检索结果-内蒙古大学图书馆

28th Signal Processing and Communications Applications Conference (SIU)

作者： Kolukisa, Burak Gungor, V. Cagri Gungor, Burcu Bakir Abdullah Gul Univ Bilgisayar Muhendisligi Bolumu Kayseri Turkey

ISBN: (纸本)9781728172064

Coronary Artery Disease (CAD) is the condition where, the heart is not fed enough as a result of the accumulation of fatty matter called atheroma in the walls of the arteries. In 2016, CAD accounts for 31% (17.9 million) of the world's total deaths and its diagnosis is difficult. It is estimated that approximately 23.6 million people will die from this disease in 2030. With the development of machine learning and data mining techniques, it might be possible to diagnose CAD inexpensively and easily via examining some physical and biochemical values. In this study, for the CAD classification problem, a novel ensemble feature selection methodology that incorporates domain knowledge is proposed. Via applying the proposed methodology on the UCI Cleveland CAD dataset and using different classification algorithms, performance metrics are compared. It is shown that in our experiments, when Multilayer Perceptron classifier is used with 9 selected features, our proposed solution reached 85.47% accuracy, 82.96% accuracy and 0.839 F-Measure. As a future work, we aim to generate a machine learning model that can quickly diagnose CAD on real-time data in hospitals.

关键词： Data mining Machine Learning classification algorithm Coronary Artery Disease

来源：评论

学校读者我要写书评

暂无评论

Revealing Political Sentiment with Twitter: The Case Study of the 2016 Italian Constitutional Referendum 10

Revealing Political Sentiment with Twitter: The Case Study o...

引用

IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

作者： Campanale, Marco Caldarola, Enrico G. Enel Italia SRL Rome Italy CNR Inst Intelligent Syst & Ind Technol Adv Mfg Bari Italy

ISBN: (纸本)9781538660515

In this work we argue about the use of Twitter as a Palantir for predicting and revealing the political orientation of users in election campaigns. Specifically, our study aims at revealing the political orientation of a Twitter user in the context of the 2016 Italian Constitutional Referendum. After having collected and processed over 1,200,000 tweets, we classified them as YES-oriented, NO-oriented or UNCERTAIN, by exploiting the Naive Bayes Multinomial Text classification algorithm. We found that Twitter is used massively for political deliberation and just by counting the messages related to a political party we can reveal the election result. Moreover, the words used by the YES party and the NO party twits are in line with the language used by politicians in the real word and this strongly supports our analysis. Furthermore, our approach can be applied to different scenarios, in which it is necessary to distinguish between two main classes and another UNCERTAIN class. Finally, the results obtained by our classification methodology are very promising and encourage us to continue investigating this topic, deriving suggestions for further research.

关键词： Opinion minding Sentiment Analysis Politics classification algorithm WEKA Naive Bayes Multinomial Text

来源：评论

学校读者我要写书评

暂无评论

THE APPLICATION OF MACHINE LEARNING TO PAINT CONDITION ASSESSMENT USING HYPERSPECTRAL DATA 12

THE APPLICATION OF MACHINE LEARNING TO PAINT CONDITION ASSES...

引用

12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)

作者： Alayoub, Ayoub El Rahim, Samer Abed Mustapha, Samir Salam, Darine Tehrani, Ali Khoa, Nguyen Lu Dang Amer Univ Beirut Dept Mech Engn Lab Smart Struct & Struct Integr SSSI Beirut Lebanon Alto Univ Dept Civil & Environm Engn Espoo Finland Alto Univ Sch Chem Engn Espoo Finland CSIRO Data61 13 Garden St Eveleigh NSW 2015 Australia

ISBN: (数字)9781665470698

ISBN: (纸本)9781665470698

Paint provides a shield that protects our structures, particularly steel structures, from corrosion and damage due to harsh environmental conditions such as sunlight and humidity. It is essential to ensure that paint coating works effectively and remains in good structural conditions (without peeling or fracture). Assessing the paint condition is complex, especially on large structures such as bridges, and can be time-consuming and costly. The traditional visual inspection methods depend on the experience and evaluation of inspectors in the field and require hard labor and time to perform. This study aims to employ hyperspectral imaging and image classification approaches to develop a structural condition monitoring system that rapidly assesses paint conditions and degradation. Several classification algorithms, such as Decision Tree, Support Vector Machines, Logistic Regression, and Naive Bayes, were trained and tested. The results obtained showed that the Decision Tree classifier outperformed the rest of the classifiers, achieving a highly accurate assessment of the paint condition and degradation levels with a detection accuracy of 0.98.

