检索结果-内蒙古大学图书馆

Vital sign normalisation for improving performance of multi-parameter patient monitors

ELECTRONICS LETTERS 2015年第25期51卷 2089-2090页

作者： Kumar, C. S. Ramachandran, K. I. Kumar, A. A. Amrita Vishwa Vidyapeetham ECE Dept Machine Intelligence Res Lab Coimbatore Tamil Nadu India Amrita Inst Med Sci Dept Neurol Kochi and Kerala India

Using covariance normalisation (CVN) of vital signs is explored to improve the performance of multi-parameter patient monitors with heart rate, arterial blood pressure, respiration rate, and oxygen saturation (SpO(2)) as its input. The baseline system for the experiments is a support vector machine classifier with a radial basis function kernel. Although an improvement in the overall classification accuracy with the use of CVN is obtained, there was a deterioration in sensitivity. Furthermore, it is noted that the estimate of the covariance is often noisy, and therefore the covariance estimates is smoothed to obtain a performance improvement of 0.23% absolute for sensitivity, 1.34% absolute for specificity, and 1.08% absolute for the overall classification accuracy. Multi-parameter intelligent monitoring in intensive care II database for all the experiments is used.

关键词： biomedical electronics blood pressure measurement medical signal processing patient monitoring radial basis function networks signal classification support vector machines arterial blood pressure covariance normalisation heart rate multiparameter patient monitors oxygen saturation radial basis function kernel respiration rate support vector machine classifier vital sign normalisation

来源：评论

学校读者我要写书评

暂无评论

Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2015年第1期9卷 75-85页

作者： Hurney, Patrick Waldron, Peter Morgan, Fearghal Jones, Edward Glavin, Martin Natl Univ Ireland Galway Sch Elect & Elect Engn Coll Engn & Informat Connaught Automot Res Grp Galway City Ireland Intel Shannon Shannon Clare Ireland Natl Univ Ireland Galway Sch Elect & Elect Engn Coll Engn & Informat Galway City Ireland

The use of night vision systems in vehicles is becoming increasingly common, not just in luxury cars but also in the more cost sensitive sectors. Numerous approaches using infrared sensors have been proposed in the literature to detect and classify pedestrians in low visibility situations. However, the performance of these systems is limited by the capability of the classifier. This paper presents a novel method of classifying pedestrians in far-infrared automotive imagery. Regions of interest are segmented from the infrared frame using seeded region growing. A novel method of filtering the region growing results based on the location and size of the bounding box within the frame is described. This results in a smaller number of regions of interest for classification, leading to a reduced false positive rate. Histograms of oriented gradient features and local binary pattern features are extracted from the regions of interest and concatenated to form a feature for classification. Pedestrians are tracked with a Kalman filter to increase detection rates and system robustness. Detection rates of 98%, and false positive rates of 1% have been achieved on a database of 2000 images and streams of video;this is a 3% improvement on previously reported detection rates.

关键词： pedestrians traffic engineering computing feature extraction image classification infrared detectors automobiles support vector machines image segmentation filtering theory night-time pedestrian classification histogram of oriented gradient-local binary pattern vectors night vision systems high end luxury cars low-cost infrared sensors far infrared automotive image streams support vector machine classifier region of interest RoF captured infrared frame seeded region growing filtering method bounding box ROI reduced false positive rate local binary pattern feature extraction histogram of oriented gradient feature extraction Kalman filter detection rates

来源：评论

学校读者我要写书评

暂无评论

Facial Components Extraction and Expression Recognition in Static images 1

Facial Components Extraction and Expression Recognition in S...

引用

International Conference on Green Computing and Internet of Things (ICGCIoT)

作者： Pukhrambam, Mameeta Das, Arundhati Saha, Ashim NIT Agartala CSE Dept Agartala India

ISBN: (纸本)9781467379106

This paper deals with the emotion recognition in static images. Facial feature extraction plays a very important role in recognizing a particular emotion in humans. In this paper, the facial expressions in humans. i.e., happy, anger, sad, neutral and disgust, are recognized with the help support vector machine classifier. First, a static image is taken. Then, skin region is extracted from that image using Hue Saturation Value. After skin region extraction, the right eye, the left eye and the mouth part are extracted as they are the most important part for facial expression recognition. These processes are done for every images collected in the training set. Then, support vector machine classifier is used to classify which image belongs to which class category by comparing the feature vectors of the trained images. This paper produces a model which predicts a set of testing images into which class categories the image belongs to, namely anger, disgust, fear, happy and neutral.

关键词： Facial feature extraction support vector machine classifier Hue Saturation Value

来源：评论

学校读者我要写书评

暂无评论

Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors

Night-time pedestrian classification with histograms of orie...

