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

2,630 篇 会议
1,891 篇 期刊文献
6 册 图书

馆藏范围

4,527 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,296 篇 工学
- 1,238 篇 计算机科学与技术...
- 1,046 篇 软件工程
- 566 篇 信息与通信工程
- 441 篇 控制科学与工程
- 381 篇 电气工程
- 313 篇 电子科学与技术（可...
- 254 篇 仪器科学与技术
- 240 篇 核科学与技术
- 223 篇 生物工程
- 211 篇 网络空间安全
- 200 篇 生物医学工程（可授...
- 184 篇 光学工程
- 183 篇 动力工程及工程热...
- 164 篇 化学工程与技术
- 140 篇 机械工程
- 140 篇 材料科学与工程（可...
- 123 篇 安全科学与工程
2,290 篇 理学
- 1,435 篇 物理学
- 420 篇 数学
- 380 篇 地球物理学
- 283 篇 生物学
- 260 篇 化学
- 191 篇 统计学（可授理学、...
542 篇 管理学
- 417 篇 管理科学与工程(可...
- 204 篇 工商管理
- 171 篇 图书情报与档案管...
282 篇 医学
- 231 篇 临床医学
- 208 篇 基础医学(可授医学...
- 152 篇 公共卫生与预防医...
- 109 篇 药学(可授医学、理...
100 篇 法学
87 篇 经济学
69 篇 农学
22 篇 教育学
18 篇 文学
6 篇 军事学

主题

223 篇 accuracy
207 篇 hadron colliders
153 篇 internet of thin...
152 篇 deep learning
145 篇 real-time system...
112 篇 convolutional ne...
111 篇 training
101 篇 feature extracti...
100 篇 machine learning
96 篇 computational mo...
93 篇 relativistic hea...
87 篇 predictive model...
83 篇 higgs bosons
78 篇 security
73 篇 cloud computing
68 篇 support vector m...
66 篇 medical services
64 篇 neutrons
63 篇 reliability
63 篇 artificial intel...

机构

371 篇 faculty of scien...
364 篇 department for p...
362 篇 department of ph...
359 篇 department of ph...
354 篇 department of ph...
344 篇 kirchhoff-instit...
343 篇 yerevan physics ...
306 篇 department of ph...
303 篇 dept. of astrono...
302 篇 dept. of physics...
301 篇 dept. of physics...
301 篇 fakultät für phy...
296 篇 institute of phy...
292 篇 iii. physikalisc...
287 篇 department of ph...
283 篇 institute of phy...
270 篇 instituto de fís...
259 篇 department of ph...
252 篇 erlangen centre ...
252 篇 department of ph...

作者

288 篇 c. alexa
286 篇 j. m. izen
277 篇 g. bella
275 篇 j. strandberg
274 篇 d. calvet
272 篇 c. amelung
257 篇 g. spigo
257 篇 s. mohapatra
255 篇 f. siegert
249 篇 r. ströhmer
246 篇 m. rijssenbeek
245 篇 s. jin
244 篇 g. gaudio
235 篇 hoshina k.
234 篇 y. tayalati
229 篇 fürst p.
227 篇 haungs a.
222 篇 s. guindon
222 篇 halve l.
221 篇 böttcher j.

语言

4,127 篇 英文
393 篇 其他
13 篇 中文

检索条件"机构=Computer Science and Engineering R.M.K. Engineering College"

共 4527 条记录，以下是1-10 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-DSCNet: Implementing Attention-based Deep Serial Cascaded Network for Predicting Insider Threats using Human Behaviors 3

A-DSCNet: Implementing Attention-based Deep Serial Cascaded ...

引用

3rd International Conference on Electronics and renewable Systems, ICEArS 2025

作者： Ilampiray, P. ramya, S. Thanga R.M.K. Engineering College Computer Science and Engineering Thiruvallur India

