Abhijeet Madhukar Haval’s research while affiliated with Kalinga State University and other places

The programmed grouping of marine species in view of pictures is a difficult errand for which different arrangements have been progressively given in the beyond twenty years. Seas are complicated environments, hard to get to, and frequently the pictures got are of inferior quality. In such cases, creature arrangement becomes monotonous. Subsequently, it is much of the time important to apply improvement or pre-handling procedures to the pictures, prior to applying grouping calculations. The goal is to develop a deep learning system that is both extremely accurate and efficient, utilizing the YOLOv8 (You Only Look Once) algorithm to recognize a variety of aquatic living species underwater. Consequently, we proposed a submerged optical discovery organization (UODN) in light of the YOLO algorithm. The findings not only affirm the suitability of YOLOv8 for underwater exploration but also highlight its potential strength in diverse fields, such as marine resource identification, rescue operations and ecosystem preservation. The intersection of deep learning and underwater environments opens new avenues for technological advancements with far-reaching implications for both scientific research and practical applications.

The integration of big data analytics in pharmacy is revolutionizing patient care by providing insights that enhance medication management and therapeutic outcomes. By leveraging vast amounts of health data, pharmacists can deliver more personalized treatment and optimize drug therapy. Despite the potential benefits, existing methods in pharmacy often suffer from data silos, lack of interoperability, and insufficient analytical capabilities, leading to suboptimal patient outcomes and inefficient medication management. These limitations hinder the effective utilization of data for real-time decision-making in patient care. To address these challenges, it propose the Patient Care Transformation using Big Data Analytics (PCT-BDA) framework, which facilitates a holistic approach to patient data integration and analysis within smart grid systems. This framework enables seamless data flow between various healthcare entities, improving collaboration and fostering a comprehensive view of patient health profiles. The proposed method emphasizes real-time analytics, predictive modeling, and machine learning algorithms to enhance decision-making processes in medication management. By utilizing big data analytics, pharmacists can better predict patient responses, identify potential drug interactions, and tailor therapy plans to individual needs. Preliminary findings from the implementation of the PCT-BDA framework indicate significant improvements in patient outcomes, including reduced medication errors, enhanced adherence to treatment protocols, and overall increased satisfaction with pharmacy services. This innovative approach highlights the transformative potential of big data analytics in optimizing patient care in the pharmacy sector.

Wireless Mobile Networks (WMN) is a pivotal technology that can advance the development of the future digital economy. WMN delivers pervasive computational power via the multitier installation of computers, ensuring reduced latencies and enhanced interaction with multi-tier 5G networks, ledgers, and machine learning. This research presents a novel methodology for improving equipment resource management for edge nodes within a multitier WMN architecture. Alongside a centralized unit, the study evaluates active radio and dispersed units integrated with edge terminals with varying computing capabilities. A customizable Bayesian optimization is employed for hardware resource management to enhance the total computing capability of a 5G-based WMN technology. Simulation findings indicate that, under specified budget limitations, the suggested strategy surpasses pseudorandom resource management for the completion rate of computing jobs. The attainable increases range from 20% to 40%, contingent upon job difficulty and the chosen budget criterion.

The unified power flow controller (UPFC) has been shown to benefit significantly from the contributions of photovoltaic (PV), according to the consensus between scientists. The power quality issues (PQI) and stability in real-world voltage sag/swell and harmonics have been significantly improved as a result of photovoltaic (PV) technology, as is evident. Additionally, there is a growing interest in the incorporation of photovoltaics (PV) into the electrical power system (EPS). In order to strengthen the stability of the situation, this generates a UPFC by employing the maximum power point tracker (MPPT) method. As a result, the MPPT technique’s objective is to determine the most effective means of reaching peak power. Consequently, the PV-UPFC technology has a significant influence on the PQI at the EPS in this manner. Using the PV-UPFC array, this article did an excellent job of modelling the EPS utilising the array. Furthermore, the 400-kW PV-UPFC farm is composed of four PV arrays, each of which is capable of producing up to 100 kW of power when exposed to 1k KW/s2 of sunlight. Remember that a single PV-UPFC array block is composed of sixty-four parallel strings. This is an important part of the equation. The alternative is that each string of PV-UPFC panels is comprised of five Sun-Power SPR/315E modules that are connected in series through the use of MATLAB-Simulation.

