vibhakar mansotra - Academia.edu (original) (raw)

Papers by vibhakar mansotra

Social Science Research Network, 2022

Asian Pacific journal of health sciences, Jul 16, 2021

Early prediction of diabetes is very important as diabetes can turn out to be life threatening fo... more Early prediction of diabetes is very important as diabetes can turn out to be life threatening for the patients in the later stages. In this paper, a hybrid framework for the prediction of type-2 diabetes is developed. In the first step, imbalance dataset is balanced using Synthetic Minority Over-sampling Technique. Then, clustering is applied using k-means clustering technique and all the incorrectly clustered entries and outliers are removed. Principal component analysis is then used for dimensionality reduction of the dataset. In the final step, classification is done using logistic regression (LR), naïve Bayes, support vector machine, and k-nearest neighbors classification techniques. Experimental analysis shows that 98.96% of accuracy is achieved by the proposed hybrid model using LR. The results are validated using 10-fold cross-validation.

Smart innovation, systems and technologies, Dec 4, 2019

The healthcare sector generates enormous data related to electronic medical records containing de... more The healthcare sector generates enormous data related to electronic medical records containing detailed reports, test, and medications. Research in the field of health care is being carried out to utilize the available healthcare data effectively using data mining. Every year, heart disease causes millions of deaths around the world. This research paper intends to analyze a few important parameters and utilize data mining classification techniques to predict the presence of heart disease. Data mining techniques are very useful in identifying the hidden patterns and information in the dataset. Decision Tree, Naive Bayes, Support Vector Machines, and Artificial Neural Networks classifiers are used for the prediction in Weka and SPSS Modeler tools and comparison of results is done on the basis of sensitivity, specificity, precision, and accuracy. Naive Bayes classifier achieved the highest accuracy of 85.39% in the Weka tool, and in the SPSS Modeler tool, SVM classifier achieved the highest accuracy at 85.87%.

Journal of Materials Science, Dec 1, 1991

Results of EDAX, XRD, IR, TG, DSC and SEM carried out on crystalline materials obtained by diffus... more Results of EDAX, XRD, IR, TG, DSC and SEM carried out on crystalline materials obtained by diffusion of praseodymium ions through silica gel impregnated with tartaric acid are reported. The crystallized material assumed spherulitic morphology which was established to be Pr2(C4H40a)35H20. EDAX confirmed the presence of praseodymium. X-ray diffraction data giving 20, intensity and d-values is also reported for the first time. Infrared spectrum in the range of 500-4000 cm-1 and the description of peaks recorded for the material are given. Results of thermal analysis (TG and DSC) indicated that the material is thermally unstable; the decomposition only occurs at 40-560~ after which it reduces to Pr203. SEM results suggest spherulitic growth arising from diverging crystal fibres which originate from multiple nuclei dispersed within a centrally-located spherical region.

ABSTRACT Education is one of the most debatable topics in all over the world and so it should be.... more ABSTRACT Education is one of the most debatable topics in all over the world and so it should be. With limited time and limited resources the nation's future and its people depend on the efficiency of schools, colleges and universities. The world is undergoing a revolution in ICT that has tremendous implications for the current and future social and economic situation of all countries of the world. The application and use of ICTs, have tremendous potential for improvements in every sector including education. J&K state in India have a literacy rate much below the national average of 64.8%. People residing in hilly and rural areas of J & K state are not benefited especially in the field of education. A growing number of teachers are now beginning to realise the potential of ICT and all schools and teachers should be aware of what can now be achieved. In this context the authors made an attempt to study the existing scenario of education sector of the state particularly the use of technological tools in teaching learning process. For this purpose, a questionnaire was designed for getting feedback from the students with an objective to supplement the information already collected by having a visit to each school. The data so collected was analysed separately for government schools as well for public and private schools. The analysis carried out shows certain drastic differences in these different categories of schools.

