Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
12 results
Search Results
Item Predicting Vaccine Hesitancy and Vaccine Sentiment Using Topic Modeling and Evolutionary Optimization(Springer Science and Business Media Deutschland GmbH, 2021) S. Krishnan, G.S.; Kamath S․, S.; Sugumaran, V.The ongoing COVID-19 pandemic has posed serious threats to the world population, affecting over 219 countries with a staggering impact of over 162 million cases and 3.36 million casualties. With the availability of multiple vaccines across the globe, framing vaccination policies for effectively inoculating a country’s population against such diseases is currently a crucial task for public health agencies. Social network users post their views and opinions on vaccines publicly and these posts can be put to good use in identifying vaccine hesitancy. In this paper, a vaccine hesitancy identification approach is proposed, built on novel text feature modeling based on evolutionary computation and topic modeling. The proposed approach was experimentally validated on two standard tweet datasets – the flu vaccine dataset and UK COVID-19 vaccine tweets. On the first dataset, the proposed approach outperformed the state-of-the-art in terms of standard metrics. The proposed model was also evaluated on the UKCOVID dataset and the results are presented in this paper, as our work is the first to benchmark a vaccine hesitancy model on this dataset. © 2021, Springer Nature Switzerland AG.Item LATA – Label attention transformer architectures for ICD-10 coding of unstructured clinical notes(Institute of Electrical and Electronics Engineers Inc., 2021) Mayya, V.; Kamath S․, S.S.; Sugumaran, V.Effective code assignment for patient clinical records in a hospital plays a significant role in the process of standardizing medical records, mainly for streamlining clinical care delivery, billing, and managing insurance claims. The current practice employed is manual coding, usually carried out by trained medical coders, making the process subjective, error-prone, inexact, and time-consuming. To alleviate this cost-intensive process, intelligent coding systems built on patients’ structured electronic medical records are critical. Classification of medical diagnostic codes, like ICD-10, is widely employed to categorize patients’ clinical conditions and associated diagnoses. In this work, we present a neural model LATA, built on Label Attention Transformer Architectures for automatic assignment of ICD-10 codes. Our work is benchmarked on the CodiEsp dataset, a dataset for automatic clinical coding systems for multilingual medical documents, used in the eHealth CLEF 2020-Multilingual Information Extraction Shared Task. The experimental results reveal that the proposed LATA variants outperform their basic BERT counterparts by 33-49% in terms of standard metrics like precision, recall, F1-score and mean average precision. The label attention mechanism also enables direct extraction of textual evidence in medical documents that map to the clinical ICD-10 diagnostic codes. © 2021 IEEE.Item Effective Information Retrieval, Question Answering and Abstractive Summarization on Large-Scale Biomedical Document Corpora(Springer Science and Business Media Deutschland GmbH, 2023) Shenoy, N.; Nayak, P.; Jain, S.; Kamath S․, S.; Sugumaran, V.During the COVID-19 pandemic, a concentrated effort was made to collate published literature on SARS-Cov-2 and other coronaviruses for the benefit of the medical community. One such initiative is the COVID-19 Open Research Dataset which contains over 400,000 published research articles. To expedite access to relevant information sources for health workers and researchers, it is vital to design effective information retrieval and information extraction systems. In this article, an IR approach leveraging transformer-based models to enable question-answering and abstractive summarization is presented. Various keyword-based and neural-network-based models are experimented with and incorporated to reduce the search space and determine relevant sentences from the vast corpus for ranked retrieval. For abstractive summarization, candidate sentences are determined using a combination of various standard scoring metrics. Finally, the summary and the user query are utilized for supporting question answering. The proposed model is evaluated based on standard metrics on the standard CovidQA dataset for both natural language and keyword queries. The proposed approach achieved promising performance for both query classes, while outperforming various unsupervised baselines. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item A Comprehensive Analysis of Classification Techniques for Effective Multi-class Research Article Categorization on an Imbalanced Dataset(Springer Science and Business Media Deutschland GmbH, 2025) Gowhar, S.; Kempaiah, P.; Sowmya Kamath, S.; Sugumaran, V.Categorizing scientific articles into specific research fields is a challenging problem, affected by the volume and variety of literature published. However, existing classification systems often suffer from limitations regarding taxonomy or the models used for classification. This article explores a comprehensive analysis of approaches built on Sentence Transformer embeddings combined with Machine Learning algorithms, Neural Networks, and Transformers to classify articles into 123 predefined classes, with the dataset being heavily imbalanced. The effectiveness of Large Language Models (LLMs) for generating synthetic data is also experimented with, along with synonym augmentation SMOTE and employing 1D CNNs for text classification. The best-performing model is a hierarchical classification model trained on MP-Net sentence embeddings that achieved an accuracy of 78%, outperforming all other models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.Item Imbalanced Multi-Class Research Article Classification using Sentence Transformers and Machine Learning Algorithms(Association for Computing Machinery, Inc, 2025) Gowhar, S.; Kempaiah, P.; Kamath, S.S.; Sugumaran, V.Categorizing scientific articles into specific research fields is a challenging problem, considering the volume and variety of published literature. However, existing classification systems often suffer from limitations regarding taxonomy or the models used for classification. This article explores approaches built on