Bankim Patel

Big Data Analytics: Challenges And Applications For Text, Audio, Video, And Social Media Data

Zenodo (CERN European Organization for Nuclear Research), Feb 29, 2016

All types of machine automated systems are generating large amount of data in different forms lik... more All types of machine automated systems are generating large amount of data in different forms like statistical, text, audio, video, sensor, and bio-metric data that emerges the term Big Data. In this paper we are discussing issues, challenges, and application of these types of Big Data with the consideration of big data dimensions. Here we are discussing social media data analytics, content based analytics, text data analytics, audio, and video data analytics their issues and expected application areas. It will motivate researchers to address these issues of storage, management, and retrieval of data known as Big Data. As well as the usages of Big Data analytics in India is also highlighted.

Download

Stemmatizer—Stemmer-based Lemmatizer for Gujarati Text

Advances in Intelligent Systems and Computing, 2018

Stemming is an important process in Information Retrieval (IR). Stem returned by stemmer need not... more Stemming is an important process in Information Retrieval (IR). Stem returned by stemmer need not be always a valid dictionary word. While a lemma returned by lemmatizer is always a valid dictionary word, which is a requirement of many IR systems. Indian languages are poor in resources. Specifically, the Gujarati language is having a stemmer but lacking a lemmatizer. In this paper, the authors have proposed ‘The Stemmatizer’—stemmer-based lemmatizer for Gujarati language using a hybrid approach. It has the ability to learn new words. The proposed solution is tested on 2197 words and results have been found very much satisfactory.

Big Data Analytics: Challenges And Applications For Text, Audio, Video, And Social Media Data

International Journal on Soft Computing, Artificial Intelligence and Applications, 2016

All types of machine automated systems are generating large amount of data in different forms lik... more All types of machine automated systems are generating large amount of data in different forms like statistical, text, audio, video, sensor, and bio-metric data that emerges the term Big Data. In this paper we are discussing issues, challenges, and application of these types of Big Data with the consideration of big data dimensions. Here we are discussing social media data analytics, content based analytics, text data analytics, audio, and video data analytics their issues and expected application areas. It will motivate researchers to address these issues of storage, management, and retrieval of data known as Big Data. As well as the usages of Big Data analytics in India is also highlighted.

Download

Applying Supervised Learning Techniques for Constructing Predictive Models

Indian Journal of Science and Technology, 2015

Background/Objectives: The website is composed of permanent and temporary pages. Deriving a predi... more Background/Objectives: The website is composed of permanent and temporary pages. Deriving a prediction model which considers the dynamic pages generated on the website requires to consider new aspects. Methods/Statistical Analysis: We adopt supervised learning models as they give better prediction results for new input data. After reading the log files and applying preprocessing, we build the user navigation patterns and then apply the prediction of pages. The main parameter on which we have modified is the time stamp. In earlier approaches the time stamp was divided into day, month and year and based on the timestamp granule selected the prediction model was formed. In our work we consider the same granule with introduction to new timestamp namely event. Findings: Markov model are very good in predicting the pages for n length, but the model doesn’t focus on temporal aspect for prediction. Temporal n-gram model covers the temporal aspect of prediction by forming the granules of time. This model gives good accuracy in predicting pages that are permanent for any given website, but doesn’t tend to be good for pages that are temporary in nature. Our model focuses on temporal aspect for both types of pages by creating an event based temporal n-gram model. Event means creating a special named interval for which the pages are made available on the website. This means that after the interval specified in the event the page will be no more visible on the website. The pages are predicted based on the nature of pages, we form broadly two types of nature of pages 1. Regular for permanent pages and 2. Event for temporary pages. By introducing this temporal aspect the prediction algorithm considers the specified interval only for the event specific pages, after the interval is over the pages are not considered for prediction. Application/Improvements: Specifying events help to derive better accuracy in prediction when we consider permanent and temporary pages, as we predict the pages based on the condition whether they are regular or event based pages.

Comparison of UWAD Tool with Other Tools Used for Preprocessing

The purpose of Preprocessing phase is to produce accurate data with speed and accuracy. Intereste... more The purpose of Preprocessing phase is to produce accurate data with speed and accuracy. Interested patterns can be discovered based on the quality of data generated after the preprocessing phase. Designing this phase taken maximum effort in the entire process of Web Usage Mining (WUM), as it focuses on reducing the quantity of data but not compromising with the quality of data. The paper focuses the implementation concerns of preprocessing phase using tool Log parser lizard and focuses on the problems faced in using the tool. It also shows the usefulness of University Website Access Domain (UWAD) tool.