ABSTRACT ICT has a large potential to be useful in health care. While hospitals are now often equ... more ABSTRACT ICT has a large potential to be useful in health care. While hospitals are now often equipped with advanced tools using digitized analysis and embedded technology for operations etc., IT based administrative tools used to coordinate activities and communicate knowledge in the area of health care have not yet been generalized. The effect of these IT/ICT tools on the life of people world over has been mostly witnessed by the urban populace. The rural population almost world over has been the least beneficiary of such technological developments with the result that the digital divide between the rural and the urban still remains an area of concern. It is in this context that an attempt has been made by the authors to assess the penetration of Information and Communication Technologies in Present Health Care System in the State of Jammu and Kashmir in India. The impact of these technologies in health care system of the state has been studied in terms of various facilities existing in various hospitals established at the village, block, district and provincial level. The authors have tried to make an extensive study of various infrastructural facilities in these hospitals along with the use of IT/ICT tools to make the best use of these facilities. The study of the existing health care system has been carried from the govt, published available literature as well as by seeking public opinion through questionnaire and personal interviews. The data so obtained from the literature and through the questionnaires has been analyzed. Based on the observations made through the data analysis and by making a thorough investigations of the similar infrastructural facilities in the neighboring states, the authors have proposed an IT/ICT supported Health Care Model for implementation in the state of Jammu and Kashmir with an objective to carry out the benefits of the facilities existing in big hospitals to the village level hospitals as well. The proposed components/activities have to - be implemented in phased manner based on the present availability of infrastructure in the state, the geographical conditions of the state and the budget involved in implementing the model.

Journal of Materials Science, Jul 1, 1991

ABSTRACT The growth of praseodymium tartrate crystals in the system Pr(NO3)3-Na2 SiO3-C4H6O6, usi... more ABSTRACT The growth of praseodymium tartrate crystals in the system Pr(NO3)3-Na2 SiO3-C4H6O6, using a single-tube-single-gel technique is described. The growth conditions are delineated and a spherulitic morphology is reported. The spikes attached to the spherulites are single crystals of praseodymium tartrate. The mechanisms of crystallization for various types of spherulites are described. The information presented contributes to the understanding of spherulitic growth in general, and that of praseodymium tartrate in particular.

International Journal for Research in Applied Science and Engineering Technology, Aug 31, 2023

Digital images are widely used in various domains, including social media, military, and healthca... more Digital images are widely used in various domains, including social media, military, and healthcare. However, the security of digital images is threatened by cyber-attacks and privacy concerns. Cryptography plays a crucial role in ensuring the privacy and integrity of data, including digital images. Encryption methods are employed to protect digital images from unauthorized access. Among these methods, elliptic curve cryptography (ECC) is particularly effective, offering robust security with shorter key lengths. This research paper analysis ECC-based encryption methods for digital image encryption, considering parameters that impact their performance.

Evolving Systems, May 22, 2021

Coronary artery disease (CAD) is the most prominent disease that is responsible for increasing mo... more Coronary artery disease (CAD) is the most prominent disease that is responsible for increasing mortality and morbidity rate from past few decades. Early and accurate detection of CAD (a type of cardiovascular diseases) is among the most pressing needs of society. In this research work, experiments have been carried out with Cleveland dataset in four phases such as (i) single classifiers, (ii) boosted stacking nested ensemble, (iii) boosted voting nested ensemble, and (iv) boosted stacked voting nested ensemble. A generalized framework NestEn_SmVn has been proposed for designed nested ensemble models (phases ii to iv above). The proposed framework (NestEn_SmVn) using boosted stacked voting nested ensemble learning techniques having model (ID EID3-GID6) designed with adaptive boosting and Bayesian network as base-classifiers along with SMO and LMT as meta learners that achieved an highest accuracy of 98.68% with F-measure and ROC values of 98.70 and 99.00% respectively. The best proposed model (ID EID3-GID6) from nested ensemble (phase iv) using proposed framework (NestEn_SmVn) has outperformed all other models from phases (i-iv) and all previous works. Our proposed framework can support the clinical decision system and is able to replace previous CAD diagnostic techniques.

Advances in intelligent systems and computing, 2018

The series "Advances in Intelligent Systems and Computing" contains publications on theory, appli... more The series "Advances in Intelligent Systems and Computing" contains publications on theory, applications, and design methods of Intelligent Systems and Intelligent Computing. Virtually all disciplines such as engineering, natural sciences, computer and information science, ICT, economics, business, e-commerce, environment, healthcare, life science are covered. The list of topics spans all the areas of modern intelligent systems and computing. The publications within "Advances in Intelligent Systems and Computing" are primarily textbooks and proceedings of important conferences, symposia and congresses. They cover significant recent developments in the field, both of a foundational and applicable character. An important characteristic feature of the series is the short publication time and worldwide distribution. This permits a rapid and broad dissemination of research results.

