检索结果-内蒙古大学图书馆

International Conference on Economic Management and Model Engineering (ICEMME)

作者： Mingjia Yan Tai'an No.1 High School of Shandong Province Tia'an Shandong China

ISBN: (纸本)9781728155890

Credit card rating has become an increasingly crucial problem in the society as credit card system greatly improves the efficiency and convenience of people's life. The rating of credit card is an important part of risk control. In this research we focus on predicting credit card holder's default rate. Classical classifiers are implemented in this research to find the optimal model and method of data preprocessing.

关键词： bank data processing credit transactions nearest neighbour methods pattern classification regression analysis risk management smart cards credit transactions bank data processing Credit cards Health Smart Cards Pattern recognition Risk Management nearest neighbor algorithm regression analysis risk control

来源：评论

学校读者我要写书评

暂无评论

A Multi-sensor Image Matching Method Based on KAZE-HOG Features

A Multi-sensor Image Matching Method Based on KAZE-HOG Featu...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Xin Wang Lin Duan Yue Fan Chen Ning College of Computer and Information Hohai University Nanjing China School of Physics and Technology Nanjing Normal University Nanjing China

ISBN: (纸本)9781728123264

This paper presents a multi-sensor image matching algorithm based on KAZE-HOG features. First, the multi- sensor images to be matched are preprocessed by bilateral filtering so as to remove noise. Then, a novel feature descriptor, namely KAZE-HOG is designed to extract as well as describe the feature points. Third, a nearest neighbor algorithm is used to match the obtained feature points of the images. Finally, a M-estimator sample consensus (MSAC) algorithm is utilized to remove the mismatches, so that the precise matching results can be gotten. Experimental results show that the proposed method has strong robustness, and it has good capability to resist scale and rotation transformations. As a result, it can achieve precise matching results for multi-sensor images.

关键词： Multi-sensor images KAZE-HOG features Image matching M-estimator sample consensus (MSAC) image matching Sensors (image) multi sensor nearest neighbor algorithm bilateral filtering MISMATCH Feature Points

来源：评论

学校读者我要写书评

暂无评论

Automated textural features based skin disease diagnosis system

Automated textural features based skin disease diagnosis sys...

引用

IEEE International Conference on Signal Processing, Computing and Control (ISPCC)

作者： Khushmeen Kaur Brar Ashima Kalra Piyush Samant Chandigarh engineering college Mohali India

ISBN: (纸本)9781728139890

Skin texture analysis is one of the demanding issues in the field of therapeutic diagnosis. Various categories of skin diseases are distressing human life like skin dryness, fungus, and allergic indications. The purpose of this paper is to examine the skin disease using texture analysis of skin image and by comparing the test image to a definite images or reference images. In the accessible situation, the skin images are investigated in frequency domain. However, it is scrutinized that the skin color in texture images does not vary over a wide range. Hence, the histogram profile of the skin texture remains almost flat. In the proposed work, we have shifted the skin texture analysis towards the gray level profile analysis. In the proposed thesis work, Gray Level Co-occurrence Matrix of the skin image is computed. The GLCM functions characterize the texture of an image by calculating how often pairs of pixel with specific values and in a specified spatial relationship occur in an image, creating a GLCM, and then extracting statistical measures from this matrix. Further, the image entropy and energies are also computed in order to correlate the skin symptoms to the skin texture images. The segmentation performance is evaluated maneuvering six performance metrics that are accuracy(ACC), sensitivity(SE), specificity(SP), jaccard index(JA), dice co-efficient(DI) and the divergence value(DV). The application on the PH2 dataset acquired good segmentation results with JA value of 89.88% of Fine Gaussian SVM classifier. Better results are achieved with DV of 10.3% and DI of 94.67% by Fine Gaussian SVM classifier. Promising results with sensitivity of 97.26%, specificity of 84.61% maneuvering RUS Boosted Tree and Fine Gaussian SVM classifier respectively are achieved. The accuracy of 91% is achieved by different classifiers namely Quadratic SVM, Cosine KNN, Boosted Tree, and Fine Gaussian SVM classifiers respectively. Fine Gaussian SVM classifier outperformed all other classif

