Biswaranjan Acharya
@marwadiuniversity.ac.in
Marwadi University
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Nihar Ranjan Sabat, Rashmi Ranjan Sahoo, Manas Ranjan Pradhan, and Biswaranjan Acharya
Universitas Ahmad Dahlan
ABSTRACT
Anusha Chhabra, Monika Arora, Arpit Sharma, Harsh Singh, Saurabh Verma, Rachna Jain, Biswaranjan Acharya, Vassilis C. Gerogiannis, Dimitrios Tzimos, and Andreas Kanavos
World Scientific Pub Co Pte Ltd
Text classification involves organizing textual information into predefined classes, a task which is particularly useful in domains like sentiment analysis, spam detection, and content labeling. In India, where a massive amount of information is generated daily through newspapers and social media, Hindi is one of the most widely used and spoken languages. However, there is limited research on Hindi text classification and, particularly, regarding Hindi news classification. This paper presents a research study to classify Hindi news articles published in Hindi-language newspapers in India by using and comparing various Machine Learning (ML) and Deep Learning (DL) algorithms. To prepare the textual news data for classification, pre-processing and feature engineering techniques, such as count vectorizer, Tf-Idf vectorizer and Doc2Vec, were used and applied to convert texts into vectors. This pre-processing step on the textual data was very challenging due to the presence of multimodal words, conjunctions, punctuation, and special characters in Hindi texts. The study considered Hindi news headlines from predetermined categories (Science, Sports, Entertainment and Business) and, among the different ML and DL models tested and evaluated, Linear Regression with Doc2Vec vectorizer and SGD classifier with Tf-Idf vectorizer produced best accuracies of 97.04% and 96.59%, respectively. The best performing DL model was found to be the Bi-LSTM with an accuracy of approximately 97% on the testing data.
Sourav Ghosh, K Martin Sagayam, Dibyajyoti Haldar, A Amir Anton Jone, Biswaranjan Acharya, Vassilis C Gerogiannis, and Andreas Kanavos
IOP Publishing
Abstract Biosensors have gained significant attention in various fields such as food processing, agriculture, environmental monitoring, and healthcare. With the continuous advancements in research and technology, a wide variety of biosensors are being developed to cater to diverse applications. However, the effective development of nanobiosensors, particularly the synthesis of nanomaterials, remains a crucial step. Many nanobiosensors face challenges related to instability and selectivity, making it difficult to achieve proper packaging. While some biosensors have been successfully implemented in commercial settings, there is a pressing need to address their limitations and advance their capabilities. The next generation of biosensors, based on nanomaterials, holds promise in overcoming these challenges and enhancing the overall performance of biosensor devices. The commercial viability of these biosensors will rely on their accuracy, reliability, and cost-effectiveness. This review paper provides an overview of various types of nanomaterials and their applications in the development of nanobiosensors. The paper highlights a comparison of different nanomaterial-based biosensors, discussing their advantages, limitations, and performance characteristics.
Majdi Sukkar, Madhu Shukla, Dinesh Kumar, Vassilis C. Gerogiannis, Andreas Kanavos, and Biswaranjan Acharya
MDPI AG
Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules.
Kirtirajsinh Zala, Biswaranjan Acharya, Madhav Mashru, Damodharan Palaniappan, Vassilis C. Gerogiannis, Andreas Kanavos, and Ioannis Karamitsos
The Science and Information Organization
—This paper investigates the integration of Artificial Intelligence (AI) into systematic literature reviews (SLRs), aiming to address the challenges associated with the manual review process. SLRs, a crucial aspect of scholarly research, often prove time-consuming and prone to errors. In response, this work explores the application of AI techniques, including Natural Language Processing (NLP), machine learning, data mining, and text analytics, to automate various stages of the SLR process. Specifically, we focus on paper identification, information extraction, and data synthesis. The study delves into the roles of NLP and machine learning algorithms in automating the identification of relevant papers based on defined criteria. Researchers now have access to a diverse set of AI-based tools and platforms designed to streamline SLRs, offering automated search, retrieval, text mining, and analysis of relevant publications. The dynamic field of AI-driven SLR automation continues to evolve, with ongoing exploration of new techniques and enhancements to existing algorithms. This shift from manual efforts to automation not only enhances the efficiency and effectiveness of SLRs but also marks a significant advancement in the broader research process.
