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

671 篇 会议
16 篇 期刊文献
7 册 图书

馆藏范围

694 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

592 篇 工学
- 520 篇 计算机科学与技术...
- 281 篇 软件工程
- 155 篇 信息与通信工程
- 117 篇 电气工程
- 41 篇 生物医学工程（可授...
- 40 篇 生物工程
- 28 篇 控制科学与工程
- 24 篇 动力工程及工程热...
- 22 篇 化学工程与技术
- 21 篇 光学工程
- 21 篇 环境科学与工程（可...
- 20 篇 电子科学与技术（可...
- 18 篇 材料科学与工程（可...
- 15 篇 机械工程
- 12 篇 安全科学与工程
- 11 篇 建筑学
200 篇 理学
- 133 篇 数学
- 52 篇 统计学（可授理学、...
- 46 篇 生物学
- 34 篇 物理学
- 30 篇 系统科学
- 22 篇 化学
136 篇 管理学
- 88 篇 图书情报与档案管...
- 55 篇 管理科学与工程(可...
- 34 篇 工商管理
33 篇 医学
- 32 篇 临床医学
- 26 篇 基础医学(可授医学...
- 19 篇 药学(可授医学、理...
20 篇 法学
- 15 篇 社会学
14 篇 经济学
- 14 篇 应用经济学
9 篇 教育学
7 篇 农学
3 篇 文学
2 篇 军事学

主题

39 篇 big data
34 篇 data mining
27 篇 cloud computing
14 篇 data models
13 篇 internet of thin...
13 篇 soft sensors
12 篇 mapreduce
12 篇 machine learning
10 篇 deep learning
9 篇 predictive model...
9 篇 forecasting
8 篇 soft computing
8 篇 accuracy
7 篇 support vector m...
7 篇 feature extracti...
7 篇 privacy
6 篇 data security
6 篇 optimization
6 篇 data analytics
6 篇 computational mo...

机构

5 篇 taiyuan univ tec...
5 篇 beihang univ sch...
4 篇 univ chinese aca...
4 篇 cairo
4 篇 school of data a...
4 篇 nanjing univ inf...
3 篇 beijing univ pos...
3 篇 department of in...
3 篇 university of el...
3 篇 business develop...
3 篇 chongqing univ p...
3 篇 sun yat sen univ...
3 篇 chongqing univ p...
3 篇 henan univ sch c...
3 篇 department of co...
3 篇 edinburgh napier...
3 篇 south china univ...
3 篇 school of comput...
2 篇 school of inform...
2 篇 department of co...

作者

4 篇 guo shuai
3 篇 kirichek ruslan
3 篇 zaslavsky arkady
3 篇 wang ping
3 篇 hassanien aboul ...
3 篇 huang haihui
3 篇 gao yuxiang
3 篇 liu qi
3 篇 vikrant bhateja
3 篇 suresh chandra s...
3 篇 fuyong ge
3 篇 ziyi su
3 篇 liu xiaodong
3 篇 misra sanjay
3 篇 gai keke
3 篇 qiu meikang
3 篇 bera tushar kant...
3 篇 liu tao
3 篇 nagaraju j.
3 篇 zhou jiehan

语言

690 篇 英文
3 篇 其他
1 篇 中文

检索条件"任意字段=3rd International Conference on Soft Computing in Data Science, SCDS 2017"

共 694 条记录，以下是41-50 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：

A Model for Evaluating the Effectiveness of News Dissemination under the Combination of Big data and Artificial Intelligence

A Model for Evaluating the Effectiveness of News Disseminati...

