Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
11 results
Search Results
Item Gender Identification from Children's Speech(Institute of Electrical and Electronics Engineers Inc., 2018) Ramteke, P.B.; Dixit, A.A.; Supanekar, S.; Dharwadkar, N.V.; Koolagudi, S.G.Children's speech can be characterized by higher pitch and format frequencies compared to the adult speech. Gender identification task from children's speech is difficult as there is no significant difference in the acoustic properties of male and female child. Here, an attempt has been made to explore the features efficient in discriminating the gender from children's speech. Different combinations of spectral features such as Mel-frequency cepstral coefficients (MFCCs), ΔMFCCs and ΔΔMFCCs, Formants, Linear predictive cepstral coefficients (LPCCs); Shimmer and Jitter; Prosodic features like pitch and its statistical variations along with Δpitch related features are explored. Features are evaluated using non linear classifiers namely Artificial Neural Network (ANNs), Deep Neural Network (DNNs) and Random Forest (RF). From the results it is observed that the RF achieves an highest accuracy of 84.79% amongst the other classifiers. © 2018 IEEE.Item Gender Identification using Spectral Features and Glottal Closure Instants (GCIs)(Institute of Electrical and Electronics Engineers Inc., 2019) Ramteke, P.B.; Supanekar, S.; Koolagudi, S.G.Automatic identification of gender from speech may help to improve the performance of the systems such as speaker speech recognition, forensic analysis, authentication processes. The difference in the physiological parameters of male and female vocal folds results in significant changes in their vocal fold vibration pattern. These changes can be characterized from the differences in the duration of their glottal closure. In this paper, an attempt has been made for gender recognition from speech using spectral features such as MFCCs, LPCCs, etc.; pitch (F0), excitation source features like glottal closure instants (GCIs) and its statistical variations. Western Michigan University's Gender dataset is used for experimentation. The dataset is collected from 93 speakers consisting of speech from 45 male and 48 female speakers respectively. Random forests (RFs) and Support vector machines (SVMs) are used to measure the performance of the proposed features. Random forest is observed to achieve average frame level accuracy of 96.908% using 13 MFCCs, 13 LPCCs, Pitch (F0) and GCI Stats (5). SVM is observed to achieve an average accuracy of 98.607% using 13 MFCCs, 13 LPCCs and GCI Stats (5). From the results, it is observed that the proposed features are efficient in discriminating the gender from speech. © 2019 IEEE.Item Cardiovascular Disease Prediction Using Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2022) Prajwal, K.; Tharun, K.; Navaneeth, P.; Anand Kumar, M.As the human population increases, so is the chance of getting diseases. There are many illnesses globally, and one of the biggest problems faced by the hospital systems today is the lack of technology to know when the patients are ill. One such illness is Cardiovascular Disease or CVD. It refers to any heart disease, vascular disease, or blood vessel disease. According to WHO, more people die of CVD's worldwide than any other cause. It affects the low and middle-income countries more. It is very hard for people living alone to contact the hospital when they are sick. Therefore, we have developed a model that can detect when a patient is ill and report back to the hospital. The system currently only identifies patients with heart disease and reports back to the hospital. We decided to go with heart disease identification because it is one of the most deadly diseases, and the risk of patients dying because of heart disease is high. Predicting whether a patient has heart disease or not is very clearly a classification problem. Therefore, we have used five models to classify. We take several factors such as blood sugar level, age, cholesterol level, and many more and give the outcome based on the input. © 2022 IEEE.Item Modeling Uber Data for Predicting Features Responsible for Price Fluctuations(Institute of Electrical and Electronics Engineers Inc., 2022) Sindhu, P.; Gupta, D.; Meghana, S.; Anand Kumar, M.In the field of economics, the features and patterns of the transportation system, including classical modes of transportation such as subways and taxis, as well as innovative tools such as car pooling platforms(Uber, Lyft, etc), are key research topics. The study here demonstrates how an Uber dataset is, which comprises Uber's New York City data, works. Uber is an online service provider platform via internet or a mobile application that avails ride-hailing service. In essence, it matches passengers with drivers of vehicles to book a ride from one place to another. The service connects users with drivers who will drive them to their desired location. The dataset contains primary data about Uber pick-ups, including the date, time, longitude, and latitude coordinates. The paper attempts to examine data from different locations, weathers, hours, and dates (intraday and midweek) in New York City and apply time series data analysis, statistical regression on the dataset, and predict Uber ride prices. We arrive at conclusions by analyzing data using various graphs, calculating and estimating the influence of these elements on Uber riders' payment amounts, and emphasizing features that cause price fluctuation. © 2022 IEEE.Item Fake News Detection Using Machine Learning Algorithms(Association for Computing Machinery, 2022) Imbwaga, J.L.; Chittaragi, N.; Koolagudi, S.G.There has been an exponential growth in users sharing news and information in real-time on various social media platforms worldwide. However, few of the users share fake and misleading news for various reasons. The reasons for sharing fake news may not be limited to financial, personal, and/or political