scispace - formally typeset
Search or ask a question
Author

Kanwal Habib

Bio: Kanwal Habib is an academic researcher from University of Engineering and Technology, Lahore. The author has contributed to research in topics: Phonocardiogram. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Papers
More filters
Proceedings ArticleDOI
15 Jul 2021
TL;DR: In this paper, an algorithm for classifying various types of cardiovascular diseases using PCG auscultations is proposed. But, the proposed methodology obtained a cumulative accuracy of 98.8 %, specificity of 97.56 %, and sensitivity of 99.99 %.
Abstract: Cardiovascular diseases (CVD) have been one of the top two causes of death globally, accounting for 633,842 fatalities. An intelligent system capable of detecting these disorders is needed urgently. Phonocardiogram (PCG) signals are useful in the earlier detection of CVDs as they help determine the actual nature and condition of the heart. Cardiac auscultation is the most used procedure for examining, classifying, and analyzing the cardiac sounds in a PCG. We formulated an algorithm for classifying various types of cardiovascular diseases using PCG auscultations. Dataset repository (Normal & Extrahls) is made up of personally acquired PCGs from different clinical facilities. Empirical Mode Decomposition (EMD) helps denoise and pre-process these raw signals. To extract the area of interest, soft threshold-based signal segmentation is applied. Then, four Impulsive domain features are extracted from each class’s pre-processed signal and fed to six separate machine learning-based ensemble classifiers to evaluate optimum accuracy. The proposed methodology obtained a cumulative accuracy of 98.8 %, specificity of 97.56%, and sensitivity of 99.99 %. This system will assist Pakistani doctors to detect and classify heart disease without any invasive technology usage.

6 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.
Abstract: Abstract Background and Motivation: Cardiovascular disease (CVD) causes the highest mortality globally. With escalating healthcare costs, early non-invasive CVD risk assessment is vital. Conventional methods have shown poor performance compared to more recent and fast-evolving Artificial Intelligence (AI) methods. The proposed study reviews the three most recent paradigms for CVD risk assessment, namely multiclass, multi-label, and ensemble-based methods in (i) office-based and (ii) stress-test laboratories. Methods: A total of 265 CVD-based studies were selected using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) model. Due to its popularity and recent development, the study analyzed the above three paradigms using machine learning (ML) frameworks. We review comprehensively these three methods using attributes, such as architecture, applications, pro-and-cons, scientific validation, clinical evaluation, and AI risk-of-bias (RoB) in the CVD framework. These ML techniques were then extended under mobile and cloud-based infrastructure. Findings: Most popular biomarkers used were office-based, laboratory-based, image-based phenotypes, and medication usage. Surrogate carotid scanning for coronary artery risk prediction had shown promising results. Ground truth (GT) selection for AI-based training along with scientific and clinical validation is very important for CVD stratification to avoid RoB. It was observed that the most popular classification paradigm is multiclass followed by the ensemble, and multi-label. The use of deep learning techniques in CVD risk stratification is in a very early stage of development. Mobile and cloud-based AI technologies are more likely to be the future. Conclusions: AI-based methods for CVD risk assessment are most promising and successful. Choice of GT is most vital in AI-based models to prevent the RoB. The amalgamation of image-based strategies with conventional risk factors provides the highest stability when using the three CVD paradigms in non-cloud and cloud-based frameworks.

14 citations

Proceedings ArticleDOI
30 Aug 2021
TL;DR: In this paper, a Cubic-Support Vector Machine classifier is trained on four different EMG (Electromyography) based hand gestures named as wrist flexion, wrist extension, resting hand, clenched fist.
Abstract: Machines are built to give accessibility, precision, cost-effectiveness, and adaptability characteristics. This work will facilitate the recognition of hand gestures based on supervised learning. Signal processing-based techniques such as pre-processing (normalization) and segmentation (empirical mode decomposition) are employed. The Cubic-Support Vector Machine classifier is trained on four different EMG (Electromyography) based hand gestures named as wrist flexion, wrist extension, resting hand, clenched fist. Spectral domain features are extracted, which provide less variance than other extraction methods. This supervised machine learning model achieved a cumulative classification accuracy of 98.9%. This hand gesture-based system can help handicapped people in nonverbal communication and physically challenged individuals in non-invasive machine communication.

6 citations

Journal ArticleDOI
TL;DR: A detailed summary of research done on fall detection systems, with comparisons across different types of studies, is provided in this paper , where datasets, limitations, and future imperatives in fall detection are discussed in detail.
Abstract: Falls are a major public health concern among the elderly and the number of gadgets designed to detect them has increased significantly in recent years. This document provides a detailed summary of research done on fall detection systems, with comparisons across different types of studies. Its purpose is to be a resource for doctors and engineers who are planning or conducting field research. Following the examination, datasets, limitations, and future imperatives in fall detection were discussed in detail. The quantity of research using context-aware approaches continues to rise, but there is a new trend toward integrating fall detection into smartphones, as well as the use of artificial intelligence in the detection algorithm. Concerns with real-world performance, usability, and reliability are also highlighted.
Proceedings ArticleDOI
24 Nov 2022
TL;DR: In this paper , a range of classical methodologies that includes diverse factors such as ECG, blood pressure, blood glucose and cholesterol are reviewed in order to diagnose each type of cardiovascular disease and build a framework to help physicians.
Abstract: Cardiovascular disease (CVD), the predominant reason of deaths across the globe, has been a significant challenge to healthful living all over the world, placing a vast social-economic load on patients, families and nations annually. WHO (World Health Organization) report states that increase in cardiovascular risk factors such as high blood pressure, diabetes, overweight and smoking will lead to a maximize the mortality rate by 24.5 million in 2030. In many cases, the time before a doctor's visit and necessary hospitalization is significantly relied upon saving the life of patients. Therefore, the frequent updates are provided to the doctors about the medicinal status of patient in order to reduce the mortality rate. To find the risk of this disease, it is important to diagnose each type of cardiovascular disease (CVD) and build a framework to help physicians so that the accurate and effectual decisions are made during diagnosis. The doctors attempt to differentiate a coronary disorder by analyzing the values of various features. This work considers a range of classical methodologies that includes diverse factors such as ECG, blood pressure, blood glucose and cholesterol. The techniques of detecting the cardiovascular disease are reviewed in this paper.