Download

Preprocessing phase for University Website Access Domain

ABSTRACT

Dna Compression Using Hash Based Data Structure

ABSTRACT

Big Data Analysis: Recommendation System with Hadoop Framework

2015 IEEE International Conference on Computational Intelligence & Communication Technology, 2015

Recommendation system provides the facility to understand a person's taste and find new, desi... more Recommendation system provides the facility to understand a person's taste and find new, desirable content for them automatically based on the pattern between their likes and rating of different items. In this paper, we have proposed a recommendation system for the large amount of data available on the web in the form of ratings, reviews, opinions, complaints, remarks, feedback, and comments about any item (product, event, individual and services) using Hadoop Framework. We have implemented Mahout Interfaces for analyzing the data provided by review and rating site for movies.

Fuzzy K-Means Clustering in Measuring Course Outcome Attainment System for Higher Educational Institutes

Advances in intelligent systems and computing, Oct 2, 2020

Higher education is meant to produce knowledge in society. With this objective, the apex bodies o... more Higher education is meant to produce knowledge in society. With this objective, the apex bodies of higher education frame policies to achieve it. One such policy is introducing outcome-based education (OBE) system in education institutes offers higher studies. As outcome-based assessments are integral part of it, the mechanism to measure the outcome’s attainment becomes crucial. In this technological era, the need for a system that automatically measures course outcome’s (CO) attainment is obvious. But challenges like missing data and one-to-many mapping between question and COs exist. The purpose of this paper is to model a system that can be used by academic bodies to measure CO attainment automatically given the abovementioned constraints.

Feature Extraction and Opinion Mining of Gujarati Language text

International journal of research and scientific innovation, 2022

The field of opinion mining has gained much popularity in last few years. Many new techniques and... more The field of opinion mining has gained much popularity in last few years. Many new techniques and methods are being developed in different languages like English, Hindi etc. However, it is observed that there is no significant progress in the field of Opinion Mining for languages like Gujarati. The presented work uses a deep learning approach for the Opinion Mining of Gujarati language text. The paper also discusses feature extraction which is one of the most important steps in machine learning or deep learning method.

Download

Biological Data Integration Using Virtual Database

Biological data integration is considered to be one the most important and challenging tasks in b... more Biological data integration is considered to be one the most important and challenging tasks in bioinformatics. The scientific achievements greatly depend on the integrated view of largely diverse set of data. Biological data reside in hundreds of database and there is no single database providing an integrated view of data. It greatly invokes the need of data integration. Though they are different approaches for data integration like data warehouse, federation, webservices; each has its own pros and cons and challenges of implementation. In this research paper, we have proposed a framework using virtual database to integrate different biological data sources.

Best Practices for Adaptation of Data Mining Techniques in Education Sector

Best practices help to make the business processes smooth. As best practices are always recommend... more Best practices help to make the business processes smooth. As best practices are always recommended and not forced, the authors have recommended few best practices to be followed in Educational institutes so that the activities related to educational data mining becomes easy to implement. The best practices suggested are with the objective to gain and maintain data quality; as quality data leads to correct analysis.

Fuzzy K-Means Clustering in Measuring Course Outcome Attainment System for Higher Educational Institutes

Higher education is meant to produce knowledge in society. With this objective, the apex bodies o... more Higher education is meant to produce knowledge in society. With this objective, the apex bodies of higher education frame policies to achieve it. One such policy is introducing outcome-based education (OBE) system in education institutes offers higher studies. As outcome-based assessments are integral part of it, the mechanism to measure the outcome’s attainment becomes crucial. In this technological era, the need for a system that automatically measures course outcome’s (CO) attainment is obvious. But challenges like missing data and one-to-many mapping between question and COs exist. The purpose of this paper is to model a system that can be used by academic bodies to measure CO attainment automatically given the abovementioned constraints.

