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

771 篇 会议
5 册 图书
1 篇 期刊文献

馆藏范围

777 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

462 篇 工学
- 401 篇 计算机科学与技术...
- 230 篇 软件工程
- 134 篇 信息与通信工程
- 107 篇 电气工程
- 60 篇 生物医学工程（可授...
- 58 篇 生物工程
- 37 篇 控制科学与工程
- 33 篇 电子科学与技术（可...
- 20 篇 光学工程
- 15 篇 化学工程与技术
- 14 篇 仪器科学与技术
- 13 篇 机械工程
- 12 篇 安全科学与工程
- 11 篇 动力工程及工程热...
- 10 篇 交通运输工程
173 篇 理学
- 91 篇 数学
- 65 篇 生物学
- 43 篇 物理学
- 37 篇 统计学（可授理学、...
- 28 篇 系统科学
- 15 篇 化学
97 篇 管理学
- 63 篇 图书情报与档案管...
- 38 篇 管理科学与工程(可...
- 23 篇 工商管理
63 篇 医学
- 54 篇 临床医学
- 40 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
13 篇 法学
- 12 篇 社会学
13 篇 农学
- 13 篇 作物学
12 篇 教育学
- 12 篇 教育学
8 篇 经济学
1 篇 军事学

主题

207 篇 machine learning
93 篇 signal processin...
87 篇 deep learning
64 篇 signal processin...
62 篇 feature extracti...
56 篇 support vector m...
50 篇 training
49 篇 machine learning...
30 篇 neural networks
21 篇 natural language...
20 篇 image processing
16 篇 computational mo...
14 篇 prediction algor...
13 篇 svm
13 篇 sentiment analys...
13 篇 data models
12 篇 internet of thin...
12 篇 estimation
12 篇 convolutional ne...
11 篇 covid-19

机构

6 篇 college of engin...
6 篇 department of co...
4 篇 xidian universit...
3 篇 department of el...
3 篇 university of du...
3 篇 peng cheng labor...
3 篇 uttaranchal inst...
3 篇 department of el...
3 篇 national laborat...
3 篇 graphic era deem...
2 篇 kl business scho...
2 篇 khulna universit...
2 篇 khulna universit...
2 篇 northwest minzu ...
2 篇 shandong univers...
2 篇 central universi...
2 篇 imt cdl ghaziaba...
2 篇 department of co...
2 篇 school of marine...
2 篇 school of comput...

作者

8 篇 wathiq mansoor
4 篇 yassine himeur
3 篇 alavikunhu panth...
3 篇 li zheng
3 篇 abigail copiaco
3 篇 jing wang
3 篇 joel alanya-belt...
3 篇 rashid ali
3 篇 shadi atalla
3 篇 abbes amira
3 篇 lei huang
2 篇 cheng xinzhou
2 篇 sherin m. yousse...
2 篇 liashchynskyi pe...
2 篇 kumar ashwani
2 篇 sarno riyanarto
2 篇 khawla a. alnajj...
2 篇 chang ming-ching
2 篇 liu ze-guo
2 篇 taleb mohammed

语言

761 篇 英文
13 篇 其他
2 篇 西班牙文
2 篇 中文

检索条件"任意字段=5th International Conference on Signal Processing and Machine Learning, SPML 2022"

共 777 条记录，以下是241-250 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 Unique Approach to Efficient Fraudulent Signature Detection Using Deep Convolutional Neural Network, Xception, and EfficientNet 5

A Unique Approach to Efficient Fraudulent Signature Detectio...

引用

5th IEEE international conference on Artificial Intelligence and Virtual Reality (IEEE AIVR)

作者： Lodha, Srishti Malani, Harsh Vellore Inst Technol Sch Comp Sci & Engn Vellore Tamil Nadu India

ISBN: (纸本)9781665457255

Signatures act as the key to the validation of important documents, both in offline and digitized forms. this also means that forged signatures are vastly used to commit fraud. With machine learning gaining importance in every field, manual techniques are becoming obsolete and inefficient in several technology-related areas, including fraudulent signature detection. Hence, this research focuses on the use of Deep learning to construct a generalized yet accurate model, which can directly classify a given signature as genuine or forged instead of having a separate class for genuine and fraud for each of the signatures in the output layer. We train separate models with Deep Convolutional Neural Network, Xception, and EfficientNet respectively, then, we analyze and compare the results obtained by these models, as well as by the existing related works, inclusive of various performance metrics. After rigorous hyperparameter tuning and experimenting, we obtained the best results from Xception, with the highest training accuracy of 100% and validation accuracy of 98.02%.