gain. Since users cannot determine or censor the type of content that appears on their respective platforms, fake news can pose significant and detrimental effects on an individual and society at large. In this regard, we have proposed the work with the primary objective of development of a fake news detection system by applying supervised machine learning algorithms on an annotated (labeled) dataset. The dataset was selected from Kaggle, consisting of fake news with 23503 entries and true news with 21418 entries. An overall better accuracies are observed with tree-based decision tree classifiers and a gradient boosting ensemble algorithm. © 2022 ACM.Item IOT Devices Using Supervised Machine Learning Models for Anomaly Based Intrusion Detection(Institute of Electrical and Electronics Engineers Inc., 2023) Divakarla, U.; Chandrasekaran, K.Identifying dangers and irregularities in any infrastructure is a growing problem in the Internet of Things (IoT) industry. IoT infrastructure is utilised more frequently across a wide spectrum of organisations, which increases the risks and attack methods. Attacks and anomalies that could lead an IoT system to malfunction include denial of service attacks, data type probing, malicious control, malicious operation, scans, surveillance, and improper configuration. This article studies the ability of several machine learning models to predict attacks and abnormalities on IoT devices. The f1 score, area under the receiver operating characteristic curve, accuracy, precision, recall, and precision are among the metrics used to assess performance. ANNs, decision trees, and random forests all shown performance with a 99.4% accuracy rate in the system's tests. © 2023 IEEE.Item Robustness Analysis of EV Charging System using Random Forest Algorithm(Institute of Electrical and Electronics Engineers Inc., 2023) Barre, U.P.V.; Satyanarayan, S.; Reddy, H.; Pulikala, A.; Bajaj, A.Electric cars offer numerous benefits and are considered the future of the automobile industry. However, their worldwide adoption still needs to grow. One of the primary reasons for this delay in electrification is charge anxiety, which refers to the uncertainty customers feel when connecting the charging cable to the car. To address this issue, this study analyses the performance of the charging system using a machine learning model to identify sensitive signals that influence the charging process and can cause successful charging or charge termination. The analysis will also help to define robust operating regions where the charging component can reliably function, regardless of external conditions. This study's findings will provide insights into electric vehicle charging behavior with the supply station. © 2023 IEEE.Item Hybrid Genetic Algorithm and Machine Learning Approach for Software Reliability Assessment in Safety-Critical Systems(Institute of Electrical and Electronics Engineers Inc., 2024) Goyal, G.; Sharma, K.; Anshuman; Mittal, V.; Singla, B.; Das, M.; Mohan, B.R.Software reliability is a paramount determinant of software quality. In this research paper, we delve into utilizing Genetic Algorithms (GAs) for feature selection and classification. We undertake a comprehensive evaluation and comparative analysis of Machine Learning models, specifically Random Forest and Logistic Regression, both with and without Genetic Algorithmdriven feature selection. Our findings substantiate the significant impact of Genetic Algorithms in improving the accuracy of software reliability analysis. © 2024 IEEE.Item Hate Speech Detection Using Audio in Portuguese Language(Springer Science and Business Media Deutschland GmbH, 2024) Tembe, L.A.; Anand Kumar, M.This study focuses on hate speech in Portuguese language using audio and introduces a novel methodology that integrates audio-to-text and self-image technologies to effectively tackle this problem. We utilize Machine Learning and Deep Learning models to differentiate between hate speech and normal speech. The research utilized a total of 200 datasets, which were categorized into hate speech and normal speech. These datasets were collected by me personally for this project. Four distinct models are presented in the analysis: LSTM, SVM, CNN, and Random Forest. The findings highlight the superior performance of the CNN model when applied to spectrogram data, achieving an accuracy rate of 90%. Conversely, the Random Forest model outperforms others when dealing with text data, achieving an impressive accuracy rate of 73.1%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.Item Interval Type-2 Fuzzy-Support Vector Regression in Representation of Uncertainty in a Non-linear System(Springer Science and Business Media Deutschland GmbH, 2025) Umoh, U.; Eyoh, I.; Asuquo, D.; Vadivel, S.M.; Alimot, O.Machine learning algorithms such as Support Vector Machine (SVM and Support Vector Regression (SVR) are faced with challenges when confronted with imprecise and noisy data, which can lead to less meaningful outcomes. This paper introduces Interval Type-2 Fuzzy Support Vector Regression (IT2FSVR) as a solution to address uncertainty in non-linear systems. By combining Interval Type-2 Fuzzy Sets (IT2FS) and SVR, the proposed method enhances performance in systems with high levels of noise and non-linearity. The integration of IT2F membership in SVR directly tackles uncertainty in prediction problems, enabling adaptive learning to varying inputs and improving generalization performance. To demonstrate the effectiveness of this approach, the authors tested the performance of IT2F-SVR using a dataset of cardiovascular disease patients. Experimental results demonstrate that IT2F-SVR effectively eliminates uncertainty and significantly improves the learning process, outperforming individual approaches when applied to the same dataset and achieving faster execution times compared to some alternatives, albeit taking more time than SVR. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.