Stemming Techniques and Naïve Approach for Gujarati Stemmer

Ijca Proceedings on International Conference on Recent Trends in Information Technology and Computer Science 2012, Feb 2, 2013

This paper focuses on stemming techniques used by various researchers for English language. Furth... more This paper focuses on stemming techniques used by various researchers for English language. Further the review of different approaches used for Hindi and Bengali languages are discussed. The authors have proposed a model for Gujarati stemmer by incorporating traditional as well as naïve approaches.

Download

Chunker for Gujarati Language Using Hybrid Approach

Rising Threats in Expert Applications and Solutions, 2020

For free word order languages, chunking is quite challenging as they have relatively unrestricted... more For free word order languages, chunking is quite challenging as they have relatively unrestricted phrase structures. A robust chunker helps in other NLP applications. This paper presents a Hybrid chunker for Gujarati Language. Contextual information in the form of last two unicodes of the word and of part-of-speech (POS) is used as the key features in developing the chunker using Machine learning approach. Four different statistical techniques, namely, SVM, CRF, Naive Bayes, and HMM have been implemented to identify the most appropriate technique for Chunking the text in Gujarati language. Further, to improve performance, linguistic rules have been designed. Finally, achieved accuracy is 98.21% with precision, recall, and F1 score of 96.42%, 95.62 and 96.02, respectively.

Hkda-Iqpgs: A True Intelligent Question Paper Generator System to Find Patterns of Questions That Help Student Success in Modern E-Learning

There is a great boom in e-learning in the area of technology-enhanced Intelligent Tutoring Educa... more There is a great boom in e-learning in the area of technology-enhanced Intelligent Tutoring Educational Systems where excellent virtual instructors/teachers guide their learners/students. Progress has been made, addressing a variety of educational needs, ranging from supplements to existing “traditional” courses, to complete on-line courses, to complete on-line programs. Despite all this effort, hype, and even product development, most of the courseware material available for use at the educational level is still not judged to be as effective as a teacher lecturing and leading discussions with students. It is often necessary for a teacher to prepare a test over information for which students have been previously quizzed or to administer multiple versions of same test. When this situation occurs, teachers are required to spend extra time creating equivalent questions. The major difficulty with this problem lies in efficiently creating sets of equivalent questions. To solve this probl...

Download

PDLB: An Effective Prediction-Based Dynamic Load Balancing Algorithm for Clustered Heterogeneous Computational Environment

Advances in Intelligent Systems and Computing, 2018

Load balancing is one of the major requirements of distributed systems for the effective utilizat... more Load balancing is one of the major requirements of distributed systems for the effective utilization of resources. Existing dynamic load balancing algorithms take the corrective actions once the system becomes unbalanced. It could be more appropriate to design algorithm which can schedule incoming jobs in such way that system remains in balance state without increasing unnecessary system overhead. In this paper, prediction-based dynamic load balancing algorithm is designed which can balance load between clusters using predicted status of clusters. The designed algorithm is applied on priority scheduling algorithm. Our experimental result shows that the prediction-based load balancing algorithm improves the cluster utilization as compared to existing scheduling algorithm.

Feature Extraction and Opinion Mining of Gujarati Language text

International Journal of Research and Scientific Innovation

The field of opinion mining has gained much popularity in last few years. Many new techniques and... more The field of opinion mining has gained much popularity in last few years. Many new techniques and methods are being developed in different languages like English, Hindi etc. However, it is observed that there is no significant progress in the field of Opinion Mining for languages like Gujarati. The presented work uses a deep learning approach for the Opinion Mining of Gujarati language text. The paper also discusses feature extraction which is one of the most important steps in machine learning or deep learning method.

Download

Hybrid POS Tagger for Gujarati Text

Soft Computing and its Engineering Applications, 2021

Sentence Tokenization Using Statistical Unsupervised Machine Learning and Rule-Based Approach for Running Text in Gujarati Language

Advances in Intelligent Systems and Computing, 2018

Sentence tokenization is the foundational step in natural language processing to analyze the sent... more Sentence tokenization is the foundational step in natural language processing to analyze the sentence. Apart from others, main causes which make the sentence tokenization difficult are quotation marks and the multipurpose usage of punctuation marks especially dot “.”. In this paper, a framework has proposed for sentence tokenization for running text in Gujarati language using statistical unsupervised machine learning approach and rule-based approach.

Uploads

Papers by Bankim Patel

Log In