Authors: Ishira Venkatesh

Abstract: Bioinformatics has become a pivotal force in transforming neuroscience research, enabling deep insights into the structure and function of the brain. By integrating computational approaches with experimental data, neuroscientists can now analyze complex neural networks, decipher molecular mechanisms, and unravel the genetic underpinnings of neurological disorders. The surge in large-scale data—from genomics and transcriptomics to neuroimaging and electrophysiology—has created both opportunities and challenges, necessitating advanced analytical tools capable of processing and interpreting vast datasets. Bioinformatics methods have empowered the identification of novel biomarkers, the understanding of brain development, and the discovery of therapeutic targets, bringing precision and efficiency to neuroscience studies. Moreover, bioinformatics facilitates interdisciplinary collaborations, connecting computer scientists, biologists, and clinicians to resolve intricate questions related to cognition, behavior, and disease. The application of machine learning, network analysis, and data mining techniques has enhanced the predictive accuracy for diagnosis and treatment strategies. As neural data repositories expand, bioinformatics supports the harmonization and sharing of information, promoting reproducibility and fostering the growth of open science. Despite these advances, challenges remain, including data standardization, the need for high computational power, and the integration of multi-modal data. Continuous development of bioinformatics tools is required to address these challenges while ensuring ethical considerations are met in data management. Ultimately, bioinformatics is reshaping neuroscience, fueling discoveries that have the potential to transform our understanding of the brain, mental health, and neurological diseases.

DOI: https://doi.org/10.5281/zenodo.16979834

 

Published by: vikaspatanker

Authors: Arhaan Madavi

Abstract: Cloud-native security has become an essential paradigm in modern computing, aligning security strategies with the dynamic and scalable architecture of cloud-native applications. As enterprises transition from traditional on-premises environments to distributed, containerized, and microservices-based infrastructure, the security landscape shifts dramatically. This review synthesizes current research and best practices in cloud-native security, outlining critical challenges, innovative solutions, and industry trends. Cloud-native environments are characterized by their reliance on containers, Kubernetes, service meshes, and serverless functions, which bring new opportunities alongside new threats. The paper discusses how traditional perimeter-based security approaches are being replaced by identity-driven, zero-trust models, embedding security into every layer of application design and deployment. Topics such as secure software supply chains, runtime protection, compliance automation, and infrastructure-as-code security are explored. This review aims to provide a single resource for researchers, DevSecOps practitioners, and enterprise architects seeking a comprehensive understanding of cloud-native security, emphasizing the importance of collaboration between development, operations, and security teams. Through an in-depth analysis of technologies, frameworks, and strategies, the article clarifies how organizations can address the unique risks present in modern cloud-native ecosystems while enabling agility and continuous delivery. By surveying academic literature and industry reports prior to 2014, we situate key advancements in their historical context, revealing the trajectory toward the current state of cloud-native security. The findings underscore the necessity for proactive, automated, and scalable security practices that evolve with cloud-native application lifecycles.

DOI: https://doi.org/10.5281/zenodo.16979595

 

Published by: vikaspatanker

Authors: Samaira Lodh

Abstract: Artificial Intelligence (AI) is revolutionizing healthcare diagnostics by providing unprecedented capabilities in data analysis, pattern recognition, and predictive modeling. AI-powered tools have demonstrated potential in increasing diagnostic accuracy, reducing diagnostic errors, optimizing treatment pathways, and ultimately improving patient outcomes. The integration of AI with healthcare diagnostics stands at the forefront of digital transformation, leveraging advancements in machine learning, deep learning, and natural language processing. These technologies enable precise identification of diseases from various forms of medical data, including imaging, genomics, and patient records. Despite remarkable progress, the field faces challenges such as data privacy concerns, ethical dilemmas, integration with existing healthcare workflows, and the need for transparency and explainability in AI-driven decisions. Emerging trends like explainable AI, federated learning, and the use of AI for point-of-care diagnostics are shaping the future of healthcare diagnostics. This article explores these trends, evaluates their potential impact, and discusses the implications for practitioners, patients, and policymakers. The ultimate aim is to provide an in-depth understanding of how AI is redefining healthcare diagnostics, the directions in which the field is evolving, and the unresolved questions that must be addressed to leverage the full potential of AI while safeguarding ethical and clinical standards.

