learning and knowledge graph.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review on DDoS attack Detection in SDN using ML

A Review on DDoS attack Detection in SDN using ML

引用

Advances in Computing, Communication Control and Networking (ICAC3N), international conference on

作者： Ritu Raj Sandeep Singh Kang University Institute of Engineering Computer Science & Engineering Chandigarh University Mohali India

the world has completely transformed in terms of technology as a result of virtualization. One application of this virtualization is SDN. In recent years, it has become a popular and widely utilised network architecture. Using SDN, or a software-defined network, the control network is divided from the data plane. Although Software Defined Networks provide a simple and obvious method for network control, they have also created a new security danger. DoS attacks, man-in-themiddle attacks, and other threats are examples of these dangers. the most frequent and common danger on this list is DDoS. By impacting the server, DDoS made it simpler to start the attack. this results in the network as a whole failing. therefore, it is essential to identify this threat in order for a server to operate safely. this research analyses the various machine learning approaches that are employed in the SDN context to identify DDoS attacks.

关键词： Systematics machine learning Telecommunication traffic Denial-of-service attack Servers Security Reliability

来源：评论

学校读者我要写书评

暂无评论

machine-learning-Based Methods for Optimizing Smartphone Performance in Fitness Activity Recognition

Machine-Learning-Based Methods for Optimizing Smartphone Per...

引用

computer Science and Blockchain (CCSB), international conference on

作者： Xun Zhang Can Lin Xiaoyang Han Junqing Yuan Zengyi Yu Zhejiang University of Technology Hangzhou China

ISBN: (数字)9798350356502

ISBN: (纸本)9798350356519

With the expanding application areas of IoT, smart fitness has become an area of growing interest. IoT based fitness trackers are already playing an important role in the smart fitness domain. this paper presents a hierarchical Human Activity Recognition (HAR) framework based on smartphone sensors and an IoT fitness activity assistance system, aiming to build a tool to support fitness training without the requirement of a personal trainer. To begin with, we propose a novel hierarchical recognition framework and creatively introduce labels related to fitness activities. We use the SMOTE algorithm for data augmentation and evaluate the performance of six ML classifiers for fitness activity recognition with different feature subsets, and the experimental results clearly demonstrate the significant advantage of the hierarchical recognition strategy in terms of accuracy. After that we focus on the recognition performance of transitional postures. Comprehensive analyses reveal that SVM and RF models excel in recognizing Continuous Activities for real-time fitness tracking, while RF and KNN are effective for Counted Activities, ideal for transitional posture recognition. Additionally, we conduct ablation experiments with time-domain, frequency-domain, and time-frequency-domain features, which show that the model exhibits superior performance when time-frequency-domain features are used simultaneously. Finally, we delve into classifier performance in specific activities by introducing confusion matrices in order to find the most accurate classifier for a specific activity. the results highlight that specific classifier selection tailored to the activity type can significantly enhance the precision and reliability of fitness tracking systems.

关键词： Support vector machines Training Accuracy Frequency-domain analysis Real-time systems Human activity recognition Reliability Time-domain analysis Classification tree analysis Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

the application of Audio Control in Social Robotics 22

The Application of Audio Control in Social Robotics

引用

proceedings of the 2022 4th international conference on Robotics, Intelligent Control and Artificial Intelligence

作者： Qiwu Zhang National University of Singapore Singapore

ISBN: (纸本)9781450398343

Along with the development of the voice recognition technology, voice control plays an increasingly important role in daily life as it offers an intuitive interface that enables hands-free control of various devices, as a result blurring the sense of boundaries between human and robot. the rising demand for voice control in daily life has motivated this paper to develop a voice control system using machine learning models for the robot model LoCoBot WX250. In conjunction with robot hardware, this trained audio control system achieves the goal of improving the experience of interaction between human and robot. Based on this system, the LoCoBot WX250 can serve as a tour guide in museums by communicating with tourists via speaker and microphone. What's more, while talking to people, the robot can respond to certain instructions, such as navigation, change position and so on. this audio control system improves upon all previous similar projects in terms of the accuracy of intent classification and keyword recognition by implementing the state-of-the-art BERT (Bidirectional Encoder Representations from Transformers) model, so that it can have a smoother conversation with human. Furthermore, to accommodate the foreign visitors in the museum and tourist spot, the audio control system can be instructed to change the language, making it even more accommodating than a human tourist guide.

关键词：

来源：评论

学校读者我要写书评

暂无评论

4th international conference on Optimization and learning, OLA 2021

4th International Conference on Optimization and Learning, O...

