Dr Hemant Pasusangai Kasturiwale
@tcetmumbai.in
Associate Professor and HOD
THAKUR COLLEGE OF ENGINEERING AND TECHNOLOGY MUMBAI INDIA
EDUCATION
PhD( Engineering and Technology) ME( Electronics) BE( Electrical)
RESEARCH, TEACHING, or OTHER INTERESTS
Multidisciplinary, Computer Engineering, Artificial Intelligence, Information Systems
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Prachi Janrao, Sujata Alegavi, Vedant Pandya, Chetashri Bhadane, Rutvi Thakar, and Hemant Kasturiwale
AIP Publishing
Samarjeet Borah, B. K. Mishra, and Hemant Kasturiwale
Apple Academic Press
Hemant Kasturiwale, Swati Bhisikar, and Sandhya Save
Wiley
Rajesh Karhe, Hemant Kasturiwale, and Sujata N. Kale
Wiley
Hemant Kasturiwale, Rajesh Karhe, and Hemant Kasturiwale
Wiley
Khandare V. Ninad, , Kasturiwale P. Hemant, Sedamkar R. Raghvendra, , and
Rajarambapu Institute of Technology
Laboratory classes are an essential part of an engineering course. Laboratory sessions are primarily designed to develop proficiency in technical skills, offer an opportunity to place theory in context, develop critical thinking skills and promote investigation-based learning. Laboratory experiences will help to develop as independent learners, researchers, critical thinkers, and generators of knowledge. There are several improvements that need to be implemented to improve student laboratory experiences. The purpose of this research is to integrate with end semester examination in view of requirements of the 21st century.This paper highlight the evaluation system which is robust and dynamic as compared to the traditional evaluation system. This research is based on the feedback collected from industrialists and academicians on the present examination system. The paper has come up with the result that 50 % of academicians are of the opinion that examination paper patterns should include the laboratory-based question. The paper highlights the curriculum design aspect related to the question paper setting. The paper brings some critical points related to the integration of laboratory conduct and evaluation system with end semester examination. Keywords:- laboratory work, Learner, Knowledge, Integration, Examination, Evaluation
Hemant Kasturiwale and Sujata N Kale
IOP Publishing
Abstract The machine learning based model is designed for robustness on the basis of both ECG based HRV analysis and non-ECG based analysis. The goal is to evaluate the efficacy of different machine learning classification models. A statistical analysis is provided with repositories such as MIT/BIH Normal Sinus Rhythm (NSR) and MIT/BIH Atrial Fibrillation (AF) and Peripheral Pule Analyzer. The model was checked on all possible subject conditions, the form of ECG database and the non-ECG signal. The Best Feature was chosen from the various HRV Settings that will be used for classification. In our intra group selection analysis, traditional and well-known machine learning classification techniques, such as Random Forest, Support Vector Machine, K-Nearest Neighbours, Adaptive Boosting, Support Vector Machine. Robustness is driven primarily by precision, flexibility and specificity. The 5 percent higher accuracy band and lower band model are tested. The Random forest has produced better performance and has been tested for its robustness. Testing is carried out for more than 20 indices and more than 40,000 combinations generated and added to the model for study. The efficacy of these classifier-based Intra-Group selection models is tested by performing variety of dataset experiments obtained from standard sets as well as acquired data. Overall experimental findings and discussions will enable all researchers to assess the effect of the features on the model.
