Papers by Biswaranjan Acharya
Lecture notes in business information processing, 2024
Telkomnika, Apr 1, 2024
Since cloud computing has an abundance of users, the system has to execute a wide range of tasks.... more Since cloud computing has an abundance of users, the system has to execute a wide range of tasks. Task scheduler methods that are both robust and efficient while delivering the best outcomes are required. The task volume and runtime in the cloud vary rapidly, making task assessment and resource mapping difficult. Security issues, communication delays, and data loss are substantial barriers to scheduling. Furthermore, optimization techniques can be utilized to reduce load and assign tasks so that the user can finish tasks faster. This paper offers a hybrid job scheduling technique for cloud computing using adaptive particle swarm optimization and ant colony optimization particle swarm optimization-ant colony optimization (adaptive PSO-ACO). After rapidly finding the initial solution via particle swarm optimization, the ant colony optimization approach establishes its first pheromone distribution. The suggested hybrid algorithm is compared to standalone PSO and ACO algorithms. Compared to ACO, the percentage decrease is 7.9%. Hybrid method has the lowest total cost, 55% less compared to PSO. Tasks vary when virtual machines (VMs) are constant and VMs vary when tasks are constant. Parameters like final cost, makespan, fitness value, computation time and weighted time are assessed to evaluate the performance of the hybrid task scheduling algorithm.
Information, Feb 9, 2024
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
SN Computer Science, Jan 9, 2024
Algorithms, Nov 24, 2023
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Information, Sep 27, 2023
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
International journal of advanced computer science and applications/International journal of advanced computer science & applications, 2024
This paper investigates the integration of Artificial Intelligence (AI) into systematic literatur... more 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.
IEEE Access
In this quickly developing world, automatic currency identification and recognition are crucial t... more 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, imagebased 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 stateof-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 realworld 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.
International Journal of Computers and Applications
Algorithms
The COVID-19 pandemic has posed significant challenges in accurately diagnosing the disease, as s... more 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...
Research Square (Research Square), Jun 26, 2023
The prediction of household food price index has always been a signi cant challenge for the food ... more The prediction of household food price index has always been a signi cant challenge for the food industry, especially in developing countries like India, where the majority of the population depends on agriculture for their livelihoods. In this project, we aim to develop a food price index prediction system for household food items like cereals, millets, and pulses using three popular timeseries forecasting models, namely SARIMA, ETS, and FB Prophet. We use historical price index data to build and evaluate the forecasting models. The performance of each method is assessed using evaluation metrics such as MAE and RMSE. The results show that all three methods can effectively predict the demand for food items with high accuracy. However, FB Prophet has better performance than the other two methods when it comes to forecasting accuracy and computation time. This project presents a food prediction model that can be used by grocery stores and households to effectively plan and manage their food inventory. The study highlights the effectiveness of time series forecasting techniques such as SARIMA, ETS, and FB Prophet in predicting the demand for household food items, which can aid in reducing food wastage and improving food supply chain management The developed forecasting model can help retailers and suppliers to manage their inventory and plan their production based on the predicted demand for household food items. Additionally, this study provides valuable insights into the application of time series forecasting methods in the food industry.
IEEE Access, 2023
In recent years, blockchain technology has gained significant attention for its potential in vari... more In recent years, blockchain technology has gained significant attention for its potential in various domains. However, the lack of interoperability between different blockchain platforms poses a significant challenge in meeting the demands of the modern world. To address this issue, our research focuses on unlocking blockchain interconnectivity through smart contract-driven cross-chain communication. We aim to contribute to the development of a model that enhances the functionality and usability of blockchain technology. To achieve interoperability, we explore various options and leverage the power of smart contracts. These contracts enable seamless communication and exchange of services between different blockchain platforms, as well as with legacy systems. By implementing our proposed model, we intend to bridge the gap between isolated blockchain systems, enabling them to work together efficiently and effectively. To validate the effectiveness of our model, we have conducted a comparative analysis with existing parent blockchain models for cross-chain communication. We have measured and compared their mean and standard deviation, which indicate the performance improvements achieved by our approach. The results demonstrate that our model outperforms the existing parent blockchain model, offering better cross-chain communication capabilities and showing a 42.27% improvement in efficiency as well. Through our research, we aim to contribute to the advancement of blockchain technology by addressing the critical issue of interoperability. By enabling seamless communication and collaboration between different blockchain platforms, our model has the potential to revolutionize various industries and unlock new opportunities for innovation and growth.
Multimedia Tools and Applications, May 11, 2023
Algorithms, Mar 20, 2023
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
CRC Press eBooks, Apr 21, 2022
CRC Press eBooks, Apr 21, 2022
Uploads
Papers by Biswaranjan Acharya