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

2,823 篇 会议
2,277 篇 期刊文献
24 册 图书

馆藏范围

5,124 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,972 篇 工学
- 2,306 篇 计算机科学与技术...
- 1,974 篇 软件工程
- 646 篇 信息与通信工程
- 493 篇 生物工程
- 481 篇 控制科学与工程
- 346 篇 电气工程
- 343 篇 生物医学工程（可授...
- 299 篇 光学工程
- 244 篇 电子科学与技术（可...
- 155 篇 化学工程与技术
- 152 篇 网络空间安全
- 150 篇 机械工程
- 139 篇 安全科学与工程
- 125 篇 动力工程及工程热...
- 103 篇 交通运输工程
- 92 篇 仪器科学与技术
1,695 篇 理学
- 764 篇 数学
- 567 篇 生物学
- 505 篇 物理学
- 310 篇 统计学（可授理学、...
- 198 篇 化学
- 142 篇 系统科学
834 篇 管理学
- 485 篇 管理科学与工程(可...
- 390 篇 图书情报与档案管...
- 234 篇 工商管理
341 篇 医学
- 302 篇 临床医学
- 268 篇 基础医学(可授医学...
- 154 篇 公共卫生与预防医...
- 147 篇 药学(可授医学、理...
157 篇 法学
- 142 篇 社会学
72 篇 经济学
53 篇 农学
48 篇 教育学
21 篇 文学
3 篇 军事学
1 篇 艺术学

主题

351 篇 accuracy
267 篇 deep learning
207 篇 training
204 篇 machine learning
183 篇 feature extracti...
180 篇 real-time system...
179 篇 convolutional ne...
164 篇 computational mo...
150 篇 predictive model...
123 篇 data models
105 篇 artificial intel...
104 篇 internet of thin...
98 篇 reinforcement le...
93 篇 support vector m...
93 篇 optimization
88 篇 security
86 篇 semantics
82 篇 machine learning...
76 篇 measurement
72 篇 adaptation model...

机构

177 篇 department of co...
141 篇 moe key lab of a...
80 篇 tencent ai lab
76 篇 department of co...
66 篇 lovely professio...
51 篇 moe key lab of a...
44 篇 key laboratory o...
41 篇 the islamic univ...
39 篇 department of co...
39 篇 the islamic univ...
38 篇 shanghai ai labo...
36 篇 department of co...
32 篇 department of co...
30 篇 university of ch...
30 篇 school of comput...
30 篇 school of comput...
29 篇 department of cs...
27 篇 department of el...
26 篇 peng cheng labor...
25 篇 department of co...

作者

106 篇 yu kai
98 篇 zhao hai
57 篇 qian yanmin
55 篇 yan junchi
41 篇 zhang zhuosheng
36 篇 chen xie
33 篇 li zuchao
33 篇 chen lu
31 篇 yanmin qian
30 篇 al-turjman fadi
27 篇 lyu michael r.
25 篇 fadi al-turjman
23 篇 zhu su
22 篇 zhu jun
21 篇 guo yiwei
21 篇 junchi yan
20 篇 ramiz salama
20 篇 liu tongliang
19 篇 han bo
18 篇 pareek piyush ku...

语言

4,462 篇 英文
655 篇 其他
8 篇 中文
2 篇 德文
2 篇 朝鲜文

检索条件"机构=Department of Computer Science and Engineering-AI and ML"

共 5124 条记录，以下是471-480 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：

Comparative Analysis of Reinforcement Learning Techniques in Simulated Robotics Environments 7

Comparative Analysis of Reinforcement Learning Techniques in...

引用

7th International Conference on Intelligent Robotics and Control engineering, IRCE 2024

作者： Yoseph, Abey Tanveer, M. Hassan Voicu, Razvan Cristian Shahid, M. Farrukh Kennesaw State University Department of Robotics & Mechatronics Engineering MariettaGA United States National University of Computer and Emerging Sciences Department of Ai and Data Science Karachi Pakistan

