{"title":"Multi Tasking Synthetic Speech Detection on Indian Languages","authors":"A. R. Ambili, Rajesh Cherian Roy","doi":"10.1109/ICITIIT54346.2022.9744221","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744221","url":null,"abstract":"Anti-spoofing research plays an important role in audio forensics. It has found a lot of traction in several languages around the world. With that in mind, the purpose of this work is to assess the impact of several synthetic spoofing detection approaches on a multilingual, low-constrained Indian language set. This paper aims at a multitasking spoofing detection by identifying real/spoof utterance identification as well as the regional language spoofing attack vector. To accomplish this, the features and the classifiers that are best candidate for the synthetic spoofing detection and language identification are appropriately chosen. Our methodology compares the performances of three main different classifiers GMM, SVM, DNN on the vector formulated from the accumulation of MFCC features. Hindi, Malayalam, Tamil, Telugu are the four languages which are taken into account for the comparison. Out of these classifiers, SVM and DNN are found to give the best results with EER rates of 1.98 % and 1.19 % respectively.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125463296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sainath Reddy Sankepally, Nishoak Kosaraju, K. Mallikharjuna Rao
{"title":"Data Imputation Techniques: An Empirical Study using Chronic Kidney Disease and Life Expectancy Datasets","authors":"Sainath Reddy Sankepally, Nishoak Kosaraju, K. Mallikharjuna Rao","doi":"10.1109/ICITIIT54346.2022.9744211","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744211","url":null,"abstract":"Data is a collection of information from the activities of the real world. The file in which such data is stored after transforming into a form that machines can process is generally known as data set. In the real world, many data sets are not complete, and they contain various types of noise. Missing values is of one such kind. Thus, imputing data of these missing values is one of the significant task of data pre-processing. This paper deals with two real time health care data sets namely life expectancy (LE) dataset and chronic kidney disease (CKD) dataset, which are very different in their nature. This paper provides insights on various data imputation techniques to fill missing values by analyzing them. When coming to Data imputation, it is very common to impute the missing values with measure of central tendencies like mean, median, mode Which can represent the central value of distribution but choosing the apt choice is real challenge. In accordance with best of our knowledge this is the first and foremost paper which provides the complete analysis of impact of basic data imputation techniques on various data distributions which can be classified based on the size of data set, number of missing values, type of data (categorical/numerical), etc. This paper compared and analyzed the original data distribution with the data distribution after each imputation in terms of their skewness, outliers and by various descriptive statistic parameters.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115910343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"String Kernels for Document Classification: A Comparative Study","authors":"Nikhil V. Chandran, A. S., A. V. S.","doi":"10.1109/ICITIIT54346.2022.9744134","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744134","url":null,"abstract":"In machine learning and data mining, String Kernels combined with classifiers like Support Vector Machines (SVM) show state-of-the-art results for tasks such as text classification. Traditional pairwise comparisons of strings on large datasets are computationally expensive and result in quadratic runtimes. This work compares the performance of various String Kernels and similarity measures on the document classification task. We compare different String Kernels such as Spectrum Kernel, String Subsequence Kernel, Weighted Degree Kernel, and Distance Substitution Kernel in this paper for classifying text documents. A detailed comparative study of these Kernel techniques on real-life document corpus such as Reuters-21578 shows different insights when used with and without other feature extraction techniques. The results indicate that string similarity measures give the best performance when run over the entire corpus but for small and medium-sized datasets. The complexity increases with an increase in the size of the dataset.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121933667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Speed Control of Permanent Magnet Synchronous Machine using Genetic and Fuzzy Algorithm","authors":"Arundhuti Haldar, Riddhi Khatua","doi":"10.1109/ICITIIT54346.2022.9744234","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744234","url":null,"abstract":"This paper investigates the different advanced algorithms employed for the speed control of a Permanent Magnet Synchronous Machine (PMSM). Speed control is achieved by tuning the PI controller with fuzzy and genetic algorithm. Finally, the results are compared with the conventional method of PI tuning. The simulation process has been carried out in MATLAB.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116761602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"NLP Based Automated Business Report Summarization","authors":"Faizal B, Sajimon Abraham","doi":"10.1109/ICITIIT54346.2022.9744151","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744151","url":null,"abstract":"A business report usually contains customer feedback, analysis, findings and recommendations for future implementation for the improvement in the specified business. Automated text summarization of business reports will help the analysis team to enhance the building of the business proposal model. The business report summarization is quite different from generic text summarization as it conveys most of the data through tables, graphs and images. Several text summarization methods can be considered for generating the summary of a business report. This paper provides a comprehensive study on different approaches that can be considered for business report summarization and the latest evaluation methods. Moreover, it discusses some future research directions in the field of business text summarization using a combination of natural language processing with statistics and deep learning.