In recent years, Vehicle-to-Vehicle (V2V) communication has gained significant traction in the automotive industry due to its ability to monitor key metrics such as vehicle speed, proximity to nearby vehicles, and road conditions in real time. This technology greatly enhances road safety and traffic management by enabling continuous information exchange between vehicles. However, conventional systems often face challenges when monitoring road safety and traffic flow in dense urban environments. To overcome these limitations, this study proposes a novel autonomous vehicle application security framework that integrates quantum cryptography with cloud-based networks, supported by noise deciphering through a machine learning approach. The framework draws on three types of input data sources, each containing distinct attack types, to monitor and analyze the autonomous vehicle network for malicious activity. Authentication is carried out using a convolutional federated quantum key encryption algorithm within the cloud environment. To handle cloud network noise, the system employs a fast Fourier Gaussian encoder model. By combining historical and real-time behavioral data, the system evaluates the reliability of traffic data and network nodes, enabling accurate anomaly detection. Experimental evaluations were conducted using multiple autonomous vehicle security datasets, assessing metrics such as detection accuracy, noise ratio, average precision, Quality of Service (QoS), and data integrity. The proposed method achieved 90% average precision, 89% data integrity, 95% QoS, 96% detection accuracy, and a 65% noise ratio. These findings demonstrate that the proposed framework delivers enhanced security for V2V applications compared to existing solutions.

Cloud computing is a dynamic technology that requires efficient resource allocation strategies, and the task scheduling is optimized in heterogeneous cloud environments. The virtualization technology is largely responsible for the popularity of the cloud. During peak load periods, due to resource scarcity, some tasks are migrated to other data centers to achieve balance. To tackle this challenge, a novel method is proposed such as the genetic water evaporation optimization (GWEO) algorithm to perform an effective resource allocation in diverse cloud infrastructures. In order to reduce task execution time, the GWEO is associated with genetic algorithms and water evaporation optimization algorithm that maximize resource allocation. The scalability and adaptability of novel GWEO were explored through experiments involving larger-scale cloud deployments, showcasing its efficacy in handling complex scheduling tasks in real-world cloud environments. The promising results indicate its potential to significantly enhance performance and scalability in diverse cloud computing environments, addressing critical challenges associated with resource optimization and task scheduling.

On-demand, automatic resource delivery in a transparent manner to users is a remarkable feature offered by the cloud computing environment. User demands are met by dynamically provisioning the cloud resources. Incidental failures during task execution in cloud could be attributed to a variety of reasons. Such failures bring down the cloud performance. Recently, a variety of intelligent task scheduling algorithms have been demonstrated to address several issues in cloud scheduling. Most of these algorithms neglect the fault tolerance criterion, which if addressed appropriately could contribute to better cloud performance. In this research, we had proposed a Dynamic Clustering Cuckoo Whale Optimization Algorithm (DCCWOA) for carrying out efficient scheduling in the cloud by paying equal attention to the fault tolerance parameter. The proposed fault tolerance aware algorithm addresses the scheduling of tasks by maintaining a tab on the currently available resources such that unfortunate failures of autonomous tasks get effectively addressed leading to reduced failures. The performance of the proposed fault tolerance aware DCCWOA has been compared with Ant Colony Optimization algorithm (ACO), Genetic Algorithm (GA) and League Championship Algorithm (LCA)with respect to makespan, failure ratio and failure slowdown parameters under three different scenarios, where in each scenario the number of tasks were appropriately varied. It has been found that the proposed DCCWOA had produced an improvement of 58.19%, 19.88% and 29.32% under scenario 1 for makespan, failure ratio and failure slowdown parameters respectively when compared to ACO, GA and LCA algorithms respectively. Detailed experimental results for scenarios 1, 2 and 3 had been presented in the results section of this article. Results obtained prove the efficacy of the proposed algorithm in overcoming the faults and increasing the scheduling performance of the cloud with respect to the failure rate.

