Bhaskar Pant

Maharishi Dayanand University, Computer Science and Engineering, Undergraduate

Pokhara University, Masters in Business Administration, Graduate Student

Follower

Following

Public Views

Phone: 9858780220
Address: Kathmandu, Nepal

less

Interests

Uploads

Papers by Bhaskar Pant

Classification of Textual Data in Distributed Environment

2018 Second International Conference on Advances in Computing, Control and Communication Technology (IAC3T)

Nowadays data is generating at a very fast pace through internet usage and other sources in large... more Nowadays data is generating at a very fast pace through internet usage and other sources in large volumes termed as Big Data. A large portion of generated data is in text form collected through emails, blogs, social networking sites, e-commerce reviews etc. which requires deep analysis to extract meaningful patterns from it for applications such as business decision making, social media monitoring, spam detection etc. This results in incapability for processing and storing this data. So it must be handled or processed using parallel computing tools and machine learning algorithms. In this work, we have used Naive Bayes classifier to classify textual data in Hadoop environment using Mahout. This experiment is carried out by using 20 news group dataset and achieved accuracy with 88.38%. After evaluating results we have found that when we increase the number of Hadoop clusters, the processing speed on clusters increase as Apache Hadoop can process large volume of datasets efficiently using map-reduce paradigm.

DDITA: A Naive Security Model for IoT Resource Security

Smart Innovations in Communication and Computational Sciences

Information security has its own importance in information era. It forms the third pillar of info... more Information security has its own importance in information era. It forms the third pillar of information world after the performance upsurge and power issues. Security, as the term suggests, is the state of being free from threats. Resultantly Internet of Things receives almost all of the existing security threats from the world of Internet, along with some newly generated threats. In this paper, we are essentially and largely focussing on the security of data as well as resources involved in an Internet of Things system. In this paper, we propose a naive security model, namely DDITA (Definition, Design, Implementation, Testing and Amendment) that emphasizes on security policies, their implementation, their testing under various strategies and finally the amendments if required. In this paper, we have focussed on data involved in Internet of Things. We have classified data as private data and public data. We have also extended our studies toward the further classification of private data into Stored Data and Data in Transit. The security of Stored Data is proposed keeping encryption, authorization, authentication, attestation, and encryption using TPM under its umbrella.

Download

An Effective Vision Based Framework for the Identification of Tuberculosis in Chest X-Ray Images

Communications in Computer and Information Science, 2020

Tuberculosis is an infection that influences numerous individuals worldwide. While treatment is c... more Tuberculosis is an infection that influences numerous individuals worldwide. While treatment is conceivable, it requires an exact conclusion first. Especially in developing countries there are by and large accessible X-beam machines, yet frequently the radiological aptitude is missing for precisely surveying the pictures. An automated vision based framework that could play out this undertaking rapidly and inexpensively could radically improve the capacity to analyze and at last treat the sickness. In this paper we propose image analysis based framework using various machine learning techniques like SVM, kNN, Random Forest and Neural Network for effective identification of tuberculosis. The proposed framework using neural network was able to classify better than other classifiers to detect Tuberculosis and achieves accuracy of 80.45%.

Inter-stock Trend Prediction of Stock Market using Outlier Mining and Association Rule Mining

With the advancement of storage techniques and Digitization of work in every field, the amount of... more With the advancement of storage techniques and Digitization of work in every field, the amount of stored data is tremendously increasing. Influence in Information Technology has caused a sizeable change in every sector of the digitized world. One of such sectors is the stock market where data changes constantly. The economy of the country is indicative of the stock market; this sector needs more support for its development in developing countries, which now rely to a great extent on Investments. Stock market generates a large amount of data on daily basis. Using Data Mining techniques like Clustering, Outlier Mining, Association Rule various operations will be performed to analyze the data and retrieve information. This information will serve us to predict the trend of the stock. Ups and downs in stocks of different companies may be related and so may be their trends. The historical data of such companies will be used to derive the relation to determine the collateral effect on the ...

