Omkaresh Kulkarni

Bio: Omkaresh Kulkarni is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Deep learning & Statistical model. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Multi-label classification with classifier chains of ANN models

Abstract: Multi-label classification is a generalization of a multi-class classification problem where one entity can belong to more than one class from the class set. Recent works have proposed multiple methods of solving this problem that involves both statistical and deep learning methods. While methods exist for using deep learning models for this problem, most of them require the model to have a high dimension output vector and the property of inter-dependency of classes has not been explored. An ensemble of statistical models called the chain classifiers can be used to address these issues. This study explores methods of using neural network classifiers in the classifier chain model and tries to address some problems with such architecture while compare their performance on different types of data using different metrics with each other and with other well performing multi-label classification methods.

Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach

Abstract: Myocardial Infarctions (MI) or heart attacks are among the most common medical emer-gencies globally. Such an episode often has mild or varied symptoms, making it hard to diagnose and respond in a timely manner. An electrocardiogram (ECG) is used to analyze the heart’s electrical activity and, through this help, clinicians detect and localize a heart attack. However, interpretation of the ECG is made manually by trained professionals. In order to make this diagnosis more efficient, multiple methods have tried to automate the MI detection and localization process. In this work, we aim to create a more effective method of MI detection by restructuring the localization as a multi-label classification (MLC) problem, in which one set of attributes can belong to one or more classes. For this classification, features like the ST-deviation, T wave amplitude, and R-S ratios have been extracted and fed into the MLC model, which in our case, is a chain classifier of random forest. This proposed model will have five classes as the target, which represent the loca-tions where an MI can occur. Our method achieves the best overall hamming accuracy of 81.49% in a k-fold cross validation test, with the highest accuracy for an individual class being 97.72% for anterior.

Bi-Directional Chains of Neural Nets for Multi-Target Regression

Abstract: Multi-Target Regression refers to the problem where a set of n independent variables are used to predict the values of k target variables where both k and n are greater than 1. Most methods provide the provision for a regression problem with multiple targets including decision tree regressors and artificial neural networks. However, these methods end up making an assumption that their is no inter-dependency among the target variables. In numerous problems, this assumption turns out to be false which can be notably seen with the variance inflation factor and co-relation of these variables. This consideration was addressed in both classification and regression using chain models, which although mostly competent, possess the issue of a uni-directional dependency. In this work, the significance of directionality problem has been discussed and is addressed by proposing an ensemble based methodology. The comparative analysis of the proposed model is studied against the pre-existing models to explore the improvements in the performance of the model.