Background: The accelerated digital revolution in healthcare has greatly enhanced data management with electronic health records. Nonetheless, challenging issues of centralized control, privacy breaches, absence of patient ownership of their data, and inability to support decentralized scientific collaboration remain barriers to scalable healthcare research ecosystems. Recent developments in decentralized science (DeSci) create a paradigm shift, using blockchain, cryptographic primitives, and decentralized governance to facilitate transparent, trust-minimized, and collaborative biomedical research. This article provides a DeSci-friendly lightweight blockchain architecture that is used to support privacy-preserving and incentive-sensitive decentralized healthcare research infrastructure. Methods: The framework combines a permissioned blockchain with a lightweight hybrid consensus protocol, off-chain storage, and zero-knowledge proof-based authentication to permit secure and privacy-preserving access to data without revealing identity. Also, a tokenomics-based governance layer is proposed to support decentralized engagement, transparent policy implementation, and incentive-based research participation. The suggested system is tested in simulation with the following different network conditions and the key performance metrics such as latency, throughput, and computational cost. Results: Experiments prove that the suggested framework offers the following advantages:when compared to the current blockchain-based healthcare systems such as medical records, Fast Healthcare Interoperability Resources, and HealthChain. In addition, the framework goes past traditional data management by allowing a DeSci-oriented research life cycle, such as decentralized data contribution, validation, and provenance tracking. Conclusions: The proposed framework will help build scalable, secure, and patient-centered decentralized healthcare research ecosystems. Furthermore, the framework bridges the gap between blockchain-based healthcare systems and DeSci-driven research ecosystems.

Disruptions in distributed systems can cause widespread failures and downtime which costs the company and lowers productivity. A recovery and fault tolerance system is essential because distributed system's complexity, unpredictability, and inner workings exacerbate failures. Predictive analytics has emerged in fault management, helping firms to move from reactive to proactive fault management. In this research, we examine the achievements of intelligent fault prediction approach that employs Gated Recurrent Units (GRU), Temporal Convolutional Networks (TCN), and Long Short-Term Memory (LSTM) networks to improve fault tolerance in distributed systems. The GRU and LSTM models can describe temporal, sequential data for a distributed system and identify and comprehend data changes. By employing these designs and TCNs, companies may better recognize fault patterns that emerge over time, forecast future failures, and increase fault management efficiency. TCNs identify long-range time dependencies and allow parallel processing to swiftly discover and respond to defects in largescale settings using causal and dilated convolutions. This framework uses deep learning models to examine system log and resource consumption data to identify probable failure symptoms and accurately predict future problems. The experimental results show that combining GRU, LSTM, and TCN models improves fault prediction accuracy and reduces unexpected downtime by identifying faults quickly and taking preventative action. Additionally, since the framework continuously collects data from the distributed system and monitors the logged information in real time, users can make better decisions and implement proactive responses to failures, proving that predictive analytics driven by deep learning technology increases intelligent fault tolerance in distributed systems. With 95% accuracy, 93% precision, 95% recall, 94% F1-score, and 0.97 ROC-AUC, the GRU + LSTM + TCN model outperforms all single and dual-model configurations. With a +7% accuracy boost over GRU, +5% over LSTM, and +4% over TCN, multi-model temporal feature fusion is beneficial for fault prediction.

IIoT and cyber-physical systems transform industries through intelligent and adaptable automation. As connectivity increases, cybersecurity dangers escalate. Certain methods for ensuring safety are ineffective in decentralized industrial environments. This study examines how blockchain safeguards the transmission of IIoT and Industry 4.0 data, creates immutable records, and regulates access via smart contracts. We examine blockchain for device authentication, data integrity, and decentralized access management. The paper provides practical examples of how blockchain may enhance transparency, trustworthiness, and resilience in many sectors.

