检索结果-内蒙古大学图书馆

Smoke detection in ship engine rooms based on video images

IET IMAGE PROCESSING 2020年第6期14卷 1141-1149页

作者： Park, Kyung-Min Bae, Cherl-O Mokpo Natl Maritime Univ Grad Sch Dept Marine Engn Mokpo 58628 South Korea Mokpo Natl Maritime Univ Dept Marine Engn & Coast Guard Mokpo 58628 South Korea

Fire detection systems in ships are based on smoke and heat detection in accordance with safety regulations. The rapid advancement of machine vision technology has led to the development of video smoke detection (VSD) systems. In this study, a VSD system is applied to smoke detection within the engine room of the ship. A dataset for a range of scenarios was created with a smoke generator. The method for smoke detection was based on motion detection and a support vector machine classifier, which was used to make candidate regions and perform classification. A local binary pattern descriptor was used to extract the feature vector. A training set was made from a variety of video frames, randomly. Experimental results seldom produced false positive windows in the non-smoke region. However, if the greyscale value of difference image between background and the smoke is lower than the setting value for motion detection, the system could not detect smoke. Processing time is sufficiently fast for use in real-time smoke detection systems. To install a VSD system on-board a vessel, the authors recommend a performance standard of the system which must be met.

关键词： support vector machines feature extraction object detection computer vision image classification ships video signal processing smoke smoke detectors fire safety image motion analysis ship engine rooms fire detection systems heat detection video smoke detection systems VSD system smoke generator motion detection support vector machine classifier nonsmoke region real-time smoke detection systems video frames video images local binary pattern descriptor feature vector extraction machine vision

来源：评论

学校读者我要写书评

暂无评论

Accurate power transformer PD pattern recognition via its model

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2016年第7期10卷 745-753页

作者： Rostaminia, Reza Saniei, Mohsen Vakilian, Mehdi Mortazavi, Seyyed Saeedollah Parvin, Vahid Shahid Chamran Univ Ahvaz Fac Engn Ahvaz Iran Sharif Univ Technol Dept Elect Engn Tehran Iran Sharif Univ Technol Ctr Excellence Power Syst Management & Control Tehran Iran

In this study, a transformer model is proposed to simulate the behaviour of a real transformer, under presence of different types of defects which contribute to partial discharge (PD) generation, as closely as possible. Five different types of defects (scratch on winding insulation, bubble in oil, moisture in insulation paper, very small free metal particle in transformer tank and fixed sharp metal point on transformer tank) are implemented artificially into these transformer models to investigate the resultant PD current signal magnitude and characteristics. Time-domain PD current waveforms are recorded on those transformer models which have one type of those defects. The resultant statistical PD current wave shapes and texture features are extracted from these captured PD current signals. The principal component analysis (PCA) is used to reduce the dimension of feature spaces which are required to develop the inputs for the classifier. The principal components obtained through PCA are applied to the support vector machine classifier, as an input. The classification results indicate that the extracted texture features (using grey-level covariance matrix) preserve the best characteristics for separation of the related patterns of those five defect models, accurately.

关键词： power transformers feature extraction partial discharges time-domain analysis principal component analysis covariance matrices support vector machines power transformer PD pattern recognition transformer model partial discharge generation PD current signal magnitude time-domain PD current waveforms feature extraction principal component analysis support vector machine classifier grey-level covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Local probabilistic descriptors for image categorisation

引用

IET COMPUTER VISION 2009年第1期3卷 8-23页

作者： Mele, K. Suc, D. Maver, J. Univ Ljubljana Fac Comp & Informat Sci Ljubljana Slovenia Univ Ljubljana Fac Arts Ljubljana Slovenia Boronia Capital Pty Ltd Crows Nest NSW 2065 Australia

Image categorisation involves the well known difficulties with different visual appearances of a single object, but also introduces the problem of within-category variation. This within-category variation makes highly distinctive local descriptors less appropriate for categorisation. Difficulties because of the within category variation and clutter are tackled by modelling image fragments in a new manner. The authors propose a family of local image descriptors, called probabilistic patch descriptors (PPDs). PPDs encode the appearance of image fragments as well as their variability within a category. PPDs extend the usual local descriptors by also modelling the variance of the descriptors' elements, for example pixels or bins in a histogram. To compare two PPDs, and a PPD with an image, a new similarity measure called PPD matching score is introduced. For each object category, a set of representative PPDs is learnt. Images are represented as feature vectors of the best matching scores obtained for representative PPDs in images. support vector machine classifiers are then trained on the feature vectors. PPDs are applied to image categorisation using machine learning where the features are the matching scores between images and PPDs. The authors experiment with two variants of PPDs that are based on complementary local descriptors. An interesting observation is that combining the two PPD variants improves the accuracy of categorisation. Experiments indicate that the benefits of modelling the within-category variation give results that are comparable with the state-of-the-art categorisation methods, and show good robustness with respect to noise and occlusions.