引用

data Analytics, computing and Artificial Intelligence (ICDACAI), international conference on

作者： Chenjun Liu Yan Xu College of Liberal Arts Journalism and Communication Ocean University of China Qingdao China School of Information Science and Engineering Hunan Institute of Science and Technology Yueyang China

ISBN: (数字)9798331519032

ISBN: (纸本)9798331519049

In today's era of information explosion, with the rapid development of big data technology and artificial intelligence, the form of news dissemination and the assessment mode of dissemination effect are undergoing profound changes. The traditional method of evaluating the effect of news dissemination relies on limited indicators and a single data source, which is difficult to accurately reflect the multidimensional response of the audience and its dissemination path in modern news dissemination. In contrast, this paper proposes a new news communication effect assessment model by combining big data analysis and artificial intelligence algorithms, which can effectively process massive data, deeply explore the audience's behavioral characteristics, emotional changes and information dissemination path, and then provide a more accurate assessment of the communication effect. Although AI reduces the demand for labor in conventional occupations, it increases the demand for labor in non-conventional occupations, which mainly comes from the increase in the demand for non-conventional cognitive occupations such as management and technology. The job creation effect of AI is not only reflected in the connotation, i.e., the increase in the number of demand for the labor force of the already existing non-conventional occupations. The results of the study show that the deep combination of big data and artificial intelligence not only significantly improves the depth and breadth of the analysis of news communication effects, but also provides a more intelligent and automated solution for the future evaluation of communication effects.

关键词： Industries Privacy Technological innovation Sentiment analysis Accuracy soft sensors Big data data models User experience Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Machine Learning Security for the Internet of Things: A Bibliometric Analysis

Blockchain and Machine Learning Security for the Internet of...

引用

Pervasive computing and Social Networking (ICPCSN), international conference on

作者： Jaideep Kaur Mudhar Jyoteesh Malhotra Ajay Kumar Singh Monika Anand Computer Engineering Guru Nanak Dev University Amritsar India Electronics Engineering Regional Campus Guru Nanak Dev University Jalandhar India Computer Science and Engineering Chandigarh University Mohali India

The Internet of Things has developed as a catalyst for innovation across numerous industries, from home automation to smart cities to 4IR primarily Industry 4.0. Through the internet, IoT devices interact and exchange information. Beyond its potential for development, IoT devices are divergent, ubiquitous, memory-and computational-power-constrained, making them vulnerable to a range of security and privacy risks. Blockchain, a decentralised and tamper-proof technology, has recently been introduced in the BIoT domain for securing data handling activities and inculcating trusted transactions. In anticipation of IoT System vulnerabilities, Machine Learning (ML) algorithms yield accurate findings for large and complicated databases. This study conducts a bibliometric study from the Web of science (WoS) database from 2017 to 2022 in the area of ML-based BIoT security using Prisma guidelines. Rankings of the most productive and influential writers, articles, and sources are based on total publications and citations. Text data content analysis, Author keywords, index keywords are utilized to highlight research hotspots and future trends in the ML-Based BIoT security domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Twitter data Using Machine Learning Approaches 3rd

Sentiment Analysis of Twitter Data Using Machine Learning Ap...

引用

3rd international conference on soft computing and its Engineering Applications, icsoftComp 2021

作者： Gaba, Vishal Verma, Vijay National Institute of Technology Kurukshetra Haryana Kurukshetra India

ISBN: (纸本)9783031057663

Twitter is one of the most widely used social media microblogging platforms. It generates a large amount of opinioned data every day in the form of tweets. This makes it a suitable choice for sentiment analyses and many other studies. This work investigates different machine learning approaches for analyzing sentiments of tweets aiming at enhanced accuracy. In particular, we have suggested a framework that is based on a hybrid neural network model by combining Convolutional Neural Network (CNN) and Bi-Directional Long Short Term Memory (BiLSTM). Twitter API is used to collect tweets with specific keywords related to sports, politics, news, healthcare, and technology. While fetching data, hashtags and emojis are used, which are later converted into text form for assessing their effect on overall performance. The textual data is encoded using modified TF-IDF and Glove Vector embedding in Neural Network (NN) models with vectors pre-trained on Twitter data. A comparative analysis is also presented for the various machine learning algorithms (SVM, Naïve-based, Decision tree, KNN) with different datasets (IMDB, CMrd, 1.6M Kaggle, and custom-built datasets) based on accuracy and other metrics such as f-score, precision and recall. A considerable improvement is observed when hashtags and emojis are utilised with the hybrid CNN-BiLSTM model. © 2022, Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