Fault tolerance is crucial to distributed systems to remain reliable and to mitigate unanticipated loss of services. Through predictive analytics we are able to identify and anticipate underlying faults enabling us to intervene and take appropriate steps to ensure continuity of services. The goal of this initial research was to introduce a new predictive fault tolerance method that exploits Logistic Regression (LR) and Support Vector Machine (SVM) models. Our approach developed predictive models to analyze logs, performance data, and environmental factors which include resource utilization and network latency to identify advance warning signs of instability. The LR model gives you the probability of failure which represents a form of risk assessment and the SVM provides a limiting factor in operational stability and potential failure. To illustrate our approach, we built two distinct systems that operated within a simulated distributed environment and both models offered realistic predictive accuracy. The combinations of the two techniques are significant: LR provides a transparent model of potential failure and SVM guarantees an accurate definition of faulty. With predictive fault tolerance, we give back some fault mitigation planning to distributed systems, enabling that systems can remediate faults proactively and build resilience to ensure uninterrupted operations. These techniques will be especially relevant when scaling up to large data centers, traditional cloud environments, or to critical infrastructure where very short amounts of downtime can have severe consequences..

Advancement of artificial intelligence or machine learning, deep learning technology has great impact on the healthcare system; it revolutionized the entire operations of healthcare, like patient care, diagnostic system, treatment approach, and patient caring approach. But the prime concern of integration of machine learning model with healthcare is the security. Healthcare system faced the security threats, after the integration with the machine learning technology. In this article, the detailed and critical insights of security concerns are discussed. Security is the paramount concern, as in healthcare the sensitive healthcare data are used. Sometime, the vulnerability of machine learning model is adversely affecting the security threats, compromising the patient privacy and integrity in the diagnostic procedure or in the patient care. Ethically the patient record is sensitive, and the system safeguards the record and sensitized the security and privacy concern of the safeguarding of the patient data. However the robust machine learning models come across with the solution to give the better interoperability and low biasness in the result. Interpretability of machine learning predicts it equally important in the healthcare to gain the trust of the healthcare professional. This article has various ways of making medical care-related ML models safer and powerful. In medical services, security dangers and model constancy are tended through methodologies like combined learning, differential protection, and reasonable models. This study investigates possible assaults on medical services frameworks, orders these assaults, and inspects different structures used to survey security and protection issues. Furthermore, it assesses the benefits and drawbacks of various strategies pointed toward further developing security and protection in medical services settings. This examination talks about the difficulties confronted while utilizing AI (ML) in medical services and proposes likely regions for future exploration in security and protection inside this field. It centers around tending to information protection and classification issues, and furthermore looks at the datasets and apparatuses utilized in medical services frameworks.

In distributed and scalable systems including cloud computing, Hadoop, spark, and large-scale computing environments, fault tolerance is an important characteristic. During a system failure, the computing system will not be interrupted, systems continue to operate. Machine learning offers several types of training algorithms that also possess self-correcting. In this chapter, the first distributed computing framework and various approaches for fault tolerance are discussed. The next part of the chapter focuses on the various machine-learning approaches used in distributed systems for fault detection and correction. We aim to discuss various challenges and issues in the instances of distributed system failure and also focus on how the distributed system detects all the issues automatically and corrects them, without disturbing the computing.

Due to price volatility and multifactor, stock price prediction is difficult in financial markets. This paper explores the use of multivalued regression models for stock price forecasting, with a particular focus on improving prediction accuracy through the application of various data normalization techniques. Normalization plays a crucial role in machine learning by ensuring that different features are on a comparable scale, which can enhance model convergence and generalization. In this study, we employ multivalued regression as the primary forecasting method, as it offers flexibility in handling multiple continuous outputs. Min-Max scaling, Z-score normalization, and robust scaling are tested for model performance. Hyper parameter tweaking optimizes regression models to minimize prediction errors across numerous stock datasets. We optimize the regression models using hyper parameter tuning, aiming to minimize prediction errors across multiple stock datasets. Through comprehensive experimentation, we demonstrate that the choice of normalization technique significantly affects the prediction accuracy of multivalued regression models. Our findings reveal that specific normalization methods can improve model performance by reducing over fitting and improving the model's ability to generalize to unseen data. The results highlight the importance of selecting appropriate data preprocessing methods to achieve reliable and accurate stock price forecasts. This research contributes to the growing field of financial machine learning by offering insights into how normalization techniques can enhance stock price prediction when applied to multivalued regression models. The study’s findings could help financial analysts, traders, and researchers develop more robust predictive models for complex market conditions.