关键词： Signature Verification Cyber-attack Deep learning Image processing OpenCV Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Research on a Chinese Character Recognition Framework based on Multi-dimensional Image Information 5

Research on a Chinese Character Recognition Framework based ...

引用

5th international conference on Inventive Computation Technologies (ICICT)

作者： Guo, Li He Nan Polytech Cultural Tourism Sch Zhengzhou 450046 Peoples R China

ISBN: (数字)9781665408370

ISBN: (纸本)9781665408387;9781665408370

this paper conducts the research on a Chinese character recognition framework based on the multi-dimensional image information. Since the font data storage structure is designed by the user and is not in the directly addressable space of the code, it is necessary to call the external memory access interface function. therefore, it is designed as a callback function to copy the font to the buffe. Hence, the pattern analysis model is then integrated. therefore, the method of fuzzy mathematics is proposed and studied here, that is, the method of fuzz y pattern recognition is used to select the best expression of spatial entities. Furthermore, the novel image recognition algorithm is designed for the scenario of the Chinese character recognition. through the experimental result, the performance is validated.

关键词： Image Information Multi-dimensional Data Character Recognition Image processing machine learning

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementation of High Performance Precise Signed and Unsigned Multiplier using Ternary 6-LUT Architecture 5

FPGA Implementation of High Performance Precise Signed and U...

引用

5th international conference on Inventive Computation Technologies (ICICT)

作者： Mahendra, Palle Ramesh, S. R. Amrita Vishwa Vidyapeetham Dept Elect & Commun Engn Amrita Sch Engn Coimbatore Tamil Nadu India

ISBN: (数字)9781665408370

ISBN: (纸本)9781665408387;9781665408370

Recent applications using arithmetic computations such as multiplication and division are often used in video/image processing and ML (machine learning). DSP blocks that are available on FPGAs are high-performance multipliers that may be used to accelerate computation. these multipliers are less and have fixed placement on FPGAs. Also, they generate additional routing delays which are inefficient for lower bit width multiplications. this results in greater power consumption. Soft IP cores that are specifically intended for multiplication are supplied as an optional feature by FPGA vendors to their customers. It improves the performance while using less power, but these IP cores need further improvement. this has led to the development of general low-latency, reduced area, and accurate soft-core multiplier designs based on the architectural properties of FPGAs, such as lookup table (LUT) structures and rapid carry chains. this work aims to build accurate and approximate signed and unsigned multipliers for 8-bit configurations. It utilizes a single LUT5 with multiplexers instead of double LUT5 in LUT6 architecture. To sum it up, this architecture was designed in Verilog HDL and synthesized in Xilinx software. In this work, for a signed multiplier, a notable decrease in area and delay by 42.69% and 11.79% was observed and for an unsigned multiplier, 43.8% and 6.61% reduction were attained.

关键词： Approximate Multiplier Accurate Multiplier LUT (Lookup table) DSP (Digital signal processing) Blocks Ternary adder

来源：评论

学校读者我要写书评

暂无评论

5th international conference on Computing and Informatics, ICCI 2022

5th International Conference on Computing and Informatics, I...

引用

5th international conference on Computing and Informatics, ICCI 2022

ISBN: (纸本)9781665499729

the proceedings contain 64 papers. the topics discussed include: real-time fixed-point hardware accelerator of convolutional neural network on FPGA based;dependable cnc controller using raspberry pi and cloud computing;smart potato disorders diagnostic system based on fuzzy k-nearest neighbor;review of personalized cancer treatment with machine learning;image processing-based vehicle class identification in mixed traffic;image cryptography: a systematic review;why bee colony is the most suitable with multi-query optimization?;gamification tool design for reducing requirements ambiguity during elicitation;new graphical ultimate processor for mapping relational database to resource description framework;group of models of error flow sources for discrete q-ary channels;predicting banking customer churn based on artificial neural network;and a framework for enhancing the supply of scientific research projects using blockchain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimate Height Weight and Body Mass Index From Face Image Using machine learning 5

Estimate Height Weight and Body Mass Index From Face Image U...

