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

47,795 篇 会议
7,576 篇 期刊文献
327 册 图书

馆藏范围

55,698 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

34,424 篇 工学
- 21,276 篇 计算机科学与技术...
- 17,610 篇 软件工程
- 9,594 篇 信息与通信工程
- 6,349 篇 电子科学与技术（可...
- 6,184 篇 电气工程
- 5,875 篇 控制科学与工程
- 3,121 篇 生物工程
- 2,649 篇 光学工程
- 2,640 篇 生物医学工程（可授...
- 2,308 篇 机械工程
- 2,304 篇 动力工程及工程热...
- 2,180 篇 仪器科学与技术
- 1,693 篇 化学工程与技术
- 1,274 篇 材料科学与工程（可...
- 1,187 篇 安全科学与工程
- 1,113 篇 交通运输工程
17,984 篇 理学
- 9,486 篇 数学
- 5,864 篇 物理学
- 3,396 篇 生物学
- 3,102 篇 统计学（可授理学、...
- 2,212 篇 系统科学
- 1,800 篇 化学
7,437 篇 管理学
- 4,567 篇 管理科学与工程(可...
- 3,206 篇 图书情报与档案管...
- 2,476 篇 工商管理
2,136 篇 医学
- 1,814 篇 临床医学
- 1,686 篇 基础医学(可授医学...
- 1,116 篇 药学(可授医学、理...
1,369 篇 法学
- 1,127 篇 社会学
926 篇 经济学
- 925 篇 应用经济学
598 篇 农学
593 篇 教育学
264 篇 文学
149 篇 军事学
51 篇 艺术学
3 篇 哲学
2 篇 历史学

主题

1,393 篇 accuracy
1,248 篇 computational mo...
1,069 篇 feature extracti...
955 篇 training
789 篇 deep learning
719 篇 computer science
719 篇 real-time system...
692 篇 machine learning
636 篇 predictive model...
614 篇 optimization
519 篇 support vector m...
510 篇 computer archite...
510 篇 data models
508 篇 internet of thin...
444 篇 convolutional ne...
442 篇 neural networks
402 篇 wireless sensor ...
401 篇 bandwidth
398 篇 reliability
389 篇 monitoring

机构

168 篇 dept. of electri...
82 篇 north-west unive...
81 篇 institut univers...
79 篇 infn sezione di ...
79 篇 national centre ...
76 篇 infn sezione di ...
76 篇 institute of inf...
66 篇 università di ca...
62 篇 dept. of electr....
58 篇 dept. of electri...
57 篇 dept. of informa...
56 篇 dept. of compute...
52 篇 dept. of electri...
52 篇 school of automa...
51 篇 leiden universit...
44 篇 dept. of compute...
43 篇 dept. of electri...
42 篇 infn lnf via enr...
42 篇 in2p3 lpc campus...
39 篇 dept. of compute...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
84 篇 gal t.
84 篇 bozza c.
81 篇 chen a.
76 篇 kalekin o.
64 篇 díaz a.f.
63 篇 huang f.
53 篇 boumaaza j.
52 篇 kulikovskiy v.
41 篇 benoit d.m.
41 篇 eddymaoui a.
40 篇 gagliardini s.
40 篇 labalme m.
37 篇 androulakis g.
36 篇 coleiro a.
34 篇 de palma m.
34 篇 khatun a.
33 篇 eirini eleni tsi...

语言

48,531 篇 英文
6,296 篇 其他
639 篇 中文
212 篇 朝鲜文
59 篇 日文
4 篇 德文
4 篇 斯洛文尼亚文
1 篇 阿拉伯文
1 篇 法文
1 篇 葡萄牙文
1 篇 土耳其文

检索条件"机构=Dept. of Computer and Electrical Engineering and Computer Science"

共 55698 条记录，以下是491-500 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：

Approaches for Identifying Suicide Ideation in Social Media Texts: Comprehensive Review 3

Approaches for Identifying Suicide Ideation in Social Media ...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Sonawane, Jayshri Suresh Jain, Dinesh Sage University Dept. of Computer Science and Engineering Indore India