Proactively detecting infectious illnesses aids in delivering superior therapy and improves preventing and managing such diseases. This work proposed a Convolutional Neural Network for early Infectious Disease Detection during Public Health Emergencies (CNN-IDD-PHE). The objective is to mitigate the significant damages that Public Health Emergencies (PHE) inflicted on individuals' well-being, everyday routines, and the whole national economy. Statistics on Tuberculosis (TB) cases in a city were gathered from July 2020 to 2022. The Structural Equation Model (SEM) is designed to ascertain the correlation between latent and observed variables by identifying the appropriate indicators and estimating the parameters. A prediction model using Convolutional Neural Network (CNN) has been developed. The strategy's efficacy is validated by assessing the loss value and accuracy of the detection model during both the training and testing phases. Hence, using CNN in Deep Learning (DL) for early warning systems performs better in predicting and alerting Public Health (PH) situations. This advancement is of great importance in enhancing the capabilities of early warning systems.

Twitter is a significant forum for individuals to discuss and disseminate health-related data. The system offers substantial data for immediate monitoring of contagious diseases (such as COVID-19), relieving disease-prevention organizations from the laborious tasks associated with Personal Health Measures (PHM). PHM identification is a crucial technique for staying informed about the status of an epidemic. It aims to determine an individual's health by analyzing web text data. This research investigates the process of identifying PHM related to COVID-19 using data from Twitter. The research has constructed a COVID-19 PHM dataset with tweets labeled with four distinct categories of health disorders connected to COVID-19: self-mention (SM), other-mention (OM), awareness, and non-healthcare (NHC). The research achieved favorable outcomes in the PHM identification task. The categorizing results enable prompt health tracking and oversight for digital epidemiology. The study assesses the impact of the attention strategy and training methodology on the predictive capabilities.

The strategy for personalized medicine is the incorporation of regular health check-ups and wearable health devices into public health campaigns. These innovations have the potential to reduce the burden on healthcare systems by enabling early detection, improved management of chronic conditions, and provision of real-time personal health data to individuals. To achieve this, problems related to the accuracy of devices used, security of data stored in these devices, compliance with usage requirements by consumers, and relations with the current healthcare system must be addressed. A solution to these barriers has been proposed as a Non-Invasive Flexible Sensors for Health Monitoring (N-IFS-HM) approach which involves making sensors that are lightweight, attractive looking, and provide accurate continuous health information without disturbing the users during their daily activities. Through detailed simulation studies conducted in different healthcare settings, this paper examine the dependability and effectiveness of N-IFS-HM implementation. Consequently, based on simulation results done on delicate sensors such as these, vital signs, activities and minimal discomforting healthcare products can be traced accurately. According to this finding, wearable digital technology with sophisticated flexible electronics can revolutionize how public health is assessed.

The integration of Internet of Things (IoT) technologies in healthcare has revolutionized data management, yet challenges in data security and efficient communication persist. Existing solutions often struggle with balancing security and performance, particularly under varying conditions. To address these limitations, we propose a novel approach using Homomorphic Fuzzy Identity-Based Encryption (HFIE) to enhance both data security and communication efficiency in healthcare IoT systems. Our implementation includes a robust architecture that securely collects and transmits health data from sensor nodes to cloud storage, employing a three-tier user access system. HFIE combines homomorphic encryption for secure data processing and FIBE for flexible, error-tolerant access control. This combination addresses the limitations of traditional methods by providing enhanced privacy and performance. Evaluation metrics, including decryption time, energy consumption, and execution time, demonstrate the effectiveness of our approach. HFIE's ability to ensure secure and efficient data management in public health makes it a significant advancement in healthcare IoT technology.

The development of websites, applications, and the first social networks profoundly altered everyone's life and became the catalyst for advancement on a global scale. The days of immovable points, phones, and printing presses are long gone. But is everything really as perfect as it looks? Perhaps the most contentious thing in history is progress. We now have the freedom to express our ideas without fear, connect with individuals around the globe, and access a seemingly limitless amount of knowledge thanks to the Internet. But as time goes on, concerns about the cloudlessness of virtual existence become more and more prevalent; we have been captured by things that do not exist in reality. Apart from the well-known hazards like terrorism and global warming, the growth of the Internet has given rise to entirely unknown and novel perils that have infiltrated our life. We refer to this phenomena as "cybercrime". Any form of criminal activity carried out virtually is referred to as cybercrime. Ten to twenty years ago, this phenomena was known only to specialised specialists. IT industry, and it is currently a worldwide issue. Although everyone and the IT sector receive adequate security measures and equipment, cybercrime is nevertheless increasing at a very rapid pace in parallel. There are several security problems and cyberthreats in the modern world. With new technology emerging daily, we can predict major issues in the road. In this work a Secure Healthcare Data Storage and Transmission in WAN area is discussed.