- Computer Science Researcheredit
Research Interests:
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... 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 Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This paper develops an integrity protection technique based on image demosaicking. To provide the reversible property, the rebuilt components in color pixels are used for secret data embedding. The random value and the hashed result of... more
This paper develops an integrity protection technique based on image demosaicking. To provide the reversible property, the rebuilt components in color pixels are used for secret data embedding. The random value and the hashed result of the most significant high-order bits of the color components are employed to generate the authentication code for each rebuilt component. In addition, the optimal single bit map block truncation coding (OSBMBTC) technique is adopted for generating recovery codes. A block-based image recovery procedure is designed to reconstruct the modified areas. Experimental results reveal that the illegally tampered objects in the test images can be found in these tests even when 87.5% pixels are modified. From the results, the image quality of the recovery image is acceptable when 50% of pixels are modified. Moreover, the demosaicked image can be reversibly constructed when the embedded image is not tampered.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Recently, usage of image processing in machine learning (ML) is growing fast. Medical image processing, image segmentation, computer-aided diagnosis, image transformation, image fusion combined with AI play a crucial role in the... more
Recently, usage of image processing in machine learning (ML) is growing fast. Medical image processing, image segmentation, computer-aided diagnosis, image transformation, image fusion combined with AI play a crucial role in the healthcare field. Other industries are different from the healthcare sector. This is the people’s highest priority sector for those whose expectation levels of the people about care and services are high at a decent cost. It consumes a huge percentage of budgets, but still, it does not affect the social expectations. Many times it is observed that explanations provided by medical experts seem to be ambiguous. Few experts are able to effectively explain the details of medical images due to its complexity and subjective nature; interpreters and fatigue exist in different extensives. Later, the achievement of deep learning concept in varieties of real-time application domains also provides thrilling solutions with a good accuracy percentage in a medical image which will help the medical society soon. Deep learning (DL) methods are a set of algorithms in machine learning (ML), which provides an effective way to analyse medical images automatically for diagnosis/assessment of a disease. DL enables a higher level of abstraction and provides better prediction from data sets. Therefore, DL has a great impact and becomes popular in recent years. In this chapter, we discuss different states of deep learning architecture, image classifications and the medical image segmentation optimizer. This chapter provides a detailed analysis of algorithms based on deep learning that is used in clinical image with regards to recent works and their future approaches. It provides some important knowledge and the way of approaching deep learning concept in the field of healthcare image analysis. Afterwards, we will discuss the challenges that are faced when it is applied to medical images and some open research issues. In the end, a successful medical image processing is presented where implementation is done by deep learning.
Research Interests:
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... more
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 ...
Research Interests:
The prediction of household food price index has always been a significant challenge for the food industry, especially in developing countries like India, where the majority of the population depends on agriculture for their livelihoods.... more
The prediction of household food price index has always been a significant 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 time-series 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 th...
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... more
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 achiev...
Research Interests:
Research Interests:
Research Interests:
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... more
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 analyti...
Research Interests:
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,... more
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 improvin...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Basically, it is hard for endeavors to recognize plant leaf images by a layman due to the varieties in some plant leaves and the extensive information collected for investigation. It is hard to build an automated recognition framework... more
Basically, it is hard for endeavors to recognize plant leaf images by a layman due to the varieties in some plant leaves and the extensive information collected for investigation. It is hard to build an automated recognition framework that can handle massive data and give an intermediate analysis. Image examination and order and pattern recognition are some issues that are effectively connected to the existing methods. This paper focuses on designing an automated plant recognition system based on the best recognition algorithm and the Google platform to locate all plant locations on a map. A case study of India, which has huge biodiversity, is illustrated. The proposed system can show the detailed location of that particular species, where they can be found, and the shortest distance from the current location.
Research Interests:
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... more
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, cla...
Research Interests:
Research Interests:
Clinical support systems are affected by the issue of high variance in terms of chronic disorder prognosis. This uncertainty is one of the principal causes for the demise of large populations around the world suffering from some fatal... more
Clinical support systems are affected by the issue of high variance in terms of chronic disorder prognosis. This uncertainty is one of the principal causes for the demise of large populations around the world suffering from some fatal diseases such as chronic kidney disease (CKD). Due to this reason, the diagnosis of this disease is of great concern for healthcare systems. In such a case, machine learning can be used as an effective tool to reduce the randomness in clinical decision making. Conventional methods for the detection of chronic kidney disease are not always accurate because of their high degree of dependency on several sets of biological attributes. Machine learning is the process of training a machine using a vast collection of historical data for the purpose of intelligent classification. This work aims at developing a machine-learning model that can use a publicly available data to forecast the occurrence of chronic kidney disease. A set of data preprocessing steps we...
Research Interests:
Research Interests:
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... more
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...