The methodology of component-based software development, or CBSD, depends heavily on the reliability of its components. The reliability assessment of software components is currently the most common and significant problem in CBSS. The components chosen for integration from a variety of comparable functionally qualified components offered by multiple service providers in the market play an essential role in the reliability of the CBSS. As a result, the most reliable component must be chosen while considering the users’ business needs and budget. To estimate the reliability of software components, this study uses an alternative method known as an information entropy weight (IEW) fuzzy comprehensive evaluation model (FCEM) to rank the components based on their performance index. A case study is discussed to validate the results, and IEW FCEM is compared with fuzzy MOORA, fuzzy TOPSIS, CoCoSo, and FCEM-MULTIMOORA-FG methods. According to the results, components A8, or “Devices,” will significantly influence estimating the system’s overall reliability. On the other hand, option A2, which refers to the “Server” component, would have the least. The simulation results demonstrate that the suggested approach has better position accuracy than previous algorithms and is easier to implement in a computer system due to its simple and logical basic idea and computational simplicity.

Germin-like proteins (GLPs) play an important role against various stresses. Vitis vinifera L. genome contains 7 GLPs; many of them are functionally unexplored. However, the computational analysis may provide important new insight into their function. Currently, physicochemical properties, subcellular localization, domain architectures, 3D structures, N-glycosylation & phosphorylation sites, and phylogeney of the VvGLPs were investigated using the latest computational tools. Their functions were predicted using the Search tool for the retrieval of interacting genes/proteins (STRING) and Blast2Go servers. Most of the VvGLPs were extracellular (43%) in nature but also showed periplasmic (29%), plasma membrane (14%), and mitochondrial- or chloroplast-specific (14%) expression. The functional analysis predicted unique enzymatic activities for these proteins including terpene synthase, isoprenoid synthase, lipoxygenase, phosphate permease, receptor kinase, and hydrolases generally mediated by Mn+ cation. VvGLPs showed similarity in the overall structure, shape, and position of the cupin domain. Functionally, VvGLPs control and regulate the production of secondary metabolites to cope with various stresses. Phylogenetically VvGLP1, -3, -4, -5, and VvGLP7 showed greater similarity due to duplication while VvGLP2 and VvGLP6 revealed a distant relationship. Promoter analysis revealed the presence of diverse cis-regulatory elements among which CAAT box, MYB, MYC, unnamed-4 were common to all of them. The analysis will help to utilize VvGLPs and their promoters in future food programs by developing resistant cultivars against various biotic (Erysiphe necator and in Powdery Mildew etc.) and abiotic (Salt, drought, heat, dehydration, etc.) stresses.

The correlation between the artificial intelligence and electrical energy has revolutionized the industry landscape by providing the good solution and enhanced automation, efficiency, sustainability, throughput. This article going to explore the plenty application of artificial intelligence in the field of electrical energy, electrical energy automation powered by artificial intelligence for real-time data analysis, predictive algorithm, and machine learning approach for optimization of various aspect of electrical energy utilization and production. Predictive maintenance techniques allow industries to preemptively identify faults and issues in electrical equipment, minimizing unplanned downtimes, and reducing maintenance costs. Artificial intelligence-based grid management system justify the efficient distribution of electrical energy supply and demand, and it is also ensuring the smart grid implementation and distribution of balance electrical load across the grid. Artificial intelligence system also plays the significant role for the integration of renewable energy, like wind energy and solar energy into the grid, optimizing their output by forecasting of generation-based weather condition the AI system also ensuring the energy storage capacity optimization charged and discharged, extending the better storage life and enabling seamless integration of renewable energy source. Electrical industry also benefited by the artificial intelligence system, in the context of demand and supply module of AI, demand and supply of AI, allowing for real-time modifications in energy consumption during peak demand times, contributing to grid reliability. Additionally the AIs are also use in load forecasting and enable the industries to expect electricity demand, thereby optimizing energy procurement and reducing costs. In the context of energy efficiency, the AI-based system continuously monitor the regulate consumption of energy in the building and manufacturing the energy and minimizing the energy wastage. The energy grid system also strengthens by the AI system, to detect and response of cyber threats. Ensuring the integrity of electrical energy systems, micro-grid can also manage and respond by the AI system. Improving resilience and sustainability, particularly in remote or off-grid locations. The application of AI extends to energy trading markets, where algorithms analyze vast datasets and make real-time decisions, enhancing the efficiency of electricity trading.

