Remote sensing is widely used in the prediction of forest cover. Forest plays an important role in the balance of the ecosystem. It helps to maintain the balance between climate. We depend a lot on forests for wood, oxygen, and also for the control of soil erosion. Hence it is our duty to maintain the forest cover on earth. Remote sensing images provide us with lots of information regarding the different landforms and materials. It is also used to predict natural disasters like forest fires, floods, etc. The normalized difference vegetation index is a simple graphical indicator that is used to analyze remote sensing measurements,(eg. space platform) predicting whether the target is live green vegetation or not. However, we have found out that it cannot be used for accurate prediction of forest land cover. With the help of time series data on the Amazon forest, it has been observed that the NDVI index fails to determine some of the important changes in the landform. To rectify this problem, the deep learning model was used to give an accuracy of 100 percent. The deep learning model gives similar results as observed results, hence making it the best-preferred method for predicting forest cover. With the help of multispectral analysis of the data, the deep learning model gives the best results for the red band, and near-infrared bands.
{"title":"Forest Change Detection in the Amazon Rainforest","authors":"Tanisha Agrawal, Aarti Karandikar, Avinash Agrawal","doi":"10.47164/ijngc.v14i1.1047","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1047","url":null,"abstract":"Remote sensing is widely used in the prediction of forest cover. Forest plays an important role in the balance of the ecosystem. It helps to maintain the balance between climate. We depend a lot on forests for wood, oxygen, and also for the control of soil erosion. Hence it is our duty to maintain the forest cover on earth. Remote sensing images provide us with lots of information regarding the different landforms and materials. It is also used to predict natural disasters like forest fires, floods, etc. The normalized difference vegetation index is a simple graphical indicator that is used to analyze remote sensing measurements,(eg. space platform) predicting whether the target is live green vegetation or not. However, we have found out that it cannot be used for accurate prediction of forest land cover. With the help of time series data on the Amazon forest, it has been observed that the NDVI index fails to determine some of the important changes in the landform. To rectify this problem, the deep learning model was used to give an accuracy of 100 percent. The deep learning model gives similar results as observed results, hence making it the best-preferred method for predicting forest cover. With the help of multispectral analysis of the data, the deep learning model gives the best results for the red band, and near-infrared bands.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"37 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79272769","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}
Agriculture is a major sector for economic growth and development. The cultivation of fruit crops is a part of agriculture thus helping in the prosperity of our nation. In recent years, there has been a sudden hike in health problems and therefore, it has led to increasing demand for fruits and vegetables. Therefore, the use of innovative technologies is of significant importance for the fruit sector to give ripe and fresh fruits. Currently, Artificial Intelligence is a technology that is transforming every line of work. Particularly, Deep Learning (DL) has diverse applications due to its potential to learn mighty representations from images. A Convolutional Neural Network (CNN) is a noteworthy class of Deep Learning architecture that is built with the capability to bring out distinctive characteristics from image data. The utmost concern of many customers, vendors, and farmers is the quality of fruits and vegetables produced. Differentiating the fruits according to their ripening stages is the most crucialfactor in regulating the quality of fruits. This work used a high-quality dataset with 9997 images comprising 15 fruit classes. Moreover, based on the significant applications that Convolutional Neural Networks have had till now, it proposes an analysis of deep learning algorithms for fruit detection and three-stage maturity grading and achieves 90.24 percent accuracy. The results obtained will help in the development of fast and accurate detection of fruits and their quality
{"title":"Fruit Detection and Three-Stage Maturity Grading Using CNN","authors":"Harsh Mundhada, Sanskriti Sood, Saitejaswi Sanagavarapu, Rina Damdoo, Kanak Kalyani","doi":"10.47164/ijngc.v14i1.1099","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1099","url":null,"abstract":"Agriculture is a major sector for economic growth and development. The cultivation of fruit crops is a part of agriculture thus helping in the prosperity of our nation. In recent years, there has been a sudden hike in health problems and therefore, it has led to increasing demand for fruits and vegetables. Therefore, the use of innovative technologies is of significant importance for the fruit sector to give ripe and fresh fruits. Currently, Artificial Intelligence is a technology that is transforming every line of work. Particularly, Deep Learning (DL) has diverse applications due to its potential to learn mighty representations from images. A Convolutional Neural Network (CNN) is a noteworthy class of Deep Learning architecture that is built with the capability to bring out distinctive characteristics from image data. The utmost concern of many customers, vendors, and farmers is the quality of fruits and vegetables produced. Differentiating the fruits according to their ripening stages is the most crucialfactor in regulating the quality of fruits. This work used a high-quality dataset with 9997 images comprising 15 fruit classes. Moreover, based on the significant applications that Convolutional Neural Networks have had till now, it proposes an analysis of deep learning algorithms for fruit detection and three-stage maturity grading and achieves 90.24 percent accuracy. The results obtained will help in the development of fast and accurate detection of fruits and their quality","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"61 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74408355","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}
