Cloud tasks are scheduled to the respective VM for execution. Scheduling process selects the resources and allocates the requesting task to them. The resources are selected in advance and then the request is forwarded for processing of tasks. It suffers the overestimation problem which means that the requested task size is less than the allocated resource level. Various scheduling problems are addressed but still the problem arises during the resource allocation. Auto scaling process is implemented in the cloud which allocates the resource based on the demand. The proposed model uses the dynamic method of cloud allocation and provisioning based on the workload level and resource level. Priority queue is implemented prior to the provisioning process for ordering the resource in specific order. The main aim of the proposed method is to allocate the resources using dynamic priority manner. The efficiency is achieved at maximum level by selecting and allocating the workload.

Resource management is a vital process in the cloud for satisfying the customer requirement. Resources get the task from the user and perform necessary action. The task needs the data which are collected from various environments. The existing systems are not concentrating on the data but it maps the request to the resources. Resource level management provides the service response to the user. It suffers the data related issues, so it is solved by incorporate the efficient machine learning over the cloud. The proposed model classifies the dataset based on the workload condition namely GPU and CPU level. The model also developed related to the workload. The resources from the cloud are provisioning and allocate to the specific region with necessary parameters. Dynamic load assignment helps to the user for keeping the cost in their acceptable level. Various machine and deep learning models have been analysed related to workload parameters. It achieves high efficient resource monitoring in order to handle faulty resource and make then to active level.

Cloud Computing provides various services to the customer in a flexible and reliable manner.Virtual Machines (VM) are created from physical resources of the data center for handling huge number of requests as a task.These tasks are executed in the VM at the data center which needs excess hosts for satisfying the customer request.The VM migration solves this problem by migrating the VM from one host to another host and makes the resources available at any time.This process is carried out based on various algorithms which follow a predefined capacity of source VM leads to the capacity issue at the destination VM.The proposed VM migration technique performs the migration process based on the request of the requesting host machine.This technique can perform in three ways namely single VM migration, Multiple VM migration and Cluster VM migration.Common Deployment Manager (CDM) is used to support through negotiation that happens across the source host and destination host for providing the high quality service to their customer.The VM migration requests are handled with an exposure of the source host capabilities.The proposed analysis also uses the retired instructions with execution by the hypervisor to achieve high reliability.The objective of the proposed technique is to perform a VM migration process based on the prior knowledge of the resource availability in the target VM.

The plants play a vital role in our day-to-day life. It is important to monitor the health of the plants. Generally, plant diseases are identified using image processing techniques. In those techniques, the input images of plants are of an only megapixel size. In this method image processing of plan

Nowadays the human faces the problem in maintaining the health condition in proper level. The problem is occurred due to excess consumption of the food which leads to obesity and also causes health issues. Mismanagement of the human health system is monitored using automated system which provides th

Text mining is the process of extracting the word from the document which is collected from various sources. It is used to transform the text into normalized data for performing machine learning operations. Feature extraction process in the text considers various words in the text then converted into features. Traditional extraction methods extract the features without semantic meaning of the data due to different data formats. Because of the natural language representation, the text mining process uses the document as an input and evaluates the meaning and relationship between the documents. The main objective of the proposed analysis for extracting the features forms the text with various models and parameters. Bag of Words, GloVe, Word2Vec, TF-IDF and Doc2Vec models are analyzed. This analysis considers parameters like cost, number of iteration, learning rate, similarity measure and object relationship for performance measurement. This model uses the Wikipedia data source for analysis and gives raw data with high volume

Time series data are analyzed for predicting the future based on the consistent time period using statistical methods. These analyses are based on the data which are extracted from different sources. Existing method for performing the forecasting process does not fit into the crypto currency data. GARCH and ARIMA models with intelligent mechanisms provide the solution but it is not at the proper level. RNN model takes the data from preexisting intervals and decides the next time series data which is represented as a directed graph. Two types of behavior are considered namely spatial and temporal. The linear model uses the homogeneous data and heterogeneous data analysis is based on the nonlinear model. The nodes and layers are connected based on the input and corresponding activation unit. The memory model is attached to the RNN model for making persistent storage for keeping the processed data for a longer time. The proposed model uses the ensemble method for integrating various RNN models for achieving a high level of accuracy.

