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

3,079 篇 会议
141 册 图书
24 篇 期刊文献

馆藏范围

3,243 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,107 篇 工学
- 1,924 篇 计算机科学与技术...
- 1,068 篇 软件工程
- 399 篇 信息与通信工程
- 285 篇 电气工程
- 265 篇 生物工程
- 215 篇 控制科学与工程
- 170 篇 生物医学工程（可授...
- 79 篇 化学工程与技术
- 72 篇 机械工程
- 69 篇 光学工程
- 68 篇 仪器科学与技术
- 63 篇 电子科学与技术（可...
- 62 篇 安全科学与工程
- 55 篇 动力工程及工程热...
- 53 篇 网络空间安全
760 篇 理学
- 424 篇 数学
- 291 篇 生物学
- 148 篇 统计学（可授理学、...
- 140 篇 物理学
- 127 篇 系统科学
- 90 篇 化学
499 篇 管理学
- 301 篇 图书情报与档案管...
- 229 篇 管理科学与工程(可...
- 93 篇 工商管理
216 篇 医学
- 191 篇 临床医学
- 123 篇 基础医学(可授医学...
- 87 篇 药学(可授医学、理...
- 53 篇 公共卫生与预防医...
70 篇 法学
- 68 篇 社会学
51 篇 教育学
- 46 篇 教育学
35 篇 经济学
30 篇 农学
6 篇 艺术学
4 篇 军事学
1 篇 文学

主题

568 篇 data mining
542 篇 machine learning
241 篇 pattern recognit...
184 篇 deep learning
173 篇 feature extracti...
154 篇 artificial intel...
152 篇 support vector m...
113 篇 accuracy
113 篇 machine learning...
111 篇 training
93 篇 data models
80 篇 neural networks
77 篇 data mining and ...
65 篇 classification
62 篇 sentiment analys...
61 篇 classification a...
59 篇 big data
57 篇 predictive model...
50 篇 face recognition
48 篇 prediction algor...

机构

7 篇 maharishi school...
6 篇 guangdong univer...
5 篇 centre of interd...
5 篇 chitkara univers...
5 篇 uttaranchal univ...
5 篇 uttaranchal inst...
5 篇 institute of aut...
4 篇 shanghai jiao to...
4 篇 chitkara univers...
4 篇 school of inform...
4 篇 indian statistic...
4 篇 south china univ...
4 篇 galgotias univer...
4 篇 zhejiang univers...
4 篇 maharishi school...
4 篇 department of cs...
4 篇 pune
4 篇 university of ca...
4 篇 school of comput...
4 篇 department of co...

作者

9 篇 de-shuang huang
7 篇 coenen frans
7 篇 venkatesh svetha
7 篇 petra perner
7 篇 tianrui li
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 jacek m. zurada
6 篇 krasotkina olga
6 篇 lotfi a. zadeh
6 篇 mottl vadim
6 篇 leszek rutkowski
5 篇 vitoantonio bevi...
5 篇 sankar k. pal
4 篇 waiyamai kitsana
4 篇 sozo inoue
4 篇 sergei o. kuznet...
4 篇 duoqian miao
4 篇 shengli xie
4 篇 hepu deng

语言

3,105 篇 英文
129 篇 其他
32 篇 中文
1 篇 西班牙文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3244 条记录，以下是3041-3050 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：

machine learning Based pattern recognition with HOG Features for Detection of Islanding

Machine Learning Based Pattern Recognition with HOG Features...

引用

international conference on Electrical Power and Energy Systems (ICEPES)

作者： Kumaresh Pal Subhadip Goswami Anshuman Bhuyan Santanu Koley Bidisha Bera Sarmistha Basu Department of Electrical Engineering National Institute of Technology Jamshedpur India Department of Electrical Engineering National Institute of Technology Arunachal Pradesh India Department of Electrical Engineering Gandhi Institute for Education & Technology Bhubaneswar India Department of Computer Science Engineering Haldia Institute of Technology Haldia India Department of Computer Science and Technology Global Institute of Science and Technology Haldia India Department of Physics Calcutta Institute of Engineering and Management Kolkata India