An enriched computational platform has been unfolded with the introduction of cloud technology offering ensemble services to users that includes storage, database and processing power.More recently, the cloud technology has been upgraded to a federated environment that offers even more features where various service providers could interconnect for providing an integrated service in a transparent way to cloud users.Applications that demand enormous computing resources like for instance bioinformatics workflow applications could very well make use of the abundant cloud resources for effective execution.Fine tuning the task scheduling activity in cloud could further boost the overall cloud performance.In this paper, we had designed an optimal and ideal task scheduling algorithm that primarily focuses on reducing the cost and makespan QoS parameters, eventually leading to enhanced cloud performance.The proposed algorithm, which is a meta-heuristic enhanced hybrid version named, grey wolf optimizer cuckoo (GWOC) is formally designed from the existing grey wolf optimizer and cuckoo search algorithms.results obtained clearly justify the goal accomplishment of the proposed GWOC algorithm and its swiftness in achieving convergence, thereby clearly outperforming existing contemporaries like gravitational search algorithm (GSA), whale optimization algorithm (WOA) algorithm and grey wolf optimizer (GWO) algorithm.The proposed GWOC technique had produced an improvement of 2.11%, 3.5% and 5.17% for makespan and had reduced the cost to the tune of 7.71%, 11.3%, and 15.4% when compared with gravitational search algorithm (GSA), whale optimization algorithm (WOA) algorithm and grey wolf optimizer (GWO) algorithm respectively when used with 100 VMs.Detailed results have been presented in section 5.

Conventional loan avenues generally focus more on the formal sector than the unbanked sector. A peer to-peer (p2p) lending platform built on blockchain can help bridge the gap between potential lenders and borrowers in need of money in a secure and decentralized environment. The Ethereum blockchain allows for the creation of smart contracts to perform actions in the network by setting logic rules and conditions thereby removing the need for middlemen and can be inclusive of the unbanked sector. The p2p platform introduces swarm learning for credit scoring, which is a novel methodology that utilizes smart contracts to train decentralized machine learning models. Each training round happens on the local device with the user data, which then exchanges the training parameters and weights to the machine learning model maintained in the smart contract. This allows for preserving the privacy of the user data by ensuring the data never leaves the device but only the inference does. Upon analyzing the user's behavior, a statistical credit score is assessed for validating the chances of the user to default his/her loan repayment. The performance of the proposed model that has been trained using the swarm learning technique is close to the model that had been trained in a centralized environment while overcoming the drawbacks of federated learning by incorporating blockchain and swarm methodology.

Abstract The growth of cloud computing is astounding in the business and research domains in the last decade. The popularity of cloud could be attributed to the virtualization technology. To achieve balance and due to resource scarcity during peak load period, a few of those tasks are migrated to other datacenters. The potential of cloud computing can be harvested to its fullest by employing efficient task scheduling techniques. In cloud, focus is on makespan and maximum system utilization phenomenon owing to which tasks may be scheduled on different virtual machines. Meta-heuristic scheduling algorithms could be employed to provide solution to such issues since task scheduling is a NP-hard problem. In this proposed research work, a integration of Genetic Water Evaporation Optimization Algorithm (GWEO) had been presented for efficiently scheduling of tasks on a heterogeneous cloud environment. The proposed research work objective is to minimize the time of task execution, cost and energy consumed by the resources during task execution. The proposed hybrid GWEO algorithm is hybridization of Genetic Algorithm (GA) and Water Evaporation Optimization Algorithm (WEO). Different datasets had been employed for evaluating the proposed GWEO algorithm. The proposed hybrid technique performance was evolved for the metrics cost, energy and execution time using CloudSim toolkit. The experimental results obtained through simulation had been compared with other algorithms, which showed that the proposed GWEO technique achieve a significant improvement in the QoS metrics (cost, energy consumption and execution time).