Pub Date : 2023-02-15DOI: 10.47164/ijngc.v14i1.1024
S. Rawat, Lakshita Werulkar, Sagarika Jaywant
Language Identification is among the crucial steps in any NLP based application. Text - based documents and webpages are rapidly increasing in the modern Internet. It is simple to locate documents written in different languages from all across the world that are available with just one click. Therefore, a language identifier is absolutely necessary in order to help the user interpret the content. Language identification has so far tended to be more concentrated on European languages and is still rather limited for Indian Traditional Languages. Many researchers have become more interested in the study of language identification for similar languages from popular languages. In this paper, Multinomial Na¨ıve Bayes Algorithm is used for detecting languages in Devanagari like Marathi, Sanskrit and Hindi, and three European languages French, Italian and English. An experiment done ondatasets of each language has produced satisfactorily accurate results after training and testing the model.
{"title":"Text-based Language Identifier using Multinomial Naïve Bayes Algorithm","authors":"S. Rawat, Lakshita Werulkar, Sagarika Jaywant","doi":"10.47164/ijngc.v14i1.1024","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1024","url":null,"abstract":"Language Identification is among the crucial steps in any NLP based application. Text - based documents and webpages are rapidly increasing in the modern Internet. It is simple to locate documents written in different languages from all across the world that are available with just one click. Therefore, a language identifier is absolutely necessary in order to help the user interpret the content. Language identification has so far tended to be more concentrated on European languages and is still rather limited for Indian Traditional Languages. Many researchers have become more interested in the study of language identification for similar languages from popular languages. In this paper, Multinomial Na¨ıve Bayes Algorithm is used for detecting languages in Devanagari like Marathi, Sanskrit and Hindi, and three European languages French, Italian and English. An experiment done ondatasets of each language has produced satisfactorily accurate results after training and testing the model.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"110 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76082976","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}
A crucial ability for every person is the capacity to ask pertinent questions. By automating the process of question formation, an automatic question generator is able to decrease the time and effort needed for manual question creation. Along with benefitting educational institutions like schools and colleges, automated question generation can be used in chatbots and for automated tutoring systems. Question Generation is an area in NLP that is still under research for greater accuracy. Research work has been done in many languages too. The goal of an automatic question generator is to generate syntactically and semantically correct questions, valid according to the given input. The Bidirectional Encoder Representations from Transformers (BERT) model is one of the pre-trained models adopted to implement the same. Additionally, we used Python packages, including NLTK, Spacy, and PKE. To test our findings, we evaluated the validity and relevance of generated questions using human-level cognition and evaluation. We were successful in creating inquiries that adequately reflected several of the peculiarities of English so that a person might comprehend them.
{"title":"An Approach for generating best possible questions from the given text using Natural Language Processing","authors":"Neha Bhagwatkar, Kimaya Vaidya, Aditi Singh, Sneha Borikar, Hirkani Padwad","doi":"10.47164/ijngc.v14i1.1044","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1044","url":null,"abstract":"A crucial ability for every person is the capacity to ask pertinent questions. By automating the process of question formation, an automatic question generator is able to decrease the time and effort needed for manual question creation. Along with benefitting educational institutions like schools and colleges, automated question generation can be used in chatbots and for automated tutoring systems. Question Generation is an area in NLP that is still under research for greater accuracy. Research work has been done in many languages too. The goal of an automatic question generator is to generate syntactically and semantically correct questions, valid according to the given input. The Bidirectional Encoder Representations from Transformers (BERT) model is one of the pre-trained models adopted to implement the same. Additionally, we used Python packages, including NLTK, Spacy, and PKE. To test our findings, we evaluated the validity and relevance of generated questions using human-level cognition and evaluation. We were successful in creating inquiries that adequately reflected several of the peculiarities of English so that a person might comprehend them.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"33 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75609358","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}
Pub Date : 2023-02-15DOI: 10.47164/ijngc.v14i1.1036
P. Pardhi, P. Sonsare
With the progress of the internet from web 2.0 to web 3.0, the increased use of decentralized applications has emerged. Popularized by BlockChain but not limited to decentralized finance, decentralized applications have vast applications with regards to security, storage, and delivery of content over the web. In this paper we outlines the development of a web application prototype using JavaScript programming language, JavaScript based libraries such as BugOut and PeerJS, and the WebRTC (Web Real Time Communication) framework. We have also discuss the brief comparisons between the existing centralized applications and our proposed model. An essential component of this prototype is outlined via the use of P2P networking, which is the backbone of decentralization.
