Browsing by Author "Banshal, Sumit Kumar"

Now showing 1 - 12 of 12

A Comprehensive Roadmap on Bangla Text-Based Sentiment Analysis
(Springer, 2022-09-20) Shammi, Shumaiya Akter; Das, Sajal; Chakraborty, Narayan Ranjan; Banshal, Sumit Kumar; Nath, Nishu
The effortless expansion of Internet access has eventually transformed the dissemination behavior toward E-Mode. Thus, the usage of online or, more specifically, “Digital” texts has expanded abruptly. “Bangla,” the seventh most spoken language globally, has no different nature. Communication in the Bangla language has also been exposed on the Internet, which describes the feelings of individuals in any specific context. These enormously generated data from diverse sources have drawn the interest of the researchers working in the Natural Language Processing domain. Despite its relatively complicated structure, a lesser amount of annotated data, as well as a limited number of frameworks and approaches, exist. This lacking of resources has kept several stones unturned in this diverse, emotion-rich, and widely spoken language. To bridge the lacking and absence of resources, this article aims to provide a generalized deduced working procedure in this domain. To do so, the existing research work in the domain of sentiment analysis using Bangla text has been collected, evaluated, and summarized. Also, in this article, the techniques used in pre-processing, feature extraction, and eventually used algorithms have been identified and discussed. Considering these facts, this research work sketches a tentative blueprint of sentiment analysis using Bangla text. Additionally, this article discusses existing regional language corpora such as Tamil, Urdu, and Hindi, as well as English and methodologies used to extract emotional essence from Bangla language comparing other languages. That will assist in determining the probable chosen path of exploring Bangla in a deeper aspect. Moreover, this work has deduced and presented a generalized framework that will direct aspiring researchers to decide the pathway of choosing data vis-à-vis methodologies based on their interests.
A large-scale comparison of coverage and mentions captured by the two altmetric aggregators: Altmetric.com and PlumX
(Springer, 2021-03-20) Karmakar, Mousumi; Banshal, Sumit Kumar; Singh, Vivek Kumar
The increased social media attention to scholarly articles has resulted in creation of platforms & services to track the social media transactions around them. Altmetric.com and PlumX are two such popular altmetric aggregators. Scholarly articles get mentions in different social platforms (such as Twitter, Blog, Facebook) and academic social networks (such as Mendeley, Academia and ResearchGate). The aggregators track activity and events in social media and academic social networks and provide the coverage and transaction data to researchers for various purposes. Some previous studies have compared different altmetric aggregators and found differences in the coverage and mentions captured by them. This paper attempts to revisit the question by doing a large-scale analysis of altmetric mentions captured by the two aggregators, for a set 1,785,149 publication records from Web of Science. Results obtained show that PlumX tracks more altmetric sources and captures altmetric events for a larger number of articles as compared to Altmetric.com. However, the coverage and average mentions of the two aggregators, for the same set of articles, vary across different platforms, with Altmetric.com recording higher mentions in Twitter and Blog, and PlumX recording higher mentions in Facebook and Mendeley. The article also analysed coverage and average mentions captured by the two aggregators across different document types, subjects and publishers.