ISBN: (纸本)9798350352399

Machine learning is a critical component of artificial intelligence and computer science that uses data and algorithms to emulate the way that humans learn and predict. Reinforcement learning, one of the many forms of machine learning, trains an agent through trial and error, with successful outcomes being rewarded and unsuccessful outcomes being penalized. The implementation of three reinforcement learning algorithms, Qlearning, Deep Q-Learning, and Double Deep Q-Learning, was tested using a series of ROS (Robot Operating System) packages in the Gazebo simulation environment. The Python openai-ros package and Gym libraries were used to input a robot into a configurable environment and test out the performance of a specific reinforcement learning algorithm. The agent's action space was discretized into three specific actions, move forward, turn left, or turn right, that the robot could take. The reward or punishment was given after each step based on if the current action moved the robot towards the goal state or away from it. For each algorithm, the agent was first pre-trained on an obstacle free environment for 200 episodes and then was placed in an environment with two box-shaped obstacles to avoid. The algorithm/neural network parameters from the pre-training environment were loaded prior to the agent being tested in the new environment. The goal state at each episode was randomly generated and the robot's performance was evaluated using the cumulative reward achieved per episode and the number of times it reached the goal. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of VADER and RoBERTa Methods for Smart Retail Customer Sentiment on Amazon Go Store

Performance Analysis of VADER and RoBERTa Methods for Smart ...

引用

2023 International Conference on Modeling and E-Information Research, Artificial Learning and Digital Applications, ICMERALDA 2023

作者： Rahmania, Rissa Pohan, Husni Iskandar Arrahmah, Annisa Istiqomah Wibowo, Suryo Adhi School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Electrical Engineering Telkom University Ai Center Bandung40257 Indonesia

ISBN: (纸本)9798350369359

The implementation of intelligent systems in the retail industry is still limited in various regions of the world. Amazon Go currently has four stores, located in the Seattle area, and has received customer reviews based on ratings that can be seen in the Google Maps feature. This paper aims to analyze Amazon Go customer sentiment through reviews and star ratings obtained from Google Maps reviews. First, we collect and prepare data from Google Maps Review. Second, we perform experiments and analysis of the VADER and Robustly Optimized BERT Pretraining Approach (RoBERTa) and compare both methods, which are represented by graphs. Lastly, both methods are evaluated in terms of precision, recall, F1-Score, and accuracy. Sentiment analysis from Amazon Go shows that most customers give it a rating of 5.0. Supported by text data from customer comments containing positive, neutral, and negative sentiments showing the relation between the rating given and the sentiment of the comment by the compound score from the results of the VADER method. Sentiment analysis on smart retail from the Amazon Go Store has provided insight and future challenges in the scope of smart retail implementation. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference 30

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Mul...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Kang, Woosung Lee, Jinkyu Lee, Youngmoon Oh, Sangeun Lee, Kilho Chwa, Hoon Sung DGIST Dept. of Electrical Engineering and Computer Science Korea Republic of Dept. of Computer Science and Engineering Korea Republic of Hanyang University Dept. of Robotics Korea Republic of Ajou University Department of Software and Computer Engineering Korea Republic of School of AI Convergence Soongsil University Korea Republic of

ISBN: (纸本)9798350358414

The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-Time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-Time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU's physical capacity. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

McCrolin: Multi-consistency Cross-lingual Training for Retrieval Question Answering

McCrolin: Multi-consistency Cross-lingual Training for Retri...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Limkonchotiwat, Peerat Ponwitayarat, Wuttikorn Lowphansirikul, Lalita Manakul, Potsawee Udomcharoenchaikit, Can Chuangsuwanich, Ekapol Nutanong, Sarana AI Singapore Singapore SCB 10X Thailand School of Information Science and Technology VISTEC Thailand Department of Computer Engineering Chulalongkorn University Thailand

ISBN: (纸本)9798891761681

Automated question answering (QA) systems are increasingly relying on robust cross-lingual retrieval to identify and utilize information from multilingual sources, ensuring comprehensive and contextually accurate responses. Existing approaches often struggle with consistency across multiple languages and multi-size input scenarios. To address these challenges, we propose McCrolin, a Multi-consistency Cross-lingual training framework, leveraging multi-task learning to enhance cross-lingual consistency, ranking stability, and input-size robustness. Experimental results demonstrate that McCrolin achieves state-of-the-art performance on standard cross-lingual retrieval QA datasets. Furthermore, McCrolin outperforms competitors when dealing with various input sizes on downstream tasks. In terms of generalizability, results from further analysis show that our method is effective for various encoder architectures and sizes. Codes and models are available at https://***/mrpeerat/McCrolin. © 2024 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Real-Time air Quality Monitoring with Edge ai and Machine Learning Algorithm