引用

4th international conference on Optimization and learning, OLA 2021

ISBN: (纸本)9783030856717

the proceedings contain 27 papers. the special focus in this conference is on Optimization and learning. the topics include: An Exploratory Analysis on a Disinformation Dataset;automatic Synthesis of Boolean Networks from Biological Knowledge and Data;solving Inventory Routing Problems with the Gurobi Branch-and-Cut Algorithm;iterated Local Search with Neighbourhood Reduction for the Pickups and Deliveries Problem Arising in Retail Industry;a Genetic Algorithm for the three-Dimensional Open Dimension Packing Problem;formulation of a Layout-Agnostic Order Batching Problem;neighborhood Enumeration in Local Search Metaheuristics;cryptographic Primitives Optimization Based on the Concepts of the Residue Number System and Finite Ring Neural Network;investigating Overlapped Strategies to Solve Overlapping Problems in a Cooperative Co-evolutionary Framework;comparing Local Search Initialization for K-Means and K-Medoids Clustering in a Planar Pareto Front, a Computational Study;Improved SAT Models for NFA learning;synthesis of Scheduling Heuristics by Composition and Recombination;Solving QAP with Auto-parameterization in Parallel Hybrid Metaheuristics;theoretical Analysis of a Dynamic Pricing Problem with Linear and Isoelastic Demand Functions;A Hybrid FLP-AHP Approach for Optimal Product Mix in Pulp and Paper Industry;An application of BnB-NSGAII: Initializing NSGAII to Solve 3 Stage Reducer Problem;the Horizontal Linear Complementarity Problem and Robustness of the Related Matrix Classes;incorporating User Preferences in Multi-objective Feature Selection in Software Product Lines Using Multi-Criteria Decision Analysis;reinforcement learning-Based Adaptive Operator Selection;a learning-Based Iterated Local Search Algorithm for Solving the Traveling Salesman Problem;a Hybrid Approach for Data-Based Models Using a Least-Squares Regression;a Bayesian Optimisation Approach for Multidimensional Knapsack Problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text mining and Statistical Analysis based study on the effectiveness of Work Integrated learning Program: Evidence from industry-academia collaboration between SAP Labs and BITS Pilani 22

Text mining and Statistical Analysis based study on the effe...

引用

proceedings of the 4th international conference on Information Management & machine Intelligence

作者： Annapoorna Gopal Gaurav Nagpal Department of Management BITS Pilani India

ISBN: (纸本)9781450399937

the industry and academia need to work for bridge the gap between two of them. the significance of this is acknowledged widely in the industry as well as in academics, which has led to the birth of many collaborative education programs between the industry and academic institutions. While the intent of creating these partnerships is very noble, the extent to which they have been successful needs to be continuously measured. this study evaluates the performance of one such collaborative education program that was offered for the employees of SAP Labs, an ERP solutions provider by Birla Institute of Technology and Science- Pilani, a leading university in India. It collates and analyses the 360-degree feedback from the students, the alumni, the faculty, and the organization, through text mining and statistical analysis. It concludes that such Work Integrated learning Program collaborations can produce significant benefits for both- the industry and the academia. Vaders Sentiment Analysis and Transformer have been used to sense the feeling of the alumni after pre-processing of text data and the word cloud has been generated.

关键词： learning by doing workforce upskilling 360-degree feedback industry-academia collaboration

来源：评论

学校读者我要写书评

暂无评论

Botnet Forensic Analysis in Software Defined Networks using Ensemble Based Classifier

Botnet Forensic Analysis in Software Defined Networks using ...

引用

international conference on Circuits, Communication, Control and Computing

作者： R. Sanjeetha Monica. R. Mundada G.S Vaibhavi Department of Computer Science and Engineering Sambhram Institute of Technology Bangalore India

Software Defined Networks (SDN), a developing technology is replacing the conventional networking solutions that are currently in use. It helps greatly with network programmability and disassociates data plane from control plane. Due to its centralized administration, SDN is susceptible to number of threats. Botnet attacks are the most predominant kind of attacks. Peer-to-peer (P2P) botnets are a new, sophisticated variety of botnets. It is a decentralized network of computers that lack C & C servers and have been infected with malware and cooperate for the benefit of an attacker without the owners' permission. To combat botnet attacks, there are networking system solutions that use a single machine learning (ML) classifier, like the Support Vector machine (SVM), decision tree (DT), etc. To create a more dependable and precise detection and mitigation application, detection speeds must be improved. In order to provide a system that effectively detects, classifies botnet traffic as Peer-to-Peer (P2P) and mitigates it, this paper uses extensive forensic analysis by combining SDN with decision tree and bagging integrated as ensemble machine learning classifiers to satisfy the necessary needs. this suggested method has 97 percent accuracy rate for identifying and mitigating botnet attacks on SDN networks.