ISBN: (纸本)9798350384598

In contemporary society, Suicide has become a notable concern within the realm of public health. Suicidal ideation (SI) encompasses thoughts about ending one's life. Factors contributing to suicidal thoughts and actions are diverse, ranging from personal life events to enduring emotional distress. We investigate the issue of identifying such ideation on Twitter, emphasizing the usefulness of a collection of characteristics taken from the literature as well as the function of discussion context in this process. Numerous machine learning algorithms have been put forth to identify SI from internet channels, but because feature engineering and classification techniques are still lacking, the accuracy of these algorithms is still low. Therefore, by using novel deep learning and natural language processing-based feature engineering technique accuracy can be increased. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

LG-FAL: Locality-customized GSA Federated Active Learning 15

LG-FAL: Locality-customized GSA Federated Active Learning

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Wang, Shuwen Zhu, Xingquan Portland State University Department of Computer Science Portland United States Florida Atlantic University Dept. of Electrical Engineering & Computer Science Boca Raton United States

ISBN: (纸本)9798331508821

Federated Learning (FL) is a learning paradigm which constructs machine learning models using decentralized datasets, with the goal of training a globally optimized model while preserving data privacy. In practice, annotating training data for FL is expensive and time-consuming. To solve this problem, researchers proposed to integrate active Learning (AL) strategy as Federated Active Learning (FAL) framework. However, existing research on FAL has two main limitations: (1) In the active learning part, more attention is paid to the global model, while ignoring the local information;(2) In the federated learning part, the popular Federated averaging (FedAvg) method relies on the assumption that the corresponding nodes in distributed neural networks share the same importance when averaging. In this paper, in order to tackle the two limitations, we propose a locality-customized GSA federated active learning (LG-FAL) method. Specifically, (i) both local and global information are taken into consideration to evaluate and select informative data samples to annotate for active learning;(ii) we integrate Gravitational Search Algorithm (GSA) to dynamically average local network parameters into the global parameter, by mimicking the principles of gravity and motion in the universe, for effective federated learning. As a result, LG-FAL can select a small subset of informative samples considering both local and global information, and at the same time, provide an improved trade-off between communication cost and learning accuracy. Experimental results show that LG-FAL significantly outperforms the current state-of-the-art baselines in terms of performance and effectiveness. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

RPC Relay protocol for NaaS platforms 2

RPC Relay protocol for NaaS platforms

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Anirudh, R.H. Darshan, V. Dey, Kohav Phaneesh, S. Jadon, Shruti Pes University Computer Science & Engineering Dept. Bengaluru India

ISBN: (纸本)9798350360523

The decentralized internet, often termed as Web3, is envisioned as the future of the online world. It holds the promise of addressing the centralization and censorship issues prevalent in today's web landscape. Yet, a significant hurdle faced by Web3 is its reliance on centralized servers provided by major entities like AWS and Azure. The vulnerability of this reliance becomes apparent when these servers encounter downtime or other disruptions, potentially causing widespread issues. This paper focuses on the crucial necessity of decentralizing Web3's infrastructure to bolster its resilience against such outages. To accomplish this objective, we introduce an innovative RPC (Remote Procedure Call) relay protocol tailored specifically for Web3. This protocol not only caters to the requirements of Network as a Service (NaaS) platforms but also introduces incentives to motivate network nodes to function as relays. Our research and development efforts focus on two fundamental aspects: first, the technical implementation of the RPC relay protocol, and second, the incentivization mechanisms that reward network nodes for participating as relays. By enabling a more decentralized and robust infrastructure, we aim to enhance the reliability and stability of Web3 services. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Battery Degradation Heuristics for Predictive Energy Management in Shipboard Power Systems 50

Battery Degradation Heuristics for Predictive Energy Managem...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Vedula, Satish Olajube, Ayobami Omiloli, Koto Anubi, Olugbenga Moses Dept. of Electrical and Computer Engineering FAMU-FSU College of Engineering Tallahassee United States

ISBN: (纸本)9781665464543

The presence of Pulse Power Loads (PPLs) in the Notional Shipboard Power System (SPS) presents a challenge in the form of meeting their high ramp rate requirements. Considering the ramp rate limitations on the generators, this might hinder the power flow in the grid. Failure to meet the ramp rate requirements might cause instability. Aggregating generators with energy storage elements usually addresses the ramp requirements while ensuring the power demand is achieved. This paper proposes an energy management strategy that adaptively splits the power demand between the generators and the batteries while simultaneously considering the battery degradation and the generator’s efficient operation. Since it is challenging to incorporate the battery degradation model directly into the optimization problem due to its complex structure and the degradation time scale which is not practical for real-time implementation, two reasonable heuristics in terms of minimizing the absolute battery power and minimizing the battery state of charge are proposed and compared to manage the battery degradation. A model predictive energy management strategy is then developed to coordinate the power split considering the generator efficiency and minimizing the battery degradation based on the two heuristic approaches. The designed strategy is tested via a simulation of a lumped notional shipboard power system. The results show the impact of the battery degradation heuristics for energy management strategy in mitigating battery degradation and its health management. © 2024 IEEE.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