引用

20th ITS World Congress

来源：评论

学校读者我要写书评

暂无评论

Heart Rate Variability: Analysis and Classification of Healthy Subjects for Different Age Groups 2

Heart Rate Variability: Analysis and Classification of Healt...

引用

2nd International Conference on Computing for Sustainable Global Development (INDIACom)

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

ISBN: (纸本)9789380544168

Heart rate and its variability contain subtle information about cardiac health, which are very much difficult to extract without a suitable computer based computation technique. The objective of this study is to evaluate the HRV analysis of healthy subjects of different age groups by features computed from time domain, frequency domain and non-linear methods and classify those using SVM, KNN and PNN multi classifier modules with PCA as a feature space reduction technique. For short term HRV analysis, 60 normal and healthy male volunteers were chosen for ECG recording. 20 subjects in each age group of 18 to 30 years: named as young, 30 to 45 years: named as middle and 45 to 60 years: named as old were considered. In this study, analysis results show that, young age group has higher values in all features than other two groups and PCA-PNN classifier module classifies with a better accuracy of 70% and sensitivity 70% with all age groups.

关键词： Heart rate variability Age group Time domain Frequency domain Non-linear Principal component analysis support vector machine classifier K-nearest neighbor classifier Probabilistic neural network classifier

来源：评论

学校读者我要写书评

暂无评论

classifier Based Text Simplification for Improved machine Translation 2

Classifier Based Text Simplification for Improved Machine Tr...

引用

International Conference on Advances in Computer Engineering and Applications (ICACEA)

作者： Tyagi, Shruti Chopra, Deepti Mathur, Iti Joshi, Nisheeth Banasthali Univ Rajasthan Dept Comp Sci Vanasthali India

ISBN: (纸本)9781467369114

machine Translation is one of the research fields of Computational Linguistics. The objective of many MT Researchers is to develop an MT System that produce good quality and high accuracy output translations and which also covers maximum language pairs. As internet and Globalization is increasing day by day, we need a way that improves the quality of translation. For this reason, we have developed a classifier based Text Simplification Model for English-Hindi machine Translation Systems. We have used support vector machines and Naive Bayes classifier to develop this model. We have also evaluated the performance of these classifiers.

关键词： machine Translation Text Simplification Naive Bayes classifier support vector machine classifier

来源：评论

学校读者我要写书评

暂无评论

Pedestrian detection and vehicle type recognition using CENTROG features for nighttime thermal images 11

Pedestrian detection and vehicle type recognition using CENT...

引用

11th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP)

作者： Irhehhude, Martins E. Ali, Mohammad Athar Edirisinghe, Eran A. Univ Loughborough Deparment Comp Sci Loughborough Leics England

ISBN: (纸本)9781467382007

This paper proposes a feature-based technique to detect pedestrians and recognize vehicles within thermal images that have been captured during nighttime. The proposed technique applies the support vector machine (SVM) classifier on CENsus Transformed histogRam Oriented Gradient (CENTROG) features in order to classify and detect humans and/or vehicles. Although thermal images suffer from low image resolution, lack of colour and poor texture information, they offer the advantage of being unaffected by high intensity light sources such as vehicle headlights which tend to render normal images unsuitable for nighttime image capturing and subsequent analysis. Since contour is the most distinctive feature within thermal images, CENTROG is used to capture this feature information and is used within the experiments. The experimental results so obtained were compared with those obtained by employing the CENsus TRansformed hISTogram (CENTRIST). Experimental results revealed that CENTROG offers better detection and classification accuracy for both pedestrian and detection and vehicle type recognition.

关键词： image classification image resolution infrared imaging object detection object recognition pedestrians support vector machines CENTROG features SVM classifier census transformed histogram oriented gradient features low image resolution nighttime thermal images pedestrian detection support vector machine classifier vehicle type recognition Accuracy Computed tomography Feature extraction Histograms Image edge detection Vehicles Pedestrians support vector Network vehicle Edge detection histograms image resolution Infrared imaging Object detection Image classification object recognition Feature extraction model cars X-Ray Computed Tomography images Nighttime

来源：评论

学校读者我要写书评

暂无评论

Ensembling Brain Regions for Brain Decoding 37

Ensembling Brain Regions for Brain Decoding

引用

37th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Alkan, Sarper Yarman-Vural, Fatos T. Middle E Tech Univ Dept Cognit Sci TR-06531 Ankara Turkey Cankaya Univ Dept Mechatron Engn Ankara Turkey Middle E Tech Univ Fac Comp Enginering TR-06531 Ankara Turkey

