The advent development of cloud computing is an on-demand adaptive technology for many IT organizations due to its dynamic scalability and virtualization resources as a global service. There are numerous energy-conscious approaches in existence that attempt to minimize energy consumption and Service Level Agreements (SLAs) degradation of the host. In this paper, we proposed a novel load balancing approach that identifies overloaded or underloaded hosts, and selects the VMs (Virtual Machines) for allocation to the host based on the predicted load. We consider CPU utilization parameter for evaluating host loading which is far enough to compute all the characteristics of Physical Machines (PM) provided to the Linear Adam Algorithm for Overloaded detection followed by Interquartile Range (IQR) method for underloaded detection. The Power-Aware Best Fit Decreasing (PABFD) algorithm sorts the VM in descending order based on CPU utilization. Then those filtered VM is allocated to the corresponding host thereby reducing the energy consumption and SLAs degradation. We evaluate the proposed algorithm through CloudSim-3.0.3 simulation and random datasets with different workloads on a real Planet Lab. After the evaluation, the simulation result of the proposed method indicates a significant performance by reducing the metric parameters such as SLA degradation, number of VM migration, the total number of host shutdowns, and reduce energy consumption.

Location based services have potential due to promising technologies in mobile communication, and information services.LBS users use their location information to get important information from the service providers.There are many popular applications like maps & navigation, information services, Tourist information service, social networking, etc. LBS users need to submit their location and personal information to the location based service providers.i.e.: Location Information & Personal Identity.Location privacy refers to unauthorized users who should not be able to trace the exact location information of the user.Unauthorized users should not be known or reveal the private information of the users during communication.Location and communication privacy & security are the most challenging issues in LBS.Collaborative approach is the fully distributed approach where trusts are distributed among each peer that performs their task mutually.It uses cryptographic approaches that provide highest location privacy and security in LBS.Nowadays; the growth of LBS users is increasing rapidly.Currently, none of the approaches are there that support scalability features.It's a challenge to design a computationally efficient and practical solution that provides strong privacy by reducing the processing overhead that improves scalability.The proposed approach provides privacy, high fault tolerance, strong resilience against security and privacy attacks, support scalability and reduced cost.

Hyperspectral Images (HSI) provide a rich set of spatial and spectral information that is used for the classification of the HSI dataset. The large-scale hyperspectral image data leads to many processing challenges for the conventional data analysis techniques. To minimize the computational complexity and enhance the classification performance of the HSI dataset, we presented a new hybrid learning technique for feature extraction and classification (Hybrid-LN) model in this work. It is a simple two-step approach, to reduce computational complexity, the first step is applied to generate a spatial-spectral reduced HSI dataset by identifying the most significant pixels from each class and the most significant bands of the HSI. To increase HSI classification performance, the second step involves training a CNN to extract spatial-spectral features from the reduced HSI. Results from three benchmark HSI datasets -Salinas scene (SA), Indian Pines (IP), and Pavia University scene (PU)-are compared to those from the current models. Experimental results show that the computational complexity of the proposed approach is significantly reduced and producing relatively good classification accuracy with the state-of-the-art methods.

Software defined networking (SDN) plays a very important role to define enhanced content centric network for Industry 4.0 future internet architecture. The primary objective of the future internet architecture foundation is to provide better content delivery among various forms of connected objects. It also aims to connect enormous amount of physical objects through heterogeneous operating communication protocols. The communication protocols are mostly being designed taking three crucial factors into account-i) Scalability, ii) Interoperability and iii) Security for network and physical layer attributes. However, the conventional form of host IP centric protocols such as IPV4 and IPV6 generate communication burden when considered in the context of FIA and also do not ensure significant security measures for FIA. Thereby, it is necessary to redefine a solution taking the baseline reference architecture of novel security policies which can balance the communication performance and security trade-off by identifying potential security threats. This research study introduces a combine framework of data security aiming the futuristic Internet hosting services for content centric networks. The system is analytically conceptualized with two different novel algorithms which are tested under variable operating conditions and different set of data. The outcome exhibited that both the security mechanisms poses computational efficiency by boosting secure communication at SDN in FIA.

The prediction of stock movements has gained huge interest amongst the business world and academia. Due to globalization of advanced information technologies, the majority of peoples look forward in stock markets for earning huge returns. This paper presents stock market prediction using optimization driven deep model. Here, the review data of user and stock data are fed as an input to feature extraction. The extraction of features is done from the stock data and review data. From stock data, the technical indicators, like Absolute Price Oscillator (APO), Directional Movement Indicators (DMI), Simple Moving Average (SMA), WILLIAMS's % R (WILLR), triangular moving average (TRIMA), and percent price oscillator (PPO) are extracted. From review data, the stemming and stop word removal methods are applied for extracting the irrelevant words. Then, the SentiWordNet is applied for extracting the review features. The obtained features are modeled in the feature vector and fed to deep convolutional long short-term memory (Deep-ConvLSTM) for stock prediction. Here, the training of Deep-ConvLSTM is performed by newly devised optimization technique, namely Rider based Elephant herd Optimization (Rider-EHO), which is obtained by integrating Rider Optimization Algorithm (ROA) and Elephant Herd Optimization (EHO). The proposed Rider-EHO-based Deep-ConvLSTM offered enhanced performance with smallest MSE of 0.003 and smallest RMSE of 0.059.

