Search

This work aims to develop a minimally obtrusive simple system for the automatic detection and classification of sleep apnea (SA) events using the single-channel abdomen respiratory effort signal (Abd RES) taken from the ISRUC sleep database. The discrete wavelet transform energy, time domain respiratory rate variability and the Shannon entropy features are extracted from the Abd RES to build a classifier system. The performance of linear multi-class support vector machine (SVM) and random forest (RF) classifiers is compared for the application. Furthermore, an improved random forest (IRF) classifier is proposed, which is a combination of data re-sampling, RF algorithm and threshold moving method. It is designed to deal with the imbalance in the input dataset for better classification results. Various systems are designed using individual feature sets, but classification accuracy increases when feature sets are combined. A maximum accuracy of 89.66% is achieved with the IRF based system using reduced feature set obtained by principal component analysis. Thus, the proposed method can provide an effective, economical and accessible screening tool for SA. [ABSTRACT FROM AUTHOR]

This paper presents a low dimensional edge descriptor, based on local diagonal and non-diagonal maxima-minima pattern for medical images. The methods utilize local relationship of a middle pixel to its diagonal/non-diagonal maxima-minima. The scheme reduces the length of feature vector to a great extent without compromising the quality of edge map. The designed methods are validated on digital X-ray for bone fracture detection, dental images and ultrasound images. Improved depth local binary pattern, anisotropic diffusion & Canny edge detection, Canny and Sobel methods are also used for a comparative analysis. The local diagonal maxima-minima pattern and local non-diagonal maxima-minima pattern methods are robust to noise, while preserving the useful edge information. The experimental results reveal the superiority of proposed methods as compared to the state-of-the-art methods in terms of accuracy, Jaccard similarity index, specificity, sensitivity and dice similarity coefficient. [ABSTRACT FROM AUTHOR]

Automated accurate categorization of brain magnetic resonance images (MRI) is very important for disease diagnosis and treatment. In this paper, a new methodology for the detection of abnormality in brain MRI is suggested. The scale-invariant feature transform is first employed to extract features of MRI. Principal component analysis is applied to the extracted features and a minimal set of more essential features is obtained. Lastly, the obtained feature set is categorized as healthy or unhealthy using support vector machine (SVM)-based classification. The parameters of SVM, i.e. C and s are optimized using Gray Wolf Optimization. However external noise and patient/organ movement degrade the quality of MRI, which in turn affect the classification accuracy. Therefore, a hybrid of Savitzky-Golay smoothing filter and speckle reducing anisotropic diffusion filter is used for preprocessing of the source image, which efficiently reduces the noise while preserving edges of the image. It is revealed from the results that proposed technique provides a classification accuracy of 99.61%. Thus the suggested technique may effectively diagnose diseases using MRI. [ABSTRACT FROM AUTHOR]

The present work focuses on the development of non-invasive blood glucose measurement device to revolutionize diabetes management and reduce severe complications associated with it. A low cost, painless and non-invasive blood glucose measurement system is designed using near-infrared (NIR) LED and four photodiodes for the purpose. NIR light emitted by LED passes through the skin and is detected by photodiodes after attenuation. The detector converts the attenuated light into a voltage signal. The interference due to background noise generated by human skin is removed by taking floating or internal reference. The voltage signal obtained from the photodiodes is calibrated using Levenberg-Marquardt-based Artificial Neural Network to obtain the glucose concentration. The accuracy of proposed prototype was examined by comparing non-invasively predicted data with invasively measured reference data. It is observed that all measurements lie in A and B zones of Clarke error grid and thus clinically accurate. [ABSTRACT FROM AUTHOR]