LSTM-DAM: Malicious Network Traffic Prediction for Cloud Manufacturing System 1

引用

3rd EAI international conference on Edge computing and IoT, EAI ICECI 2022

作者： Zhao, Longbo Li, Bohu Gu, Mu School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Aerospace Smart Manufacturing Technology Development Co. Ltd. Beijing China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

With the rapid development of Internet of Things (IoT), the applications of cloud manufacturing system are growing dramatically, resulting in increasing network heterogeneity and complexity. Network traffic prediction plays an important role in the stable operation of cloud manufacturing systems and the optimal configuration of network systems. However, existing works perform poorly confronting the data which has long time series properties and complex temporal features. To address this problem, we construct a malicious network traffic prediction model based on long and short-term memory (LSTM) neural network and dual attention mechanism. Integrated with the dual attention units of feature space and time sequence, our LSTM model can realize the dynamic correlation between malicious traffic and features series. We first obtain the weight parameters of the input data based on feature attention mechanism, and then leverage LSTM model with the attention mechanism to form a temporal attention module. These two modules strengthen the influence of key historical information. Finally, the malicious traffic prediction result of cloud manufacturing systems can be obtained from our model. The experimental results on real industrial dataset show that the prediction effect of LSTM-DAM model is better than LSTM and CNN-LSTM. Based on CIC-IDS-2017 dataset, the method also performs well in Internet malicious traffic prediction, representing great generalization ability. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Toxic Comments Classification using LSTM and CNN

Toxic Comments Classification using LSTM and CNN

引用

Applied Artificial Intelligence and computing (ICAAIC), international conference on

作者： Sampurna Bhattacharya Bhavani Gowri Shankar B. Pitchaimanickam A. Alice Nithya Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Online platforms have grown to be an important medium for expression and communication in the digital era. But the anonymity and absence of in-person communication on these platforms often encourage the spread of offensive remarks, which can be harmful to both people and communities. Before classifying comments as dangerous, natural language processing, or NLP, must first comprehend and assess textual data in order to identify feelings, patterns, and context that may be harmful. Tokenizing the comments, generating features for the classification model, and preprocessing the text input are all done in this instance using natural language processing approaches. Specific NLP methods such as sequence padding, text vectorization, and tokenization may be covered in more detail. This study combines the architectures of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) to present a unique technique for categorizing harmful remarks. This study pre-processes the text data to eliminate noise and unnecessary information. Next, we use word embeddings to embed the comments into numerical vectors. Next, in order to capture the spatial and sequential relationships present in the text data, this study uses a hybrid model that combines CNN and LSTM layers. The CNN component assists in identifying local patterns and characteristics in the comments, while the LSTM component allows the model to comprehend the sequential flow of language. This study uses a publicly accessible dataset of labelled harmful remarks to train and assess the proposed model. The proposed model’s performance is measured using common measures including accuracy, precision, recall, and F1-score.

关键词： Deep learning soft sensors Noise data preprocessing data models Vectors Tokenization

来源：评论

学校读者我要写书评

暂无评论

Wildfire and Smoke Detection Using YOLO-NAS

Wildfire and Smoke Detection Using YOLO-NAS

引用

computing and Machine Intelligence (ICMI), international conference on

作者： Stephane Maillard Mohammad Safayet Khan Alexander Cramer Ebru Karanci Sancar Department of Computer Science Central Michigan University Mount Pleasant MI United States