随着互联网从web 2.0到web 3.0的发展，分散式应用程序的使用越来越多。由区块链推广，但不限于去中心化金融，去中心化应用程序在安全性，存储和网络内容交付方面具有广泛的应用。在本文中，我们概述了使用JavaScript编程语言，基于JavaScript的库(如BugOut和PeerJS)和WebRTC (web Real Time Communication)框架开发web应用程序原型。我们还讨论了现有集中式应用程序与我们提出的模型之间的简要比较。这个原型的一个重要组成部分是通过使用P2P网络来概述的，P2P网络是去中心化的支柱。
{"title":"A Secure approach for point-to-point communication in a real time environment using a WebRtc framework","authors":"P. Pardhi, P. Sonsare","doi":"10.47164/ijngc.v14i1.1036","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1036","url":null,"abstract":"With the progress of the internet from web 2.0 to web 3.0, the increased use of decentralized applications has emerged. Popularized by BlockChain but not limited to decentralized finance, decentralized applications have vast applications with regards to security, storage, and delivery of content over the web. In this paper we outlines the development of a web application prototype using JavaScript programming language, JavaScript based libraries such as BugOut and PeerJS, and the WebRTC (Web Real Time Communication) framework. We have also discuss the brief comparisons between the existing centralized applications and our proposed model. An essential component of this prototype is outlined via the use of P2P networking, which is the backbone of decentralization.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"23 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80560561","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}
Pub Date : 2023-02-15DOI: 10.47164/ijngc.v14i1.1004
Nilotpal Chatterjee, Inshal Khan, Mrigank Pagey, Anant Loiya, A. Agrawal, A. Zadgaonkar
Calculating the similarity between two legal documents to find similar legal judgments is an important challenge in legal information. Efficiently computing this similarity by expanding widely used information retrieval and search engine techniques has practical applications in a number of tasks, like locating pertinent prior cases for a specific case document. Programmed data recovery frameworks or reports are the main parts of today’s selected emotional support networks or web indexes to reduce data overload. Investigating methodologies to work on the presentation of report recovery frameworks and web search tools is a working area of research. Various methods have been pro- posed in this research paper to explore ways to search the common law system for cases with a similar outcome. Building a legal decision support system is intended to increase efficiency by assisting stakeholders—including judges and attorneys—in finding related rulings promptly. In order to prepare arguments, a lawyer typically has to review earlier decisions that are comparable to (or pertinent to) the current case. The attorney examines the judgement database to discover similar judgements. Legal rulings are complex in nature and refer to other judgments. For this, proper techniques are needed for quality analysis of judgments and correct deductions from them. A proper analysis of several types of similarity measures, such as all-term-based similarity methods, legal terms, co-citations, and bibliographic links, performed to look for comparable conclusions. According to experimental findings, the law term similarity approach outperforms all term cosine similarity methods. The out- comes also demonstrate that the co-citation approach performs worse than the bibliographic linkage similarity method and improves performance over the co-citation approach. After proper analysis of various methods in this field, proper comparison can be made between documents and similar legal documents can also be easily searched based on their similarity pattern and can be used to make meaningful deductions.