ISBN: (纸本)9798331509675

Insider threats are considered a major issue in the field of system engineering. For modern applications, which demand a seamless integration among humans and machines, human interactions along with the applications are assumed as a significant phase of operation. It generates security issues within the network while safeguarding the network from insider threats. Due to the development of technologies, vulnerabilities within the networks and third-party access from the external environment remain the primary keys for security issues. Among other security threats, insider attacks are similarly challenging as exterior threats. However, insider attacks are unrecognized for a long period, and currently no effective measures to address the security issues as well as to safeguard the network from insider threats. The primary issue faced by the current technology is to detect insider attacks within the cloud. If the information in the system gets lost, then negotiating with the cloud consumers becomes hard. moreover, cloud networks are less trusted as they lack to guarantee of security and privacy to the data. Currently, various solutions are presented to ensure external privacy for cloud systems. Yet, the challenges due to internal or insider threats must be tackled. Thus, it is crucial to address various problems produced by the traditional insider threat detection model including human actions. So, a novel deep learning-based insider threat prediction model using human behavior is suggested here. Initially, insider thread prediction data utilized for the validation are collected from benchmark resources. Next, the collected data is provided for the insider threats prediction phase. In the insider threats prediction phase, a developed Attention-based Deep Serial Cascaded Network (A-DSCNet) is used to identify the insider threats. The developed A-DSCNet is the integrated version of Deep Belief Network (DBN) and Capsule Network (CapsNet). Finally, various analyses are exec

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Air Quality Prediction with Hybrid Deep Learning Techniques: A review 4

Enhancing Air Quality Prediction with Hybrid Deep Learning T...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Divya, J. Jaison, B. Computer Science and Design R.M.K. Engineering College India

ISBN: (纸本)9798331515720

Nowadays, air pollution is among the significant and crucial areas of concern to policymakers and environmental and public health experts internationally. It has been considered that bad air can badly affect human health, ecosystems, and climate change. This air pollution, or poor air quality, has been proven to have negatively life-Threatening and serious impacts. Accurate and timely adaption of air quality for various impacts is critical to avert the adverse impacts. The paper aims to provide an in-depth review of recent advances in air quality prediction using hybrid deep learning techniques. mostly, the current methods of predicting the quality of air face challenges, like the inability to reproduce the complex and non-linear characteristics of air pollution. To tackle the existing challenges that bedevil traditional approaches, deep learning, being part of artificial intelligence with the capacity to bolster the efficiency and accuracy of the projections, has been adopted. Hybrid deep learning models, in association with physical or statistical models, offer promising approaches to enhance air quality prediction. This paper introduces the state-of-The-Art review of the major concepts and methodologies applied to air quality prediction with hybrid deep learning techniques, showing benefits and limits of such models, the summary of recent studies, and discussions on future research trends in this fast-growing and interesting field. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a Wireless IoT Networks with robust resource Distribution mechanism

Performance Analysis of a Wireless IoT Networks with Robust ...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： rohini, S. Shankari, S. R.M.K. Engineering College Department of Computer Science and Engineering Chennai India R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665462631

IoT, or the Internet of Things, has great potential as a means to link together vast quantities of equipment and gadgets in upcoming communication systems. In this research, we examine a hybrid access point (HAP) that wirelessly supplies power to the Internet of Things (IoT) gadgets and that in turn uses that power to send back to the HAP small packets received accomplished by limited block length codes. SPC has a lower transmission rate and a higher packet error rate than traditional wireless systems' long packet communication. Given this new reality, the traditional method of allocating resources in the current literature, which is based on the Shannon capacity attained by unlimited block length codes, is no longer the most efficient. In this article, we defined organizational and effective-amount-of-information even as evaluation criteria to control the network throughput as well as the packet dropping rate, as well as Enhancing transmitting effectiveness and reliability, we conscious efforts throughput of the network and the packet losses rate of each client to maximize or limit the overall effective-throughput, depending on people's unique effective-amount-of-information requests. We build effective methods to discover well-enough suboptimal solutions to the defined issues in order to deal with their non-convexity. The suggested techniques have been shown to outperform the benchmark schemes in simulations, and attain operating efficiency comparable to those of the ideal solution found by exhaustive search. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A robust model for the Identification of Bolt Loosening in Steel Structures Based on modified Convolutional Neural Network

A Robust Model for the Identification of Bolt Loosening in S...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Shankari, S. rohini, S. R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Chennai India R.M.K. Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665462631

When a bolt becomes free owing to stress, pressure, or bending stresses, this is called spontaneous releasing. A fastened joint may lose all of its preload with even a little amount of spin. That's the number one reason fasteners go loose. Preventing bridge collapse is often possible if missing bolts and nuts are identified before they are used. The focus of this study is on applying deep learning methods to create a new architecture for the early identification of bolt-nut losses in steel structures. The goals are to use deep learning methods to create a methodology for detecting nuts, bolts, and nut slots;to implement that strategy in Python;and to evaluate the effectiveness of that architecture. An 8x8 grid of bridge photos was used as input for CNN-LSTm methods. The CNN's unusually high recognition rate may be explained by the sequential nature of its extraction through convolution and pooling. Nevertheless, statistical analysis of the data indicated that there was no statistically significant distinction in object identification and classification performance among the methods used in the final design. The CNN model is recommended for spotting nuts, bolts, and nut holes on structural steel bridges because to its excellent detection rate, high accuracy, and fast throughput. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

reactive Fault Tolerance aware Workflow Scheduling Technique for Cloud Computing using Teaching Learning Optimization Algorithm 5

Reactive Fault Tolerance aware Workflow Scheduling Technique...