International Conference on Computing for Sustainable Global Development, Mar 16, 2016

This paper throws light on issues pertinent to use of public healthcare data. It provides how the... more This paper throws light on issues pertinent to use of public healthcare data. It provides how these data and data mining can be used for decision-making at different levels of the health sector in India, and to spotlights impediments to improve data utilization. This study is among few attempts to examine data use issues in India's health sector. Methodologically, this study is designed to establish application of data mining in public healthcare data. It is mainly conceptual in nature and an attempt to identify associations between data use and data mining techniques for decision making at all the levels of public healthcare system in India. The proposed model also shows that analytical skills are necessary to improve data use in the health sector. But mere skills are not sufficient in public healthcare management. So, linking models with decisions would create strong basis for data use. To implement generated models are perhaps the most effective intervention that improves usability of data. For promoting data mining analysis and continuous evaluation of models on agreed set of indicators of success on which their performance are assessed, is also highly associated with perfect use of data.

Springer eBooks, Oct 26, 2021

With the internet growing at an exponential rate the web is increasingly hosting web pages in dif... more With the internet growing at an exponential rate the web is increasingly hosting web pages in different languages. It is essential for the search engines to be able to search information stored in a specific language. The native users also tend to look for any information on web nowadays. This leads to the need of effective search engines to fulfill native user's needs and provide them information in their native languages. The major population of India use Hindi as a first language. The Indian constitution identifies 22 languages, of which six languages (Hindi, Telugu, Tamil, Bengali, Marathi and Gujarati) are spoken by at least 50 million people within the boundaries of the country-there are a large number of them living outside the country. The Hindi language web information retrieval is not in a satisfactory condition. The presence of Hindi on the World Wide Web is still limited and tentative because of attitudinal and technical factors. Besides the other technical setbacks the Hindi language search engines face the problem of morphology, phonetics, word sense disambiguation etc. The performance of search engines is affected by these problems. This paper covers the comprehensive analysis and also the comparison of the affect of language structure related factors (morphology, phonetics, WSD, synonyms,) on the performance of search engines supporting Hindi language.

International journal of computer sciences and engineering, Nov 30, 2017

Computers in Human Behavior, Mar 1, 2022

Abstract Social Networking Sites have significant potential to reveal valuable explicit as well a... more Abstract Social Networking Sites have significant potential to reveal valuable explicit as well as implicit statistics and patterns when deep learning is applied to their raw and unstructured data. Tweets posted by the users on their timeline not only reflect their mindset, their likes and dislikes but could also be used to unveil significant amount of information about many psychological aspects and behavior that may be hard to study directly. This paper aims to predict the personality of the 100 real-time Twitter users conforming to personality traits in the BIG 5 model by extracting features from their tweets using ensemble of CNN (Convolutional Neural Network) and BiLSTM (Bidirectional Long Short Memory). The finding of our experiment shows that our model performs slightly better than previous baselines methods achieving an accuracy 75.134% on testing data. We have further hypothesized that unrestricted data available on Twitter may contain features that can be used to predict the personality of its user. It was concluded that personality of Twitter users in the real world is reflected in their online behaviour, reinforcing the premise that the nature of online interactions does not significantly differ from that of real-world interactions. Overall, the study provides a deep insight into the impact of social media data in providing predictive indicators of user behavior.

The new interesting subject that offered by institution to interact more student is "DATA MINING"... more The new interesting subject that offered by institution to interact more student is "DATA MINING". In this paper we will discuss about the problem that are faced by students how to choose the best institutes for learning. One of the biggest challenges that student's faced tough time selecting the right engineering college that opens doors to exciting careers. Students would like to know, which college provides better quality education and its alumni are successful in the real world. Data Mining helps to students to take decision more accurately. Data mining is better tool to predict the general information of the college, courses offered and no. of seats, selection criteria, infrastructure, faculty performance, industry interface, placement, and potential to network, exchange programs and global exposure and national and international alumni chapter. In this paper we will discuss about data mining, their different phase's, advantages and also we classify data using weak data mining tool which helps to understand the data. In this paper we will use decision tree algorithm to predict the status of colleges, faculty performance, student feedback, student performance, infrastructure, placements and emotion states of students.

