Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
6 results
Search Results
Item A Simple Displacement Function to Determine the Response of a Micro Capacitive Pressure Sensor(2011) Simha, A.; Kulkarni, S.M.; Meenatchi Sundaram, S.; Bhat, S.The response of a capacitive pressure sensor is generally represented by a fourth order partial differential equation which is complex to solve and does not possess an exact solution. Several attempts have been made earlier through various techniques such as the Galerkin method, Finite Difference Method etc.... In this paper an attempt has been made to develop a simple approximate analytical approach to determine the response of a micro capacitive pressure sensor whose diaphragm is designed to undergo very small deflections (typically less than 25% of the thickness). The non-uniform gap between the electrodes is mathematically expressed as a combination of the initial gap between the electrodes (in the undeformed state) and a displacement function in (x,y). The proposed displacement function is then utilized in evaluating the capacitance as a function of the applied pressure. The results obtained from the analytical approach are benchmarked against those obtained from COMSOL Multiphysics®, a popular Finite Element Analysis tool in the MEMS industry. It is observed that the results obtained from COMSOL Multiphysics® and those from the analytical approach are in good agreement with a maximum deviation of about 8.66%. © 2011 American Institute of Physics.Item Heat treatment of friction surfaced steel-aluminum couple(Trans Tech Publications Ltd ttp@transtec.ch, 2015) Bhat, K.; Nithin; Bhat, S.; SudeendranFriction surfacing is a solid state process and it is amenable for deposition of aluminum on steel. In this investigation, the mild steel surface was coated with a layer of aluminum using friction surfacing route. The aluminum thickness was in the range of 40-50 μm. It was followed by a heat treatment step to convert aluminum layer in to an aluminide layer. Heat treatment was done in open atmosphere at 700 °C for 2 hours. Microstuctural analysis showed that the aluminide layer is mainly made of Fe2Al5 and Fe4Al13, FeAl and Fe3Al are minor in fraction. Formation of Fe2Al5 is discussed. The aluminide layer also has some amount of porosities. © (2015) Trans Tech Publications, Switzerland.Item Monophone and Triphone Acoustic Phonetic Model for Kannada Speech Recognition System(Institute of Electrical and Electronics Engineers Inc., 2022) Kumar, T.N.M.; Jayan, A.; Bhat, S.; Anvith, M.; Narasimhadhan, A.V.The automatic Speech Recognition system (ASR) is the most widely used application in the speech domain. ASR systems generate text data from spoken utterances without manual intervention. In this work, we build an ASR system for the Kannada language. For building the proposed system, we extract Mel Frequency Cepstral Coefficients (MFCC) features from the audio data, and the Kannada language model is developed using corresponding labels. The dictionary generation and phonetic labelings are automated. Recognition performance is compared for both monophonic and triphone models. The word error rate of 15.73 % and the sentence error rate of 55.5 % are achieved for the triphone model. Comparatively, the triphone model gives a better performance than the monophonic model. © 2022 IEEE.Item Big data in roads and pavements: Insights from a bibliometric study and a critical review of recent publications(CRC Press/Balkema, 2022) Bhat, S.; Suresha, S.N.This article is intended to present the quantitative study of scientific research publications in the recent decade on the application of big data in the area of road transport and pavement engineering. The present study was conducted in two phases. In the first phase, 5036 Scopus indexed research documents such as research articles, review articles, conference papers, books, and book chapters published during 2010 and 2021 were referred. The study presents the geographical origin of the research documents; list of journals in which articles frequently featured; trends in the annual publication of research articles in journals, citations, and average citations per documents; and the frequency distribution of articles with different range of citations. In the second phase, nearly 100 articles that had cited the research article on the application of big data tools for the pavement distress detection were examined for the various types of machine learning, deep learning algorithms. © 2022 the Author(s).Item Leveraging SIR and Barabási-Albert Models for Epidemic Modelling(IEEE Computer Society, 2024) Bhat, S.; Ragha Sai, V.; Mundody, S.; Guddeti, R.M.R.The Susceptible, Infected, and Recovered (SIR) model predicts the number of living beings in a population who are infected and recovering from a disease. This article addresses the critical challenge of modelling and simulating the spread of contagious diseases in a population. Drawing inspiration from global events like the COVID-19 pandemic, our proposed simulation aims to comprehensively understand the epidemic dynamics and thus enhances the public awareness for effective decision-making. The proposed simulation integrates the computational models and simulation techniques, including the logistic functions, agent-based models, SIR models, and network-based spread models. © 2024 FRUCT.Item Accuracy Comparison of Logistic Regression and Decision Tree Prediction Models Using Machine Learning Technique(Springer Science and Business Media Deutschland GmbH, 2025) Tantri, B.R.; Bhat, S.With the advancements in data science and machine learning, it has become beneficial for scientists, technologists, social scientists, and businessmen to adopt the latest developments in machine learning into their domains to make important decisions about their problems of interest. The biggest advantage of machine learning algorithms in such fields is their prediction capability. Statistical tools in powerful machine-learning languages like R have led to simpler solutions to more complex problems. Various models are in use in the process of making decisions and predictions. The most commonly used model in many situations is the regression model. Herein, it is intended to use the logistic regression model and the decision tree model in the prediction of binary categorical variables. R programming is used in the development of these prediction models. It is intended to compare the accuracy of the two models by using the confusion matrices. Two different datasets have been used for the prediction using these models and their comparisons. It has been observed that prediction using a decision tree model has a better accuracy as compared to that of a logistic regression model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.