引用

5th IEEE International Conference on Electrical, computer and Communication Technologies, ICECCT 2023

作者： Vigilson Prem, m. Paulraj, D. R.M.K. College of Engineering and Technology Department of Computer Science and Engineering Puduvoyal India R.M.K. Engineering College Department of Computer Science and Engineering Kavaraipettai India

ISBN: (纸本)9781665493604

Cloud computing has led to a metamorphosis within the delivery model of information technology, from a product to a service. The resources of cloud computing should operate without mistakes or malfunctions is one of the primary challenges. Nevertheless, the cloud environment's ever-changing characteristics lead to a variety of unforeseen problems and malfunctions. Cloud services are hampered by their own vulnerability to disruption as a result of faults or failures in operations, causing them to perform less well than they could. To ensure the availability and dependability of crucial resources, fault tolerance is a fundamental concern. Failures should be anticipated and handled proactively. In order to achieve resilience and reliability in cloud computing, effective failure evaluation and management are required. To anticipate these problems and take the right action before they really happen, many proactive fault tolerance techniques have been proposed and are being deployed. However, most of the proactive fault tolerance methods could not yield a significant solution or help anticipate the faults. Failure to complete a task is no longer an accident but rather a typical feature in cloud computing environments. In this paper, a reactive fault tolerance-aware workflow scheduling approach (rFT A WS) for cloud environment is proposed, that is optimized for teaching and learning. This approach aims to reduce the likelihood of dynamic tasks failing before they are supposed to by taking into account the resources that are already available. The effectiveness of the suggested approach rFT A WS is assessed using the failure ratio, performance improvement rate, and rejection ratio to estimate the scheduling task. The result shows that the suggested system works better than the ones that are already in place and makes data more accessible and reliable. © 2023 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Anonymization of Sensitive Data in the Diabetes Prediction using Private Bayesian Networks 5

Anonymization of Sensitive Data in the Diabetes Prediction u...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Sethukarasi, T. Therasa, P.r. Thilagavathy, A. Ajay kumar, T.m. Dinesh, P.N. Devi Prasad, S.m. R.M.K. Engineering College Department of Computer Science and Engineering Tamil Nadu Thiruvallur India

ISBN: (纸本)9798350367171

In the modern era of automated learning and computational intelligence, early disease detection is critical for assisting practitioners in disease diagnosis and decision-making. Traditional methods, including Support Vector machine (SVm), random Forest (rF), and XGBoost, have proven effective for disease predictions but raise significant privacy concerns due to the sensitive nature of the data involved. To mitigate these privacy issues, this research study proposes the creation of a synthetic dataset for training the supervised classification models for Diabetes mellitus (Dm) prediction, ensuring the preservation of the ground truth. The proposed method employs a discriminative-generative distillation approach using private Bayesian networks to protect the data confidentiality. By using the models as intermediaries to extract information from personal data, the proposed technique enables knowledge transfer to a student network through dual channels, preventing data leakage and safeguarding sensitive healthcare information. This approach enhances the security and privacy of medical data while maintaining the accuracy and reliability of predictive models. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Forecasting Electricity Price using Convolutional Neural Networks with Chicken Swarm Optimization Algorithm 1

Forecasting Electricity Price using Convolutional Neural Net...

引用

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICAISC 2023

作者： Neelakandan, S. Varma, m. Bharath reddy, k. Sanvith reddy, N. Yeswanth R.M.K. Engineering College Department of Computer Science and Engineering India