Smart innovation, systems and technologies, Dec 4, 2019

Stemming is a process that maps morphologically similar words to a common root/stem word by remov... more Stemming is a process that maps morphologically similar words to a common root/stem word by removing their prefixes or suffixes. In Natural Language Processing, stemming plays an important role in Information Retrieval, Machine Translation, Text Summarization, etc. Stemming reduces inflected word to its root form without doing any morphological analysis of the word and sometimes it is not necessary that stemming always provides us meaningful/dictionary root words as a lemmatizer always provides meaningful dictionary words. For example, in the Hindi word Open image in new window , (pakshion) is formed as ( Open image in new window (paksh) + Open image in new window ) having Open image in new window as suffix; if we remove this suffix, then it becomes Open image in new window (paksh) and Open image in new window (paksh) which is not a meaningful Hindi dictionary word. In the context of information retrieval, the stemmer reduces varied (morphologically inflected) words to a common form, thereby reducing the index size of the inverted file and increasing the recall. In this paper, researchers have attempted to develop a rule-based Hindi Stemmer Suffix Stripping Approach for Hindi Information Retrieval. A python-based web interface has been designed to implement the proposed algorithm. Also, the developed stemmer is being tested for accuracy and efficiency in two scenarios, first as an independent stemmer and second as a supporting module to indexing in Hindi Information Retrieval. The proposed stemmer has shown an accuracy of 71% as an individual stemmer and also reduced the index size by 26% (approx.) when used in indexing.

International journal of engineering trends and technology, May 25, 2022

Advances in intelligent systems and computing, Oct 2, 2020

Early prediction of heart disease is very important as diseases related to heart can turn out to ... more Early prediction of heart disease is very important as diseases related to heart can turn out to be life-threatening. In this paper, a hybrid framework using unsupervised clustering technique with dimensionality reduction technique and regression technique is developed to predict the likelihood of presence of heart disease. Experimental results showed that our framework using k-means clustering, Principal Component Analysis (PCA) and Logistic Regression (LR) technique performed better, and 98.82% of accuracy has been achieved by the framework. The results are validated using tenfold cross validation.

Social Science Research Network, 2022

Asian Pacific journal of health sciences, Jul 16, 2021

Early prediction of diabetes is very important as diabetes can turn out to be life threatening fo... more Early prediction of diabetes is very important as diabetes can turn out to be life threatening for the patients in the later stages. In this paper, a hybrid framework for the prediction of type-2 diabetes is developed. In the first step, imbalance dataset is balanced using Synthetic Minority Over-sampling Technique. Then, clustering is applied using k-means clustering technique and all the incorrectly clustered entries and outliers are removed. Principal component analysis is then used for dimensionality reduction of the dataset. In the final step, classification is done using logistic regression (LR), naïve Bayes, support vector machine, and k-nearest neighbors classification techniques. Experimental analysis shows that 98.96% of accuracy is achieved by the proposed hybrid model using LR. The results are validated using 10-fold cross-validation.

Smart innovation, systems and technologies, Dec 4, 2019

The healthcare sector generates enormous data related to electronic medical records containing de... more The healthcare sector generates enormous data related to electronic medical records containing detailed reports, test, and medications. Research in the field of health care is being carried out to utilize the available healthcare data effectively using data mining. Every year, heart disease causes millions of deaths around the world. This research paper intends to analyze a few important parameters and utilize data mining classification techniques to predict the presence of heart disease. Data mining techniques are very useful in identifying the hidden patterns and information in the dataset. Decision Tree, Naive Bayes, Support Vector Machines, and Artificial Neural Networks classifiers are used for the prediction in Weka and SPSS Modeler tools and comparison of results is done on the basis of sensitivity, specificity, precision, and accuracy. Naive Bayes classifier achieved the highest accuracy of 85.39% in the Weka tool, and in the SPSS Modeler tool, SVM classifier achieved the highest accuracy at 85.87%.