关键词： Paint condition assessment hyperspectral imaging machine learning classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Design of Image Classifier for Web Application

Design of Image Classifier for Web Application

引用

11th International Conference of Computer Communication and Informatics (ICCCI)

作者： Shivani Gaur, Nidhi Amity Univ Dept Elect & Commun Engn ASET Noida Uttar Pradesh India

ISBN: (纸本)9781728158754

An image classifier uses machine learning algorithm to recognize the images. A classifier allocates class labels to specific data points and classifies the images using supervised learning. It recognizes the target classes using labelled sample images by training a Convolutional neural network model (CNN). This paper aims to design an image classifier for web application. Image classification will eliminate the need of manual search in the web application. CNN is an efficient algorithm to classify the images according to the category label. An image classification model has been designed using CNN to classify the images of fruits and vegetables. Accuracy of the model is based on the classification technique. For successful classification data pre-processing, data augmentation and feature extraction are involved. Positive results were obtained by the CNN model after testing it with the input images. The model can classify the 90483 images of 131 fruits and vegetables. This paper involves the description and methodology for designing the image classifier.

关键词： Machine learning Object recognition Convolutional neural network Mufti class classification Fruits classifier Vegetables classifier classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning algorithm Based on AFS Theory and LogitBoost algorithm 41

Semi-Supervised Learning Algorithm Based on AFS Theory and L...

引用

第41届中国控制会议

作者： Peng Gao Xiaodong Liu School of Control Science and Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

There are a wide variety of classification problems in the world,so the classification task has always been a fundamental and important machine learning ***,many scholars have focused on the accuracy and training speed of classification models,while neglecting an important factor of classifier models:*** many cases,it is extremely difficult to collect labeled data,so the use of both labeled and unlabeled data to train classifiers that generate better semi-supervised learning is also the focus of many *** the above reasons,this paper proposes a new classifier,which is based on the axiomatic fuzzy set(AFS) *** not only realizes the interpretability of the fuzzy theory,but also uses the LogitBoost algorithm to verify the inconsistency of the axiomatic fuzzy set theory.

关键词： Semi-supervised Learning Axiomatic Fuzzy Set Theory classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Transformer Fault Diagnosis Based on Support Vector Machine

Transformer Fault Diagnosis Based on Support Vector Machine

引用

3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT)

作者： Zhang, Yan Zhang, Bide Yuan, Yuchun Pei, Zichun Wang, Yan Xihua Univ Inst Elect & Informat Chengdu 610039 Peoples R China

ISBN: (纸本)9781424455379

Analysis of dissolved gases content in power transformer oil is very important to monitor transformer latent fault and ensure normal operation of entire power system. Analysis of dissolved gases content in power transformer oil is a complicated problem due to its nonlinearity and the small quantity of training data. Support vector machine (SVM) has been successfully employed to solve classification problem of nonlinearity and small sample. However, SVM has rarely been applied to diagnosis transformer fault by analysis the dissolved gases content in power transformer. In this study, support vector machine is proposed to analysis dissolved gases content in power transformer oil, among which cross-validation is used to determine free parameters of support vector machine. The experimental data from the electric power company in Sichuan are used to illustrate the performance of proposed SVM model. The experimental results indicate that the proposed SVM model can achieve very good diagnosis accuracy under the circumstances of small sample. Consequently, the SVM model is a proper alternative for diagnosing power transformer fault.