Biswaranjan Acharya, Sucheta Panda, and Niranjan K. Ray
Springer Science and Business Media LLC
Narina Thakur, Eshanika Bhattacharjee, Rachna Jain, Biswaranjan Acharya, and Yu-Chen Hu
Springer Science and Business Media LLC
Annwesha Banerjee Majumder, Somsubhra Gupta, Dharmpal Singh, Biswaranjan Acharya, Vassilis C. Gerogiannis, Andreas Kanavos, and Panagiotis Pintelas
MDPI AG
Heart disease is a leading global cause of mortality, demanding early detection for effective and timely medical intervention. In this study, we propose a machine learning-based model for early heart disease prediction. This model is trained on a dataset from the UC Irvine Machine Learning Repository (UCI) and employs the Extra Trees Classifier for performing feature selection. To ensure robust model training, we standardize this dataset using the StandardScaler method for data standardization, thus preserving the distribution shape and mitigating the impact of outliers. For the classification task, we introduce a novel approach, which is the concatenated hybrid ensemble voting classification. This method combines two hybrid ensemble classifiers, each one utilizing a distinct subset of base classifiers from a set that includes Support Vector Machine, Decision Tree, K-Nearest Neighbor, Logistic Regression, Adaboost and Naive Bayes. By leveraging the concatenated ensemble classifiers, the proposed model shows some promising performance results; in particular, it achieves an accuracy of 86.89%. The obtained results highlight the efficacy of combining the strengths of multiple base classifiers in the problem of early heart disease prediction, thus aiding and enabling timely medical intervention.
Vivek Kumar Prasad, Debabrata Dansana, Madhuri D. Bhavsar, Biswaranjan Acharya, Vassilis C. Gerogiannis, and Andreas Kanavos
MDPI AG
With the proliferation of IoT devices, there has been exponential growth in data generation, placing substantial demands on both cloud computing (CC) and internet infrastructure. CC, renowned for its scalability and virtual resource provisioning, is of paramount importance in e-commerce applications. However, the dynamic nature of IoT and cloud services introduces unique challenges, notably in the establishment of service-level agreements (SLAs) and the continuous monitoring of compliance. This paper presents a versatile framework for the adaptation of e-commerce applications to IoT and CC environments. It introduces a comprehensive set of metrics designed to support SLAs by enabling periodic resource assessments, ensuring alignment with service-level objectives (SLOs). This policy-driven approach seeks to automate resource management in the era of CC, thereby reducing the dependency on extensive human intervention in e-commerce applications. This paper culminates with a case study that demonstrates the practical utilization of metrics and policies in the management of cloud resources. Furthermore, it provides valuable insights into the resource requisites for deploying e-commerce applications within the realms of the IoT and CC. This holistic approach holds the potential to streamline the monitoring and administration of CC services, ultimately enhancing their efficiency and reliability.
Debabrata Swain, Badal Parmar, Hansal Shah, Aditya Gandhi, Biswaranjan Acharya, and Yu-Chen Hu
Springer Science and Business Media LLC
Manav Garg, Pranshav Gajjar, Pooja Shah, Madhu Shukla, Biswaranjan Acharya, Vassilis C. Gerogiannis, and Andreas Kanavos
MDPI AG
The musical key serves as a crucial element in a piece, offering vital insights into the tonal center, harmonic structure, and chord progressions while enabling tasks such as transposition and arrangement. Moreover, accurate key estimation finds practical applications in music recommendation systems and automatic music transcription, making it relevant across academic and industrial domains. This paper presents a comprehensive comparison between standard deep learning architectures and emerging vision transformers, leveraging their success in various domains. We evaluate their performance on a specific subset of the GTZAN dataset, analyzing six different deep learning models. Our results demonstrate that DenseNet, a conventional deep learning architecture, achieves remarkable accuracy of 91.64%, outperforming vision transformers. However, we delve deeper into the analysis to shed light on the temporal characteristics of each deep learning model. Notably, the vision transformer and SWIN transformer exhibit a slight decrease in overall performance (1.82% and 2.29%, respectively), yet they demonstrate superior performance in temporal metrics compared to the DenseNet architecture. The significance of our findings lies in their contribution to the field of musical key estimation, where accurate and efficient algorithms play a pivotal role. By examining the strengths and weaknesses of deep learning architectures and vision transformers, we can gain valuable insights for practical implementations, particularly in music recommendation systems and automatic music transcription. Our research provides a foundation for future advancements and encourages further exploration in this area.