Journal of Materials Science, Dec 1, 1991

Results of EDAX, XRD, IR, TG, DSC and SEM carried out on crystalline materials obtained by diffus... more Results of EDAX, XRD, IR, TG, DSC and SEM carried out on crystalline materials obtained by diffusion of praseodymium ions through silica gel impregnated with tartaric acid are reported. The crystallized material assumed spherulitic morphology which was established to be Pr2(C4H40a)35H20. EDAX confirmed the presence of praseodymium. X-ray diffraction data giving 20, intensity and d-values is also reported for the first time. Infrared spectrum in the range of 500-4000 cm-1 and the description of peaks recorded for the material are given. Results of thermal analysis (TG and DSC) indicated that the material is thermally unstable; the decomposition only occurs at 40-560~ after which it reduces to Pr203. SEM results suggest spherulitic growth arising from diverging crystal fibres which originate from multiple nuclei dispersed within a centrally-located spherical region.

ABSTRACT Education is one of the most debatable topics in all over the world and so it should be.... more ABSTRACT Education is one of the most debatable topics in all over the world and so it should be. With limited time and limited resources the nation's future and its people depend on the efficiency of schools, colleges and universities. The world is undergoing a revolution in ICT that has tremendous implications for the current and future social and economic situation of all countries of the world. The application and use of ICTs, have tremendous potential for improvements in every sector including education. J&K state in India have a literacy rate much below the national average of 64.8%. People residing in hilly and rural areas of J & K state are not benefited especially in the field of education. A growing number of teachers are now beginning to realise the potential of ICT and all schools and teachers should be aware of what can now be achieved. In this context the authors made an attempt to study the existing scenario of education sector of the state particularly the use of technological tools in teaching learning process. For this purpose, a questionnaire was designed for getting feedback from the students with an objective to supplement the information already collected by having a visit to each school. The data so collected was analysed separately for government schools as well for public and private schools. The analysis carried out shows certain drastic differences in these different categories of schools.

ABSTRACT ICT has a large potential to be useful in health care. While hospitals are now often equ... more ABSTRACT ICT has a large potential to be useful in health care. While hospitals are now often equipped with advanced tools using digitized analysis and embedded technology for operations etc., IT based administrative tools used to coordinate activities and communicate knowledge in the area of health care have not yet been generalized. The effect of these IT/ICT tools on the life of people world over has been mostly witnessed by the urban populace. The rural population almost world over has been the least beneficiary of such technological developments with the result that the digital divide between the rural and the urban still remains an area of concern. It is in this context that an attempt has been made by the authors to assess the penetration of Information and Communication Technologies in Present Health Care System in the State of Jammu and Kashmir in India. The impact of these technologies in health care system of the state has been studied in terms of various facilities existing in various hospitals established at the village, block, district and provincial level. The authors have tried to make an extensive study of various infrastructural facilities in these hospitals along with the use of IT/ICT tools to make the best use of these facilities. The study of the existing health care system has been carried from the govt, published available literature as well as by seeking public opinion through questionnaire and personal interviews. The data so obtained from the literature and through the questionnaires has been analyzed. Based on the observations made through the data analysis and by making a thorough investigations of the similar infrastructural facilities in the neighboring states, the authors have proposed an IT/ICT supported Health Care Model for implementation in the state of Jammu and Kashmir with an objective to carry out the benefits of the facilities existing in big hospitals to the village level hospitals as well. The proposed components/activities have to - be implemented in phased manner based on the present availability of infrastructure in the state, the geographical conditions of the state and the budget involved in implementing the model.

Journal of Materials Science, Jul 1, 1991

ABSTRACT The growth of praseodymium tartrate crystals in the system Pr(NO3)3-Na2 SiO3-C4H6O6, usi... more ABSTRACT The growth of praseodymium tartrate crystals in the system Pr(NO3)3-Na2 SiO3-C4H6O6, using a single-tube-single-gel technique is described. The growth conditions are delineated and a spherulitic morphology is reported. The spikes attached to the spherulites are single crystals of praseodymium tartrate. The mechanisms of crystallization for various types of spherulites are described. The information presented contributes to the understanding of spherulitic growth in general, and that of praseodymium tartrate in particular.

International Journal for Research in Applied Science and Engineering Technology, Aug 31, 2023

Digital images are widely used in various domains, including social media, military, and healthca... more Digital images are widely used in various domains, including social media, military, and healthcare. However, the security of digital images is threatened by cyber-attacks and privacy concerns. Cryptography plays a crucial role in ensuring the privacy and integrity of data, including digital images. Encryption methods are employed to protect digital images from unauthorized access. Among these methods, elliptic curve cryptography (ECC) is particularly effective, offering robust security with shorter key lengths. This research paper analysis ECC-based encryption methods for digital image encryption, considering parameters that impact their performance.