An AIoT-based hydroponic system for crop recommendation and nutrient parameter monitorization
(Scopus, 2024) Rahman, Md Anisur; Chakraborty, Narayan Ranjan; Sufiun, Abu; Banshal, Sumit Kumar; Tajnin, Fowzia Rahman
Antimicrobials are molecules that prevent the formation of microorganisms such as bacteria, viruses, fungi, and parasites. The necessity to detect antimicrobial peptides (AMPs) using machine learning and deep learning arises from the need for efficiency to accelerate the discovery of AMPs, and contribute to developing effective antimicrobial therapies, especially in the face of increasing antibiotic resistance. This study introduced AMP-RNNpro based on Recurrent Neural Network (RNN), an innovative model for detecting AMPs, which was designed with eight feature encoding methods that are selected according to four criteria: amino acid compositional, grouped amino acid compositional, autocorrelation, and pseudo-amino acid compositional to represent the protein sequences for efficient identification of AMPs. In our framework, two-stage predictions have been conducted. Initially, this study analyzed 33 models on these feature extractions. Then, we selected the best six models from these models using rigorous performance metrics. In the second stage, probabilistic features have been generated from the selected six models in each feature encoding and they are aggregated to be fed into our final meta-model called AMP-RNNpro. This study also introduced 20 features with SHAP, which are crucial in the drug development fields, where we discover AAC, ASDC, and CKSAAGP features are highly impactful for detection and drug discovery. Our proposed framework, AMP-RNNpro excels in the identification of novel Amps with 97.15% accuracy, 96.48% sensitivity, and 97.87% specificity. We built a user-friendly website for demonstrating the accurate prediction of AMPs based on the proposed approach
An Aiot-based Hydroponic System for Crop Recommendation and Nutrient Parameter Monitorization
(Elsevier, 2024-08-15) Rahman, Md Anisur; Chakraborty, Narayan Ranjan; Sufiun, Abu; Banshal, Sumit Kumar; Tajnin, Fowzia Rahman
Advancements in technology have revolutionized various sectors, including agriculture, which serves as the backbone of many economies, particularly in Asian countries. The integration of new technologies and research has consistently aimed to enhance cultivation rates and reduce reliance on manual labor. Two key technologies, Artificial Intelligence (AI) and the Internet of Things (IoT), have emerged as pivotal tools in automating processes, providing recommendations, and monitoring agricultural activities to optimize results. While traditional soil cultivation has been the preferred method, the increasing urbanization trend necessitates alternative approaches such as hydroponics, which replaces soil with water as the medium for crop cultivation. Having many significant advantages, hydroponics serves a crucial role in achieving efficient space utilization. To get a higher density of plants in a confined area hydroponic approach provides water, nutrients and other essential elements directly to the plant's root. To utilize the hydroponic system more effectively, our proposed method, integrating AI and IoT helps to provide suitable crop recommendations, monitor the parameters of the plants and also suggest the necessary changes required for gaining optimal parameters. To ensure optimal resource allocation and maximize yields we have used machine learning models and trained them to recommend suitable crops from the given parameters and also refer to the changes in parameters that are needed for better plant growth. We have used the crop recommendation dataset from the Indian Chamber of Food and Agriculture to train our proposed machine-learning model. Our selected machine learning algorithms to predict the best crops are Random forests, Decision trees, SVM, KNN, and XGBoost. Our research combines AI and IoT with hydroponic systems to streamline crop recommendations, automate monitoring processes, and provide real-time guidance for optimized cultivation. Among them, the Random forest algorithm outperformed other algorithms with an accuracy of 97.5%.
Cyberbullying detection from Bangla text on social media
(Scopus, 2024) Asif, Imtiaz Ahmmed; Roy, Apurbo; Mamun, Md. Al; Siddiquee, Md. Tanvir; Banshal, Sumit Kumar
The potential of social media is expanding as more and more people utilize it. As more individuals use social media, however, bullying in the comment sections of posts by well-known users and of viral material is also on the rise. This number of bullying texts is on the rise and should be eliminated prior to being shown. Using natural language processing and classifier techniques, we identify cyberbullying in this article. We created our data by ourselves. We receive 3500 records, of which 22.1% pertain to bullying and 77.9% do not. After the data were prepared for the classifier model, they were separated into training and testing groups. Multinominal naive Bayes had an accuracy rate of 78.99%, whereas a decision tree classifier had an accuracy rate of 69.48%. The k-nearest neighbor classifier required the shorted time, at 0.0018 seconds, whereas the random forest classifier required the longest time, at 1.44 seconds.
Exploring the Relationship Between Cardiac Disease and Patterns of 12-Lead ECG through Neural Network
(Elsevier, 2024-07-15) Sufiun, Abu; Chakraborty, Narayan Ranjan; Banshal, Sumit Kumar
Heart disease is a significant public health concern, affecting a large number of people worldwide daily. With a shortage of qualified cardiologists, particularly in low-income countries, the diagnosis and management of heart disease can be challenging. The electrocardiogram (ECG) is the primary diagnostic tool for heart disease, but interpreting ECG reports requires the expertise of a qualified cardiologist, making it time-consuming and costly. To address this issue, automated ECG signal interpretation is necessary. Hence, this article has made an encyclopedic review of the existing literature. The article includes a demonstration of frequently utilized data sets and tools and techniques for this domain. Therefore, a framework is proposed based on the observation of existing works. The proposed framework aims to improve the analysis of ECG reports for both cardiologists and non-experts. Our framework considers the 12-lead ECG, the different types of leads, wave patterns, and their relationship with heart disease. The objective is to produce reliable and accurate results while reducing analysis time. The proposed framework is inherent to improve the diagnosis and management of heart disease by enabling a wider range of healthcare providers and individuals to interpret ECG reports. This could lead to earlier detection and treatment of heart disease, which could improve outcomes and save lives.