The limited energy and transmission capacities of wireless sensor networks and MANET present serious routing issues. Two energy-efficient position-based routing algorithms, Energy-efficient DREAM convergence and Energy-efficient LAR Coordinate routing, have been proposed in response to these issues. The development of these algorithms is based on the concepts of Location-Aided Routing (LAR) and Distance Routing Effect Algorithm for Mobility (DREAM). To successfully reduce routing overhead, our suggested algorithms make use of strategies like "compass routing" and "most forward within a specified radius." Increasing the overall network lifetime of Mobile Ad-hoc Networks (MANETs) is the main objective, with a special emphasis on sensor networks and MANET. We have rigorously experimented to prove our approach's effectiveness. The findings show a significant decrease in the number of hops needed between the source and the destination for different convergence angles. This shows that, in the context of position-based routing, energy usage in MANET nodes during data transmission has been successfully minimized. Our suggested method introduces energy-efficient algorithms that improve routing and lengthen network lifespan, thereby addressing the difficulties presented by energy and transmission limits in wireless sensor networks and MANET. The experimental findings demonstrate how well our method works in lowering hop counts and decreasing energy loss in MANET nodes while transmitting data.

Due to rapidly growing Internet facilities, intruders can steal and misuse the data saved and stored digitally. In this case, securing digital data is challenging but prominent for various purposes. However, the traditional techniques are insufficient to secure these computer networks and cloud information with a 100% success rate. Recently, machine- or deep-learning-enabled methods have been used to secure network information, but with some limits. Therefore, the study emphasizes detecting and classifying network intrusion using the proposed ensemble and deep learning models. In this case, we developed the ensemble learning-enabled random forest algorithm and deep learning-enabled deep convolutional neural network (CNN) models for securing near real-time cloud information and designed the intrusion detection system accordingly. The complex and high-volume CSE-CICIDS2018 datasets were used to test the developed model in Python programming language implemented with several Python libraries. The outcome of the proposed models indicates that the developed models are promising in securing the cloud information with 97.73% and 99.91% accuracies via ensemble-random forest and deep CNN models. Thus, the present study models can be applied to other real-time datasets and computer networks to detect cyber threats effectively.

In the era of cloud computing and large-scale distributed systems, ensuring uninterrupted service and operational reliability is crucial. Conventional fault tolerance techniques usually take a reactive approach, addressing problems only after they arise. This can result in performance deterioration and downtime. With predictive machine learning models, this research offers a proactive approach to fault tolerance for distributed systems, preventing significant failures before they arise. Our research focuses on combining cutting-edge machine learning algorithms with real-time analysis of massive streams of operational data to predict abnormalities in the system and possible breakdowns. We employ supervised learning algorithms such as Random Forests and Gradient Boosting to predict faults with high accuracy. The predictive models are trained on historical data, capturing intricate patterns and correlations that precede system faults. Early defect detection made possible by this proactive approach enables preventative remedial measures to be taken, reducing downtime and preserving system integrity. To validate our approach, we designed and implemented a fault prediction framework within a simulated distributed system environment that mirrors contemporary cloud architectures. Our experiments demonstrate that the predictive models can successfully forecast a wide range of faults, from hardware failures to network disruptions, with significant lead time, providing a critical window for implementing preventive measures. Additionally, we assessed the impact of these pre-emptive actions on overall system performance, highlighting improved reliability and a reduction in mean time to recovery (MTTR). We also analyse the scalability and adaptability of our proposed solution within diverse and dynamic distributed environments. Through seamless integration with existing monitoring and management tools, our framework significantly enhances fault tolerance capabilities without requiring extensive restructuring of current systems. This work introduces a proactive approach to fault tolerance in distributed systems using predictive machine learning models. Unlike traditional reactive methods that respond to failures after they occur, this work focuses on anticipating faults before they happen.