ISBN: (纸本)9781424492701

In this study, we propose a new method which ensembles the brain regions for brain decoding. The ensemble is generated by clustering the fMRI images recorded during an experimental set-up which measures the cognitive states associated to semantic categories. Initially, voxel clusters are formed by using hierarchical agglomerative clustering with correlation as the similarity metric. Then, for each voxel cluster, a support vector machine (SVM) classifier is trained to estimate the class-posteriori probabilities. Lastly, the class-posteriori probabilities are ensembled by concatenating them under the same feature space, which are then used to train a meta-layer SVM for the final classification of the cognitive states. By using the voxel clusters, we aim to utilize the distributed, but complementing nature of the semantic representations in the brain and improve the classification accuracy. Thus, we make an existential claim that the brain regions provide a natural basis for ensemble learning which should be superior to the random clusters formed over a selected set of voxels. Our approach yields to better classification accuracies in Mitchell [1] dataset on most of the subjects, when compared to state-of-the-art which emphasizes voxel selection and ensemble learning with random subspaces.

关键词： biomedical MRI brain cognition feature selection image classification image coding image representation medical image processing pattern clustering probability support vector machines Mitchell dataset brain decoding brain regions class-posteriori probability cognitive states ensemble learning fMRI images feature space hierarchical agglomerative clustering meta-layer SVM semantic representations support vector machine classifier voxel clusters Accuracy Clustering algorithms Decoding Indexes Mutual information Semantics support vector machines

来源：评论

学校读者我要写书评

暂无评论

Object Categories Specific Brain Activity Classification with Simultaneous EEG-fMRI 37

Object Categories Specific Brain Activity Classification wit...

引用

37th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Ahmad, Rana Fayyaz Malik, Aamir Saeed Kamel, Nidal Reza, Faruque Univ Teknol Petronas CISIR Dept Elect & Elect Engn Tronoh 31750 Malaysia Univ Sains Malaysisa Dept Neurosci Kota Baharu 16150 Malaysia

ISBN: (纸本)9781424492701

Any kind of visual information is encoded in terms of patterns of neural activity occurring inside the brain. Decoding neural patterns or its classification is a challenging task. Functional magnetic resonance imaging (fMRI) and Electroencephalography (EEG) are non-invasive neuroimaging modalities to capture the brain activity pattern in term of images and electric potential respectively. To get higher spatiotemporal resolution of human brain from these two complementary neuroimaging modalities, simultaneous EEG-fMRI can be helpful. In this paper, we proposed a framework for classifying the brain activity patterns with simultaneous EEG-fMRI. We have acquired five human participants' data with simultaneous EEG-fMRI by showing different object categories. Further, combined analysis of EEG and fMRI data was carried out. Extracted information through combine analysis is passed to support vector machine (SVM) classifier for classification purpose. We have achieved better classification accuracy using simultaneous EEG-fMRI i.e., 81.8% as compared to fMRI data standalone. This shows that multimodal neuroimaging can improve the classification accuracy of brain activity patterns as compared to individual modalities reported in literature.

关键词： bioelectric potentials biomedical MRI electroencephalography image classification image coding image resolution neurophysiology spatiotemporal phenomena support vector machines electric potential functional magnetic resonance imaging multimodal neuroimaging neural activity pattern decoding spatiotemporal resolution specific brain activity classification support vector machine classifier visual information encoding Accuracy Brain Data acquisition Electroencephalography Neuroimaging support vector machines Visualization

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Computer Aided Diagnostic System for Seizure Classification 2

Hierarchical Computer Aided Diagnostic System for Seizure Cl...

引用

2nd International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Sood, Meenakshi Bhooshan, Sunil V. Jaypee Univ Informat Technol Dept ECE Solan Himachal Prades India J Jaypee Univ Informat Technol Dept ECE Solan Himachal Prades India

ISBN: (纸本)9789380544168

EEG is the most economical and effective tool for understanding the complex dynamic behavior of the brain and studying its physiological states. In the present work, hierarchical computer aided diagnostic system (HCAD) for classification of normal, ictal and inter-ictal of EEG signals is proposed. In the present work, three different HCAD systems comprising of SVM, KNN and PNN classifiers are proposed. It is observed that the SVM based CAD system results in highest classification accuracy of 96% in comparison with 94% and 93.3% as obtained from KNN and PNN based HCAD systems. The promising results obtained from the present work indicate that the proposed SVM based HCAD system can be routinely used for seizure classification in clinical practice.

关键词： Hierarchical Computer-aided diagnostic system K-Nearest Neighbor Probabilistic Neural Network Seizure support vector machine classifier

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：