ISBN: (数字)9798350390728

ISBN: (纸本)9798350390735

Islanding is a significant difficulty that arises from the high integration of distributed generation sources. Islanding could potentially damage the clients and their equipment. According to the IEEE 1547 DG interconnection requirements, islanding must be detected within two seconds, and the DG must be shut down. This research introduces a new method for identifying islanding using image pattern recognition utilising a machine learning classification algorithm. The suggested technique utilises the Random Forest (RF) classification algorithm. Images are utilised to extract the histogram of oriented gradient (HOG) features in order to detect both non-islanding and islanding occurrences. The spectrogram images are formed from the time-series signal collected from the point of common coupling. The images are utilised to extract features from histogram of oriented gradient, which are subsequently used as feature vector inputs for training and testing the RF classifiers. The spectrogram image is derived using the rate of change of the voltage parameter. The efficacy of the RF classifier is evaluated using 5, 10, 20, and 25-fold cross-validations. The classification findings indicates that islanding detection utilising a Random Forest classifier and Histogram of Oriented Gradients (HOG) feature for image pattern recognition obtained outstanding performance with 98.75% accuracy and a detection time of 192 milliseconds.

关键词： Histograms Accuracy Voltage Feature extraction Vectors pattern recognition Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Facial recognition and Animal recognition from Live Stream Video Using machine learning

Facial Recognition and Animal Recognition from Live Stream V...

引用

Advancement in Electronics & Communication Engineering (AECE), international conference on

作者： Deepika Dua Rahul Chauhan Kiran Kumar C S. Radhika Balambigai Subramanian Chandradeep Bhatt Computing Science Department Uttaranchal University Dehradun Uttarakhand India CSE Department Graphic Era Hill University Dehradun Uttarakhand India Data Science Codecraft Technologies Bangalore Karnataka India Information Technology Department R.M.K. Engineering College Kavaraipettai Tamil Nadu India ECE Department Kongu Engineering College Perundurai Tamil Nadu India

The use of facial recognition and object detection in a surveillance system is being studied in this study. Closed-circuit television (CCTV) is typically used in video surveillance systems to record footage for security purposes. It is used to manually determine a person's identity based on how they seem on the recorded video. A facial recognition system is typically not included in today's video surveillance camera systems. With a little adjustment, a security camera system can be used for real-time face detection and recognition. The suggested method takes use of a security camera system that uses face recognition and vehicle detection technology from the “Haar cascade classifier” to automatically determine a person's identification. The data collection, recognizer training, and face recognition and vehicle detection process were the three key stages of this project's development. Using Python programming and the OpenCV package, all three phases were carried out using a video operating system. According to the findings, the suggested method correctly projects the output of human face identification at a distance of 0.4 to 1.2 metres, in medium and normal light conditions, and with a facial angle within 40°. Targeted images may use facial accessories so long as they don't obscure the facial features. The system achieves an accuracy ranging from 90.27 % to 98.2% in detection of objects like animals, car, building etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accidental Prone Area Detection in Bangladesh using machine learning Model

Accidental Prone Area Detection in Bangladesh using Machine ...

引用

international conference of Computer and Informatics Engineering (IC2IE)

作者： Khan Md. Hasib Md. Imran Hossain Showrov Anik Das Ahsanullah University of Science and Technology Dhaka Bangladesh Bangladesh Atomic Energy Commission Institute of Computer Science Dhaka Bangladesh Chittagong University of Science and Technology Chittagong Bangladesh

ISBN: (数字)9781728182476

ISBN: (纸本)9781728182483

Nowadays road accident in Bangladesh is a buzzword due to its lack of carefulness of the driver of the vehicle where some parameter exists. The traffic safety of the roadway is an essential concern not only for transportation governing agencies but also for citizens of our country. For safe driving suggestions, the important thing is to find the variables that are tensed to relate to the fatal accidents that are occurring often. In this paper, we create a model using a machine learning approach on the countrywide traffic accident dataset of Bangladesh as an aim to address this problem. The model also helps out to find the diversity of the data by grouping similar objects together to find the accident-prone areas in the country concerning different accident factors as well as detects the cooperation between these factors and causalities.

关键词： Urban areas Road accidents data mining Roads Decision trees Vehicles data models

来源：评论

学校读者我要写书评

暂无评论

A Sign Language recognition System Using Ionic Liquid Strain Sensor

A Sign Language Recognition System Using Ionic Liquid Strain...