Exploring the Relationship between Cardiac Disease and Patterns of 12-Lead Ecg Through Neural Network: A Comprehensive Review
(2023-07-19) Sufiun, Abu; Chakraborty, Narayan Ranjan; Banshal, Sumit Kumar; Shammi, Shumaiya Akter
Heart disease is a significant public health concern, affecting a large number of people worldwide daily. With a shortage of qualified cardiologists, particularly in low-income countries, the diagnosis and management of heart disease can be challenging. The electrocardiogram (ECG) is the primary diagnostic tool for heart disease, but interpreting ECG reports requires the expertise of a qualified cardiologist, making it time-consuming and costly. To address this issue, automated ECG signal interpretation is necessary. Hence, this article has made an encyclopedic review of the existing literature. The article includes a demonstration of frequently utilized data sets and tools and techniques for this domain. Therefore, a framework is proposed based on the observation of existing works. The proposed framework aims to improve the analysis of ECG reports for both cardiologists and non-experts. Our framework considers the 12-lead ECG, the different types of leads, wave patterns, and their relationship with heart disease. The objective is to produce reliable and accurate results while reducing analysis time. The proposed framework is inherent to improve the diagnosis and management of heart disease by enabling a wider range of healthcare providers and individuals to interpret ECG reports. This could lead to earlier detection and treatment of heart disease, which could improve outcomes and save lives.
Impact on GDP and the Stock Market During Pandemics or Epidemics of 21st Century
(Journal of Interdisciplinary Mathematics, 2023-09-29) Hossen, Md. Arman; Rahman, Md. Merazur; Nahid, Md. Nabil Ahmed; Islam, Rafiul; Banshal, Sumit Kumar; Gupta, Vedika; Dass, Pranav
"In this article, we present the effect on GDP growth rate during key major pandemics in the twenty-first century. Ebola, cholera, and the most dangerous pandemic, Covid-19, are all fatal pandemics. It was said that Coronavirus started spreading from Wuhan, China. The virus then afflicted the entire human race worldwide. The major goal of this paper is to compare the most catastrophic pandemic to another pandemic in terms of its effect on GDP. This study also examined the impact of the pandemic on the stock market. We offer a descriptive examination of economic impact over the course of 19 years for different countries."
Malicious Social Bot Detection: RL-RNN based Hybrid Approach
(2024-11-04) Swathi, Palagiri; Karmakar, Mousumi; Banshal, Sumit Kumar; Moni, Raka
This paper proposes a new method called RL- RNN that combines the power of Reinforcement Learning and Recurrent Neural Networks in furthering malicious bot detection. Malicious social bots on Twitter have emerged as a significant threat to this platform, spreading disinformation, manipulating public opinion, and influencing political events. The existing traditional detection methods, such as Support Vector Machines, are proven to be unable to deal with bot behaviors dynam- ically and complicatedly. The proposed model inculcates that URL features with frequency and patterns of postings are hot indicators of bot activity. The RL component enables the model to adjust dynamically to changing bot behaviors. It also adapts the RNN type to capture the sequential structure of the tweets with the associated URLs. Thus, experimental results show that this approach using RL- RNN hybrids significantly outperforms traditional SVM-based methods by precision, recall, and overall detection accuracy. The experimental results point out the RL- RNN model’s ability to scalability in detecting evolving bot strategies on Twitter. This makes the approach more effective as a mitigation method for preventing malicious activities, thus increasing security in social media systems.
Performances of Different Approaches for Fake News Classification
(Daffodil International University, 2022-02-25) Abdullah-Al-Kafi, Md.; Tasnova, Israt Jahan; Islam, Md. Wadud; Banshal, Sumit Kumar
The penetration of social and online platforms has opened a new substantial domain of Fake news dissemination in the current time. Also, this dynamic form of data opens up new dimensions for researchers to detect Fake news from the ocean of data. Therefore, Fake news detection has attracted both academia and industry indifferently as research or analytical domain in the concurrent time. Due to data availability, the classification tasks have been tested in different sets and types of data. Detecting Fake news evolves as an actual potential domain to explore with more efficient algorithms and parameter-based modified algorithms. In this work, an analytical sketch has been drawn to compare the performances of different classifiers depending on accuracy and time. Seven classifiers of four different types have been implemented and tested namely, Multilayer Perceptron, Sequential Minimal Optimization, Logistic Regression, Decision Tree, J48, Random Forest and Naïve Bayes Classifier. The analytical evaluation process has been designed with three experimental setups, 10-fold cross-validation, 70% split and 80% split. The separate setups show distinctive outcomes across the algorithms. Naïve-Bayes classifier model shows its prominence along with the Random Forest classifier. However, the and Decision Tree-based classifiers perform differently from earlier knowledge. Furthermore, this paper identifies a different aspect of using testing-training splitting in classifier tasks.
