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

30,833 篇 会议
5,143 篇 期刊文献
250 册 图书

馆藏范围

36,226 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

22,807 篇 工学
- 15,823 篇 计算机科学与技术...
- 13,311 篇 软件工程
- 5,801 篇 信息与通信工程
- 3,516 篇 控制科学与工程
- 2,697 篇 电子科学与技术（可...
- 2,676 篇 电气工程
- 2,346 篇 生物工程
- 1,879 篇 生物医学工程（可授...
- 1,557 篇 光学工程
- 1,468 篇 机械工程
- 1,335 篇 动力工程及工程热...
- 1,271 篇 仪器科学与技术
- 1,247 篇 化学工程与技术
- 1,118 篇 建筑学
- 1,093 篇 土木工程
- 1,033 篇 安全科学与工程
- 954 篇 材料科学与工程（可...
11,903 篇 理学
- 6,333 篇 数学
- 3,251 篇 物理学
- 2,603 篇 生物学
- 2,114 篇 统计学（可授理学、...
- 1,366 篇 系统科学
- 1,253 篇 化学
5,795 篇 管理学
- 3,469 篇 管理科学与工程(可...
- 2,613 篇 图书情报与档案管...
- 1,947 篇 工商管理
1,599 篇 医学
- 1,386 篇 临床医学
- 1,297 篇 基础医学(可授医学...
- 840 篇 药学(可授医学、理...
1,056 篇 法学
- 848 篇 社会学
693 篇 经济学
542 篇 农学
457 篇 教育学
156 篇 文学
78 篇 军事学
43 篇 艺术学
3 篇 哲学

主题

1,076 篇 accuracy
829 篇 feature extracti...
828 篇 computational mo...
712 篇 deep learning
676 篇 computer science
671 篇 training
513 篇 real-time system...
509 篇 support vector m...
496 篇 machine learning
442 篇 predictive model...
408 篇 internet of thin...
354 篇 convolutional ne...
349 篇 data models
340 篇 computer archite...
328 篇 reliability
312 篇 optimization
282 篇 data mining
277 篇 routing
254 篇 wireless sensor ...
249 篇 conferences

机构

83 篇 institut univers...
82 篇 north-west unive...
81 篇 national centre ...
79 篇 infn sezione di ...
76 篇 infn sezione di ...
76 篇 institute of inf...
75 篇 tno technical sc...
67 篇 université de st...
66 篇 università di ca...
62 篇 dept. of informa...
61 篇 nikhef national ...
59 篇 dept. of compute...
58 篇 dept. of informa...
56 篇 dept. of compute...
53 篇 leiden universit...
52 篇 school of automa...
49 篇 dept. of compute...
48 篇 dept. of compute...
45 篇 dept. of electri...
44 篇 dept. of compute...

作者

85 篇 ferrara g.
85 篇 ardid m.
85 篇 gal t.
85 篇 bozza c.
84 篇 calvo d.
82 篇 kalekin o.
81 篇 chen a.
80 篇 díaz a.f.
80 篇 boumaaza j.
80 篇 coleiro a.
78 篇 gozzini s.r.
70 篇 dallier r.
69 篇 huang f.
60 篇 anguita m.
52 篇 kulikovskiy v.
44 篇 del burgo r.
41 篇 benoit d.m.
41 篇 eddymaoui a.
40 篇 gagliardini s.
40 篇 labalme m.

语言

34,185 篇 英文
1,557 篇 其他
331 篇 中文
104 篇 日文
46 篇 朝鲜文
3 篇 德文
2 篇 斯洛文尼亚文
1 篇 法文
1 篇 葡萄牙文

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

共 36226 条记录，以下是721-730 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：

AI-Based Indian Currency Detection for Visually Challenged Users

AI-Based Indian Currency Detection for Visually Challenged U...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Shopika, S. Senthil Velan, A.S. Dharun Prakash, S.R. Pavithra, S. Lakshmi, R Poornima Ponnusamy, R. Chennai Institute of Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798331510022