Shubham Mathesul, Debabrata Swain, Santosh Kumar Satapathy, Ayush Rambhad, Biswaranjan Acharya, Vassilis C. Gerogiannis, and Andreas Kanavos
MDPI AG
The COVID-19 pandemic has posed significant challenges in accurately diagnosing the disease, as severe cases may present symptoms similar to pneumonia. Real-Time Reverse Transcriptase Polymerase Chain Reaction (RT-PCR) is the conventional diagnostic technique; however, it has limitations in terms of time-consuming laboratory procedures and kit availability. Radiological chest images, such as X-rays and Computed Tomography (CT) scans, have been essential in aiding the diagnosis process. In this research paper, we propose a deep learning (DL) approach based on Convolutional Neural Networks (CNNs) to enhance the detection of COVID-19 and its variants from chest X-ray images. Building upon the existing research in SARS and COVID-19 identification using AI and machine learning techniques, our DL model aims to extract the most significant features from the X-ray scans of affected individuals. By employing an explanatory CNN-based technique, we achieved a promising accuracy of up to 97% in detecting COVID-19 cases, which can assist physicians in effectively screening and identifying probable COVID-19 patients. This study highlights the potential of DL in medical imaging, specifically in detecting COVID-19 from radiological images. The improved accuracy of our model demonstrates its efficacy in aiding healthcare professionals and mitigating the spread of the disease.
Arindita Saha, Naladi Ram Babu, Puja Dash, Biswaranjan Acharya, Mahajan Sagar Bhaskar, and Baseem Khan
Institution of Engineering and Technology (IET)
AbstractTo succeed over the sudden load‐frequency variations in interlinked power systems, an equilibrium must be maintained between power generations and losses. The major problem associated to manifold interlinking arenas of power systems is load frequency control. In this paper, a multiple‐arena scheme is examined which encompasses thermal and split shaft gas turbine plants. Here, artificial rabbit optimization (ARO) is applied to procure the premium standards of the supplementary controller. The projected controller is the amalgamation of integer order integral‐derivative with filter (IDN) and fractional order integral‐derivative (FOID). So, the amalgamation is IDN‐FOID. Henceforth, the ARO augmented IDN‐FOID controller is recognized. The ARO augmented IDN‐FOID supplementary controller delivers enhanced outcomes related to additional secondary controllers like I, PI, and PIDN. Valuation articulates about the improved act of ARO over added algorithms using the IDN‐FOID controller related to converging nature, transient profile, and steady‐state assessment. Assessment is done in the presence of non‐linearities in generation rate constraints and time delay. It is also detected that scheme potent outcomes with the IDN‐FOID controller are superior when the scheme is instructed with solar photovoltaic, electric vehicles, solid oxide fuel cells, and ultra‐capacitor. The ARO optimized IDN‐FOID controller is the anticipated arrangement for the measured scheme.
Cheena Mohanty, Sakuntala Mahapatra, Biswaranjan Acharya, Fotis Kokkoras, Vassilis C. Gerogiannis, Ioannis Karamitsos, and Andreas Kanavos
MDPI AG
Diabetic retinopathy (DR) is a common complication of long-term diabetes, affecting the human eye and potentially leading to permanent blindness. The early detection of DR is crucial for effective treatment, as symptoms often manifest in later stages. The manual grading of retinal images is time-consuming, prone to errors, and lacks patient-friendliness. In this study, we propose two deep learning (DL) architectures, a hybrid network combining VGG16 and XGBoost Classifier, and the DenseNet 121 network, for DR detection and classification. To evaluate the two DL models, we preprocessed a collection of retinal images obtained from the APTOS 2019 Blindness Detection Kaggle Dataset. This dataset exhibits an imbalanced image class distribution, which we addressed through appropriate balancing techniques. The performance of the considered models was assessed in terms of accuracy. The results showed that the hybrid network achieved an accuracy of 79.50%, while the DenseNet 121 model achieved an accuracy of 97.30%. Furthermore, a comparative analysis with existing methods utilizing the same dataset revealed the superior performance of the DenseNet 121 network. The findings of this study demonstrate the potential of DL architectures for the early detection and classification of DR. The superior performance of the DenseNet 121 model highlights its effectiveness in this domain. The implementation of such automated methods can significantly improve the efficiency and accuracy of DR diagnosis, benefiting both healthcare providers and patients.
Abhishek Kadalagere Lingaraju, Mudligiriyappa Niranjanamurthy, Priyanka Bose, Biswaranjan Acharya, Vassilis C. Gerogiannis, Andreas Kanavos, and Stella Manika
MDPI AG
Massive human population, coupled with rapid urbanization, results in a substantial amount of garbage that requires daily collection. In urban areas, garbage often accumulates around dustbins without proper disposal at regular intervals, creating an unsanitary environment for humans, plants, and animals. This situation significantly degrades the environment. To address this problem, a Smart Waste Management System is introduced in this paper, employing machine learning techniques for air quality level classification. Furthermore, this system safeguards garbage collectors from severe health issues caused by inhaling harmful gases emitted from the waste. The proposed system not only proves cost-effective but also enhances waste management productivity by categorizing waste into three types: wet, dry, and metallic. Ultimately, by leveraging machine learning techniques, we can classify air quality levels and garbage weight into distinct categories. This system is beneficial for improving the well-being of individuals residing in close proximity to dustbins, as it enables constant monitoring and reporting of air quality to relevant city authorities.