关键词： diseases entropy feature extraction frequency-domain analysis image classification image colour analysis image texture matrix algebra medical image processing nearest neighbour methods skin statistical analysis support vector machines trees (mathematics) Support Vector Network Frequency-domain analysis skin texture image colour analysis image texture Medical image processing Skin Diseases matrix algebra images Image classification Classifiers Feature extraction nearest neighbor algorithm entropy epidermis (animal)

来源：评论

学校读者我要写书评

暂无评论

A Detection System for Stolen Vehicles Using Vehicle Attributes With Deep Learning

A Detection System for Stolen Vehicles Using Vehicle Attribu...

引用

IEEE International Conference on Signal Processing, Computing and Control (ISPCC)

作者： Parveen Saini Karambir Bidhan Sona Malhotra University Institute of Engineering and Technology (Kurukshetra University) Kurukshetra India

ISBN: (纸本)9781728139890

There is phenomenal growth in numbers of vehicles on road as well as in numbers of theft cases. In a few countries, vehicle theft cases are believed to be one in every 10 minutes. In such high-intensity scenario, it is not possible to identify the stolen vehicle with traditional methods such as manual check, RFID base technologies where it is easy to manipulate and remove. This paper presents a design with the implementation of a system based on deep learning technique where SSD algorithm is coupled with K-nearest neighbors algorithm and convolutional neural network classifier, to identify the stolen/suspicious vehicles without human intervention. This design operates in two stages: At first stage Tensor flow, Tensor Flow detection API from Google is used to detect the vehicle with sub-modules to identify color and registration number from a real-time video stream. In second stage it compares the extracted characteristic i.e. vehicle registration number and color with the RTO record. If in comparison it observes any anomaly in two sets or matched with stolen vehicle complaint record at police station. It would notify the concerned authorities. A prototype model is developed based on the presented design.

关键词： application program interfaces convolutional neural nets image classification learning (artificial intelligence) nearest neighbour methods radiofrequency identification road vehicles traffic engineering computing video streaming vehicle Application programming interfaces Radio frequency identification road vehicles Video streaming nearest neighbor algorithm Image classification Detection systems engineering computing Land transportation police stations Color original mold Theft

来源：评论

学校读者我要写书评

暂无评论

A new approach for fabric hand prediction with a nearest neighbor algorithm-based feature selection scheme

引用

TEXTILE RESEARCH JOURNAL 2011年第6期81卷 574-584页

作者： Yu, Yong Hui, Chi Leung Patrick Choi, Tsan-Ming Ng, Sau Fun Frency Hong Kong Polytech Univ ITC Kowloon Hong Kong Peoples R China

Fabric hand refers to the subjective perception of fabric mechanical properties. It is an important factor in fabric selection. In the literature, various instruments and tools have been developed to evaluate fabric hand by means of the related physical and mechanical properties. These works have studied the prediction of fabric specimens based on the fabric hand descriptors via either traditional statistical methods or artificial intelligence methods. The artificial neural network (ANN) model and its variation, the fuzzy neural network (FNN)-based intelligent fabric hand prediction system have been studied previously, and they show good accuracy in the forecasting task. The FNN model is especially useful as it provides good prediction accuracy and understandable rule-set at the same time. However, real-world application of the FNN model is restricted because of the great burden of required computation. In this paper, a nearest neighbor algorithm is used for feature selection to reduce computation burden. An improved FNN-based fabric hand prediction model is devised. Data sets collected from 30 participants' evaluation on a set of 20 fabric specimens, taken from the data source used by Lau et al., are used to verify the proposed system;the system is found to be capable of carrying out fabric hand predictions with many input parameters quickly and with good accuracy.