Hemant P. Kasturiwale and Sujata N. Kale
IOS Press
The Autonomous Nervous System (ANS) controls the nervous system and Heart Rate Variability (HRV) can be used as a diagnostic tool to diagnose heart defects. HRV can be classified into linear and nonlinear HRV indices which are used mostly to measure the efficiency of the model. For prediction of cardiac diseases, the selection and extraction features of machine learning model are effective. The available model used till date is based on HRV indices to predict the cardiac diseases accurately. The model could hardly throw light on specifics of indices, selection process and stability of the model. The proposed model is developed considering all facet electrocardiogram amplitude (ECG), frequency components, sampling frequency, extraction methods and acquisition techniques. The machine learning based model and its performance shall be tested using the standard BioSignal method, both on the data available and on the data obtained by the author. This is unique model developed by considering the vast number of mixtures sets and more than four complex cardiac classes. The statistical analysis is performed on a variety of databases such as MIT/BIH Normal Sinus Rhythm (NSR), MIT/BIH Arrhythmia (AR) and MIT/BIH Atrial Fibrillation (AF) and Peripheral Pule Analyser using feature compatibility techniques. The classifiers are trained for prediction with approximately 40000 sets of parameters. The proposed model reaches an average accuracy of 97.87 percent and is sensitive and précised. The best features are chosen from the different HRV features that will be used for classification. The present model was checked under all possible subject scenarios, such as the raw database and the non-ECG signal. In this sense, robustness is defined not only by the specificity parameter, but also by other measuring output parameters. Support Vector Machine (SVM), K-nearest Neighbour (KNN), Ensemble Adaboost (EAB) with Random Forest (RF) are tested in a 5% higher precision band and a lower band configuration. The Random Forest has produced better results, and its robustness has been established.
D. Jude Hemanth, Jacek Zurada, and Hemant Kasturiwale
IOS Press
Sanket B. Kasturiwala and Hemant P. Kasturiwale
IOS Press
Hemant Kasturiwale and Sujata N. Kale
IEEE
Diagnosis of Heart disease is an important and critical task which can provide prediction about the heart disease so that treatment made easy. The Electrocardiogram of a person gives the total electrical and muscular functions of a human heart and information about cardiac health. Here, the focused on exploring advanced techniques of HRV analysis and indices to develop robust methods for diagnosing patients with CHF from an ECG records. Majority of studies on HRV report several differences between patients with congestive heart failure (CHF), Coronary Artery Disease (CAD) and healthy subjects, such as time-domain, frequency domain and nonlinear HRV measure. In this study classification is performed using clustering method and by finding an optimal k-Nearest Neighbours to discriminate the patients with CHF from the normal. The wavelet entropy, which has been used in the other biomedical signal classification schemes like EEG spike detection, is also used as an HRV measure to enhance the performance of the classifier. The nonlinear and dynamic properties of signals are to be understood well by Poincare plot measures. The stress has a psychological origin but affects several physiological processes in the human body: increased muscle tension in the neck, change in concentration of several hormones and a change in heart rate (HR) and heart rate variability. Here, paper is able to give physiological parameters and its influence to predict diseases while calculating other effect on HRV.
Sunil Khatri and Hemant Kasturiwale
IEEE
Impulse noise still poses challenges in front of researchers today. The removal of impulse noise brings blurring which leads to edges being distorted and image thus being of poor quality. Hence the need is to preserve edges and fine details during filtering. The proposed method consists of noise detection and then removal of detected noise by Improved Adaptive Median Filter using pixels that are not noise themselves in gray level as well as colour images. The pixels are split in two groups, which are noise-free pixels and noisy pixels. In removing out Impulse noise, only noisy pixels are processed. The noiseless pixels are then sent directly to the output image. The proposed method adaptively changes the masking matrix size of the median filter based on the count of the noisy pixels. Computer simulation and analysis have been carried out eventually to analyse the performance of the proposed method with that of Simple Median Filter (SMF), Simple Adaptive Median Filter (SAMF) and Adaptive Switched Median Filter (ASMF). The proposed filter proves to be more efficient in terms of both objective and subjective parameters.
H. P. Kasturiwale and C. N. Deshmukh
IEEE
The immense scope in the field of biomedical signal processing Independent Component Analysis (ICA ) is gaining momentum due to huge data base requirement for quality testing. The diagnosis of patient is based on visual observation of recorded ECG signals may not be accurate. Many attempts have been carried out to remove noise or artifacts such as interference (few Hz), electromagnetic emission, muscle activities and others from ECG signal. To achieve better understanding, ICA algorithms helps in analyzing ECG signals.This paper describes some algorithms of ICA in brief, such as FastICA, Kernel-ICA, MS -ICA, JADE, EGLD-ICA,Robust ICA etc. The quality & performance of some of the ICA algorithms are tested and analysis of each can be done with respect to Noise/Artifacts, SIR(Signal Interference Ratio),PI(performance Index). In the conclusion tries giving selection type of ICA algorithm for different ECG database.