Download

Big Data Technologies: A Comprehensive Survey

In the last decade, the digitization in every aspect of life has resulted in the explosive genera... more In the last decade, the digitization in every aspect of life has resulted in the explosive generation of data. Therefore, the term Big Data had drawn the attention of researchers and the corporate world. This survey paper presents the concept and definition of Big data followed by its characteristics. We provide a brief overview of the challenges of big data, its technologies, and tools that play a significant role in storing and management of big data. We also highlight the work done by various researchers in the storage and analysis of big data. A comparison of storage technologies is also presented that will help the researchers to have a fair idea to address the different challenges.

Content based Surgical Video Retrieval via Multi-Deep Features Fusion

2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

Literature Review: Real Time Water Quality Monitoring and Management

A Machine Learning Based Framework for Intelligent High Density Garbage Area Classification

Proceedings of the Future Technologies Conference (FTC) 2020, Volume 1

With increase in pollution level, the need of proper management of garbage is also increasing rap... more With increase in pollution level, the need of proper management of garbage is also increasing rapidly. In current scenario enormous amount of garbage/waste generated every day, which require proper dumping of waste and recycling of it. The improper disposal of waste leads to numerous health related disease. Although agencies try hard to collect waste from all areas, still they lack in it. One major reason behind this is the inaccurate tracking of areas with garbage. Agencies are using traditional methodologies for assessment and tracking of areas which need to be upgraded by using current technologies. In this paper we propose a machine learning based framework to classify the areas which are free from garbage and areas with having high density garbage. In our approach we have used four different algorithms and achieved the accuracy of 98.6% with kNN and Naive Bayes, 85.4% with Decision Tree and 98.4% with Random Forest.

Cold Start Problem Resolution Using Bayes Theorem

Probabilistic Model Using Bayes Theorem Research Paper Recommender System

K-Graph: Knowledgeable Graph for Text Documents

Journal of KONBiN, 2021

Graph databases are applied in many applications, including science and business, due to their lo... more Graph databases are applied in many applications, including science and business, due to their low-complexity, low-overheads, and lower time-complexity. The graph-based storage offers the advantage of capturing the semantic and structural information rather than simply using the Bag-of-Words technique. An approach called Knowledgeable graphs (K-Graph) is proposed to capture semantic knowledge. Documents are stored using graph nodes. Thanks to weighted subgraphs, the frequent subgraphs are extracted and stored in the Fast Embedding Referral Table (FERT). The table is maintained at different levels according to the headings and subheadings of the documents. It reduces the memory overhead, retrieval, and access time of the subgraph needed. The authors propose an approach that will reduce the data redundancy to a larger extent. With real-world datasets, K-graph’s performance and power usage are threefold greater than the current methods. Ninety-nine per cent accuracy demonstrates the ro...

An Efficient Image-Based Skin Cancer Classification Framework Using Neural Network

Algorithmic Approaches to Graph Mining

Graph mining being an important research field of data mining has many interesting algorithms. Ev... more Graph mining being an important research field of data mining has many interesting algorithms. Every new approach is studied in detail, then implemented and evaluated on various benchmarks. The focus of the study revolves around the Frequent Subgraph Mining (FSM) from a given graph data set. This is directed to following categories: (1) Introducing an effective and efficient technique for complete and redundancy-free candidate subgraph generation. (2) Identifying the desired frequent subgraphs for intelligent analysis of various problems. In this paper various categories of algorithms are discussed and compared on various parameters of research issues in the field of frequent subgraph mining. And a new search algorithm is also proposed.

Exploring The Dimension of DNN Techniques For Text Categorization Using NLP

The natural language processing (NLP) area has been magically transformed by the Deep Neural Netw... more The natural language processing (NLP) area has been magically transformed by the Deep Neural Network (DNN). The two variations of Neural Networks, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) can handle the different NLP tasks effectively. CNN is based on feature extraction using N-grams at higher levels. The RNN can be effectively used to model the sequential information. Choosing a neural technique for the various NLP tasks is always a challenge. The paper focuses on the evaluating the performance of the two DNN techniques CNN and RNN for the various NLP tasks, so that appropriate technique can be selected.