Recognition of Fingerprint Images using CNN for Cybercrime Detection System 2

Recognition of Fingerprint Images using CNN for Cybercrime D...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Kavitha, T. Patil, Bhimaraya Saraswathi, S. Rajarajeswari, S. Patil, Anita New Horizon College of engineering Dept. of Computer Engineering Bangalore India Sri Sivasubramaniya Nadar College of Engineering Dept. of Computer Science Engineering Chennai India Vellore Institute of Technology School of computer science and engineering Vellore India City Engineering College Dept. of Information Science Bengaluru India

ISBN: (纸本)9798350372892

Fingerprint identification plays a crucial role in crime detection, but manual analysis is time-consuming and error-prone. This research aims to develop an automated system for accurate and efficient fingerprint matching using machine learning. The proposed approach involves image acquisition, preprocessing, feature extraction, and classification. Fingerprint images are enhanced, binarized, and segmented. Minutiae (ridge endings and bifurcations) are extracted as features. A convolutional neural network (CNN) is trained on a dataset of fingerprint images for classification. By comparing algorithms, Random Forest achieved over 8 1 % accuracy, outperforming Decision Trees (nearly 75% accuracy). The trained CNN model can accurately match fingerprints from crime scenes with potential suspects, providing reliable evidence. The developed system offers law enforcement agencies an automated and accurate fingerprint identification tool, improving crime-solving efficiency and reducing manual effort. The proposed approach showcases the potential of machine learning in forensic applications. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Call Translator with Voice Cloning Using Transformers 9

Call Translator with Voice Cloning Using Transformers

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Khan, Nawaz Fateen Hemanth, Nandan Goyal, Navyae Pranav, K.R. Agarwal, Pooja Pes University Computer Science Engineering Dept. Bangalore India

ISBN: (纸本)9798350394474

Voice Cloning employs technology and algorithms to create an artificial or synthetic reproduction of a person's voice. To understand and mimic the distinct vocal qualities of the target speaker, including tone, pitch, cadence, and pronunciation, a machine learning model must be trained on audio samples of the speaker. This project presents itself as a revolutionary approach to the enduring problem of successful cross-lingual interactions, the paper's novel approach to speech-to-speech machine translation that incorporates voice cloning. This method allows us to synthesize speech in the target language while maintaining the original speaker's vocal characteristics. The model algorithms such as Whisper AI(WER 5% for transcription, No-Language-Left-Behind-200(44% more accurate than other models) for translation, Tacotron for speech synthesis and multiple transformers for voice cloning will be incorporated. The Voice Cloning model operates effectively on unseen voices, transcending the limitations of voice cloning will be incorporated. The voice cloning model operates effectively on unseen voices, transcending the limitations of relying solely on pre-trained models. The model successfully clones users' voices in a different language with an approximate latency of 10 seconds. © 2024 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Investigation of VGG 16 Transfer Learning and CNN Integrated Brain Tumour Detection

Investigation of VGG 16 Transfer Learning and CNN Integrated...

引用

2024 International Conference on computer, Electronics, electrical engineering and their Applications, IC2E3 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Dept. of Electronics and Engineering Dehradun India

ISBN: (纸本)9798350388534

This study had conducted an intensive exploration of the possibilities of VGG-16 and VGG-19 Convolutional Neural Network models for picture categorisation. Using a thorough method comprising substantial training and severe testing, we may observe both steady loss decrease and significant model accuracy improvements. It is assumed that the models may appropriately keep track of subtle variations in data to which they are adversarial while identifying regular patterns they may generalize. The VGG models' architecture is quite sophisticated, but as seen above, they give strong classification accuracy, with performance in nearly ideal 99 percent in many trials. This integration proves that extremely advanced deep learning instruments are competent to handle and complete even very sophisticated picture recognition assignments. Additionally, our experiments identify a few essential aspects of model adjustment and tuning identifying important techniques considerably enhancing CNN outcomes in application scenarios. This study is pioneering for the automatic picture identification discipline since it provided a strong understanding of the generality and model quicker than many real-world models. Additionally, it exhibits that the CNN structures enhance artificial intelligence's power to recognize visual input and could improve many sectors like the surveillance and health systems. The findings defined here may now open the door to more progress in deep learning and picture process analyses while reiterated the importance of CNN in modern technology. © 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