关键词： Fabric hand prediction fuzzy neural network nearest neighbor algorithm fuzzy logic artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Identification of Drug-Drug Interactions Using Chemical Interactions

引用

CURRENT BIOINFORMATICS 2017年第6期12卷 526-534页

作者： Chen, Lei Chu, Chen Zhang, Yu-Hang Zheng, Mingyue Zhu, LiuCun Kong, Xiangyin Huang, Tao Shanghai Maritime Univ Coll Informat Engn Shanghai 201306 Peoples R China Chinese Acad Sci Shanghai Inst Biol Sci Inst Biochem & Cell Biol Shanghai 200031 Peoples R China Chinese Acad Sci Shanghai Inst Biol Sci Inst Hlth Sci Shanghai 200031 Peoples R China Chinese Acad Sci Shanghai Inst Mat Med Drug Discovery & Design Ctr State Key Lab Drug Res Shanghai 201203 Peoples R China Shanghai Univ Coll Life Sci Shanghai 200444 Peoples R China

Background: One drug can affect the activity of another when they are administered together, which can cause adverse drug reactions or sometimes improve therapeutic effects. Therefore, correct identification of drug-drug interactions (DDIs) can help medical workers use various drugs effectively, avoiding adverse effects and improving therapeutic effects. Methods: This study proposed a novel prediction model to identify DDIs. A new metric was constructed to evaluate the similarity of two pairs of drugs using chemical interaction information retrieved from STITCH. Validated DDIs retrieved from DrugBank were employed, from which we constructed all possible pairs of drugs that were deemed as negative samples. The whole dataset was divided into one training dataset and one test dataset. To address the imbalanced data, a complicated dataset compilation strategy was adopted to construct nine training datasets from the original training dataset, reducing the ratio of positive samples and negative samples. Nine predictors based on the nearest neighbor algorithm were built based on these training datasets. The proposed model integrated the above nine predictors by majority voting and its performance was evaluated on the test dataset. Results: The predicted results indicate that the method is quite effective for identification of DDIs. Finally, we also discussed the ability of the method for identifying novel DDIs by investigating the likelihood of some negative samples in the test dataset that were predicted as DDIs being novel DDIs. Conclusion: The proposed method has a good ability for identification of potential DDIs.

关键词： Drug-drug interaction chemical interaction chemical structure similarity nearest neighbor algorithm majority voting imbalanced dataset

来源：评论

学校读者我要写书评

暂无评论

Bayesian Recognition of Inflammatory Processes in Brain Gliomas

引用

CYBERNETICS AND SYSTEMS ANALYSIS 2017年第3期53卷 366-372页

作者： Gridina, N. Ja. Gupal, A. M. Tarasov, A. L. Natl Acad Med Sci Ukraine AP Romodanov Neurosurg Inst Kiev Ukraine Natl Acad Sci Ukraine VM Glushkov Inst Cybernet Kiev Ukraine

Application of Bayesian recognition procedures to erythrocyte sedimentation rate in brain gliomas has allowed detecting inflammatory processes in a human body. The analysis of results of the recognition methods based on tree network methods, Markov chains, and nearest neighbor algorithm has shown that Bayesian procedure was the most efficient.

关键词： Bayesian recognition procedures brain gliomas Markov chain nearest neighbor algorithm

来源：评论

学校读者我要写书评

暂无评论

Classification of Subjects with Parkinson's Disease Using Gait Data Analysis

Classification of Subjects with Parkinson's Disease Using Ga...

引用

International Conference on Automation and Computational Engineering (ICACE)

作者： Yash Mittra Vipul Rustagi Department of Information Technology Guru Gobind Singh Indraprastha University New Delhi India

ISBN: (纸本)9781538654651;9781538654644

Gait Analysis of Parkinson's Disease (PD) Patients and Control Objects has been analyzed to show differences in PD Patients and Control Objects. Using data provided by Phisonet's Gaitpdb database (in which 8 sensors have been applied to each foot of the subjects to calculate the Vertical Ground Reaction Forces (VGRF)), data compression has been performed using 7 statistical functions to get a representative image of the data. The statistical functions namely Minimum, Maximum, Mean, Median, Standard Deviation, Skewness, and Kurtosis have been used to compress over 3 million tuples into 310 tuples. Finally, various Machine Learning techniques have been applied to the transformed dataset to perform detection of Parkinson's Disease. The classification has been performed using Logistic Regression, Decision Trees, Random Forest, SVM (Linear Kernel), SVM (RBF Kernel), SVM (Poly Kernel) and k-nearest Neighbours. Experiments with Principal Component Analysis for data compression have also been performed and their incompetence (with reasons) has been stated.