Jayashree Piri, Puspanjali Mohapatra, Raghunath Dey, Biswaranjan Acharya, Vassilis C. Gerogiannis, and Andreas Kanavos
MDPI AG
The efficiency and the effectiveness of a machine learning (ML) model are greatly influenced by feature selection (FS), a crucial preprocessing step in machine learning that seeks out the ideal set of characteristics with the maximum accuracy possible. Due to their dominance over traditional optimization techniques, researchers are concentrating on a variety of metaheuristic (or evolutionary) algorithms and trying to suggest cutting-edge hybrid techniques to handle FS issues. The use of hybrid metaheuristic approaches for FS has thus been the subject of numerous research works. The purpose of this paper is to critically assess the existing hybrid FS approaches and to give a thorough literature review on the hybridization of different metaheuristic/evolutionary strategies that have been employed for supporting FS. This article reviews pertinent documents on hybrid frameworks that were published in the period from 2009 to 2022 and offers a thorough analysis of the used techniques, classifiers, datasets, applications, assessment metrics, and schemes of hybridization. Additionally, new open research issues and challenges are identified to pinpoint the areas that have to be further explored for additional study.
Satyananda Champati Rai, Samaleswari Pr Nayak, Biswaranjan Acharya, Vassilis C. Gerogiannis, Andreas Kanavos, and Theodor Panagiotakopoulos
MDPI AG
Recently, there has been a huge spike in the number of automobiles in the urban areas of many countries, particularly in India. The number of vehicles are increasing rapidly and with the existing infrastructure, the traffic systems stand still during peak hours. Some of the main challenges for traffic management are the movement of overloaded vehicles beyond their restricted zone and time, reckless driving, and overlooking road safety rules. This paper proposes an Internet of Things (IoT)-based real-time Intelligent Traffic Signal System (ITSS), which consists of inductive loops and a programmable micro-controller to determine traffic density. Inter-communication in the centralized control unit sets the timer of the traffic light and synchronizes with the traffic density in real-time for smooth mobility of vehicles with less delay. Additionally, to prioritize emergency vehicles over other vehicles in the same lane, a pre-emption mechanism has been integrated through infrared sensors. The result of traffic density determines the timer of the light post in real-time, which in result enhances the smooth flow of vehicles with reduced delay for travelers. Using its automatic on-demand traffic signaling system, the presented solution has advantages over fixed systems.
Ranjit Singh Sarban Singh, T. Joseph Sahaya Anand, Siti Aisyah Anas, and Biswaranjan Acharya
Engineering, Technology & Applied Science Research
COVID-19 is a contagious disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The disease has spread worldwide, leading to an ongoing pandemic. The most common symptom of COVID-19 is fever which can be detected using various manual screening techniques that have the risk of exposing the personnel. Since the virus has globally spread, a reliable system to detect COVID-19-infected people, especially before entering any premises and buildings, is in high demand. The most common symptom that can be detected is fever, even though people with fever might not have COVID-19. Thus, a real-time analytic face thermal recognition system integrated with email notification that has the capability to scan the person’s temperature and simultaneously analyze the measured temperature with the recorded/stored information/data is presented in this paper. The proposed system is also able to send an email notification to the relevant authorities during the real-time analytical process. Besides that, this information is also recorded in the system database for continuous monitoring of the respective person’s health status. The development of the proposed system is integrated with a Thermal Module AMG8833, Pi camera, and Raspberry Pi Zero Wireless. The proposed system has been tested and the captured results successfully accomplished the development objectives.
Vassilis C. Gerogiannis, Andreas Kanavos, Nikos Antonopoulos, Amrita Bhola, and Biswaranjan Acharya
IEEE
Sentiment analysis and text classification tasks heav-ily rely on text processing techniques. However, existing approaches often neglect domain-specific factors and rely on generic routines and pre-built dictionaries. In this paper, we investigate the impact of text processing steps on sentiment classification using Twitter data. Our approach introduces skip gram-based word embeddings that effectively capture Twitter-specific fea-tures, such as informal language and emojis. Through rigorous experimentation, we identify the detrimental consequences of conventional text processing steps like stop word removal and simple averaging of term vectors for tweet representation. To optimize sentiment classification, we propose new effective steps, including the inclusion of emoji characters, measuring word importance from embeddings, aggregating term vectors into tweet embeddings, and creating a linearly separable feature space. Our results demonstrate the superiority of context-driven word embeddings in selecting important words for tweet clas-sification, outperforming pre-built word dictionaries. Moreover, the proposed tweet embedding reduces reliance on multiple text processing steps, resulting in more accurate sentiment analysis on Twitter data.