For denomination recognition, this Indian Currency Detection System will use a CNN trained on an extremely large and diverse set of Indian banknotes from 10 to 2000. It possesses an amicable interface through which images can be captured using the camera of the user's smartphone, providing real-time audio feedback to denominate the banknote without requiring any visual assistance. Made with the features of capturing an image, real-time recognition, and user-friendly design, these are made to add a great experience for smooth navigation by a blind person. The novel and innovative features make this Indian Currency Detection System unique. Using CNN, which has been trained on the comprehensive set of Indian banknotes from 10 to 2000, the software lets a user capture banknote image directly by the smartphone camera. It allows knowing the denomination through real-time audio feedback without any visual assistance. Such characteristics include image capture, real-time identification, and designing user-friendly user interfaces that make easy navigation of the surroundings possible for the visually impaired. It does more than detect currency. It significantly contributes to the discussion regarding the development and availability of more assistive technologies. It is usable and aims to bring about greater accessibility and inclusivity in promoting financial independence among visually impaired people. Contributing to the ability of cash transactions among the visually impaired to gain confidence in freedom and security, this project aligns with a broader discussion related to assistive technologies. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Dirt Identification and Removal based on Non-Contact Infrared Temperature Sensor on Solar Panel 7

Dirt Identification and Removal based on Non-Contact Infrare...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Rupin, Rezmah Jemima Hasan, Imran Jahan, Rownak Haque Ontor, Md. Rakibul Islam, Md. Motaharul East West University Dept. of Computer Science Engineering Dhaka Bangladesh United International University Dept. of Computer Science Engineering Dhaka Bangladesh

ISBN: (纸本)9798350341485

Temperature sensing is a technique to detect dirt on a solar-panel-surface that can influence its surface temperature and can reduce its performance, which necessitates monitoring to optimize solar panel output generation, reduce unnecessary costs, and perform efficient cleaning. Temperature sensing can achieve faster and more accurate detection of dirt without using any robotic cameras or manual observation. In this study, a method is proposed to detect dirt on a solar panel with the help of an MLX90614 sensor, a DHT22 sensor connecting with Arduino UNO components. DC motors and gear motors are being used for the removal of accumulated dirt. The temperature of the solar panel surface is measured by an MLX90614 sensor using infrared radiation, while the environment's humidity and temperature are measured by a DHT22 sensor. The system implies measuring the solar panel's temperature and comparing it to the ambient temperature. This system aims at improving previously proposed dirt detection methods using this approach and suggests a motor-driven dirt removal technique. © 2023 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

Transformer-based Self-Supervised Imputation and Attention GANs Oversampling for Medical Data Processing 31

Transformer-based Self-Supervised Imputation and Attention G...

引用

31st Annual IEEE International Conference on High Performance Computing, Data, and Analytics, HiPC 2024

作者： Singh, Aryan Kumar Saikia, Arpit Baro, Pranita Borah, Malaya Dutta Dept. of Computer Science and Engineering National Institute of Technology Silchar Silchar India

ISBN: (纸本)9798331509095

Dealing with missing data and class imbalance is a necessity for the development of a solid predictive model in medical research. This work presents a novel hybrid dynamic method devoted to addressing these dual challenges, specifically focusing on medical datasets. In this work, we investigate the incompleteness and imbalance of the dataset using two sophisticated measures: the Incompleteness Factor and the Imbalance Ratio. These metrics are used to guide customized approaches. A transformer-based imputation method is employed to learn complex data dependencies to impute missing data. Second, the oversampling method of Self-Attention Enhanced Conditional Generative Adversarial Network is implemented. This technique generates better model training results by accommodating self-attention mechanisms that create fake samples that follow the actual data distributions as well as class distributions. This paper introduces one potential solution to obtain model-level accuracy increase for tasks like disease prediction, patient prognosis, etc., over medical datasets. The proposed method aims to remove the measurement biases caused by incompleteness and class imbalance and preprocess the data to enhance the credibility and clinical relevance of the experimental results. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Nature-Inspired Paticle Bee Colony Deep Neural Network Technique for Event Detection in Video Sequences 1

An Adaptive Nature-Inspired Paticle Bee Colony Deep Neural N...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Sachdeva, Kumud Sandhu, Jasminder Kaur Sahu, Rakesh Chandigarh University Dept. of Computer Science Engineering Punjab Gharuan140413 India

ISBN: (纸本)9798350361780

Classifying and detecting difficult video events based on visual modalities remains an uncertain problem. Conventional video presentation approaches ineffectively extract each modality, hindering video event detection (VED) rates. The research methodology involves pre-processing steps: uploading video data samples, extracting video frames, converting to grayscale (rgb2gray), enhancing, and calculating smooth frames from the UCF -101 dataset. This pre-processing phase aims to deliver high-quality frames without data loss. Next, the feature extraction process employs the HoG method to extract feature vectors from refined video frames, facilitating the training process and efficiently reducing dimensions. An adaptive, nature-inspired PBC method is then implemented to select reliable and optimized feature sets from the extracted ones. These selected optimized feature vectors are input into different events of the deep neural network (DNN) classifier. Finally, reliable feature sets are identified through feature matching, and experimental outcomes demonstrate a significant 21.3% enhancement in VED and classification, assessed through accuracy rate, specificity (SP), sensitivity (SN), etc. Compared with traditional approaches using manually designed feature sets, the proposed approach proves more effective. Simulation outcomes on publicly available VED databases consistently outperform state-of-the-art video representation methods such as EFS-linear multi-support vector machine (MSVM), convolutional neural network (CNN), etc. © 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