关键词： support vector machine classification algorithm cross-validation free parameters fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition in WSN: A Comparative Study

引用

INTERNATIONAL JOURNAL OF NETWORKED AND DISTRIBUTED COMPUTING 2014年第4期2卷 221-230页

作者： Awan, Muhammad Arshad Guangbin, Zheng Kim, Cheong-Ghil Kim, Shin-Dug Yonsei Univ Dept Comp Sci 134 Shinchon Dong Seoul 120749 South Korea Namseoul Univ Dept Comp Sci Cheonan South Korea

Human activity recognition is an emerging field of ubiquitous and pervasive computing. Although recent smartphones have powerful resources, the execution of machine learning algorithms on a large amount of data is still a burden on smartphones. Three major factors including;classification algorithm, data feature, and smartphone position influence the recognition accuracy and time. In this paper, we present a comparative study of six classification algorithms, six data features, and four different positions that are most commonly used in the recognition process using smartphone accelerometer. This analysis can be used to select any specific classification algorithm, data feature, and smartphone position for human activity recognition in terms of accuracy and response time. The methodology we used is composed of two major components;a data collector, and a classifier. A set of eleven activities of daily living, four different positions for data collection and ten volunteers contributed to make it a worth-full comparative study. Results show that K-Nearest Neighbor and J48 algorithms performed well both in terms of time and accuracy irrespective of data features whereas the performance of other algorithms is dependent on the selected data features. Similarly, mean and mode features gave good results in terms of accuracy irrespective of the classification algorithm. A short version of the paper has already been presented at ICIS 2014.

关键词： Activity recognition classification algorithm data feature smartphone position ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Research on the Identification Method of Cells with Deteriorating Wireless Network Indicators 8

Research on the Identification Method of Cells with Deterior...

引用

8th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA)

作者： Ye Peng Zhou Qiang Zhuang Junbo Hu Bingbing Zhou Xing China Mobile Grp Design Inst Co Ltd Dept Network Optimizat R&D Fujian Branch Fuzhou Peoples R China

ISBN: (纸本)9781665455336

The severe degradation of wireless network performance indicators in cells seriously affects user perception. Rapidly identifying small cell performance degradation based on fixed thresholds set by network optimization personnel through business experience can lead to misjudgment and omission. An anomaly detection algorithm is used to remove abnormal indicator values to eliminate sudden fluctuations caused by sudden situations. Then, the DBSCAN clustering algorithm is used to calculate the dynamic threshold of the indicators, and a method for quantifying the degree of indicator degradation is proposed. Finally, combined with historical poor quality cell label data, the Lightgbm classification algorithm is used to identify cells with degraded wireless network performance indicators. To verify the effectiveness of this method, the experimental results show that the accuracy of identifying cells with degraded wireless network performance indicators using this method is higher than that of empirical rules and traditional classification algorithms.

关键词： poor quality cell identification Abnormal detection classification algorithm LightGBM

来源：评论

学校读者我要写书评

暂无评论

Research on Network Security Risk Modeling and Quantitative Analysis Theory 2017

Research on Network Security Risk Modeling and Quantitative ...

引用

International Conference on Wireless Communications, Networking and Applications (WCNA)

作者： Zhao, Xiao-Lin Yang, Yi-Ning Li, Xu-Hui Jiang, Feng Zhang, Ji Beijing Inst Technol Sch Software Beijing Key Lab Software Secur Engn Technol Beijing 100081 Peoples R China

ISBN: (纸本)9781450353441

(1)This paper realizes the network security assessment model based on hidden Markov. Firstly, the principle and basic problem of Hidden Markov Model are analyzed. Select the Snort software alarm as the input, convert the alarm into the quantification value of the network security risk model, and quantify the network security in real time, then design and implement the whole Hidden Markov Model.

关键词： Network security Hidden Markov Model classification algorithm Learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Academic Conference Information Management System Based on Social Network 16th

A New Academic Conference Information Management System Base...

引用

16th CCF Conference on Computer Supported Cooperative Work and Social Computing (ChineseCSCW)

作者： Xiao, Wen Lan, Liantao Guo, Jiongsheng Lin, Ronghua Lai, Yu Tang, Yong South China Normal Univ Guangzhou Peoples R China

ISBN: (纸本)9789811945496;9789811945489

SCHOLAT is a free, massive and comprehensive academic social network platform, which aims to realize reliable data sharing. In this paper, a new conference information management system based on SCHOLAT is designed and developed. In addition to containing typical functions of conference information management system, the system also provides individual services, including convenient online conference space, personalized domain, association with SCHOLAT ecosystem and customized access control. A hybrid classification algorithm for SCHOLAT user's academic emails is proposed to enhance the high quality services of the system. Benefit from convenient and helpful services, the conference system has grown rapidly in popularity since it was deployed and has been applied to lots of academic conferences up to now.

关键词： Social network Conference system SVM Text processing SCHOLAT classification algorithm

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：