{"title":"Information Retrieval Based Legal Search System","authors":"Nilotpal Chatterjee, Inshal Khan, Mrigank Pagey, Anant Loiya, A. Agrawal, A. Zadgaonkar","doi":"10.47164/ijngc.v14i1.1004","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1004","url":null,"abstract":"\u0000\u0000\u0000Calculating the similarity between two legal documents to find similar legal judgments is an important challenge in legal information. Efficiently computing this similarity by expanding widely used information retrieval and search engine techniques has practical applications in a number of tasks, like locating pertinent prior cases for a specific case document. Programmed data recovery frameworks or reports are the main parts of today’s selected emotional support networks or web indexes to reduce data overload. Investigating methodologies to work on the presentation of report recovery frameworks and web search tools is a working area of research. Various methods have been pro- posed in this research paper to explore ways to search the common law system for cases with a similar outcome. Building a legal decision support system is intended to increase efficiency by assisting stakeholders—including judges and attorneys—in finding related rulings promptly. In order to prepare arguments, a lawyer typically has to review earlier decisions that are comparable to (or pertinent to) the current case. The attorney examines the judgement database to discover similar judgements. Legal rulings are complex in nature and refer to other judgments. For this, proper techniques are needed for quality analysis of judgments and correct deductions from them. A proper analysis of several types of similarity measures, such as all-term-based similarity methods, legal terms, co-citations, and bibliographic links, performed to look for comparable conclusions. According to experimental findings, the law term similarity approach outperforms all term cosine similarity methods. The out- comes also demonstrate that the co-citation approach performs worse than the bibliographic linkage similarity method and improves performance over the co-citation approach. After proper analysis of various methods in this field, proper comparison can be made between documents and similar legal documents can also be easily searched based on their similarity pattern and can be used to make meaningful deductions.\u0000\u0000\u0000","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"358 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82628594","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}
In this modern planet it is very much important to have a good and healthy life for an individual to survive. Just as we humans have a lot of diseases, similarly many diseases are found in plants too. Many models have been made who detect these diseases, but they are not able to give such good accuracy to know which disease has happened. Recognizing plant infection in crops utilizing pictures is an inherently troublesome assignment.This research demonstrates the potential of disease detection models for plant leaves. It covers a number of stages, including picture capture, classification and many more. Extensive researches have already been done by using the CNN model. We have analyzed all these CNN models and on the basis of analysis we have made our own.
{"title":"Plant Disease Detection using CNN Models","authors":"Shreyas Bobde, Kavita B. Kalambe, Anurag Tripathi, Kushal Deoda, Vyankatesh Haridas","doi":"10.47164/ijngc.v14i1.1015","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1015","url":null,"abstract":"In this modern planet it is very much important to have a good and healthy life for an individual to survive. Just as we humans have a lot of diseases, similarly many diseases are found in plants too. Many models have been made who detect these diseases, but they are not able to give such good accuracy to know which disease has happened. Recognizing plant infection in crops utilizing pictures is an inherently troublesome assignment.This research demonstrates the potential of disease detection models for plant leaves. It covers a number of stages, including picture capture, classification and many more. Extensive researches have already been done by using the CNN model. We have analyzed all these CNN models and on the basis of analysis we have made our own.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"26 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78613490","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}
After the price swings of crypto-currencies in past years, it has been considered as an asset. As crypto-currency is unpredictable, there arises the requirement of crypto-currency price prediction with greater level of accuracy. For this many researchers uses variety of ML and DL algorithms and are applying them to build a model which will predict crypto-currency price with improved accuracy. To build successful investment plan, accurate prediction is needed. The proposed method uses combination of LSTM and GRU for the bitcoin price prediction in order to find the closing price of bitcoin
{"title":"Crypto-Currency Price Prediction Using Deep Learning","authors":"Supriya S. Thombre, Aarti Devikar, Vaishnav Gangamwar, Pratik Majrikar, Tanmay Patil","doi":"10.47164/ijngc.v14i1.1029","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1029","url":null,"abstract":"After the price swings of crypto-currencies in past years, it has been considered as an asset. As crypto-currency is unpredictable, there arises the requirement of crypto-currency price prediction with greater level of accuracy. For this many researchers uses variety of ML and DL algorithms and are applying them to build a model which will predict crypto-currency price with improved accuracy. To build successful investment plan, accurate prediction is needed. The proposed method uses combination of LSTM and GRU for the bitcoin price prediction in order to find the closing price of bitcoin","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"1 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90202640","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}
Pub Date : 2023-02-15DOI: 10.47164/ijngc.v14i1.1052
Aparna Gurjar, Preeti S. Voditel
Machine learning (ML) is a data intensive process. For training of ML algorithms huge datasets are required.There are times when enough data is not available due to multitude of reasons. This could be due to lack ofavailability of annotated data in a particular domain or paucity of time in data collection process resulting innon-availability of enough data. Many a times data collection is very expensive and in few domains data collectionis very difficult. In such cases, if methods can be designed to reuse the knowledge gained in one domain havingenough training data, to some other related domain having less training data, then problems associated with lackof data can be overcome. Transfer Learning (TL) is one such method. TL improves the performance of the targetdomain through knowledge transfer from some different but related source domain. This knowledge transfer canbe in form of feature extraction, domain adaptation, rule extraction for advice and so on. TL also works withvarious kinds of ML tasks related to supervised, unsupervised and reinforcement learning. The ConvolutionalNeural Networks are well suited for the TL approach. The general features learned on a base network (source)are shifted to the target network. The target network then uses its own data and learns new features specific toits requirement.