Evolving Systems, May 22, 2021

Coronary artery disease (CAD) is the most prominent disease that is responsible for increasing mo... more Coronary artery disease (CAD) is the most prominent disease that is responsible for increasing mortality and morbidity rate from past few decades. Early and accurate detection of CAD (a type of cardiovascular diseases) is among the most pressing needs of society. In this research work, experiments have been carried out with Cleveland dataset in four phases such as (i) single classifiers, (ii) boosted stacking nested ensemble, (iii) boosted voting nested ensemble, and (iv) boosted stacked voting nested ensemble. A generalized framework NestEn_SmVn has been proposed for designed nested ensemble models (phases ii to iv above). The proposed framework (NestEn_SmVn) using boosted stacked voting nested ensemble learning techniques having model (ID EID3-GID6) designed with adaptive boosting and Bayesian network as base-classifiers along with SMO and LMT as meta learners that achieved an highest accuracy of 98.68% with F-measure and ROC values of 98.70 and 99.00% respectively. The best proposed model (ID EID3-GID6) from nested ensemble (phase iv) using proposed framework (NestEn_SmVn) has outperformed all other models from phases (i-iv) and all previous works. Our proposed framework can support the clinical decision system and is able to replace previous CAD diagnostic techniques.

Advances in intelligent systems and computing, 2018

The series "Advances in Intelligent Systems and Computing" contains publications on theory, appli... more The series "Advances in Intelligent Systems and Computing" contains publications on theory, applications, and design methods of Intelligent Systems and Intelligent Computing. Virtually all disciplines such as engineering, natural sciences, computer and information science, ICT, economics, business, e-commerce, environment, healthcare, life science are covered. The list of topics spans all the areas of modern intelligent systems and computing. The publications within "Advances in Intelligent Systems and Computing" are primarily textbooks and proceedings of important conferences, symposia and congresses. They cover significant recent developments in the field, both of a foundational and applicable character. An important characteristic feature of the series is the short publication time and worldwide distribution. This permits a rapid and broad dissemination of research results.

International Conference on Computing for Sustainable Global Development, Mar 16, 2016

This paper throws light on issues pertinent to use of public healthcare data. It provides how the... more This paper throws light on issues pertinent to use of public healthcare data. It provides how these data and data mining can be used for decision-making at different levels of the health sector in India, and to spotlights impediments to improve data utilization. This study is among few attempts to examine data use issues in India's health sector. Methodologically, this study is designed to establish application of data mining in public healthcare data. It is mainly conceptual in nature and an attempt to identify associations between data use and data mining techniques for decision making at all the levels of public healthcare system in India. The proposed model also shows that analytical skills are necessary to improve data use in the health sector. But mere skills are not sufficient in public healthcare management. So, linking models with decisions would create strong basis for data use. To implement generated models are perhaps the most effective intervention that improves usability of data. For promoting data mining analysis and continuous evaluation of models on agreed set of indicators of success on which their performance are assessed, is also highly associated with perfect use of data.

Springer eBooks, Oct 26, 2021

With the internet growing at an exponential rate the web is increasingly hosting web pages in dif... more With the internet growing at an exponential rate the web is increasingly hosting web pages in different languages. It is essential for the search engines to be able to search information stored in a specific language. The native users also tend to look for any information on web nowadays. This leads to the need of effective search engines to fulfill native user's needs and provide them information in their native languages. The major population of India use Hindi as a first language. The Indian constitution identifies 22 languages, of which six languages (Hindi, Telugu, Tamil, Bengali, Marathi and Gujarati) are spoken by at least 50 million people within the boundaries of the country-there are a large number of them living outside the country. The Hindi language web information retrieval is not in a satisfactory condition. The presence of Hindi on the World Wide Web is still limited and tentative because of attitudinal and technical factors. Besides the other technical setbacks the Hindi language search engines face the problem of morphology, phonetics, word sense disambiguation etc. The performance of search engines is affected by these problems. This paper covers the comprehensive analysis and also the comparison of the affect of language structure related factors (morphology, phonetics, WSD, synonyms,) on the performance of search engines supporting Hindi language.