Cloud computing has garnered unprecedented growth in recent years in the field of Information Technology. It has emerged as a high-performance computing option owing to its infrastructure that comprises of heterogeneous collection of autonomous computers and adaptable network architecture. The tasks that are scheduled in an optimized manner for their execution could be classified under NP-hard problems. Though meta-heuristic scheduling algorithms emerge as scheduling options, they need to be much more consistent while dealing with the dynamic set up of the cloud environment. In this paper, we had proposed a multi-objective meta-heuristic scheduling algorithm namely Quasi Oppositional Genetic Spotted Hyena Optimization (QOGSHO) algorithm that globally optimizes the makespan, resource consumption and SLA violation QoS parameters, thereby improving the performance. The algorithm proposed is an amalgamated product of meta-heuristic algorithms like Quasi Oppositional Based Learning (QOBL), Spotted Hyena Optimization (SHO), and Genetic Algorithm (GA). The performance efficiency of the proposed QOGSHO algorithm had been compared with various scheduling algorithms using uniform datasets by varying the data instance sizes in a simulated cloud environment. The obtained results clearly justify the task scheduling efficiency of the proposed algorithm with respect to the QoS parameters namely makespan, resource utilization and SLA violation.

A cloud computing system typically comprises of a huge number of interconnected servers that are organized in a datacentre. Such servers dynamically cater to the on-demand requests put forward by the clients seeking solutions to their applications through an interface. The scheduling activity concerned with scientific applications is designated under the NP hard problem category since they make use of heterogeneous resources of dynamic capabilities. Recently cloud computing researchers had developed numerous meta-heuristic approaches for providing solutions to the challenges arising in the task scheduling activities. Scheduling of tasks poses a major concern in cloud computing environment. This decreases the efficiency of the system considerably, if not handled properly. Hence, an improvised task scheduling algorithm that enhances the performance of the cloud is needed. There are two factors that affect the cloud environment: service quality and energy usage. To increase the performance in above suggested factors (memory, makespan and energy efficiency), an efficient hybridized algorithm, obtained by integrating the Cuckoo Search Algorithm (CSA) and Whale Optimization Algorithm (WOA), called the CWOA had been proposed in this work. The performance of our proposed CWOA algorithm had been compared with Ant Colony Optimization, CSA and WOA and it was found to produce an improvement of 5.62%, 4.36% and 2.27% with respect to makespan, 16.36%, 19.19% and 13.13% with respect to memory utilization and 19.08%, 19.34% and 16.75% with respect to energy consumption parameters, respectively. Comprehensive results have been tabulated in the result section of this article.

Cloud Computing provides a working environment where multiple services are used by customers through the internet. It arises as a contemporary platform for providing high performance computing environment and delivery of on-demand computing resources. Task scheduling acts as an important factor in a cloud environment. Scheduling tasks improves efficient utilization of resources and reduces task completion time. It analyses the resources and assigns tasks at a particular time instance. Various techniques were introduced to solve the issues involved in task scheduling. This paper illustrates the learning of scheduling processes that are used in clouds.

The advent of the Internet of Things (IoT) has, to a great extent, changed the day-to-day activities of the contemporary world. The traits of IoT such as connectivity, sensing and lively commitment have made it an inevitable technology to reckon with. Technological evolution in the field of the wireless sensor network supports the sensors and actuators to connect to the endpoints via the Internet gateways, forming a unified network. Devices present in such a network share the information by utilizing the Internet without any hitches. Based on the information exchanged, the endpoint systems may initiate appropriate actions, which may vary depending upon the context of the application domain. The majority of IoT devices have inherent restrictions with respect to computation, storage and network scalability, making them more vulnerable to various attacks. They can be easily negotiated and slashed. Data transferred between the devices should be secure. Security lapses during data transfer may result in data tampering, data theft and attacks on the entire network. Privacy refers to safeguarding the information of the devices from being exposed onto the network. Each and every device connected to the network is provided with a unique identifier which will be utilized during data transfer. Whenever the patchy data from multiple devices are collected and analyzed, it can result in the exposure of the critical data. Device spoofing, masquerade attack, dishonest authentication and lack of trustworthiness in data exchange are among the most noticeable obstacles in the IoT network. Hence it becomes necessary to overcome the above-mentioned technical hitches with the utmost care. A technique based on the dissemination and replication of the digital record of the exchanged information known as Blockchain addresses these issues. A Blockchain is a distributed database which records all the managed transactions in the order of their occurrence in a format that is not easy for any adversary to tamper with. Blockchain consists of three essential notions, namely blocks, nodes and miners. Miners construct the fresh blocks and each block comprises of three entities, namely data, nonce and hash. The devices in the network form the nodes. Every active node present in the network maintains a copy of the Blockchain. All the active nodes of the network share the saved ledger, which is computationally very much impossible to tamper. For a freshly mined block to be included into the chain, it should be approved algorithmically by the network. By incorporating the framework offered by Blockchain into the IoT-based systems, the security and privacy issues are all addressed with ease.