{"title":"Incorporating Transfer Learning in CNN Architecture","authors":"Aparna Gurjar, Preeti S. Voditel","doi":"10.47164/ijngc.v14i1.1052","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1052","url":null,"abstract":"Machine learning (ML) is a data intensive process. For training of ML algorithms huge datasets are required.There are times when enough data is not available due to multitude of reasons. This could be due to lack ofavailability of annotated data in a particular domain or paucity of time in data collection process resulting innon-availability of enough data. Many a times data collection is very expensive and in few domains data collectionis very difficult. In such cases, if methods can be designed to reuse the knowledge gained in one domain havingenough training data, to some other related domain having less training data, then problems associated with lackof data can be overcome. Transfer Learning (TL) is one such method. TL improves the performance of the targetdomain through knowledge transfer from some different but related source domain. This knowledge transfer canbe in form of feature extraction, domain adaptation, rule extraction for advice and so on. TL also works withvarious kinds of ML tasks related to supervised, unsupervised and reinforcement learning. The ConvolutionalNeural Networks are well suited for the TL approach. The general features learned on a base network (source)are shifted to the target network. The target network then uses its own data and learns new features specific toits requirement.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"9 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82324141","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}
Pub Date : 2023-02-15DOI: 10.47164/ijngc.v14i1.1063
Dr. Anjusha Pimpalshende, Preety Singh, Dr. Archana Potnurwar
Abstract. Text classification is very useful to search large amount of textual data available online by dividing it into smaller relevant units. Now a day’s large amount of digital documents are available in Indian languages. Designing text classifiers in Indian languages is one of the research areas so that people can search and read required documents in their local languages. In proposed work tried to design Text classifier for Hindi text documents and tried to show how stemmer affects the performance of Hindi text classifiers. Stemming is a process to convert words in any language to its base or root words. Stemmers are used for written documents not for spoken languages. Performance of many applications such as text summarization, Information Retrieval (IR) system,text classification systems, syntactic parsing can be improved by applying stemmers. Stemmer eliminates suffix or prefix of the word and form original root word. These root words helps in the preprocessing step required in many algorithms. We applied various stemmers on Hindi text classification models. Experiments and results show that performance of the classifiers is improved by applying stemmers.
{"title":"Effect of Stemming on Hindi Text Classification","authors":"Dr. Anjusha Pimpalshende, Preety Singh, Dr. Archana Potnurwar","doi":"10.47164/ijngc.v14i1.1063","DOIUrl":"https://doi.org/10.47164/ijngc.v14i1.1063","url":null,"abstract":"Abstract. Text classification is very useful to search large amount of textual data available online by dividing it into smaller relevant units. Now a day’s large amount of digital documents are available in Indian languages. Designing text classifiers in Indian languages is one of the research areas so that people can search and read required documents in their local languages. In proposed work tried to design Text classifier for Hindi text documents and tried to show how stemmer affects the performance of Hindi text classifiers. Stemming is a process to convert words in any language to its base or root words. Stemmers are used for written documents not for spoken languages. Performance of many applications such as text summarization, Information Retrieval (IR) system,text classification systems, syntactic parsing can be improved by applying stemmers. Stemmer eliminates suffix or prefix of the word and form original root word. These root words helps in the preprocessing step required in many algorithms. We applied various stemmers on Hindi text classification models. Experiments and results show that performance of the classifiers is improved by applying stemmers.","PeriodicalId":42021,"journal":{"name":"International Journal of Next-Generation Computing","volume":"40 1","pages":""},"PeriodicalIF":0.3,"publicationDate":"2023-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74309378","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：