Internet of Things connects all real time devices using the wireless nature for collecting, sharing and processing of data. These data are analyzed using machine learning models based on the structure of data. Reinforcement learning is a type of learning method which performs with past experience of data. Traditional algorithms use data with a specific environment with a learning process for prediction. Federated Learning (FL) is achieved through the integration of the various learning models for achieving accuracy. The proposed learning algorithm uses multilevel FL over the smart homes with two house data for analysis of the user behavior. Various kinds of sensors are used for analyzing the behavior, namely local and global. The data is shared with agents and servers with the use of communication networks. It suffers the bandwidth issues because of heterogeneity in the data, so this is overcome by using FL compression method. Multilevel FL compression method achieves reduced latency with efficient interaction. The proposed technique achieves better accuracy when compared to existing RL method with maximum performance and reliability.

Cloud computing models use virtual machine (VM) clusters for protecting resources from failure with backup capability. Cloud user tasks are scheduled by selecting suitable resources for executing the task in the VM cluster. Existing VM clustering processes suffer from issues like preconfiguration, downtime, complex backup process, and disaster management. VM infrastructure provides the high availability resources with dynamic and on-demand configuration. The proposed methodology supports VM clustering process to place and allocate VM based on the requesting task size with bandwidth level to enhance the efficiency and availability. The proposed clustering process is classified as preclustering and postclustering based on the migration. Task and bandwidth classification process classifies tasks with adequate bandwidth for execution in a VM cluster. The mapping of bandwidth to VM is done based on the availability of the VM in the cluster. The VM clustering process uses different performance parameters like lifetime of VM, utilization of VM, bucket size, and task execution time. The main objective of the proposed VM clustering is that it maps the task with suitable VM with bandwidth for achieving high availability and reliability. It reduces task execution and allocated time when compared to existing algorithms.

Nowadays online review and recommendation system plays major role for maintaining quality of any kind of product with various domain. The customer has to evaluate the product and provides the positive as well as negative reviews based on their interest. The education domain has various stages of the

Artificial intelligence covers a vast area of the real time domain which supports humans for all activities. Machine learning (ML) techniques learn the data and react based on the properties of these data. The properties are identified by extracting the features from the extracted data. Image and video processing methods are essentials in real time application due the IoT (Internet of Things) devices. The data of these types of data is more complex and also high dimensional in nature. These dimensions are reduced by performing reduction techniques before performing the classification process. The proposed ML model targets the traffic management by automating the traffic light based on the flow in the road. The traffic priority is assigned based on the congestion level on the road. The traffic classification is done by considering different features and infrastructure maintained by the city. Existing system suffers the problem due to the following reasons such as traffic congestion, longer waiting time, improper maintenance of the traffic signal, and high carbon emission and so on. The objective of the proposed model is to reduce the traffic congestion by performing traffic flow conditions and make the people comfortable level during the travel.

. Online transaction grows in enormous rate because of the strength of usage by the user. User always use online mode to pay the amount to the respective merchant. Various method of payment is available in the market but credit card is so popular due to the pre credit is assigned to the customer by banker. Card user gets extra time for paying the payment which gives comfortable live to them. Security of the card suffers in various factors such as theft, fraud, illegal access, so it is protected by using modern algorithm with automated capability. Artificial Intelligent algorithms are applied to detect the fraud but that is not achieving enough accuracy. This type of problem is overcome by using location based risk identification model with multidimensional features for analysis. Three phases of processing is carried out namely feature management, risk management and Location awareness. The focus of the model is to protect the credit card frauds in multi level security by identifying the source and location of access. It achieves high level of security when compared to all exiting algorithms with reliable manner.

Secure group communication is desired in many group oriented applications of mobile ad hoc network (MANET), and fruitful communication achieved only via trustable network environment. In order to enhance the privacy among group members, proper group key management schemes can be used to encrypt and decrypt the payload. This management is serious task in flexible network like MANET due to dynamic node movement and limited available resources. In order to get away from repeated group key refreshment for entire large network, rekeying done only for sub networks known as clusters. To cope up in this situation, the integrated approach of fuzzy trust based clustering (FTBC) and hierarchical distributed group key management is proposed in this paper. The FTBC isolate misbehaving node from legitimate data transmission and also categorize trusted and distrusted nodes by applying fuzzy logic rules. As well as there is no single solution adopted for all kind of applications, hence two more clustering schemes are proposed namely simple clustering and enhanced distributed weighted clustering are incorporated with key management to satisfy different needs. The performance of our proposal measured by introducing attackers and simulation results prove the proficiency of proposed schemes.