Quantifying Global Digital Journalism Research
(Scopus, 22-06-13) Banshal, Sumit Kumar; Verma, Manoj Kumar; Yuvaraj, Mayank
Purpose The purpose of this paper is to present a comprehensive analysis of the current status and development of the digital journalism field from 1987 to 2021 using the Dimensions database. Design/methodology/approach Using the Dimensions.ai database, 1734 articles were identified through search strategies which were published from 1987 to 2021. The downloaded results were analysed using specific parameters with the help of bibliometric and science mapping tools: Biblioshiny, VOSviewer and CiteSpace. The key contributions of the present comprehensive bibliometric study of the digital journalism field can be seen in terms of the following aspects: (1) Publication analysis from the perspectives of publication growth, key journals, contributing authors, institutions and countries done through Biblioshiny package. (2) Citation network analysis from the perspective of co-citation structure of papers, authors, countries and institutions done through VOSviewer. (3) Timeline analysis and keywords burst detection to identify hotspots and research trends in digital journalism with the help of CiteSpace. Findings The first paper with the keyword digital journalism was published in the year 1989. From 2011 onwards, there has been growth in digital journalism literature. The most popular journal in digital journalism studies is Digital Journalism, Journalism, Journalism Practice, Journalism Studies. Lewis, S.C. has contributed the most number of papers in digital journalism. Further, authors from the countries the USA, Spain, Brazil and UK have contributed immensely. The citation network of authors, institutions and countries contributing to digital journalism studies has also been explored in the study. Through burst analysis, hot topics in digital journalism were identified. Originality/value The paper provides a complete overview of the growth of digital journalism literature published from 1987 to 2021. The originality of this work lies in the triangulation of Biblioshiny, VOSviewer and CiteSpace software to present various aspects of bibliometric study. Findings of the study can help the researchers to identify areas as well as journals, authors, institutions working actively in the field of digital journalism.
Source Recommendation System Using Context-based Classification: Empirical Study on Multi-level Ensemble Methods
(Manuscript Techno Media Publisher, 2024-08-19) Kafi, Abdullah Al; Banshal, Sumit Kumar; Sultana, Nishat; Gupta, Vedika
Aim/Background This research aims to develop an automated contextual classifier for scholarly papers by utilizing established algorithms and understanding the information retention of different parts of a scholarly article, such as the Abstract, Article Title, and Keywords. It also seeks to recommend a contextual classifier-based recommender system to help academics identify credible sources. Scholarly articles from various study fields often use similar terms in their titles and keywords. However, finding a publication venue can be challenging for researchers at the beginning of a scientific inquiry. Thus, it is crucial to classify information based on its context, especially when abstracts, keywords, and titles receive equal attention. Materials and Methods An ensembled model was developed and trained using 114K instances from 38 classes of the Web of Science (WoS) dataset and 40 classes of the Dimensions dataset. The ensemble approach incorporated both machine learning and deep learning algorithms to build a diverse classifier. The model was evaluated by testing it with an 80:20 train-test split to assess performance. The classifier was further integrated into a recommender system designed to suggest probable publication sources based on given article information. Results The ensemble classification approach demonstrated superior performance with faster inference and efficient training time. The balanced training model, tested on 114K instances, effectively categorized scholarly articles into one of 40 categories. The recommender system was capable of recommending up to 10 probable publication sources based on the article’s Title, Keywords, and Abstract. Models utilizing abstractions yielded the best results and provided a better understanding of the context in every iteration of the experiment. Conclusion This study successfully developed an ensemble-based contextual classifier for academic papers, which can also function as a recommender system. The system aids researchers in choosing the most appropriate sources to publish by categorizing articles into 40 categories and suggesting credible publication venues. This approach simplifies the decision-making process for academics, enabling them to identify relevant publications and suitable sources for their work more efficiently.