关键词： support vector machines encoding image matching image categorisation machine learning probability image coding support vector machine classifier image representation local probabilistic patch descriptor histogram feature vector image classification learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

Biomedical compound figure detection using deep learning and fusion techniques

引用

IET IMAGE PROCESSING 2018年第6期12卷 1031-1037页

作者： Lee, Sheng Long Zare, Mohammad Reza Monash Univ Malaysia Sch Informat Technol Jalan Lagoon Selatan Bandar Sunway 47500 Subang Jaya Malaysia

Images contain significant amounts of information but present different challenges relative to textual information. One such challenge is compound figures or images made up of two or more subfigures. A deep learning model is proposed for compound figure detection (CFD) in the biomedical article domain. First, pre-trained convolutional neural networks (CNNs) are selected for transfer learning to take advantage of the image classification performance of CNNs and to overcome the limited dataset of the CFD problem. Next, the pre-trained CNNs are fine-tuned on the training data with early-stopping to avoid overfitting. Alternatively, layer activations of the pre-trained CNNs are extracted and used as input features to a support vector machine classifier. Finally, individual model outputs are combined with score-based fusion. The proposed combined model obtained a best test accuracy of 90.03 and 96.93% outperforming traditional hand-crafted and other deep learning representations on the ImageCLEF 2015 and 2016 CFD subtask datasets, respectively, by using AlexNet, VGG-16, VGG-19 pre-trained CNNs fine-tuned until best validation accuracy stops increasing combined with the combPROD score-based fusion operator.

关键词： medical image processing feature extraction neural nets support vector machines image classification image fusion learning (artificial intelligence) biomedical compound figure detection deep learning model compound figure detection CFD pre-trained convolutional neural networks CNN transfer learning image classification support vector machine classifier score-based fusion

来源：评论

学校读者我要写书评

暂无评论

Heart Rate Variability based Classification of Normal and Hypertension Cases by Linear-nonlinear Method

引用

DEFENCE SCIENCE JOURNAL 2014年第6期64卷 542-548页

作者： Poddar, M. G. Kumar, Vinod Sharma, Yash Paul Indian Inst Technol Dept Elect Engn Roorkee 247667 Uttar Pradesh India Post Grad Inst Med Educ & Res Chandigarh 160012 India

The aim of this study is to analyse and compare the heart rate variability (HRV) of normal and hypertension cases using time domain, frequency domain, and nonlinear methods. For short term HRV analysis, a five-minute electrocardiogram (ECG) of 57 normal and 56 hypertension subjects were recorded with prior verification of their clinical status by a cardiologist. Most time domain features of hypertension cases have clearly reduced values over normal subjects, frequency domain features, like power in different spectral bands, also have the distinguishable decreased values, whereas sympathovagal balance has clear edge over hypertension cases than normal cases. Nonlinear parameters of Poincare plot, approximate entropy and sample entropy, have higher values in normal cases when compared with hypertension cases. support vector machine-based binary system classifies these two classes with 100 per cent accuracy and 100 per cent sensitivity when all time domain, frequency domain, and nonlinear features were used. It may work as a better predictor for in patients with hypertension.

关键词： Heart rate variability RR tachogram hypertension time domain frequency domain nonlinear support vector machine classifier

来源：评论

学校读者我要写书评

暂无评论

TerraSAR-X dual-pol time-series for mapping of wetland vegetation

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2015年第Sep.期107卷 90-98页

作者： Betbeder, Julie Rapinel, Sebastien Corgne, Samuel Pottier, Eric Hubert-Moy, Laurence Univ Rennes 2 LETG Rennes COSTEL UMR CNRS OSUR 6554 F-35043 Rennes France ECOBIO UMR CNRS 6553 OSUR F-35042 Rennes France Univ Rennes 1 IETR UMR CNRS 6164 F-35042 Rennes France