Real-Time Air Quality Monitoring with Edge AI and Machine Le...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： V. Ramu Usikela Naresh P.Arun Prakash G Shyamala P Saritha Athiraja Atheeswaran Department of CSE (AI&ML) Kakatiya Institute of Technology and Science Hanamkonda Telangana India Department of Computer Science and Engineering (AI&ML) CVR College of Engineering Mangalpalli Rangareddy Telangana India Vadasithur (via) Coimbatore Tamil Nadu India Department of Civil Engineering School of Engineering SR University Warangal Telangana Department of Civil Engineering Malla Reddy Engineering College (Autonomous) Maisammaguda Secunderabad India Department of CSE (AI&ML) Malla Reddy College of Engineering Hyderabad India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Real-time air quality monitoring is essential for public health and environmental protection, but typical centralized systems have latency, bandwidth, and privacy concerns. This work describes a novel approach to decentralized air quality monitoring that employs Edge ai and powerful machine learning techniques. IoT sensors outfitted with NVIDIA Jetson devices collect and evaluate air quality data locally. Machine learning models, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), analyze pollutants including PM2.5, CO2, and NOx in real time. Implemented across 50 urban sites with varied pollution levels, the technology reduced latency by up to $75 \%$ and bandwidth use by $60 \%$ when compared to typical cloud-based solutions. The pollutant detection accuracy was evaluated against conventional reference monitors and yielded an average correlation coefficient of 0.92. This system also used federated learning to update models based on local data, improving model accuracy by up to $15 \%$ over six months. This new strategy not only increases data processing speed and accuracy, but also protects data privacy and lowers operational costs. Significant improvements in latency, bandwidth efficiency, and model accuracy demonstrate the utility of decentralized air quality monitoring systems in urban settings.

关键词： Data privacy Accuracy Federated learning Atmospheric modeling Edge ai Bandwidth air quality Real-time systems Data models Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Survey on Machine Learning Approaches in Water Analysis 13th

A Survey on Machine Learning Approaches in Water Analysis

引用

13th Mining Humanistic Data Workshop, MHDW 2024, 9th Workshop on 5G-Putting Intelligence to the Network Edge, 5G-PINE 2024 and 1st Workshop on ai in Applications for Achieving the Green Deal Targets, ai4GD 2024 held as parallel events of the IFIP WG 12.5 International Workshops on Artificial Intelligence Applications and Innovations, aiai 2024

作者： Tsimpidi, Ilektra Sartjärvi, Rosa Juntunen, Petri Nikolakopoulos, George Robotics and AI Team Department of Computer Science Space and Electrical Engineering Luleå University of Technology Luleå Sweden Savonia University of Applied Sciences Kuopio Finland

ISBN: (纸本)9783031632266

The aim of this article is to present a survey on Machine Learning approaches for performing water analysis as in general integrating Artificial Intelligence in water analysis has a transformative potential for optimizing and sustaining water resources. Recent trends in water treatment and desalination applications effectively address pollution and scarcity challenges, while by combining ai with technologies like data analytics, water management complexities are simplified, ensuring sustainability and cost-effectiveness through predictive data assessment. This survey presents examples of the ml’s significance in water treatment and in water quality analysis, such as for enhancing accuracy in water quality index (WQI) assessments and examples of exploring and predicting pollutants in water processes, and aiding in the early detection and categorization of contaminants. Furthermore, this survey will reveal the immense potential in leveraging ml algorithms to enhance water analysis accuracy, speed, and efficiency, paving the way for reduced chemical usage and improved understanding of microbiological processes. As it will be presented, ml approaches offer valuable tools across various stages of water analysis, from identifying critical indicators to accurately measuring and predicting water parameters. The survey concludes by emphasizing the potential of ai and particularly ml to revolutionize water resource management, offering precision, efficiency, and foresight in addressing challenges of water scarcity and sustainable resource utilization. © IFIP International Federation for Information Processing 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Thermometer: Towards Universal Calibration for Large Language Models 41

Thermometer: Towards Universal Calibration for Large Languag...

引用

41st International Conference on Machine Learning, ICml 2024

作者： Shen, Maohao Das, Subhro Greenewald, Kristjan Sattigeri, Prasanna Wornell, Gregory Ghosh, Soumya Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge United States MIT-IBM Watson AI Lab IBM Research United States

We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional applications, calibrating LLMs is uniquely challenging. These challenges stem as much from the severe computational requirements of LLMs as from their versatility, which allows them to be applied to diverse tasks. Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs. THERMOMETER learns an auxiliary model, given data from multiple tasks, for calibrating a LLM. It is computationally efficient, preserves the accuracy of the LLM, and produces better-calibrated responses for new tasks. Extensive empirical evaluations across various benchmarks demonstrate the effectiveness of the proposed method. Copyright 2024 by the author(s)

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Construction of an Intelligent Knowledge-Based System Using Transformer Model 4th

Construction of an Intelligent Knowledge-Based System Using ...