Decentralization, auditability, smart execution, and security are four ways that blockchain technology (BCT) differs from current cutting-edge technologies based on client-server architecture. Without the need of any middlemen, blockchain technology builds trust between untrustworthy parties. By employing its distinctive properties, blockchain technology is presently used to address the problems of enterprise distributed applications (EDAs) to some extent. As a result, businesses involved in a wide range of industries have shown interest in it. Despite being praised as tool for businesses to create secure applications, BCT is still not widely used. The objective of the current study is to use an extension of the technology acceptance model (TAM2), constituted by 15 hypotheses (H1–H15), to address the factors that influence professionals' desire to adopt the BCT in the EDAs. In order to achieve the research objective, the study consists of a quantitative non-experimental correlational method with the goal of creating an empirical model to evaluate the relationship between perceived usefulness, perceived ease of use, scalability, effort, performance, adaptability, maintainability, experience, and blockchain adoption in India with a focus on EDAs. Descriptive analysis, discriminant analysis, multiple linear regression, ANOVA, homoscedasticity, multicollinearity, reliability, linearity, survey question's normality, and independent errors are conducted to analyze survey data from a sample of 396 IT professionals from various firms in India. The findings show that IT professionals' desire to employ the BCT in EDAs are positively impacted by all the hypothesis except H3 and H8 that has no impact on IT professionals' desire to employ BCT.

Blockchain technology-powered applications infuse trust in the system without intermediary entities. Researchers’ interest in blockchain technology has increased dramatically in recent years as a result of this distinguishing feature. However, the adoption of this novel paradigm in enterprise distributed applications is not very encouraging. To adopt a new technology in an industry, managers and technocrats have to do multiple-criteria decision-making (MCDM) in a fuzzy environment. The aim of this study is to propose a system model for the identification and monitoring of significant factors responsible for the slow adoption rate of blockchain technology. In this research, the MULTIMOORA method for group decision-making, a popular MCDM approach, has been further extended by integrating the information entropy weight–fuzzy comprehensive evaluation model (IEW-FCEM) for an uncertain environment. The proposed method of FCEM-MULTIMOORA-FG combines the benefits of four best-in-class ranking methods, namely, the fuzzy ratio system, the fuzzy reference point method, the fuzzy full multiplicative form, and the IEW-FCEM. The idea behind integrating the IEW-FCEM with MULTIMOORA-FG is that information entropy will derive the objective weights of the criteria, thus removing the dependency upon subject matter expert experience only. An empirical study demonstrates the efficacy and practicability of the FCEM-MULTIMOORA-FG method. The simulation results demonstrate that the proposed method is computationally straightforward with better position accuracy than previous algorithms and that its basic idea is logical and understandable, making it easier to apply in a computer system. Additionally, a comparative analysis with five more MCDM methods was executed to validate the results.

This research paper aims to provide a comprehensive review of the security measures and best practices specifically tailored for Salesforce implementations. By delving into the intricacies of Salesforce's security capabilities and exploring advanced features, this paper intends to equip organizations and Salesforce administrators with the knowledge and tools necessary to establish robust security protocols and mitigate potential risks.

The use of the Internet is enhanced drastically in the current era, which connects multiple computers in a network and a group of devices. In addition, every sector uses the Internet to communicate and send data digitally. However, the Internet is affected due to unwanted activities and cyber-attacks by attackers. Hence, intrusion detection systems have recently been used to detect incoming attacks. Therefore, the present study has designed and developed the intrusion detection scheme for cloud computing through ensemble learning and a feature selection approach. The proposed system is tested on NSL-KDD datasets. The critical features were selected from the dataset, and dimensionality was reduced using feature selection methods. The ensemble learning approach combined the single process to generate the robust way and successfully confirmed with high accuracy and negligible error rate. Two machine learning methods, such as decision tree and Naïve Bayes, have been used in training the ensemble learning models. The overall accuracy was 90 and 99