Objective: The main aim is to de-duplicate the redundant files in the cloud and also to improve the security of files in public cloud service by assigning privileges to the documents when it is uploaded by confidential user. Methods: To achieve the objective the authors have used the AES algorithm to encrypt the file stored after de-duplication in the cloud. De-duplication is done based on comparison of contents, file type and size. For an authorized user to access the file from the cloud, generation of OTP using SSL protocol is adopted. Findings: Files uploaded in the cloud are encrypted using traditional encryption algorithms which don't provide high levels of security. Files can be accessed by anyone who is authorized. Privileges are not considered. During de-duplication, only the name and size of the files are considered. Application: Files within the public cloud can't be viewed by everyone who has registered with the cloud. Those who have the respective privileges can only view the file. Proof of Ownership is assured. Since de-duplication is done based on the content redundancy within the cloud storage is avoided. Usage of OTP ensures that the content is viewed by the individuals who have the respective privileges related to the file. These concepts provide additional security to the files stored in the public environment.

Background: The customers always desire to get the required services from a single cloud. It will not provide a high quality of services to the end user because all cloud services are limited to some extent i.e. lack of standard. This problem has been overcome by using the multi-cloud architecture which will provide the high quality of services with reliability. Methods: There are various parameters are analyzed to achieve multi cloud integration. The proposed work focuses on metering control which is a one of the parameter to manage the risk during the time of interaction. Findings: The common deployment model acts as a broker in various cloud interaction to achieve a high quality of services to the customer. The features are extracted from the cloud based on the services which is provided by the service provider. The services are classified and risks are assessed for selecting the suitable services from the cloud. The perfect metering gives the better confident level to the customer using the selected services. There are two essentials implemented in the customer end and provider end they are service control and service registry. The objective of the proposed system is to control the services and its interactions with the supports of cloud metering. Application: The risk assessment has been implemented for assessing the Quality of Service (QoS) with reliable multi-cloud interaction. Keywords: Common Deployment Model, Cloud Control, Cloud Services, Metering, Risk Assessment

This paper presents an effective management of VM (Virtual Machine) for heterogeneous cloud using Common Deployment Model (CDM) brokering mechanism. The effective utilization of VM is achieved by means of task scheduling with VM placement technique. The placements of VM for the physical machine are analyzed with respect to execution time of the task. The idle time of the VMis utilized productively in order to improve the performance. The VMs are also scheduled to maintain the state of the current VM after the task completion. CDM based algorithm maintains two directories namely Active Directory (AD) and Passive Directory (PD). These directories maintain VM with proper configuration mapping of the physical machines to perform two operations namely VM migration and VM roll back. VM migration operation is performed from AD to PD whereas VM roll back operation is performed from PD to AD. The main objectives of the proposed algorithm is to manage the VM’s idle time effectively and to maximize the utilization of resources at the data center. The VM placement and VM scheduling algorithms are analyzed in various dimensions of the cloud and the results are compared with iCanCloud model.

Cloud computing gives an enormous support to an individual and enterprise which can improve their needs in the global market. The customer's data are stored in different location in the cloud either in same or different region. These data should be handled securely from requester to provider end. The cloud security involves protecting and controlling the data, application and associated infrastructures by imposing the policies, technologies etc. The privacy is used to secure processing and handling the personal data in the cloud is not disclosed by the unauthorized parties. The cloud suffers a reliability issues due to lack of security and privacy over the data. The security levels are confined into a particular boundary which does not cover all access levels. The privacy information of various levels is handled by introducing a multilevel privacy technique for protecting user's data in various boundaries. The proposed framework gives an alert whenever the data are accessed by the Cloud Service Provider (CSP) or any other parties, so this will help the Cloud Service User (CSU) to know the status of data. The proposed work is simulated by introducing CDMBackupSim simulator which has various modules and it gives the simulated result for testing process.

Cloud computing is a service oriented computing which offers everything as a service by following the pay-as-you-go model. It is more popular because the cloud data are accessed by variety of customers. An important issue of the cloud computing is to secure the customer data in geographical disperse locations. There are plenty of security standards and policies are available in order to secure the data, but these standards are exist only at the cloud end. It is a critical task for the customer as well as provider to store, retrieve and transmit the data over the cloud network and storage in a secure manner. The customer can store or process the sensitive data who needs a security during the time of travel over the network to the processing environment. The existing security algorithm secures customer data at the provider end which are not known by the customer and also multiple boundaries exists in the cloud resource access which leads the reliability problem. The main objective of the proposed algorithm is to develop a customer owned security algorithm and the encrypted data are send to the provider end. The provider can also apply the security over the customer’s data by using efficient algorithm. The customer’s data are in a secure manner at both the end to achieve maximum reliability. The proposed algorithm uses ASCII and BCD security with steganography that stores the encrypted data in an image file which will be send to the provider end. The security algorithm has to be implemented by using the CDM (Common Deployment Model) which also provides an interoperable security services over the cloud. In future, steganography can be applied to secure the virtual images in the cloud computing.