AI based Facial recognition system has a number of applications in the area of biometric for authenticating a person, smart card identification, AI driven surveillance camera to identify criminals, health sectors, public security system to recognize suspected persons and as well as criminals in society and security mechanism in industry is also based on facial recognition system to identify their employees. Images used in Facial recognition system especially in real scenario have low resolution pictures taken under dark background with inadequate illumination, blurred images taken from low end cameras which has poor pixel quality. It is a cumbersome process to detect the face of a person exactly from inadequate information provided. To obtain precise output, huge amount of input data is required for training the neural network. This paper presents a comprehensive review on facial recognition system for improving improper, low quality and low light images by applying Artificial Intelligence based image and video analysis technique called Deep Convolutional Generative Adversarial Neural Network (DCGAN). DCGAN is commonly applied when the datasets are insufficient for training the neural network. The images to be detected under environment with poor illumination, due to climatic changes or due to capturing low resolution images using low quality cameras. Description regarding training and testing various datasets extracted from several freely available sources has been provided. The enactment of each model is considered and compared with other state-of-art models with respect to accuracy, complexity and execution time.

The Deep Neural Networks have gained prominence in the biomedical domain, becoming the most commonly used networks after machine learning technology. Mammograms can be used to detect breast cancers with high precision with the help of Convolutional Neural Network (CNN) which is deep learning technology. An exhaustive labeled data is required to train the CNN from scratch. This can be overcome by deploying Generative Adversarial Network (GAN) which comparatively needs lesser training data during a mammogram screening. In the proposed study, the application of GANs in estimating breast density, high-resolution mammogram synthesis for clustered microcalcification analysis, effective segmentation of breast tumor, analysis of the shape of breast tumor, extraction of features and augmentation of the image during mammogram classification have been extensively reviewed.

Techniques predicting the type of diseases affecting plants in their lifetime will be of immense help to agriculturists. This article throws light upon such techniques in the form of a survey that had been carried out comprehensively covering various image based plant leaf diseases. Such diseases are mostly grievous and they strike at any part of the plant. There are huge accumulated losses due to such diseases that bring down the productivity and increase the economic losses in the agricultural industry. Agriculture industry needs to sustain and evolve from such obstacles to be highly profitable. This can be done by precisely monitoring the health and detecting the diseases at appropriate stages of the plant's life time. Technology has spread its wings in every field of day to day life but still its reach in the field of agriculture is not up to the mark. Agriculture industry is still thriving on outdated technical methodologies. Improper diagnosis of plant disease may lead to huge losses in terms of production, time, cost and product quality. The condition of the plant needs to be tracked throughout its growing stages leading to successful cultivation. As part of technological innovation, researchers had been applying the image processing techniques for monitoring as well as diagnosing the plant diseases in its various stages. Appropriate machine learning algorithms are being designed and applied for precisely identifying the various infections on plants throughout its life cycle and the type of treatment that can be afforded for overcoming loss.

Wireless Sensor Networks have found their reach in various domains that includes defense, medicine and environmental monitoring. The network is formed by a vast collection of sensor nodes which are stationed separately from one another. The information gauged by the sensors needs to be conveyed to the sink node so as to take the obligatory steps. Routing of the compiled information from the source node to any specific sink node, attaining minimal power consumption and minimizing the presence of congestion are some of the issues encountered in wireless sensor networks. This paper throws light upon a few of the routing techniques engaged in the network for the transmitting the sensed information.