Mapping vegetation formations at a fine scale is crucial for assessing wetland functions and for better landscape management. Identification and characterization of vegetation formations is generally conducted at a fine scale using ecological ground surveys, which are limited to small areas. While optical remotely sensed imagery is limited to cloud-free periods, SAR time-series are used more extensively for wetland mapping and characterization using the relationship between distribution of vegetation formations and flood duration. The aim of this study was to determine the optimal number and key dates of SAR images to be classified to map wetland vegetation formations at a 1:10,000 scale. A series of eight dual-polarization TerraSAR-X images (HH/VV) was acquired in 2013 during dry and wet seasons in temperate climate conditions. One polarimetric parameter was extracted first, the Shannon entropy, which varies with wetland flooding status and vegetation roughness. Classification runs of all the possible combinations of SAR images using different k (number of images) subsets were performed to determine the best combinations of the Shannon entropy images to identify wetland vegetation formations. The classification runs were performed using support vector machine techniques and were then analyzed using the McNemar test to investigate significant differences in the accuracy of all classification runs based on the different image subsets. The results highlight the relevant periods (i.e. late winter, spring and beginning of summer) for mapping vegetation formations, in accordance with ecological studies. They also indicate that a relationship can be established between vegetation formations and hydrodynamic processes with a short time-series of satellite images (i.e. 5 dates). This study introduces a new approach for herbaceous wetland monitoring using SAR polarimetric imagery. This approach estimates the number and key dates required for wetland management (e.g. restorat

关键词： Wetlands Synthetic Aperture Radar (SAR) TerraSAR-X imagery Multi-temporal classifications support vector machine classifier

来源：评论

学校读者我要写书评

暂无评论

Entropy information-based heterogeneous deep selective fused features using deep convolutional neural network for sketch recognition

引用

IET COMPUTER VISION 2021年第3期15卷 165-180页

作者： Hayat, Shaukat Kun, She Shahzad, Sara Suwansrikham, Parinya Mateen, Muhammad Yu, Yao Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Peoples R China Univ Peshawar Dept Comp Sci Peshawar Pakistan Air Univ Dept Comp Sci Multan Campus Multan Pakistan

An effective feature representation can boost recognition tasks in the sketch domain. Due to an abstract and diverse structure of the sketch relatively with a natural image, it is complex to generate a discriminative features representation for sketch recognition. Accordingly, this article presents a novel scheme for sketch recognition. It generates a discriminative features representation as a result of integrating asymmetry essential information from deep features. This information is kept as an original feature-vector space for making a final decision. Specifically, five different well-known pre-trained deep convolutional neural networks (DCNNs), namely, AlexNet, VGGNet-19, Inception V3, Xception, and InceptionResNetV2 are fine-tuned and utilised for feature extraction. First, the high-level deep layers of the networks were used to get multi-features hierarchy from sketch images. Second, an entropy-based neighbourhood component analysis was employed to optimise the fusion of features in order of rank from multiple different layers of various deep networks. Finally, the ranked features vector space was fed into the support vector machine (SVM) classifier for sketch classification outcomes. The performance of the proposed scheme is evaluated on two different sketch datasets such as TU-Berlin and Sketchy for classification and retrieval tasks. Experimental outcomes demonstrate that the proposed scheme brings substantial improvement over human recognition accuracy and other state-of-the-art algorithms.

关键词： entropy-based neighbourhood component analysis multifeatures hierarchy sketch classification outcomes image classification deep learning (artificial intelligence) abstract structure deep networks entropy information-based heterogeneous deep selective fused features feature extraction deep convolutional neural networks image representation convolutional neural nets high-level deep layers SVM feature-vector space discriminative features representation asymmetry essential information sketch datasets sketch images human recognition accuracy support vector machines entropy sketch recognition support vector machine classifier DCNNs

来源：评论

学校读者我要写书评

暂无评论

classifier-based adaptive polynomial chaos expansion for high-dimensional uncertainty quantification

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2024年 422卷

作者： Thapa, Mishal Mulani, Sameer B. Paudel, Achyut Gupta, Subham Walters, Robert W. Univ Alabama Remote Sensing Ctr Dept Aerosp Engn & Mech Tuscaloosa AL 35487 USA Univ Alabama Dept Aerosp Engn & Mech Tuscaloosa AL 35487 USA Virginia Polytech Inst & State Univ Dept Aerosp & Ocean Engn Blacksburg VA 24061 USA

A novel approach for the construction of polynomial chaos expansion (PCE) is proposed to facilitate high -dimensional uncertainty quantification (UQ). The current PCE techniques are well-known for UQ;however, they are affected by the curse of dimensionality that leads to over -fitting and tractability issues. Although L1 -minimization can be used to deal with overfitting, it is still ineffective for problems with a large number of independent random inputs or requiring a very high -order PCE. Therefore, a classifier -based PCE (CAPCE) is presented to mitigate the factorial growth of basis terms and prevent over -fitting. The adaptive framework includes four basis selection strategies - enrichment, screening, discovery, and recycling - in the inner loop and the enrichment of the training samples in the outer loop. Mainly, an adaptive classifier is trained on the dominant and discarded basis terms obtained from L1 -minimization during discovery. It then allows the judicious selection of new higher -order basis candidates for L1 -solver in the next iteration, thereby alleviating the effect of the curse of dimensionality. The proposed framework has been tested with analytical problems of varying sizes of independent random inputs and an engineering composite laminate problem. The comparison of CAPCE with the available efficient PCE techniques demonstrated improvements in accuracy using fewer samples due to a faster convergence rate.