ISBN: (纸本)9798350323795

Forecasting electricity prices is critical to the efficient operation and planning of power systems, allowing market actors, governments, and consumers to make educated decisions. This abstract provides an overview of a thorough examination and comparison of power price forecasting strategies. This paper proposes a Deep Learning model using Convolutional Neural Networks (CNN) with the Chicken Swarm optimization Algorithm (CSOA) to anticipate changes in the price of power in Australia's grid. It evaluates them in relation to other cutting-edge models. The CNN architecture is intended to extract hierarchical features from input data by leveraging its capacity to learn spatial and temporal connections. Backpropagation trains the model, adjusting the network's weights and biases to decrease predicting error. The CSO algorithm improves the optimization process and prevents the CNN from becoming trapped in local optima. CSO uses a population-based search technique to efficiently explore the solution space inspired by the collective behaviors of chickens. We have selected indicators for evaluation that will show how our model outperforms the state-of-the-art approaches at predicting future electricity costs. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion recognition Using Deep Learning

Speech Emotion Recognition Using Deep Learning

引用

2023 IEEE International Conference on research methodologies in knowledge management, Artificial Intelligence and Telecommunication engineering, rmkmATE 2023

作者： Shamini, Baby P. Varma, P. Girish Sai reddy, D. Harshith khan, P. Ahammad Department of Computer Science and Engineering R.M.K. Engineering College India

ISBN: (纸本)9798350305708

recognizing the affective qualities of speech while ignoring its semantic content is the goal of Speech Emotion recognition (SEr). Automatically conducting this activity using programmed devices is still a work in progress, despite the fact that people can do it efficiently as part of voice communication. Predicting a person's emotional state based on their words is the goal of speech emotion recognition. It enhances inter-human communication between computers and people. Despite the fact that predicting a person's emotion is challenging due to the subjectivity of emotions and the difficulty of annotating audio, "Speech Emotion recognition (SEr)" enables this through its capacity to comprehend human emotion. Tone, pitch, expression, conduct, etc., are all states that can be used as indicators of an individual's emotional state. Existing systems are not only not real-time, but also only support a single emotion. Current speech emotion prediction models are based on SVm algorithms, which might take a long time to train in order to achieve high classification accuracy. Unfortunately, the current models lack a scalable framework. Since it makes use of natural language processing, the suggested system is both precise and efficient. © 2023 IEEE.

关键词： Decision Tree Speech Emotion recognition Support Vector machine Text-to-Speech

来源：评论

学校读者我要写书评

暂无评论

AI Lip reader Detecting Speech Visual Data with Deep Learning 4

AI Lip Reader Detecting Speech Visual Data with Deep Learnin...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Geetha, C. rohan Jai, D. Sandheep krishna, A. reddy, Seelam Sai Vara Prasad R.M.K. Engineering College Department of Computer Science and Engineering Kavaraipettai Tamil Nadu Thiruvallur India

ISBN: (纸本)9798350349900

Introducing an AI-driven lipreading system adept at decoding speech across diverse languages, including English, Tamil, and Telugu. Leveraging a deep learning architecture comprising a 3D Convolutional Neural Network (3DCNN) with Bidirectional Long Short-Term memory (BiLSTm) units, the model achieves remarkable accuracy in transcribing spoken words solely from visual cues provided by lip movements. Addressing critical accessibility needs, this system holds promise for applications in assistive technologies and human-computer interaction systems. Through rigorous experimentation and evaluation, the lipreading model demonstrates an impressive overall accuracy of 98.4%, underscoring its efficacy and robustness in recognizing spoken words across multiple languages. Advanced evaluation techniques, including rOC curves, confusion matrices, and classification reports, provide comprehensive insights into the model's performance, enabling targeted refinements and optimizations. This work represents a significant advancement in the field of lipreading, offering a valuable contribution to multimodal communication and fostering inclusivity in diverse linguistic contexts. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Diabetic retinopathy Image recognition Using AI Technique in rasberry PI 1st

Diabetic Retinopathy Image Recognition Using AI Technique in...

引用

1st International Conference on Intelligent Computing, Smart Communication, and Network Technologies, ICICSCNT 2023

作者： Latha, P. Sumitra, V. Yogeshwari, k. Shyamala, P. Swathi, S. Arulmurugan, T. R.M.K. Engineering College Tiruvallur India Department of Electronics and Communication Engineering R.M.K. Engineering College Tiruvallur India

ISBN: (纸本)9783031759567

regular eye exams are especially important because diabetes can interfere with eye health. Damaged or abnormal new blood vessels can cause vision loss due to high blood sugar, which may damage the eye. Various neural and layered architectures have been applied using CNN algorithms, trained on publicly available image datasets of diabetic retinopathy. Neural networks have been observed to capture lesion color and texture specific to each disease at the time of diagnosis, similar to human decision-making. Experimenting with different features of diabetic retinopathy as inputs to a convolutional neural network is recommended. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks

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453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：