Kirtirajsinh Zala, Vyom Modi, Deep Thumar, Amrita Bhola, and Biswarajan Acharya
IEEE
Medical (Healthcare) practitioners (MPs) have rapidly used mobile cloud computing (MCC) in the healthcare business, resulting in the expansion of healthcare software applications on these platforms. There are several programmes that assist MPs with numerous crucial activities. The use of mobile cloud computing have aided Medical Practioners in making better decisions and enhancing patient care. With MCC, clients may take use of cloud computing resources to meet the demands of the healthcare sector. However, the adoption of MCC comes with challenges, particularly concerning network bandwidth limitations and mobile device capacity, resulting in issues related to energy consumption and latency delays. In response to these challenges, this paper proposes the Dynamic Energy-aware Cloudlet-based Mobile Cloud Computing Model (DECMCCM), which introduces a novel approach utilizing dynamic cloudlets to address energy consumption issues in healthcare mobile devices. By intelligently distributing computational tasks between mobile devices and cloudlets, DECMCCM optimizes energy utilization, reducing the strain on the devices and improving overall system performance.
Kirtirajsinh Zala, Suraj Kothari, Hemant Patel, Amrita Bhola, and Biswaranjan Acharya
IEEE
The latest innovations enable learners to study more quickly, productively, independently, and safely. Learners use smart gadgets to reach online resources over wireless connections and engage them in individualized and smooth learning. Digital learning, a theory that represents learning in the digital world, has received more attention. This paper discussed smart education and gives a theoretical structure of smart learning and major components of smart educational environments are suggested to cultivate smart students who need to master 21st century learning expertise and abilities. Class-based customized teaching, community cooperative learning, personality customized learning, and bulk creative learning are all part of the smart pedagogy paradigm. Additionally, a technical structure of smart education is developed, demonstrating the significance of smart learning. framework and major functionality are all provided. Lastly, the difficulties of smart teaching are highlighted.
Santosh Kumar Majhi, Abhipsa Panda, Suresh Kumar Srichandan, Usha Desai, and Biswaranjan Acharya
Informa UK Limited
Debabrata Swain, Viral Rupapara, Amro Nour, Santosh Satapathy, Biswaranjan Acharya, Shakti Mishra, and Ali Bostani
Institute of Electrical and Electronics Engineers (IEEE)
In this quickly developing world, automatic currency identification and recognition are crucial tasks. Several financial institutions, such as banks and hardware-based devices such as vending machines and slot machines, play an essential role in all monetary unification fields. Accurate coin recognition is essential in various contexts, including vending machines, currency exchange, and archaeological research. However, the distinctive visual characteristics of Brazilian coins, including variations in size, color, and design, pose significant challenges for automated classification. Most of the existing currency recognition systems are based on the physical properties of the currencies, such as length, breadth, and mass. At the same time, image-based methods rely on other properties like color, shape, and edge. This paper presents a novel deep-learning framework tailored to classify Brazilian coins. Our proposed deep learning framework leverages state-of-the-art convolutional neural networks (CNNs) to address these challenges. We introduce a Repetitive Feature Extractor Convolution Neural Network (RFE-CNN) model to recognize the currency faster and accurately. Our framework employs a multi-stage approach for coin classification. First, a pre-processing module handles coin localization and image enhancement to mitigate variations in lighting and background. Next, an RFE-CNN-based feature extractor extracts discriminative features from the coin images. We explore transfer learning from pre-trained models to enhance the model’s generalization capability, given limited data availability. We used a comprehensive dataset of Brazilian coins, comprising various denominations, minting years, and conditions, to facilitate model training and evaluation. The dataset includes high-resolution images captured under diverse lighting and environmental conditions, ensuring robust model performance in real-world scenarios. In conclusion, our proposed deep learning framework offers a powerful and efficient solution for classifying Brazilian coins. The framework’s adaptability makes it a valuable tool for recognizing coins from other regions with similar visual diversity and variability challenges. The proposed model has achieved a classification accuracy of 98.34% for the classification of Brazilian coins.
Krishna Mridha, Ajoy Chandra Kuri, Trinoy Saha, Nancy Jadeja, Madhu Shukla, and Biwaranjan Acharya
Springer Nature Singapore