International journal of computer sciences and engineering, Nov 30, 2017

Computers in Human Behavior, Mar 1, 2022

Abstract Social Networking Sites have significant potential to reveal valuable explicit as well a... more Abstract Social Networking Sites have significant potential to reveal valuable explicit as well as implicit statistics and patterns when deep learning is applied to their raw and unstructured data. Tweets posted by the users on their timeline not only reflect their mindset, their likes and dislikes but could also be used to unveil significant amount of information about many psychological aspects and behavior that may be hard to study directly. This paper aims to predict the personality of the 100 real-time Twitter users conforming to personality traits in the BIG 5 model by extracting features from their tweets using ensemble of CNN (Convolutional Neural Network) and BiLSTM (Bidirectional Long Short Memory). The finding of our experiment shows that our model performs slightly better than previous baselines methods achieving an accuracy 75.134% on testing data. We have further hypothesized that unrestricted data available on Twitter may contain features that can be used to predict the personality of its user. It was concluded that personality of Twitter users in the real world is reflected in their online behaviour, reinforcing the premise that the nature of online interactions does not significantly differ from that of real-world interactions. Overall, the study provides a deep insight into the impact of social media data in providing predictive indicators of user behavior.

The new interesting subject that offered by institution to interact more student is "DATA MINING"... more The new interesting subject that offered by institution to interact more student is "DATA MINING". In this paper we will discuss about the problem that are faced by students how to choose the best institutes for learning. One of the biggest challenges that student's faced tough time selecting the right engineering college that opens doors to exciting careers. Students would like to know, which college provides better quality education and its alumni are successful in the real world. Data Mining helps to students to take decision more accurately. Data mining is better tool to predict the general information of the college, courses offered and no. of seats, selection criteria, infrastructure, faculty performance, industry interface, placement, and potential to network, exchange programs and global exposure and national and international alumni chapter. In this paper we will discuss about data mining, their different phase's, advantages and also we classify data using weak data mining tool which helps to understand the data. In this paper we will use decision tree algorithm to predict the status of colleges, faculty performance, student feedback, student performance, infrastructure, placements and emotion states of students.

Smart innovation, systems and technologies, Dec 4, 2019

Stemming is a process that maps morphologically similar words to a common root/stem word by remov... more Stemming is a process that maps morphologically similar words to a common root/stem word by removing their prefixes or suffixes. In Natural Language Processing, stemming plays an important role in Information Retrieval, Machine Translation, Text Summarization, etc. Stemming reduces inflected word to its root form without doing any morphological analysis of the word and sometimes it is not necessary that stemming always provides us meaningful/dictionary root words as a lemmatizer always provides meaningful dictionary words. For example, in the Hindi word Open image in new window , (pakshion) is formed as ( Open image in new window (paksh) + Open image in new window ) having Open image in new window as suffix; if we remove this suffix, then it becomes Open image in new window (paksh) and Open image in new window (paksh) which is not a meaningful Hindi dictionary word. In the context of information retrieval, the stemmer reduces varied (morphologically inflected) words to a common form, thereby reducing the index size of the inverted file and increasing the recall. In this paper, researchers have attempted to develop a rule-based Hindi Stemmer Suffix Stripping Approach for Hindi Information Retrieval. A python-based web interface has been designed to implement the proposed algorithm. Also, the developed stemmer is being tested for accuracy and efficiency in two scenarios, first as an independent stemmer and second as a supporting module to indexing in Hindi Information Retrieval. The proposed stemmer has shown an accuracy of 71% as an individual stemmer and also reduced the index size by 26% (approx.) when used in indexing.

International journal of engineering trends and technology, May 25, 2022

Advances in intelligent systems and computing, Oct 2, 2020

Early prediction of heart disease is very important as diseases related to heart can turn out to ... more Early prediction of heart disease is very important as diseases related to heart can turn out to be life-threatening. In this paper, a hybrid framework using unsupervised clustering technique with dimensionality reduction technique and regression technique is developed to predict the likelihood of presence of heart disease. Experimental results showed that our framework using k-means clustering, Principal Component Analysis (PCA) and Logistic Regression (LR) technique performed better, and 98.82% of accuracy has been achieved by the framework. The results are validated using tenfold cross validation.