Unveiling Insights: Vision-Based Data Mining Analysis of Webpages in Transition from HTML 3 to HTML 5 5

Unveiling Insights: Vision-Based Data Mining Analysis of Web...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Chaudhary, Meena Pooja Chandwani, Gunjan Manav Rachna University Dept. of Computer Science and Technology Faridabad India Galgotias University Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350383522

Deep web material is accessed with web database requests, and returned information is packaged into dynamically generated web pages known as deep Web pages. Due to their intricate structure, it is tedious task to retrieve organized data from deep web pages. A great many approaches to address this problem are yet to be proposed, but all of them have inherent drawbacks because they are based on the website and the programming language. The contents of Sites are always shown for users to search daily, like the common two-dimensional media. This motivates us to search for an alternative way to extract deep Web information, by using some interesting popular visual features from deep Webpages, to address the limitations of past works. A novel blog vision approach is proposed in this paper to overcome these issues. This technique uses visual features in deep web pages specifically to conduct deep web data extraction. This paper also recommends a new appraisal measure to capture the required human activity to make maximum mining. The proposed methodology is highly efficient in the deep network data extraction, according to our studies with a large set of web-based data bases. © 2024 IEEE.

关键词： Data mining HTML 3 HTML5 Vision based technique Web Content Mining

来源：评论

学校读者我要写书评

暂无评论

Sentient Sound waves: Elevating Emotional Communication with AI-Generated Speech Technology 5

Sentient Sound waves: Elevating Emotional Communication with...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Roshan, Rahul G. Roshan, Rohit Sohan, M.H. Raj, S.M. Sutharsan Prasad, V.R. Badri Dept. of Computer Science and Engineering PES University Bangalore India

ISBN: (纸本)9798350361155

This research-based project is about a new way to put feelings into computer-generated speech. It has two stages: text emotion detection and emotional speech synthesis. In the former part, labeled text data is used to build models to spot the emotions. This model learns to change pitch, volume, and rhythm based on the given emotion. During the latter phase, the text is changed into neutral speech using text-to-speech (TTS) methods. The model is used for practice to find the emotion in the text, tagging the text with that emotion. Also, a deep-learning model known as a tacotron is employed to make an emotional-sounding speech. The model perfectly uses machine learning strategies to blend feelings into speech. This opens up possibilities for turning plain text into speech with feelings of varied emotions. The proposed system makes a novice and important contribution to natural language processing for emotion identification and deep learning for emotional speech synthesis. © 2024 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

eXtended Reality Services for Outdoor Cultural Spaces: System Design and Evaluation Framework Using Unbiased Biometric Data 15

eXtended Reality Services for Outdoor Cultural Spaces: Syste...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Koukopoulos, Zois Koukopoulos, Dimitrios Fidas, Christos University of Patras Interactive Technologies Lab Dept. of Electrical & Computer Engineering Patras Greece University of Patras Dept. of History-Archaeology Patras Greece University of Patras Dept. of Electrical & Computer Engineering Patras Greece

ISBN: (纸本)9798350368833

The concept of enriching the visible reality with more information has led to the development of the eXtended Reality technology, where digital elements like text, images, 3D representations and virtual scenarios, are embedded to the real world and become visible to humans via mobile devices. Cultural Heritage is embracing eXtended Reality and tries to find new ways to harvest its merits in an endless struggle to disseminate cultural information to the public and the next generations. In this paper, we are presenting an innovative intelligent Environment, operating in outdoor cultural spaces and offering personalized eXtended Reality cultural experiences to visitors. The Environment aims to support the financial sustainability of cultural heritage institutes by attracting visitors and especially younger ones, as well as create new sources of revenue for cultural heritage professionals by allowing them to create XR experiences, without the help of IT professionals and exploiting them in an online market of XR cultural experiences. We propose a novel framework to evaluate the user experience by collecting biometric data (brain activity and eye behavior) from the visitors of outdoor cultural spaces and exploring their cognition and emotions while using the new Environment. © 2024 IEEE.

关键词： Biometric Data eXtended Reality Outdoor Cultural Spaces Sustainability

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 << < 46 47 48 49 50 51 52 53 54 55 > >>

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：