Wireless Sensor Network (WSN) is a generally hopeful technology for several real-time applications due to its cost-effective, size, and distribution nature.WSN is a collection of sensor nodes spread in a great region such that the required information can be collected.However, sensor nodes are susceptible to attacks, for example, intrusion, hackers, defective hardware starting the physical incident, etc.Therefore, it is compulsory to defend a sensor node from an intrusion.If it brings attacked next, the information transmitted through the sensor may be wrong and lead to incorrect data analysis, leading to unnecessary outcomes.To solve these issues, Reinforcement Learning for Intrusion Detection (RLID) and Improving Optimal Route by Cuckoo Search is proposed.The Reinforcement Learning uses the repeating node classification for detecting the intrusion during the route discovery.Reinforcement learning evaluates the sensor node behaviour by the quality of the link, and it is computed by sensor node packet forward rate and node residual energy.Here, the repeating node classification method classified the intrusion sensor based on node-link quality.As a result, it can improve intrusion detection performance efficiently.Besides, the Cuckoo Search Technique (CST) is used to find the optimal forwarder for transmitting the data from sender to destination.The main objective of this work is to offer optimal routing and communicate the data via normal sensor nodes in WSN.The simulation platform and the obtained results are compared with the baseline protocol to prove the efficiency of our proposed approach.

Analysis of web content and sentiment nowadays are hot topics among researchers. The dark web is that integral part of WWW, which provides freedom of content hosting. The dark web is majorly used to do illegal activities; although accessing the dark web is legal in most countries, its usage can arouse suspicion with the law. The dark web's hosted websites provide various services in multiple Categories like Adult, Counterfeits, illegal markets, Drugs, weapons are prevalent. Sentiment's analysis attempts to identify emotions and opinions based on the transactions and text communications. Pattern Detection is a process of recognizing patterns in a dataset using a machine-learning algorithm. This study provides inputs to a framework for automating Dark Web Scraping and analysis of its hosted content. During the analysis, we also find some exciting patterns in hosted content of the dark web.

Artificial neural networks (ANN) are known to be an effective forecasting method for time series data.However, a challenge of this method is how to determine an optimal set of parameters for ANN, such as number of inputs, number of hidden neurons, learning rate, set of weights, etc. so that ANN can achieve the most accurate forecasting results.Given the possible combinations of parameters, there is an explosion in the number of ANN architectures that need to be considered, so it is necessary to incorporate another intelligent technique, such as genetic algorithms (GA), to be able to find the best ANN.This paper analyzes the integration of ANN with GA, called the GANN model, in which ANNs are candidate solutions in the search space and GA tries to determine the best architecture for forecasting.Time series data on tourism demand is used to evaluate the effectiveness of the GANN model.Experimental results show that, ANN(12:14:1) is the best ANN architecture, with the minimum forecasting error (MAPE = 5.50).A comparison between ANN(12:14:1) and other architectures with the same inputs, but varied hidden neurons was also investigated and the results show that ANN(12:14:1) is the global optimal architecture.

Database watermarking has emerged as an effective solution to protect ownership of relational databases.Unlike images and videos, watermark insertion in databases can cause distortion leading to loss of data quality.In this paper, we propose a reversible database watermarking technique with distortion control.Firstly, we need to select optimal attributes for applying difference expansion.Pearson Correlation Coefficient (PCC) is employed to find a pair of attributes with the highest correlation.This ensures controlled distortion in the database.Later, difference expansion is applied on the selected attributes.It makes the method reversible and original data can be recovered whenever required.Experimental results show that the proposed method is robust against insertion, deletion, and modification attacks.

Supply chain management is an important area of logistics. It is a process involving many stakeholders with multiple areas and even more moving parts. The proposed technology aims to make the supply chain more efficient, investing in the wrong technology complicates productivity further while hampering profits, leading to multiple issues in supply chain. Blockchain technology is the solution to the problem of structuring data with built-in security features. Blockchain technology enables decentralization with the participation of members on distributed networks. There is not a single point of failure because of the distributed structure and the transaction record cannot be change by single user. In this paper for making data more secure while sharing information in supply chain a key generation process is done using data sanitization and restoration process and new improved Fittest Self Adaptive sea lion algorithm is discussed using only the authorize person will be able to use shared data and it will be compared with existing model using different parameters.