A Deep Learning Approach to Enhance Air Quality Prediction: Comparative Analysis of LSTM, LSTM with Attention Mechanism and BiLSTM

A Deep Learning Approach to Enhance Air Quality Prediction: ...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Bhardwaj, Deepanshu Ragiri, Prakash Rao Netaji Subhas University of Technology Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350364866

In this study, we address the challenge of predicting air quality indices (AQIs) by leveraging Long Short-Term Memory (LSTM) networks. Recognizing the dynamic nature of air quality data, we explore the efficacy of three LSTM variants - standard LSTM, LSTM with an attention mechanism, and Bidirectional LSTM (BiLSTM) - in capturing temporal dependencies and improving forecast accuracy. Our methodology involved preprocessing a comprehensive dataset of air quality measures, followed by an experimental design that tested each model variant under different sequence lengths (30 and 365 days). The models were evaluated based on their mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) across three response variables: Nitrogen Oxides (NO), Particulate Matter up to 10 micrometers in size (PM10), and Particulate Matter up to 2.5 micrometers in size (PM2.5). Notably, when comparing the RMSE values across the three models, the LSTM with the attention mechanism consistently outperformed the standard LSTM and BiLSTM models, particularly with a sequence length of 30 days, indicating a superior ability to capture the intricacies of temporal dependencies in environmental data. Moreover, the shorter sequence length generally yielded better predictive performance, suggesting that longer sequences might introduce unnecessary complexity or overfitting. These indications of our study suggest a promising direction for the deployment of attention-based models in real-time AQI prediction systems, which could enhance the accuracy of environmental forecasts and inform public health decisions more effectively. Future work will explore the integration of additional environmental factors, the refinement of model frameworks, and the expansion of the dataset to include multi-city comparisons. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Fair and Efficient Congestion Management for Low Voltage Distribution Networks 8

Fair and Efficient Congestion Management for Low Voltage Dis...

引用

8th IEEE International Energy Conference, ENERGYCON 2024

作者： Vadavathi, Aswin Ramesh Hoogsteen, Gerwin Hurink, Johann dept. of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands

ISBN: (纸本)9798350382150

The widespread increase of photovoltaic panels in the distribution grid often leads to overvoltage. Traditional voltage regulation techniques are unfair for prosumers at the sensitive part of the grid due to larger power curtailment. Consequently, there has been considerable research on implementing fair curtailment strategies for congestion management. However, existing fairness-incorporated curtailment approaches yield varying results based on changes in the grid topology and integration of renewable energy sources. Therefore, this paper introduces proportional voltage fairness that is independent of the above-mentioned network properties and inherently distinguishes regions for fair curtailment. Additionally, there is a need to consider the underutilisation of the grid while adhering to a fair curtailment scheme. Thus this paper proposes a control algorithm incorporating proportional voltage fairness and gives the opportunity to specify the trade-off between fairness and the total power curtailed. Further, a comparative analysis with respect to state-of-the-art notions of fairness is performed. ©2024 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Lip Reading Into Text Using Deep Learning 14

Lip Reading Into Text Using Deep Learning

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Manglani, Krishna Bahuguna, Utkarsh Gupta, Subhash Chand Amity School of Engineering and Technology Dept. of Computer Science Uttar Pradesh India

ISBN: (纸本)9798350344837

An essential part of computer vision, lip reading, has grown significantly and is now used in autonomous driving, public safety, and hearing-impaired communication. This work provides an in-dept. analysis of both conventional and deep learning-based lip reading systems, examining their development over time, difficulties encountered, and critical role in human communication. The suggested LipNet model, which leverages the complementary abilities of Long Short-Term Memory networks (LSTMs) for temporal modelling and Convolutional Neural Networks (CNNs) for spatial feature extraction, is a central focus of this research. When LipNet is tested using the GRID Corpus dataset, it outperforms baseline models in terms of performance. Saliency maps and viseme analysis highlight LipNet's ability to capture phonologically relevant areas in lip motions, providing insight into the network's attention processes. Apart from examining the importance of datasets such as OuluVs2and GRID Corpus, this study presents GhostNet, a lightweight model that tackles the requirement for effective network designs. The testing results highlight LipNet's competitive Character Error Rate (CER) and Word Error Rate (WER) in comparison to baseline models, proving that it is the best method for real-world use. The research ends with a summary of potential future developments in lip reading technology, such as modal integration, realtime applications, personalisation, ethical issues, and the goal of creating a communication environment that is more inclusive. This study highlights the effectiveness of LipNet and paves the way for future developments in the ever-evolving area of lip reading by examining a variety of methodologies. © 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