Sentence Transformer embeddings combined with Machine Learning algorithms to classify articles into 123 predefined classes, with the dataset being heavily imbalanced in nature. The effectiveness of Large Language Models (LLMs) for generating synthetic data is also experimented with, along with synonym augmentation and SMOTE. The best-performing model, the One vs Rest classifier trained on MP-Net sentence embeddings with SMOTE, achieved an accuracy of 77%, and outperformed all the other models. © 2024 Copyright held by the owner/author(s).Item Fault diagnosis of helical gear box using decision tree through vibration signals(RAMS Consultants, 2013) Sugumaran, V.; Jain, D.; Amarnath, M.; Kumar, H.This paper uses vibration signals acquired from gears in good and simulated faulty conditions for the purpose of fault diagnosis through machine learning approach. The descriptive statistical features were extracted from vibration signals and the important ones were selected using decision tree (dimensionality reduction). The selected features were then used for classification using J48 decision tree algorithm. The paper also discusses the effect of various parameters on classification accuracy. © RAMS Consultants.Item Fault diagnosis of bearings through vibration signal using Bayes classifiers(Inderscience Publishers, 2014) Kumar, H.; Ranjit Kumar, T.A.; Amarnath, M.; Sugumaran, V.Bearings are an inevitable part in industrial machineries, which is subjected to wear and tear. Breakdown of such crucial components incur heavy losses. This study concerns with fault diagnosis through machine learning approach of bearing using vibration signals of bearings in good and simulated faulty conditions. The vibration data was acquired from bearings using accelerometer under different operating conditions. Vibration signals of a bearing contain the dynamic information about its operating condition. The descriptive statistical features were extracted from vibration signals and the important ones were selected using decision tree (dimensionality reduction). The decision tree has been formulated using J48 algorithm. The selected features were then used for classification using Bayes classifiers namely, Naïve Bayes and Bayes net. The paper also discusses the effect of various parameters on classification accuracy. © 2014 Inderscience Enterprises Ltd.Item Fault diagnosis of bearings through sound signal using statistical features and bayes classifier(Krishtel eMaging Solutions Pvt. Ltd, 2016) Kumar, H.; Sugumaran, V.; Amarnath, M.Bearing is one of important rotary elements used in almost all machinery. This study concerns with fault diagnosis through machine learning approach using acoustic signals (sound) of bearings in good and simulated faulty conditions. The acoustic data was acquired from near field area of bearings using microphone under different operating conditions. Acoustic signals of a bearing contain the dynamic information about its operating condition. Abundant literature reported suitability of vibration signals for fault diagnosis applications, however, not much using sound signals for diagnosis applications. Also, transducers used for measurement of sound are less costly than transducers used for vibration measurement. Hence, usage of sound signals for fault diagnosis applications of bearings found beneficial. The descriptive statistical features were extracted from sound signals and the important ones were selected using decision tree (dimensionality reduction). The selected features were then used for classification using Bayes classifier. The paper also discusses the effect of various parameters on classification accuracy. © KRISHTEL eMAGING SOLUTIONS PVT. LTD.Item Condition monitoring of roller bearing by K-star classifier and K-nearest neighborhood classifier using sound signal(Tech Science Press sale@techscience.com, 2017) Sharma, R.K.; Sugumaran, V.; Kumar, H.; Amarnath, M.Most of the machineries in small or large scale industry have rotating element supported by bearings for rigid support and accurate movement. For proper functioning of machinery, condition monitoring of the bearing is very important. In present study sound signal is used to continuously monitor bearing health as sound signals of rotating machineries carry dynamic information of components. There are numerous studies in literature that are reporting superiority of vibration signal of bearing fault diagnosis. However, there are very few studies done using sound signal. The cost associated with condition monitoring using sound signal (Microphone) is less than the cost of transducer used to acquire vibration signal (Accelerometer). This paper employs sound signal for condition monitoring of roller bearing by K-star classifier and k-nearest neighborhood classifier. The statistical feature extraction is performed from acquired sound signals. Then two layer feature selection is done using J48 decision tree algorithm and random tree algorithm. These selected features were classified using K-star classifier and k-nearest neighborhood classifier and parametric optimization is performed to achieve the maximum classification accuracy. The classification results for both K-star classifier and k-nearest neighborhood classifier for condition monitoring of roller bearing using sound signals were compared. © Copyright 2017 Tech Science Press.Item Condition monitoring of single point cutting tools based on machine learning approach(International Institute of Acoustics and Vibrations P O Box 13 Auburn AL 36831, 2018) Gangadhar, N.; Kumar, H.; Narendranath, S.; Sugumaran, V.This paper presents the use of multilayer perceptron (MLP) for fault diagnosis through a histogram feature extracted from vibration signals of healthy and faulty conditions of single point cutting tools. The features were extracted from the vibration signals, which were acquired while machining with healthy and different worn-out tool conditions. Principle component analysis (PCA) used to select important extracted features. The artificial neural network (ANN) algorithm was applied as a fault classifier in order to know the status of cutting tool conditions. The accuracy of classification with MLP was found to be 82.5 %, which validates that the proposed approach is an effective method for fault diagnosis of single point cutting tools. © 2018 International Institute of Acoustics and Vibrations. All Rights Reserved.