引用

Material and Electrical Engineering conference (ISMEE), international Symposium on

作者： Chi Tran Nhu Phu Nguyen Dang Van Nguyen Thi Thanh Ha Tran Thi Thuy Van Dau Thanh Tung Bui Thanh Faculty of Electronics and Telecomunications VNU – University of Engineering and Technology Hanoi Vietnam School of Engineering and Built Environment Griffith University Queensland Australia

ISBN: (纸本)9781728177335

In this report, we develop a system converting sign language into voices and text. The system includes a glove attached self-developed ionic liquid-based strain sensors on each finger to detect the movement of them. When the hand move to express a letter lead to the resistance of the strain sensors on each finger change. Therefore, through the information from set of sensors, the system can recognize the letter that user want to convey. A measuring and data acquisition circuit also are developed to receive and analyze data from the sensors. Furthermore, a data digitizing method is proposed as a solution for decoding purpose. The system is tested with 10 distinguished basic letters in American Sign Language table (ASL). The results show the accuracy of system is 98%. The system operates stably with the low power of 0.81W at rest state and 1.71W when working. Besides, applications on smartphone and PC are also built to translate the data into text and speech. These apps make it easier to communicate with deaf people. With achieved results, the system is fully extensible to detect more letters in ALS table in the future.

关键词： Resistance Electrical engineering machine learning algorithms Liquids Gesture recognition Assistive technologies Capacitive sensors

来源：评论

学校读者我要写书评

暂无评论

An Improved Sensor pattern Noise Estimation Method Based on Edge Guided Weighted Averaging 3rd

An Improved Sensor Pattern Noise Estimation Method Based on ...

引用

3rd international conference on machine learning for Cyber Security, ML4CS 2020

作者： Zhang, Wen-Na Liu, Yun-Xia Zhou, Jin Yang, Yang Law, Ngai-Fong School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China School of Information Science and Engineering Shandong University Qingdao266237 China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9783030624590

Sensor pattern Noise (SPN) has proven to be an effective fingerprint for source camera identification. However, its estimation accuracy is still greatly affected by image contents. In this work, considering the confidence difference in varying image regions, an image edge guided weighted averaging scheme for robust SPN estimation is proposed. Firstly, the edge and non-edge regions are estimated by a Laplacian operator-based detector, based on which different weights are assigned to. Then, the improved SPN estimation is obtained by weighted averaging of image residuals. Finally, an edge guided weighted normalized cross-correlation measurement is proposed as similarity metric in source camera identification (SCI) applications. The effectiveness of the proposed method is verified by SCI experiments conducted on six models from the Dresden data set. Comparison results on different denoising algorithms and varying patch sizes reveal that performance improvement is more prominent for small image patches, which is demanding in real forensic applications. © 2020, Springer Nature Switzerland AG.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

The Repetitive data Problem of Relevance Vector machine Customer Identification

The Repetitive Data Problem of Relevance Vector Machine Cust...

引用

2011 3rd IEEE international conference on Information Management and Engineering(ICIME 2011)

作者： LiGang School of Economics & Management Xi’an Technological University Xi’an, China Lizhi, Wang Guilong School of Economics & Management Xi’an Technological University Xi’an, China

The 'repetitive data problem' is pervasive and ubiquitous in the real world, especially in the customer identification problem. Evidences from the experiments with Ripley's dataset indicate the 'repetitive data' significantly influence the performance of RVM pattern recognition that can be used to figure out what kind of the customers purchase the products. To identify the important customer modes, RVM automatically improves the Confidence Probability of the 'repetitive data'. Correspondingly, the classification boundary changes compared with the dataset without 'repetitive samples'. It is proved that the repetitive data should not be merged simply before the training of RVM.

关键词： repetitive data problem RVM pattern recognition Confidence Probability boundary effect customer identification

来源：评论

学校读者我要写书评

暂无评论

Blood donor's safety using data mining

Blood donor's safety using data mining

引用

international conference on Green Computing and Internet of Things (ICGCIoT)

作者： Rohini Patil Madhu Poi Pooja Pawar Tejashree Patil Namrata Ghuse Dept. of Computer Science SITRC Nasik India

ISBN: (纸本)9781467379113

Blood is most essential constituent in human body. Blood centers collect, process and transport blood to hospitals and other health care centers. Sometimes blood is collected directly from blood donors rather than taking it from blood bank. Nowadays donor safety is major issue as blood is collected from different donors. Small amount of donors face reactions after donating blood and if not treated on time then it may lead to serious injury. The reactions that occur in the donor during blood donation at different hospitals and blood banks is collected, organized and analyzed by the DonorHART tool [1, 3]. The donor reactions information are captured and analyzed by DonorHART system[1]. The tool also monitors and researches the risks involved for donors at the time of blood donation or after the donation process. data mining makes an effort to reveal the patterns in data that are difficult to detect and recognize with automatic pattern recognition. It is analyzing of data and then summarizing it into different form which is called as information and is taken from different databases. The proposed system is a web based application which helps to reduce the human mistakes or errors and different techniques can be applied for blood type classification, diagnosing diabetic symptoms, classifying blood type and identifying different donors reaction and apply preventive measures against them.