关键词： data analysis data compression decision trees diseases gait analysis medical diagnostic computing nearest neighbour methods pattern classification principal component analysis radial basis function networks random forests regression analysis support vecto medical diagnostic computing Radial basis function networks Data compression gait analysis Decision Trees Pattern recognition principal components analysis Parkinson Disease nearest neighbor algorithm Data analysis regression analysis maladjustment statistical distribution

来源：评论

学校读者我要写书评

暂无评论

Detection of Deception Using Facial Expressions Based on Different Classification algorithms

Detection of Deception Using Facial Expressions Based on Dif...

引用

Scientific Conference of Electrical Engineering (SCEE)

作者： Harith H. Thannoon Wissam H. Ali Ivan A. Hashim Department of Electrical Engineering Nineveh University Mosul Iraq Department of Electrical Engineering University of Technology-Iraq Baghdad Iraq

ISBN: (纸本)9781728115887;9781728115870

Most psychologists argue that facial behavioral during lying is different from facial behavioral when telling the truth, so the facial behavioral can be used as reliable indicators for spotting liars. The deception detection systems (DDSs) based on facial expressions are non-invasive, mobile and cost-effective. In this work a DDS is dependent on Facial Action Coding System (FACS) for facial features extraction, the main idea of FACS is to describe all facial actions using Action Units (AUs), each AU is related to movement one or more facial muscles. Eight AUs are used which incorporated into a single facial behavior pattern vector; these AUs are AUs 5, 6, 7, 10, 12, 14, 23, and 28. Datasets are collected for 43 subjects (20males, 23 females) most of them between ages 18-25. Four types of classification algorithms are used individually in the last stage of the proposed system; these classifiers are MLP, KNN, VG-RAM, and SVM. The simulation results show that the best results are obtaining when using VG-RAM and KNN classifiers. The main contributions of this work are new classification techniques in DDS, collect real database that can use to measure the performance of any DDS based on facial expressions, and select suitable facial features.

关键词： face recognition feature extraction image classification image coding multilayer perceptrons muscle nearest neighbour methods object detection random-access storage support vector machines Facial Expression random access machine Multilayer perceptrons Feature extraction Object detection Deception image coding Support Vector Network Image classification direct digital synthesis Sorting algorithm Facial Recognition nearest neighbor algorithm Face Face

来源：评论

学校读者我要写书评

暂无评论

High-Resolution Systems for Automated Diagnosis of Hepatitis

High-Resolution Systems for Automated Diagnosis of Hepatitis

引用

Scientific Conference of Electrical Engineering (SCEE)

作者： Hadeel N. Abdullah Bassam H. Abd Sara H. Muhi Department of Electrical Engineering University of Technology - Iraq Baghdad Iraq

ISBN: (纸本)9781728115887;9781728115870

This study aims to optimize the accuracy of diseases diagnosis, where many studies have been conducted to challenge the highest diagnostic accuracy of hepatitis disease because the early and correct diagnosis increases the chance of saving the patient's life from this deadly disease. Therefore, in this paper, we have done a good test for three classifications, namely: support vector machine (SVM), multilayer perceptron (MLP) and K-nearest neighbor (KNN). The accuracy of the KNN overcome the rest of the classifier with 100% accuracy for the diagnosis of hepatitis disease. We used the same division of data used in previous works for a fair comparison using the datasets gotten from the UCI machine learning database, with 19 features. This result is the best yet.

关键词： diseases medical diagnostic computing multilayer perceptrons nearest neighbour methods patient diagnosis pattern classification support vector machines medical diagnostic computing Multilayer perceptrons patient diagnosis Support Vector Network Pattern recognition automatic diagnosis Hepatitis Disease diagnosis maladjustment nearest neighbor 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：