DOI: https://doi.org/10.5281/zenodo.16979367

 

Published by: vikaspatanker

Authors: Praveen bodana, Assistant Professor Khemraj Beragi

Abstract: Thermal power plants (TPPs) are a critical component of global electricity generation, yet they often suffer from efficiency loss and unplanned outages due to equipment faults. Traditional maintenance strategies (reactive or preventive) are often too slow or costly. In contrast, machine learning (ML) methods can analyze large historical and real-time sensor data to detect anomalies and predict failures early. This paper surveys supervised methods (SVM, random forests, neural networks), unsupervised models (autoencoders, clustering, PCA), and hybrid physics-ML approaches for TPP monitoring. It also examines sensor optimization and IoT-enabled real-time monitoring. Case examples from the literature show that ML-based predictive maintenance can greatly reduce unplanned downtime and maintenance costs (e.g., cutting costs by roughly 20–40%) while improving equipment availability. The findings indicate that optimized sensor networks, integrated IoT data, and advanced ML models can substantially enhance fault detection accuracy and overall plant efficiency.

DOI: http://doi.org/10.5281/zenodo.16964139

Published by: vikaspatanker

Authors: Uchenna Evans-Anoruo

Abstract: The escalating complexity of healthcare delivery in the United States, coupled with increasing costs and demand for services, necessitates sophisticated analytical approaches to optimize system performance. This article presents a comprehensive framework for implementing data-driven decision-making in healthcare systems through the integration of operations research techniques and statistical modeling. By leveraging queuing theory, simulation modeling, and decision analysis, healthcare organizations can significantly improve resource allocation, patient flow management, and service delivery efficiency. The integration of advanced IT systems enables real-time data collection and analysis, supporting continuous optimization of healthcare operations. This research demonstrates how systematic application of these methodologies can address critical challenges in US healthcare delivery while maintaining quality standards and improving patient outcomes.

DOI: https://doi.org/10.5281/zenodo.16964206

 

Published by: vikaspatanker

Authors: Bhupesh Paliwal, Professor Amit Thakur

 

Abstract: A Mobile Ad hoc Network (MANET) is a dynamic wireless network that can be formed infrastructure less connections in which each node can act as a router. The nodes in MANET themselves are responsible for dynamically discovering other nodes to communicate. Although the ongoing trend is to adopt ad hoc networks for commercial uses due to their certain unique properties, the main challenge is the vulnerability to security attacks. In the presence of malicious nodes, one of the main challenges in MANET is to design the robust security solution that can protect MANET from various routing attacks. Different mechanisms have been proposed using various cryptographic techniques to countermeasure the routing attacks against MANET. As a result, attacks with malicious intent have been and will be devised to exploit these vulnerabilities and to cripple the MANET operations. Attack prevention measures, such as authentication and encryption, can be used as the first line of defense for reducing the possibilities of attacks. However, these mechanisms are not suitable for MANET resource constraints, i.e., limited bandwidth and battery power, because they introduce heavy traffic load to exchange and verifying keys. In this paper, we identify the existent security threats an ad hoc network faces, the security services required to be achieved and the countermeasures for attacks in routing protocols. To accomplish our goal, we have done literature survey in gathering information related to various types of attacks and solutions. Finally, we have identified the challenges and proposed solutions to overcome them. In our survey, we focus on the findings and related works from which to provide secure protocols for MANETs. However, in short, we can say that the complete security solution requires the prevention, detection and reaction mechanisms applied in MANET.