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128977929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Balancing of an imbalanced dataset by applying SMOTE variants and predicting neonatal mortality using ensemble learning techniques","authors":"Sivarajan A, Bala Aditya A, Sivasankar E","doi":"10.1109/ICITIIT54346.2022.9744204","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744204","url":null,"abstract":"Dynamic environment and imbalanced datasets are unavoidable challenges in developing medical diagnostic tools where incremental learning is a necessity. The prediction tools upon imbalanced data normally work with majority class bias, and it is not easy to recognize faulty classes. This work aims to solve the class imbalance problem by generating synthetic data using SMOTE variants to balance the dataset and predict the neonatal mortality by adopting different ensemble classification methods. This system will be applied to diagnose newborns, vulnerable to die in the initial period of 28 days after birth.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128767193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sajimon Abraham, Jyothish V R, Sijo Thomas, Benymol Jose
{"title":"Comparative Analysis of Various Machine Learning Techniques for Flood Prediction","authors":"Sajimon Abraham, Jyothish V R, Sijo Thomas, Benymol Jose","doi":"10.1109/ICITIIT54346.2022.9744177","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744177","url":null,"abstract":"A flood is a most destructive disaster that affects people, places, and lives. Due to the complication in data availability, flood prediction is always a challenging task. The conventional mode of disaster management relies on satellite images and radar outcomes. It takes enormous time for processing. Machine learning paved the way for a new perspective on this hydrological problem. Recent developments in Machine Learning (ML) and Information and Communication Technology (ICT) have led to a state-of-the-art implementation and prediction. The major objective of this work is to recognize the most accurate machine learning model to identify flood occurrence, by comparing Logistic regression, Decision Tree, Naive Bayes, and Support Vector Machines classifiers. Machine Learning strategies are evaluated using precision, recall, F1-score, RMSE, and accuracy metrics. All the strategies are applied to one-feature dataset, three-feature dataset and four-feature dataset. The quantitative evaluation demonstrates that decision tree algorithm is most suitable for flood prediction and it exponentially grows with respect to the number of features examined.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116400949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Miniature probability maps using resource limited embedded device for classification of histopathological images","authors":"Anil Johny, K. Madhusoodanan","doi":"10.1109/ICITIIT54346.2022.9744131","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744131","url":null,"abstract":"Prediction of malignancy in histopathology images using CNN is mostly performed using cloud services suffers from network latency. We propose a novel, efficient method to classify whole slide histopathology images using modular and portable embedded devices to detect the presence of cell abnormality. The proposed method generates probability maps which indicates predictions so that a bird’s-eye view of tissue malignancy can be obtained. The miniature map(mini-map) of histopathology image is the overview of binary class probabilities at the patient level. The computational overhead of device is reduced as well as prediction will be faster while using custom-trained model. The round trip time is also reduced as the computing occurs near the end-device itself. The obtained predictions in mini-map can be viewed in any portable device consuming minimum processing time as the size of the map is only few kilo-bytes. This method is found to be suitable to assist medical practitioners in patient diagnosis.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115949090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"vRecruit: An Automated Smart Recruitment Webapp using Machine Learning","authors":"Sanika Mhadgut, Neha Koppikar, Nikhil Chouhan, Parag Dharadhar, Parthak Mehta","doi":"10.1109/ICITIIT54346.2022.9744135","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744135","url":null,"abstract":"The need for global online recruitment has risen tremendously in recent years. However, this procedure presents difficulties for recruiters in managing the flood of applications and maintaining contact with the applicants. Historically, little attention has been paid to a practical solution for virtual recruitment. As a result, the paper proposes \"vRecruit - A machine learning-based web application\" for virtual recruitment in the current paper. vRecruit’s primary features include a client-specific interview process that leverages Machine Learning-based references to context provided by the client, as well as a text-based sentiment analysis engine. All components work in unison to ensure the webapp’s end-to-end functionality, which was finally launched on flask. The face recognition method using the face api model achieved a 96% accuracy. The speech to text conversion using the Mozilla DeepSpeech model had a 7.55% word error rate, whereas the rasa Natural Language Understanding (NLU) model trained for chatbots had a 95% accuracy. The webapp provides a hassle-free virtual recruiting experience for candidates and interviewers.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127080804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Self cascoded body biasing technique for ultra-low-power sub-threshold ring oscillator","authors":"K. Reddy, P. Rao","doi":"10.1109/ICITIIT54346.2022.9744168","DOIUrl":"https://doi.org/10.1109/ICITIIT54346.2022.9744168","url":null,"abstract":"The paper presents a low-power sub-threshold ring oscillator for self-powered IoT devices.Self cascoded body biasing technique is applied to each inverter in ring oscillator to enable low voltage operation. As a result, higher body biasing magnitudes are achieved compared to the conventional body biasing scheme. Furthermore, a significant reduction in subthreshold-leakage current accordingly reduces the power consumption. A three-stage ring oscillator circuit is designed for the desired oscillating frequency of 2.65 MHz. The proposed design has been implemented in standard CMOS 180 nm technology. Post-layout simulation results describe the proposed design takes low power consumption of 58.9 nW at the minimum supply voltage of 270 mV.","PeriodicalId":184353,"journal":{"name":"2022 International Conference on Innovative Trends in Information Technology (ICITIIT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126884293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}