引用

5th international conference on Multimedia, signal processing and Communication Technologies (IMPACT)

作者： Kumar, Ashwani Deeksha, Kondam Pooja, G. Sai Reddy, T. Tarun Reddy, Tera Akhil SRM Inst Sci & Technol NCR Campus Ghaziabad India Sreyas Inst Engn & Technol Hyderabad India

ISBN: (纸本)9781665476478

Human body photographs contain encodings for gender, weight, and other biometric data in addition to pupil color. When considering all of this information, body weight is a reliable indicator of health problems. Body measurements including height, weight, and body mass index (BMI) are important because they can be used for a variety of purposes like surveillance, reidentification, picture retrieval systems, and healthcare. the majority of earlier research on automated height, weight, and BMI measurement has made use of 3D whole body videos and 2D and full body 2D pictures. A person's weight in proportion to their height is gauged by their BMI. It serves more as a gauge for calculating total body fat. Because it is frequently used to evaluate health issues, BMI is important. Our chances of living a longer, healthier life are said to be increased by having a healthy body mass index (BMI).the BMI range may be identified and classified using picture analysis, which can help individuals forecast credibility, manage their BMI, and lead healthier lives. there hasn't been much discussion on face estimation. Being overweight has been linked to obesity, diabetes, and cardiovascular disease. Weight is also an important health indicator. Using the methods Linear Regression, Ridge Linear Regression, Random Forest Regressor, and Kernel Ridge Regression, CNN algorithm, and Resnet-50 Architecture, we test the feasibility of estimating height, weight, and BMI from single-shot face photos. In order to estimate height, weight, and BMI, we will evaluate these regression models and select the one with the highest test score.

关键词： Height Weight BMI Resnet-50 Regression

来源：评论

学校读者我要写书评

暂无评论

PILOT: Synergy between Text processing and Neural Networks to Detect Self-Admitted Technical Debt 5

PILOT: Synergy between Text Processing and Neural Networks t...

引用

5th international conference on Technical Debt (TechDebt)

作者： Di Salle, Amleto Rota, Alessandra Nguyen, Phuong T. Di Ruscio, Davide Fontana, Francesca Arcelli Sala, Irene Univ LAquila Laquila Italy Univ Milano Bicocca Milan Italy

ISBN: (纸本)9781665452113

During the development phase, software programmers usually introduce code that contains issues intentionally left for additional treatment. To allow for future fixing, they mark such code using textual comments, resulting in Self-Admitted Technical Debt (SATD). Detecting SATD contained in source code has become crucial in the development cycle since it helps programmers locate issues that need to be solved, thus improving code quality. We introduce PILOT, a technical debt detector built on top of a combination of different natural language processing (NLP) and machine learning (ML) techniques. First, the semantic among SATD comments is captured using feature extraction steps. then, neural network algorithms are applied to classify comments, represented as vectors. We built a PILOT prototype with a feed-forward neural network and evaluated it using real-world datasets as proof of concept. the empirical evaluation shows that PILOT obtains an encouraging performance and outperforms a well-established baseline. We anticipate that our tool will come in handy, as once being embedded in the IDE, it can help developers recognize SATD manifested in their code, allowing them to conveniently identify and fix issues.

关键词： Self-Admitted Technical Debt NLP techniques Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Roman Urdu Sentiment Analysis Using Pre-trained DistilBERT and XLNet 5

Roman Urdu Sentiment Analysis Using Pre-trained DistilBERT a...

引用

5th IEEE international conference of Women in Data Science (WiDS-PSU)

作者： Azhar, Nikhar Latif, Seemab Natl Univ Sci & Technol NUST Sch Elect Engn & Comp Sci Islamabad Pakistan

ISBN: (纸本)9781665408127

Roman Urdu is a resource-poor language, therefore training a deep learning-based model from scratch is not that fruitful due to the lack of a large dataset. this is where the magic of transfer learning comes to the rescue. Using Huggingface's transformer models DistilBERT and XLNet we see a huge improvement in the results compared to the popular machine learning models Logistic Regression and Naive Bayes. DistilBERT achieved 100% accuracy on our Roman Urdu dataset with only 2 epochs of fine-tuning while XLNet, though initially expected to perform better than the BERT model, achieved only about 86% accuracy with 4 epochs of fine-tuning.