ISBN: (数字)9798350372977

ISBN: (纸本)9798350372984

Wildfires pose a persistent threat to the environment, human lives, and property globally, necessitating effective early detection for firefighting, environmental protection, and public safety. This paper is focusing on the YOLO-NAS model and the Adam/AdamW optimizers for accurate and swift wildfire and smoke detection in various scenarios. The motivation lies in the critical need for a versatile detection model to address the challenges posed by these devastating natural disasters and their environmental impacts. The main contribution of this study resides in the integration of data from aerial, infrared, satellite, and web cam sources into a unified dataset with YOLO-NAS and the evaluation of the Adam W optimizer which was relatively unexplored in previous papers. The YOLO-NAS-M architecture, coupled with the Adam optimizer, is chosen as it provided the best global performance on evaluation when compared to other models. The model demonstrates improved performance in mean average precision and recall across diverse datasets. It achieves a mAP@0.50 of 73.39% and a mAP@0.50:0.95 of 42.86% on the full dataset. For the webcam and infrared datasets, mAP@0.50 is over 91 %, highlighting its potential for real world applications. Despite challenges in precision and F1 score, the study contributes valuable insights to wildfire detection, emphasizing the importance of architectural choices and optimization strategies.

关键词： Wildfires Satellites Webcams soft sensors Computer architecture Quality control Public security

来源：评论

学校读者我要写书评

暂无评论

Design of Watchdog Circuit using Decision Trees for Detection of Single Event Upsets in Processor 3

Design of Watchdog Circuit using Decision Trees for Detectio...

引用

3rd international conference on Inventive Research in computing Applications, ICIRCA 2021

作者： Varaprasad, B.K.S.V.L. Anilkumar, Rahul Prasad, Bondapalli Akhilesh Bondapalli, Shivani Prasad Padmapriya, K. U R Rao Satellite Centre Indian Space Research Organization Bangalore India Imaging and Camera Group Intel Technology India Pvt. Ltd. Bangalore India University Visvesvaraya College of Engineering Department of Computer Science Bangalore India

ISBN: (纸本)9780738146270

Digital circuits operating in space are susceptible to Single Event Upsets (SEU) caused by radiation. The single event upset (SEU) susceptibility is more pronounced in newer technology nodes and SRAM based FPGAs. In processors implemented with these FPGA-based systems, the resultant soft errors may lead to silent data corruption (SDC) and functional interruption (FI), spawning adverse effects which may even result in mission failure. Hence, there is a need to detect soft errors and correct them immediately to safeguard applications from SDC and FI. In this paper, the design of a watchdog circuit that can alert the system when potential radiation upsets occur in a pipelined processor by identifying a corrupted state change is proposed. A machine learning decision tree model is first built which maps the processor register values to the processor state at any given instant of time. This model is then converted to a logic function from which the watchdog circuit is derived. The decision tree model achieves F-score values of 0.99 and 0.94 in the two simulation regimes tested. The corresponding watchdog circuit implemented in hardware is miniscule at 190 logic gates and achieves an extremely fast maximum inference time of 2.1 nanoseconds. The performance metrics obtained from the watchdog circuit are in line with the decision tree model when the fault simulations are re-run with new data. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Design of an Efficient User Interface for Ubiquitous soft computing Environment 3

Design of an Efficient User Interface for Ubiquitous Soft Co...

引用

3rd international conference on Inventive Research in computing Applications, ICIRCA 2021

作者： Blesslin Sheeba, T. Sujatha, T. Premnath, S.P. Devi, V. Beno, A. Mary, S. Suma Christal R.M.K. Engineering College Department of Ece Kavaraipettai India Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Sri Krishna College of Engineering and Technology Department of Ece Coimbatore India Guru Nanak College Department of Computer Applications Chennai India Dr. Sivanthi Aditanar College of Engineering Department of Electronics and Communication Engineering Tiruchendur India Panimalar Institute of Technology Department of Information Technology Chennai India

