Nihar Ranjan - Academia.edu (original) (raw)

Papers by Nihar Ranjan

Journal of emerging technologies and innovative research, Jun 1, 2020

Documents are one of the most common methods for maintaining data and records. Everyday a lot of ... more Documents are one of the most common methods for maintaining data and records. Everyday a lot of documents/files are generated with lot of data for future research purposes or for business analytics. These files/documents must should be stored effectively so that it can be retrieved whenever needed. Organizing large documents can be a tedious task as the internal content of the files are not known. Manually organizing each and every file is not practically possible as it may take hours to categorize a file based on its contents and also the accuracy of classification cannot be guaranteed. In the fields like Library Science a huge amount of files are required to be maintained, which can be helpful in future for business decisions or for research purpose. To make this task easier Text Document Classifier can be used. Text Document Classifier can classify a given document based on the contents inside the document and label the document from the pre-defined classes. Unlike traditional classification Techniques in Machine Learning like Support Vector Machine, term frequency-identification and Naïve Bayes Classifier, Neural Networks has better analytical results. Traditional Classification Methods has limitations in terms of effective feature extraction and the dimensionality problem, these limitations can be solved by Convolutional Neural Networks.

Document Classification is one of the most important topic in Computer Science as the number of e... more Document Classification is one of the most important topic in Computer Science as the number of electronic documents are increasingly very rapidly each day. Document classification is also known as Document Categorization. Classification is training of known labels to predict the unknown labels. It is the process of assigning a particular document to predefined categories. In this paper, we apply machine learning methods for classification of Documents. Recurrent Neural Networks of which LSTM is one of the most successful and have been developed for Controlling Robots, Natural Language Text Compression, Automatic Speech Recognition, Time Series Prediction, Handwriting Recognition and many more. LSTM can also be used for document classification. Document Classification includes text processing, feature extraction, feature vector construction and label prediction or final classification. Furthermore, we first try some data processing on 20 Newsgroup Dataset, and then we extract a feat...

International Journal for Research in Applied Science and Engineering Technology, 2018

In today's technologically advancing world, there is need for smart agriculture. In this paper, w... more In today's technologically advancing world, there is need for smart agriculture. In this paper, we use two algorithms logistic regression and naive bayes for predicting amounts of water and nutrients to be released. Logistic regression algorithm is used for predicting amount of water to be released. Values received from moisture sensors are compared with the available datasets and amount to be released is calculated. Similarly, naive bayes is used to calculate the amount of nutrients to be released. Thus these two algorithms help us for more accurate recommendations. In this paper, we aim to develop a smart system which will be useful for precision agriculture.

Detection of Parkinson’s Disease using Machine Learning Algorithm

International Journal of Computer Applications

International journal of computer applications, Mar 26, 2022

Parkinson is a neurodegenerative disease that affects your ability to control movement. Parkinson... more Parkinson is a neurodegenerative disease that affects your ability to control movement. Parkinson's disease starts slowly and worsens over time. The cured for Parkinson"s disease is still unknown; medications might significantly improve your symptoms. Researchers suggest that early diagnosis of Parkinson can help improve the quality of the patient"s life. In this survey, handwriting or drawings is considered as an aspect for detecting Parkinson disease using machine learning algorithm such as Random Forest Classifier and for detailed analysis of the drawings we use, Histogram of Oriented Gradients (HOG). We take drawings drawn by Parkinson patients as well as healthy people as input for detecting the Parkinson disease

International Education and Research Journal, 2017

For security of the data as well as maintaining privacy over the internet, authentication is used... more For security of the data as well as maintaining privacy over the internet, authentication is used. For this the password is used but the user uses small password, easy to memorize password or password which can be guessed easily. People use personal information as their password for easy memorization. In this paper, we analysis the various passwords from the leaked dataset to research their personal information for finding the relation between them and the password. We use Probabilistic Context-Free Grammars (PCFG) method with semantic-rich method to propose Personal-PCFG method. This method will help us to crack the password much faster than the PCFG method which increases the chances of successful password crack. To protect user from this type of attacks we use distortion function.