关键词： Natural Language processing Roman Urdu Sentiment Analysis BERT XLNet

来源：评论

学校读者我要写书评

暂无评论

Emotion Detection using Natural Language processing 5

Emotion Detection using Natural Language Processing

引用

5th international conference on Contemporary Computing and Informatics, IC3I 2022

作者： Sakethnath, Damam Kaur, Harjeet Singh, Arun Lovely Professional University Department of Computer Science and Engineering Phagwara India Lovely Professional University School of Computer Science and Engineering Phagwara India

ISBN: (纸本)9798350398267

Online reviews of products, travel destinations, or movies are frequently given as sure opinions. As a result, sentiment analysis and opinion gathering become routine tasks. Consequently, the demand for automated text sentiment analysis has increased. Instead of reading reviews, it is useful to obtain opinions and sentiments regarding a particular subject. the Support Vector machine, Naive Bayes, Decision Tree, and K-Nearest Neighbor are machine learning approaches, as well as the deep neural network, a Recurrent Neural Network and Long Short-Term Memory (LSTM), are the two main methodologies of sentiment analysis employed in this paper. Additionally, in this work applications of two techniques using three Twitter datasets are done: Netflix, Flipkart, and Tourism. Additionally, visual comparison of several strategies is also shown, and the Recurrent Neural Network experiment results are displayed. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Development of a Sound Localization and Identification Device for Enhanced Safety of Visually Impaired Individuals 5th

Development of a Sound Localization and Identification Devic...

引用

5th international conference on Electrical and Electronics Engineering, ICEEE 2024

作者： Bhadra, Mohnish Jain, Reetu Oberoi International School JVLR Mumbai India On My Own Technology Mumbai India

ISBN: (纸本)9789819790364

this research presents the design and implementation of a novel device aimed at enhancing the safety of visually impaired individuals during travel through sound localization and identification. the prospect of diminished productivity resulting from varying degrees of visual impairment underscores the urgency of addressing blindness. this imperative extends beyond mere poverty alleviation;it serves as a gateway to female empowerment and societal integration. Leveraging Raspberry Pi 4 microcontroller and a suite of Python libraries including NumPy, Sound device, SciPy, TensorFlow, and pyttsx3, the device identifies sound sources and their directional orientation, alerting users in real-time. Methodologically, the project involves loading necessary data and parameters onto the microcontroller, integrating pre-trained sound classification models, and initializing a speech synthesizer for user notification. Key functions include angle calculation for sound direction determination, audio capture for data acquisition, and sound localization and identification through signal processing and machine learning. this research signifies a significant advancement in assistive technology, ensuring safer mobility for visually impaired individuals through innovative sound-based navigation systems. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Obstacle detectors

来源：评论

学校读者我要写书评

暂无评论

A Two-stage H.264 based Video Compression Method for Automotive Cameras 5

A Two-stage H.264 based Video Compression Method for Automot...

引用

IEEE 5th international conference on Industrial Cyber-Physical Systems (ICPS)

作者： Wang, Yiting Chan, Pak Hung Donzella, Valentina Univ Warwick WMG Coventry W Midlands England

ISBN: (纸本)9781665497701

With the development of automated vehicles and advanced driver assistance systems, the compression of the large amount of data generated by the vehicle camera sensors becomes a necessary processing step to improve the automated driving system efficiency. H.264 is a widely adopted video compression scheme, and it has been designed for human vision. Rate control in H.264 uses fixed quantisation parameter, however, this process can lead to fluctuation in different regions of the image quality of each frame. In this paper, we propose a two-stage H.264 based video compression framework, named "Two Stage Compression (TSC)", to compress the automotive camera videos with different values of compression rate in different regions of each frame. In the first stage, each frame will be divided into the region-of-interest and the region-out-of-interest. In the second stage, different compression ratios will be applied based on the importance of the region. the experimental results show that under the same overall compression ratio, our proposed TSC increments the semantic-aware PSNR by 3.213 dB compared to uniform H.264 compression. Our method is also compared to uniform H.264 compression using a segmentation algorithm, with an improvement of 1.77% in mIOU, the average Intersection over Union.

关键词： Automotive camera data video compression semantic segmentation machine learning Intelligent Vehicles Automated and Assisted driving

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78页 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：