Eva: Python-based Desktop Virtual Assistant for Visually Impaired 7

Eva: Python-based Desktop Virtual Assistant for Visually Imp...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Abraham, Anishamol Mathew, Benita Susan Mathew, Dona Lisa Mohammad, Fiaz S Krishnan, Gokul Amal Jyothi College of Engineering Dept. of Computer Science Kottayam686518 India

ISBN: (纸本)9798350372816

Virtual assistants have become essential resources in the digital age, providing users with a wide range of functionalities to expedite work and increase productivity. In this research, we provide a complete examination of Eva, a virtual assistant created using Python, and compare it to other virtual assistants such as Cortana and Copilot. Through a meticulous examination of Eva's features, we demonstrate its superiority in versatility and effectiveness. By embracing Eva's strengths and capitalizing on its competitive advantages, we push for a future in which digital experiences are inclusive and empowering for all users. © 2024 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Improving Time Series Forecasting Accuracy with Transformers: A Comprehensive Analysis with Explainability 3

Improving Time Series Forecasting Accuracy with Transformers...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Joseph, Susmera Jo, Ashly Ann Raj, Ebin Deni Indian Institute of Information Technology Dept. of Computer Science Engineering Kottayam India

ISBN: (纸本)9798350369083

Time series forecasting is crucial in numerous sectors, including healthcare, energy, and finance. Transformer models, initially designed for natural language processing applications, demonstrate potential in capturing temporal dependencies within sequential data. In this paper, the application of transformer models in time-series forecasting is explored, and their performance and interpretability are investigated. Transparent models build trust and facilitate decision-making, especially in industries with ethical guidelines. While inherently interpretable time-series Transformers exist, there is a gap in research regarding post hoc methods, which is an area ripe for exploration. Understanding and comparing complex Transformer models for time series forecasting can benefit from advancements in explainability, ensuring accurate and comprehensible predictions. In comparison to five other transformer-based models and classical models, the Temporal Fusion Transformer (TFT) model outperformed them in short-term forecasting. Further enhancement of the model performance was achieved through a meticulous analysis of the Encoder-Decoder's importance, which contributed significantly to refining the forecasting accuracy. The vanilla transformer was explained using permutation feature importance. The model stability was analyzed using perturbation methods. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Architectural Design for AdhaarAssist - A Forward-Looking Lock-Free STM Solution for Adhaar

Architectural Design for AdhaarAssist - A Forward-Looking Lo...

引用

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Jafar, Sana Pranveer Singh Institute of Technology Dept. of Computer Science and Engineering Kanpur India

ISBN: (纸本)9798350385199

Any parallel program is judged based on its efficiency in doing multiple tasks at the same time without getting stuck due to an underlying problem. The main purpose of a parallel program is to effectively and quickly solve a large and complicated problem at hand. This is why;parallel programs form the basis of many powerful supercomputers where parallel computing is supported through special hardware which is complemented with parallel software achieving hundreds of petaflop/s of performance. The biggest challenge for a parallel programmer is to build a program that has a minimum tradeoff for increased parallelism and good concurrency control among the parallel tasks. One of the biggest applications of parallelism is the huge, ever-increasing database of Adhaar biometric. Its crucial to have a robust, fast and efficient way of accessing and manipulating this data so that along with faster results, consistency of the database is also maintained. This paper proposes a schema AdhaarAssist which is a lock-free STM based algorithm that will work on a shared in-memory data structure. Some of its features are increased concurrency by lazy conflict detection, partial aborts that optimize the algorithm for maximum throughput when complex and lengthy transactions are employed, memory barriers and timestamping. The algorithm proposed in this paper will open the way for leveraging it for distributed-shared in-memory databases like the one used by Adhaar. © 2024 IEEE.

关键词： Concurrency control

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 << < 69 70 71 72 73 74 75 76 77 78 > >>

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：