关键词： High-dimensionality Adaptive polynomial chaos expansion Uncertainty quantification support vector machine classifier Stochastic nonlinear buckling

来源：评论

学校读者我要写书评

暂无评论

Evaluation of gene importance in microarray data based upon probability of selection

引用

BMC BIOINFORMATICS 2005年第1期6卷 1-11页

作者： Fu, LM Fu-Liu, CS Pacific TB & Canc Res Org Pasadena CA USA Univ Florida Gainesville FL USA

Background: Microarray devices permit a genome-scale evaluation of gene function. This technology has catalyzed biomedical research and development in recent years. As many important diseases can be traced down to the gene level, a long-standing research problem is to identify specific gene expression patterns linking to metabolic characteristics that contribute to disease development and progression. The microarray approach offers an expedited solution to this problem. However, it has posed a challenging issue to recognize disease-related genes expression patterns embedded in the microarray data. In selecting a small set of biologically significant genes for classifier design, the nature of high data dimensionality inherent in this problem creates substantial amount of uncertainty. Results: Here we present a model for probability analysis of selected genes in order to determine their importance. Our contribution is that we show how to derive the P value of each selected gene in multiple gene selection trials based on different combinations of data samples and how to conduct a reliability analysis accordingly. The importance of a gene is indicated by its associated P value in that a smaller value implies higher information content from information theory. On the microarray data concerning the subtype classification of small round blue cell tumors, we demonstrate that the method is capable of finding the smallest set of genes ( 19 genes) with optimal classification performance, compared with results reported in the literature. Conclusion: In classifier design based on microarray data, the probability value derived from gene selection based on multiple combinations of data samples enables an effective mechanism for reducing the tendency of fitting local data particularities.

关键词： support vector machine Microarray Data support vector machine classifier Gene Selection Subtype Classification

来源：评论

学校读者我要写书评

暂无评论

Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease

引用

ARTIFICIAL INTELLIGENCE IN MEDICINE 2016年第Feb.期67卷 39-46页

作者： Drotar, Peter Mekyska, Jiri Rektorova, Irena Masarova, Lucia Smekal, Zdenek Faundez-Zanuy, Marcos Brno Univ Technol Dept Telecommun Tech 12 Brno 61200 Czech Republic St Anns Univ Hosp Fac Med Dept Neurol 1 Pekarska 664 Brno 66591 Czech Republic Escola Univ Politecn Mataro Signal Proc Grp TecuocampusAvda Ernest Llunch 32 Mataro 08302 Spain

Objective: We present the PaHaW Parkinson's disease handwriting database, consisting of handwriting samples from Parkinson's disease (PD) patients and healthy controls. Our goal is to show that kinematic features and pressure features in handwriting can be used for the differential diagnosis of PD. Methods and material: The database contains records from 37 PD patients and 38 healthy controls performing eight different handwriting tasks. The tasks include drawing an Archimedean spiral, repetitively writing orthographically simple syllables and words, and writing of a sentence. In addition to the conventional kinematic features related to the dynamics of handwriting, we investigated new pressure features based on the pressure exerted on the writing surface. To discriminate between PD patients and healthy subjects, three different classifiers were compared: K-nearest neighbors (K-NN), ensemble AdaBoost classifier, and support vector machines (SVM). Results: For predicting PD based on kinematic and pressure features of handwriting, the best performing model was SVM with classification accuracy of P-acc = 81.3% (sensitivity P-sen = 87.4% and specificity of P-spe = 80.9%). When evaluated separately, pressure features proved to be relevant for PD diagnosis, yielding P-acc = 82.5% compared to P-acc = 75.4% using kinematic features. Conclusion: Experimental results showed that an analysis of kinematic and pressure features during handwriting can help assess subtle characteristics of handwriting and discriminate between PD patients and healthy controls. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Decision support system support vector machine classifier Handwriting database Handwriting pressure Parkinson's disease PD dysgraphia

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：