A Multi-function Robot for Military Application

Imperial journal of interdisciplinary research, 2017

With the development of technology, scientists and researcher has now come up with the invention ... more With the development of technology, scientists and researcher has now come up with the invention of robots. These robots help to make human life much easier especially in dangerous area. One of the concern areas of today is the military. Military robots are used to take the risky job which is difficult to be handled manually by human. These robots take the job as the assistant of a soldier. Today, many military organizations take the helps of military robots to take risky jobs. These robots used in military are usually employed with the integrated system, including video screens, sensors, gripper and cameras. The military robots also have different shapes according to the purposes of each robot. In other words, these robots have helped military organizations in many ways.

Full Length R eview Article A SURVEY ON TEXT ANALYTICS AND CLASSIFICATION TECHNIQUES FOR TEXT DOCUMENTS

Text Mining is termed as extraction of relevant yet hidden information from the text document. On... more Text Mining is termed as extraction of relevant yet hidden information from the text document. One of the essential concepts in the field of text mining is Text classification (Also called Text Categorization). Through the sudden growth in digital world and available documents, the task of organizing text data becomes one of the p rincipal problems. The classification problem has been widely studied in data mining, machine learning, database, and information retrieval. On the basis of text information processing, we have made a study of support vector machine in text categorization. By introducing the basic principle of SVMs, we described the process of text classification. Comparative Study of other classification algorithm is done and this paper states that how SVM is an effective machine learning algorithm for classification. A th eoretical study of SVM and other machine learning techniques can be found in this paper along with their advantages and disadvantages.

International Journal of Computer Applications, 2018

Every day the mass of information available, merely finding the relevant information is not the o... more Every day the mass of information available, merely finding the relevant information is not the only task of automatic text classification systems. The main problem is to classify which documents are relevant and which are irrelevant. The Automated text classification consists of automatically organizing clustered data. We propose a method of automatic text classification using Convolutional Neural Network based on the disambiguation of the meaning of the word we use the WordNet ontology and word embedding algorithm to eliminate the ambiguity of words so that each word is replaced by its meaning in suitable context. The closest ancestors of the senses of all the words in a given document are selected as folders for the specified document.

International Journal for Research in Applied Science and Engineering Technology, Jun 30, 2018

Seismic activities pose high risks to everyone who lives in an active coal mine region. Even thou... more Seismic activities pose high risks to everyone who lives in an active coal mine region. Even though the hazard is well recognized, no one knows when it will strike or how severe it will be. In this paper, we introduce a method using Random Forest and Rotation Forest for building classifier ensembles based on decision trees using WEKA tool. While Random Forest dealt with the outliers of dataset efficiently, Rotation Forest proved to increase accuracy by using Principal Component Analysis (PCA) to each rotated subset of features. The system provides additional feature of notifying the engineer in charge prior with the danger. This paper mainly aims to advance knowledge and practice that could lead to prevention of seismic activities.

International Journal of Computer Applications, 2016

The field of natural language processing (aka NLP) is an intersection of the study of linguistics... more The field of natural language processing (aka NLP) is an intersection of the study of linguistics, computation and statistics. The primary goal of NLP is automated understanding of the semi-structured language that humans use. This study stems application in diverse fields like semantic analysis, summarization, text classification and the like. The domain natural language processing is a fledgling domain with no concrete indication of when it will mature. Compared to well established domains like "Study of Algorithms", NLP is yet in its emerging period and hence there's dearth of a concise piece of literature that elaborates on the phases of NLP and lists different techniques that can be adapted. NLP borrows heavily from foundational subjects of study like statistics, probability theory and theory of computation. In this paper, we describe three phases of natural language processing namely, language modelling, parts-of-speech tagging and parsing, outlining the approaches used that can be used.