DOI: https://doi.org/10.5281/zenodo.16962628

 

Published by: vikaspatanker

Authors: Dr. Jyoti, Associate Professor, Ms. Jyoti

Abstract: The rapid expansion of the Internet of Things (IoT) has led to a massive increase in the number of connected devices, generating large volumes of heterogeneous data. Managing this data and ensuring efficient device performance requires advanced computing infrastructures. Cloud computing offers a scalable and cost-effective platform to support IoT ecosystems by providing storage, processing, and analytics capabilities on demand. This study explores the integration of IoT ecosystems with cloud computing to optimize IoT performance. It examines IoT architecture, communication protocols, and data management strategies while highlighting the role of cloud-based services in reducing latency, improving scalability, and enhancing security. The research also emphasizes performance optimization through edge computing, load balancing, and intelligent resource allocation. The findings suggest that a well-structured IoT-cloud integration can significantly improve system efficiency, reduce operational costs, and enable real-time decision-making, paving the way for smarter and more sustainable IoT deployments.This paper lays the foundation for this research by introducing the concepts of cloud computing, IoT ecosystems, and deep learning, while highlighting their interdependencies and potential for performance optimization. The paper also outlines the motivation behind this study, identifies key challenges, and presents the significance and contributions of the research.

Published by: vikaspatanker

Authors: Anand Kumar Yadav

Abstract: Fortified Toward those extreme vitality emergency and the expanding consciousness around the necessity for Ecological protection, the proficient utilization of renewable vitality need turn into a heated point. The virtual control plant (VPP) will be a compelling method for coordination conveyed vitality frameworks (DES) successfully deploying them to force grid dispatching or power exchanging. In this paper, those working mode of the VPP with infiltration from claiming wind power, sun based force vitality stockpiling may be investigated. Firstly, the grid-connection prerequisites about VPP as stated by the current wind Also sun based photovoltaic (PV) grid-connection requirements, broke down its productivity need aid analyzed. Secondly, under a few average situations gathered a affiliation toward oneself guide (SOM) grouping calculation utilizing those VPP’s yield data, An benefit streamlining model may be created as An guideline for those VPP’s ideal operation. In light of this model, case investigations are performed and the effects show that this model may be both practical furthermore viable.

Published by: vikaspatanker

Authors: Sushil Panda

Abstract: Autonomous vehicles and Electric Vehicles are the new definitions of modern vehicles. Centralised control over the vehicle and data-driven decision-making are the main features of these systems. User experience is the product, where vehicle and software combined, are the main selling features in the business world for an Automaker. Neural networks play a crucial role in the backend, providing real-time updates to the user about the vehicle's status. The current study focuses on analysing the importance of the User interface and experience, as well as the important characteristic features of an infotainment system. This paper also presents a classic scenario of neural networks in State of Charge (SoC) monitoring for an Electric Vehicle, integrating real-time results updates with the User Interface and suggesting the user/driver through the dashboard, thereby enhancing data-driven communication and decision-making through an infotainment system in an automobile

Published by: vikaspatanker

Authors: Sushil Panda

Abstract: CAN bus in software-defined vehicles is vital to enhancing the vehicle's performance, safety, and cybersecurity. The CAN bus is the digital nervous system of modern cars, handling the communication stream between all the Electronic Control Units (ECUs) of a Software Defined Vehicle. This research aims to provide a comprehensive security-aware framework for CAN bus data prediction using advanced temporal neural networks, which are designed for a cybersecurity-aware framework for SDVs. The paper proposes a new hybrid architecture that combines a Transformer-based attention mechanism with novel Graph Neural Networks (GNNs) to capture both temporal dependencies and network topology patterns in bus communications. The approach aims to address the challenges associated with high-frequency, complex time series data while ensuring compliance with ISO/SAE 21434 cybersecurity standards and ISO 26262 functional safety requirements. This is achieved by preserving privacy while simultaneously involving multiple vehicle training and capabilities for detecting real-time intrusion. This paper aims to implement a hybrid architecture with transformers and GNNs together on data using random functions in Python. The results thus obtained demonstrate a significant improvement in prediction accuracy (96.3%), cybersecurity threat detection (98.1% precision), and energy efficiency (34% reduction in computational overhead). The proposed framework achieved ASIL-C compliance and reduced false alarm rates by 31% compared to existing methods while maintaining sub-millisecond inference latency suitable for safety-critical automotive applications.

Published by: vikaspatanker