关键词： Blood data mining Classification algorithms Safety Cloud computing pattern matching machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Design and Application of Sports Management Decision Support System based on B/S Model

Design and Application of Sports Management Decision Support...

引用

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

作者： Qinqin Zhang Gansu Institute of Mechanical & Electrical Engineering Tianshui China

ISBN: (数字)9798331519032

ISBN: (纸本)9798331519049

Due to complex data and changing environments, sports managers face many challenges when making decisions. In order to provide scientific and accurate decision-making support, a sports management decision-making support system based on the B/S model came into being. This research adopts the method and process of system design to develop the system, and uses data analysis and mining techniques to conduct in-depth analysis of the data, including statistical analysis, data modeling, and machine learning methods, to identify patterns, trends, and relevance in the data, and design and implement specific decision-making models and algorithms, based on historical data and domain knowledge, used to predict competition results, evaluate athlete status, and formulate training plans. After experimental testing, the response time range of the system is 0.4-1s. It provides sports managers with powerful tools and resources to improve the efficiency and accuracy of decision-making.

关键词： Training Decision support systems Analytical models Accuracy Predictive models Prediction algorithms Market research data models data mining Sports

来源：评论

学校读者我要写书评

暂无评论

Foreign language speech recognition and correction system aided by machine learning algorithm

Foreign language speech recognition and correction system ai...

引用

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

作者： Jinmei Zhou Shuang Su Rongxing Li Army Logistics Academy Chongqing China

ISBN: (数字)9798331519032

ISBN: (纸本)9798331519049

This paper discusses the application of machine learning algorithm in foreign language speech recognition and correction system, aiming at improving the oral pronunciation quality of foreign language learners. Firstly, the limitations of traditional foreign language teaching mode in pronunciation correction are analyzed, and then the construction scheme of foreign language speech recognition and correction system based on machine learning is put forward. The system constructs an efficient and accurate foreign language speech recognition model through data preprocessing, feature extraction, model training optimization and other steps. In the data preprocessing stage, spectral subtraction is used for noise reduction, and sliding window method is used for framing. In the feature extraction stage, mel-frequency cepstral coefficients (MFCC) is used as the speech feature, and MFCC features are extracted through pre-emphasis, windowing, fast Fourier transform, Mel filtering, logarithmic operation and discrete cosine transform. We chose deep neural network (DNN) as the base model and designed a hybrid model based on long short-term memory network (LSTM) and convolutional neural network (CNN) (LSTM-CNN-DNN model) to improve recognition accuracy. At the same time, L2 regularization term, pre-training, data enhancement and Adam algorithm are introduced to prevent the model from over-fitting and accelerate the training process. In addition, this paper also puts forward foreign language pronunciation correction strategies, including the construction of standard pronunciation database, instant feedback, personalized training plan, interactive exercises, intelligent counseling services and multimodal strategies. The system implementation and test results show that the system can accurately identify and correct pronunciation errors, has good stability, and can meet the needs of a large number of users for speech recognition and correction. This study has successfully constructed an

关键词： Training Accuracy databases Speech recognition Feature extraction data models Stability analysis Convolutional neural networks Long short term memory Standards

来源：评论

学校读者我要写书评

暂无评论

Efficient Classification of Bird Species Using Photographic Images: A MobileViT Based Approach

Efficient Classification of Bird Species Using Photographic ...

引用

Artificial Intelligence For Internet of Things (AIIoT), international conference on

作者： Venkata Ramana Murthy Polisetty Sp Chokkalingam Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

abstract-In the quest to enhance biodiversity conservation and support ecological monitoring, the identification of bird species through automatic recognition systems has emerged as a vital tool. This study introduces a novel approach employing the Mobile Vision Transformer model, capitalizing on its efficiency in handling complex visual data across a comprehensive dataset encompassing 525 bird species. MobileViT integrates the advantages of Convolutional Neural Networks (CNNs) with Transformer technology, surpassing typical deep learning models in terms of feature extraction and contextual comprehension abilities. Incorporating advanced data augmentation methods has bolstered the dataset’s variability, ensuring the model’s preparedness for a wide spectrum of imaging scenarios. With a direct and impressive outcome, the model achieved a 97.5% accuracy rate in species identification. The adoption of MobileViT promises a scalable and potent solution for bird species recognition within ornithological research, marking a forward leap in employing machine learning for environmental conservation.

关键词： Deep learning Biological system modeling Birds Transformers data augmentation data models 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325页 << < 301 302 303 304 305 306 307 308 309 310 > >>

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：