Machine learning model for HIV1 and HIV2 enzyme secondary structure classification

The structure of a protein can reveal its function and its evolutionary history. Extracting this ... more The structure of a protein can reveal its function and its evolutionary history. Extracting this information requires knowledge of the structure and its relationship with other proteins. Secondary structures of protein are compact with helices and strands. Hence there is a need for development of computational techniques for prediction and classification of HIV-1and HIV-2 protein (enzymes) structures. In this paper a machine learning model has been developed for classification of alpha, beta and residues of HIV ribonuclease, HIV reverse transcriptase, protease, integrase, and these four types of HIV enzymes are present in HIV1 & HIV2 cycle. Various machine learning algorithms such as J48, Rotation Forest, and Random Forest have been used to classify alpha, beta and residues of HIV reverse transcriptase, protease, ribonuclease, integrase and model developed gives fair accuracy. The information generated from these models can be of great use in clinical applications.

Molecular Docking Studies on Follistatin as a Target for Polycysticovary Syndrome (Pcos)

PCOS (polycystic ovary syndrome) is one of the endocrinopathies. Its main symptoms include menstr... more PCOS (polycystic ovary syndrome) is one of the endocrinopathies. Its main symptoms include menstruation irregularities, polycystic ovaries, hyperandrogenism and hyperinsulinemia which may cause infertility, type-2 diabetes and endometrial carcinoma. Precisely, the cause of PCOS is unknown till date, but recent researches have shown that certain genes are linked with the PCOS. FST gene is one of these genes which encodes follistatin protein. It inhibits release of follicle-stimulating hormone. FST protein binds with the activin and functions as an antagonist of activin and inhibitor synthesis and secretion of pituitary follicle stimulating hormone (FSH).Ayurvedic treatment regimens have shown evidence for treating PCOS and hence, in this study, phytochemicals of Commiphora mukul and Asphaltum and target protein follistatin docking interaction is used to prove the efficacy of ayurvedic treatments that are present in the market. Out of nine phytochemicals (Z)- guggulsterone and E-guggu...

Effectiveness of Crop Advisory Services in Aurangabad District of Maharashtra in India

The project was undertaken to study the evaluation of effectiveness of crop advisory services and... more The project was undertaken to study the evaluation of effectiveness of crop advisory services and suggested measures for filling the gap in Aurangabad district of Maharashtra in India. The survey was carried out in 2010. The data was collected with the help of a specifically designed and pre-tested questionnaire. The project carried out in catchment area of advisory services has given substantial insight on the current status of different dimensions of advisory services running in Aurangabad and also recommends strategies to make advisory services accessible to all. The farmer’s willingness to pay assumes a key role in determining the success of a cost-recovery strategy. During the study it was interesting to note that of all the 115 respondents 46.67% agreed that their critical need was supply of inputs followed by credit purchase on which the advisory services provider should focus. The dissemination channels were not utilized properly. The results of correlation study indicate th...

Download

Experimental nanomechanics of 1D nanostructures

Unsupervised Learning of Visual Representations via Rotation and Future Frame Prediction for Video Retrieval

Communications in Computer and Information Science

Categorical Data Analysis and Pattern Mining of Top Colleges in India by Using Twitter Data

2016 8th International Conference on Computational Intelligence and Communication Networks (CICN)

This paper is a detailed summary of the work conducted in the novel domain of categorical data an... more This paper is a detailed summary of the work conducted in the novel domain of categorical data analysis of eminent colleges in India by mining Twitter data and uncovering integral traits/events characteristic of these institutes by determining key rules. The information thus collected could be beneficial to the entire academia: it can be utilized by students in making informed decisions about which college to join or by institutes themselves to address their potentially weak points and maintain the standards of their positive features. Apart from performing extensive preprocessing including spelling correction and netspeak expansion, irrelevant tweets were further segregated by means of a unigram dictionary containing education-oriented keywords. The Apriori algorithm was then applied to the dataset thus obtained resulting in characteristic markers or patterns of these institutes.

Bhaskar Pant

Uploads

Papers by Bhaskar Pant

Log In