关键词： Support vector machines Botnet Forensics Computational modeling machine learning Predictive models Peer-to-peer computing

来源：评论

学校读者我要写书评

暂无评论

Explainable AI-Driven machine learning Approach for Prediction of Acoustic-Based Fire Extinction

Explainable AI-Driven Machine Learning Approach for Predicti...

引用

Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), international conference on

作者： Baneswar Sarker Suraj Gupta Gajendra Singh Piyush Kumar J Maiti Department of Industrial and Systems Engineering Indian Institute of Technology Kharagpur Kharagpur India Ranbir & Chitra Gupta School of Infrastructure Design & Mgmt. Indian Institute of Technology Kharagpur Kharagpur India Centre of Excellence in Safety Engineering and Analytics Indian Institute of Technology Kharagpur Department of Industrial and Systems Engineering Centre of Excellence in Safety Engineering and Analytics Indian Institute of Technology Kharagpur Kharagpur India

ISBN: (数字)9798350369786

ISBN: (纸本)9798350369793

Acoustic fire-extinguishing system is an alternative system for the safe handling and control of fire accidents by extinguishing different classes of fires. It is necessary to accurately identify and predict the extinction and non-extinction states of the flames based on certain characteristic features. It is also important to identify the most important features governing the classification of the states of the flame. Both of these can be achieved by the combination of deep learning techniques and explainable artificial intelligence (XAI). In this study, models like artificial neural networks (ANN) and convolution neural networks (CNN) were deployed on an experimental dataset to classify the extinction states of the flame based on features, namely, flame sizes, fuel type, airflow, decibel, frequencies, and distance range. On the implementation of ANN, 95% and 92% accuracy were obtained, while 97% and 98% accuracy were obtained on a CNN model, for the liquid and LPG fuels respectively. the application of XAI in this study indicates that distance range has the maximum impact among all features of the model.

关键词： Deep learning Explainable AI Atmospheric modeling Computational modeling Fires Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Risk Assessment Analysis for SMEs Loan Grant 4

Machine Learning Based Risk Assessment Analysis for SMEs Loa...

引用

4th international conference on Communication, Information and Computing Technology, ICCICT 2021

作者： Anglekar, Sumegh Chaudhari, Urvee Chitanvis, Atul Shankarmani, Radha Sardar Patel Institute of Technology Mumbai India

ISBN: (纸本)9781665404303

Lending money is a major activity of the banking industry. Principal borrowers pays interest to the bank along with the principal the depositor has borrowed. Large number of Non-Performing Assets (NPAs) are formed due to failure to repay the money. Evaluation of the customers data for credit risk is an important field in risk management in finance. the decision whether the application is rejected or accepted is led by credit risk evaluation. Many times loans are sanctioned without any background check because the firm has/had a good name in the market;thus lessening the scope of new Small Medium Enterprises (SMEs) to get financial help. Also most of the current systems consider only the financial aspects. Our idea is to create a model which automatically calculates the credit worthiness of an applicant which not only considers the data directly provided by applicants but also extract insights from their behavioral and psychological trends of spending using Clustering Algorithms, Classifiers,etc. © 2021 IEEE

关键词： Finance

来源：评论

学校读者我要写书评

暂无评论

Named Entity Recognition of Chinese Legal Text Based on BERT

Named Entity Recognition of Chinese Legal Text Based on BERT

引用

international conference on Applied machine learning (ICAML)

作者： Huawei Lu Yinan Peng Internet Application Security Department Unicom Digital Technology Co. Ltd Beijing China Central South University The School of Computer Changsha China

With the deepening of national judicial reform, how to combine artificial intelligence with judicial work has become a research emphasis in judicial intelligence research. Aiming at polysemy problem in Chinese, and characteristics of Chinese legal text that complicated context, professional, and diverse types of entities, we design a named entity recognition method for Chinese legal text based on BERT. Firstly, we build a Chinese legal text corpus, and utilize the corpus to domain pre-train the pre-training model BERT to make it perform better for named entity recognition task in Chinese legal text. Secondly, we design the method of adding clue words and the method of replacing synonyms for training data augmentation to increase the diversity of training data. Finally, we combine the BERT model after domain pre-training with a CRF layer, and utilize the datasets after data augmentation to train it. Meanwhile, we utilize adversarial training in the training process to improve the generalization ability of the model. To verify the performance of our model, we conduct experiments on the competition data set of the information extraction track of the China Legal Intelligence Technology Evaluation Competition, which proves the feasibility and effectiveness of the method.

关键词： Training Adaptation models Solid modeling Law Text recognition Bit error rate Semantics

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419页 << < 342 343 344 345 346 347 348 349 350 351 > >>

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：