Cloud computing, with its huge potential has started evolving as a new age technology. The varied applications of cloud that includes QoS, Charging based on usage, virtualization, offering self-services that are in demand, elasticity etc. make it a viable option for businesses in today’s IT industry. Allocating the optimal task over the available set of resources is termed to be task scheduling. The task scheduling must be done effectively for the sake of maximizing the usage of cloud computing. For this purpose various task scheduling strategies have been adopted. In this paper, a systematic survey on various task scheduling approaches in cloud computing has been carried out and the same has been presented herewith.

Cloud computing is considered to be a predominant technology in the course of events occurring and has an enchanting contribution in software and hardware setup. In cloud environment the performance improvement is highly dependent on features like load balancing and task scheduling. The major issue in cloud computing is task scheduling which leads to reduction in the performance of the system. Efficient resource scheduling algorithm is required in order to resolve this low performance issue. Through which the clients and users can demand services based on pay-as-you-go basis. There are numerous algorithms proposed especially for explaining load balancing and task scheduling. Since cloud infrastructure is based on huge client's requirement, appropriate decision is required for each and every scheduled job. This paper illustrates a detailed study on huge algorithms which are explained to resolve the common issues taking place in various scheduling of resources.

Online transaction systems require a high level of consistency and availability for it to perform well for the end use. Though there are tools like google analytics, which are more towards click streams, but very less focus has been given on tracing the critical events happening in ecommerce space. Business like online commerce or e-commerce require excellent fault tolerant mechanism for improved customer retention and increase profitability. The online events which captures the user behavior helps to understand the end customers spending patterns on the given site. Capturing of user behavior will be essential for profiling the customers into different categories based upon which they can be given preference to complete an online-transaction in the event of a fault. There are various access violations occurring at multiple interaction levels exist in order to complete a successful transaction in the web application. The constant demands for increased performance from the end-users are the rationale behind such an implementation. This paper focuses on implementation of fault tolerance event transactions in online e-commerce solution actor based approach to ensure better the user experience in the case of any faults during an online e-commerce events or transactions.

Users use the web for accessing all type of real time information. The user generates the request with required parameters that are verified at the remote end thereby allowing access to all type of resources. Such resources are extracted from more than one page. A user's interaction over a web page will differ from another with respect to the access level. The users may be classified based on the access level as basic, normal and advanced. A user committing a fault in an online transaction may face problems in successfully completing the transaction. The user session is maintained based on the access level with fault tolerance technique. The flow of the session is allotted based on the user access level only. The basic user cannot continue the session flow further, upon committing a fault, because this type of user never completes the transaction successfully. The normal user continues the session until he reaches the threshold level where as the advanced user always get a proper session flow to complete his online transaction. The main objective of the proposed work is to control the session flow based on the user access level in conjunction with fault committed by them. The session flow is properly assigned to the user who actually completes the online transaction with necessary information in a successful manner.

Nowadays the customer demand for accessing a web ba sed application has grown enormously as everything is available in the Internet. Sensitive application providers retain their resources in safe from unau thorized access by using single signon technique. In this te chnique if a user gives an irrelevant information i n a particular session, he may be asked to continue the session by using sign on technique once again irre spective of whether the user is a sensitive user. This paper proposes a new strategy which classifies the sensi tive user and allows him to continue the session even if the user does a mistake (fault) that could be tolerated to some level. The proposed method focuses on the fault ide ntification and classification in order to keep the sensitive user for assigning some tolerance level for accessi ng the web application. The users are classified ba sed on the access level by setting the tolerance level for the type of fault identified. An efficient algorit hm is proposed for handling the fault tolerance in the we b application more efficiently. In future the fault tolerance can be extended by AI based technique with multi-le vel security for improving the performance over onl ine transaction.