ISBN: (纸本)9780738146270

The Fuzzy Agent computing System is a competitive way of establishing an interactive middleware component in a Ubiquitous computing Environment (UCE). However, there are some difficulties faced along the way such as high component building time imposed on users working in a heterogeneous environment and also high memory consumption. To make the middleware adapt to the users benefit, the proposed fuzzy agent computing system attempts to work in an online deep-rooted learning methodology. The purpose of this work is to establish a full-fledged connection between the data innovation gear and the individuals with the help of UCE devices in an undetectable network. It ensures that users prerequisites are fulfilled with this dynamically built computational environment. Because of the vast database available online without metadata repository and ontology, finding the apt service that will meet customers' requirements, proves to be a hassle. To aid the end users with the necessary services, a fuzzy agent computing system in an ubiquitous computing environment is proposed in this work resulting in reduced CBT and MC. This work focuses on the communication between the device and the user to create quick access to the administration and elements available in the Ubiquitous computing Environment. © 2021 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Evaluating RAG Pipeline in Multimodal LLM-based Question Answering Systems

Evaluating RAG Pipeline in Multimodal LLM-based Question Ans...

引用

Automation, computing and Renewable Systems (ICACRS), international conference on

作者： Madhuri Barochiya Pratishtha Makhijani Hetul Niteshbhai Patel Parth Goel Bankim Patel Computer Science & Engineering Department Devang Patel Institute of Advance Technology and Research Charotar University of Science and Technology (CHARUSAT) Changa Anand India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Recent improvements have increased the adoption of Multimodal Large Language Models (MLLMs) over traditional uni-modal systems since they can manage and combine information from several types of data. However, current multimodal systems have certain limitations, particularly when it comes to retrieving relevant information for domain-specific queries. This study investigates how Retrieval-Augmented Generation (RAG) approaches can help multimodal LLMs provide more contextually accurate answers from external data sources for Question and Answering (Q&A) systems. The research compares two state-of-the-art models—Google's Gemini-1.0-Pro and OpenAI's GPT-4o-mini for a Q&A system that utilizes Multimodal RAG architecture. Additionally, the study incorporates several embedding models, including Text-embedding-ada-002-v2 and embedding-001, to further improve retrieval performance. In the absence of any standardized criterion, the study used a custom-made multimodal dataset and evaluated the system using six metrics defined by human analysis. The results revealed that using RAG with multimodal LLMs greatly improves performance in Q&A tasks, with GPT-4o-mini slightly outperforming Gemini-1.0-Pro by 5%. These findings promote advancements for research in the field of Multimodal-RAG systems and highlight their potential for much better information retrieval in specialized areas.

关键词： Measurement Renewable energy sources Generative AI soft sensors Large language models Retrieval augmented generation Pipelines Computer architecture Information retrieval Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Treatment Prediction using Dual Adaptive Sequential Networks

Treatment Prediction using Dual Adaptive Sequential Networks

引用

Applied Artificial Intelligence and computing (ICAAIC), international conference on

作者： Salva Sachin Benedict A Reyana Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

The application of advanced forecasting techniques has attracted major interest in the area of medicinal study and treatment as a method of increasing quiet care. This research study introduces a new method for predicting the best course of treatment based on individual persistent profiles, called Double Adaptive Sequential Networks (DASN). The DASN enhances the accuracy and strength of treatment predictions by combining the control of successive neural systems with adaptable learning components. The system prepares and fine-tunes two parallel successive systems using verifiable persistent information, including genomic data, treatment outcomes, and restorative records. While the moment arrange focuses on encoding flexible designs that evolve over time as patients respond to various medications, the primary arrange records different conditions inside persistent information. DASN’s adaptable character is then achieved. DASN’s adaptability is accomplished by a method of active learning that continually adjust the network’s weights in response to ongoing data from responses. This enables the display to detect slight modifications to uniform responses and adjust predictions accordingly. Furthermore, DASN is integrated with a fortification learning component, which enables it to iteratively improve treatment recommendations by simulating possible persistent reactions was carried out using various runs of understanding cases and treatment scenarios in order to validate the viability of DASN. The results demonstrate that, in terms of treatment precision and flexibility, DASN consistently outperforms current predictive models. The model has the potential to revolutionize personalized medication due to its ability to adapt to changing quiet elements and treatment patterns.

关键词： Adaptation models Sentiment analysis Adaptive systems Computational modeling soft sensors Text categorization data models

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70页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：