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Madhumathi, B. Srivani, M. Abirami, S. Student Department of Information Science and Technology College of Engineering Guindy Anna University Tamil Nadu Chennai India Assistant Professor Department of AI/ML Sri Ramachandra Faculty of Engineering and Technology SRIHER Porur Tamil Nadu Chennai India Professor Department of Information Science and Technology College of Engineering Guindy Anna University Tamil Nadu Chennai India

ISBN: (纸本)9789819700363

A knowledge-based system (KBS) is a type of artificial intelligence (ai) that seeks to capture the knowledge of human experts in order to aid in decision-making. The process of populating a knowledge base by extracting information from unstructured sources such as pdfs, text, images, and so on is known as knowledge base construction (KBC). It is frequently difficult to deal directly with unstructured data, such as documents. KBC systems assist in storing information in an easy-to-use format. When data is stored in structured format, it becomes easier for applications to use previously inaccessible data. A knowledge-based system’s typical architecture includes a knowledge base and an inference engine. The inference engine derives insights from the knowledge base’s information. Knowledge-based systems also include an interface through which users can query and interact with the system. The main aim is to analyse and extract the key evidence from research papers by constructing a knowledge base using the Transformer Model that helps the teachers identify multiple teaching methods that are effective for the students with learning disorders. The major steps involved in the implementation of the proposed system are text preprocessing and analysis, transformer-based joint entity relation extraction and model evaluation. The dataset consists of full text file (PDF) research papers. The text preprocessing and analysis step defines two pipelines for identifying data and targets. The sentences are then represented as tokens using simple Bag-of-Words and weighted TF-IDF. The tokens are then passed through BERT to extract the relevant entities and predict relations. The joint entities and relations consist of teaching methods as entities. Finally, token embedding is performed to classify the entity. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Guided Transformer for Machine Translation: English to Hindi 20

Guided Transformer for Machine Translation: English to Hindi

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Bisht, Akhilesh Gupta, Deepa Parida, Shantipriya Amrita Vishwa Vidhyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Silo Ai Helsinki Finland

ISBN: (纸本)9798350305593

In the area of machine translation, the objective is to develop a model which can translate a piece of text from one language to another language. Large sized neural networks requires a large amount of training data to achieve a good performance level. The objective of this study is to build an explicit knowledge from the dependency parser, which can be integrated into transformer architecture. Adding an explicit knowledge to a neural machine translation network can enhance its learning process. The baseline transformer model and the proposed guided transformer model were tested on the same test data set of PMIndia Man Ki Baat session. With an addition of explicit knowledge, the proposed guided transformer model surpass the performance of baseline transformer model by +1.0 BLEU (approx.), +1.0 SacreBLEU (approx.), +1.48 Chrf, +1.44 Chrf+ and +1.39 Chrf++. © 2023 IEEE.

关键词： Blue-score Decoder Dependency Graph Dependency Parser Encoder English-Hindi Translation Explicit Knowledge Machine translation Multi head attention Positional encoding Self-attention Transformers

来源：评论

学校读者我要写书评

暂无评论

ai Approaches to Investigate EEG Signal Classification for Cognitive Performance Assessment 6

AI Approaches to Investigate EEG Signal Classification for C...

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Chatterjee, Rajdeep Chatterjee, Siddhartha Samanta, Saikat Biswas, Suman KIIT Deemed to be University School of Computer Engineering Bhubaneswar751024 India Amygdala AI Bhubaneswar751024 India College of Engineering and Management Department of Computer Science and Engineering Kolaghat721171 India Manipal University Jaipur Department of IoT & IS Rajasthan Jaipur303007 India

ISBN: (纸本)9798331516796

Scientists utilize Electroencephalogram (EEG) brain waves to evaluate different cognitive processes. It can involve the assessment of cognitive activities or the analysis of motorimagery motions. The EEG is a non-invasive and portable technique that offers exceptional temporal resolution. We have utilized two distinct EEG benchmark datasets to evaluate the efficacy of our suggested methods for extracting features and classifying data. We have utilized a range of well-known machine learning classifiers, such as long short-term memory (LSTM), one-dimensional convolutional neural networks (1D-CNN), and deep neural networks (DNN), to verify the model's accuracy both prior to and following feature selection. Our analysis reveals that the suggested process of extracting, selecting, and classifying features surpasses the current leading model in terms of performance. The suggested approaches achieve an accuracy of 93.36% and 98.65% for the EEGMAT and EEGMMIDB datasets, respectively. © 2024 IEEE.

关键词： Electroencephalography

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 << < 44 45 46 47 48 49 50 51 52 53 > >>

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：