The market is pounded with the same hazardous material to users, specifically skin and healthcare. It also affects people both in terms of their health and economy. This makes it necessary to monitor products from user opinions for its protection from duplicates. Online users have increased rapidly and share their opinions on occasions, brands, individuals, products, and events occurring across the world. Millions of users participate in SNSs (Social Networking Sites) like Facebook, Twitters, Instagram and WhatsApp etc. Product reviews in public forums like SNSs can provide early clues on such duplicates in terms of allergies or adversities while using them. SA (Sentiment Analysis) can play a significant role in such surveillances. This paper proposes a framework for reviewing experiences in cosmetics in skincare using the Amazon reviews dataset. The proposed technique is based on safety lexicons which are trained for classifications from user sentiments.

In recent times, massive quantity of data and its exponential rise have modified the significance of data security and analysis systems for Big Data.An intrusion detection system (IDS) is a process which helps to monitor and analyze the data for detecting the intrusions in the network.The huge quantity, variation, and high speed of data produced in the system pose a difficulty to the conventional techniques for the detection of attacks.Big Data methods are utilized in IDS for dealing with Big Data for precise and effective data analytic processes.This paper introduces a novel feature subset selection (FSS) with deep belief network (DBN) based intrusion detection in big data environment, called FSS-DBN model.The presented model involves data preprocessing stage to improve the data quality to a certain extent.In addition, the FSS can be considered as an optimization problem and is effectively solved by the use of teaching and learning based optimization (TLBO) algorithm.Moreover, DBN model is applied for identifying the class labels (i.e.intrusions) in the network.For validating the proficient results analysis of the FSS-DBN model, an extensive set of simulations were performed and the superior performance is also highlighted with the maximum sensitivity of 0.9898, specificity of 0.9865, accuracy of 0.9854, F-score of 0.9872, and kappa of 0.9867.

Artificial Intelligence (AI) is inevitable in this era for automation requirements in all large scale industries like Automotive, Aerospace, Railways, Industrial automation, and Renewable energy industries. Among the AI techniques, deep learning algorithm with artificial neural network (ANN) receives greater attention on estimation and control requirements. In this paper, control of autonomous passenger vehicle using deep multi view convolutional neural network (CNN) for the identification of obstacles with 3 dimensional (3D) images of the same using Winograd Minimal filter algorithm (WMFA) has been presented. Authors also have clearly articulated the accuracy level difference between Machine learning (ML) algorithm, basic CNN algorithm and the proposed CNN algorithm in this paper for obstacle identification, collision avoidance and steering control. Most importantly, training of neural networks with multi view topology using Matlab/Simulink coding has been presented with the results. Real-time 3D images have been captured and compared with the stored and trained data. Output of trained CNNs have been captured and the results have been compared and discussed in this paper.

Cloud Computing has advanced as another worldview in which clients can use on-request services, as indicated by their necessities. Nonetheless, security concerns are essential obstructions to a more extensive reception of clouds. Recently conceived ideas that clouds presented, for example, multitenancy, asset sharing and redistributing, make new difficulties for the security research. DDoS (Distributed Denial of service) attack is the greatest danger to the cloud since it influences the availability of services. The objective of this exploration is to build up a security service calculation that lessen the time intricacy, increment the security level and improves the presentation in different factors. The presentation consequence of this proposed calculation is investigated by contrasting it and other existing cryptographic calculations. This exploration work centers primarily around plan a data security calculation to decrease the encryption and decoding time and attack discovery in cloud environment. A progression of investigations were performed and the outcomes exhibit that this methodology can effectively recognize and relieve DDoS attacks from an assortment of known and obscure sources. The Optimised results like accuracy, precision and recall produced by KNN(k=4) compare with other models for this research work. This model has given the optimal solutions.

Wireless Sensor Networks (WSNs) refer to a collection of innumerous sensing de-vices and actuators that form a network to sense the environment or physical conditions and relay the information back to the base station. When the network size grows, clustering becomes intrinsic for the network and many clustering protocols have been studied so far but it is observed that they follow a probabilistic CH election process that gives rise to uncertainties in the algorithm like variable cluster size, uneven node degree of the CHs etc. Here a resilient and scalable novel protocol Maximum Energy Clustering Protocol (MEC) is proposed for the WSN which takes a deterministic route to find CH nodes and optimal number of CHs in a round, rather than probabilistic approach followed by its counterparts. Results are compared to a well-known protocol DEEC (Distributed energy efficient clustering) and it is examined that Maximum Energy Clustering Protocol (MEC) outperforms DEEC as it follows a fair CH election process. MEC is able to attain a significant reduction in network traffic besides utilizing the network to its fullest capacity. Results show that Maximum Energy Clustering Protocol (MEC) outperforms its predecessor DEEC in terms of energy efficiency, life span of network and controlling intra cluster traffic in the network.

Mobile ad hoc network (MANET) is a decentralized, infrastructure less network, where the mobile nodes can transmit the information energetically. Optimizing the energy consumed during transmission is one among the essential requirements in MANET because of the restricted battery power and intricacy in replacing the battery. Transmission Range based Optimal Backbone Path (TROBP) algorithm is proposed to resolve this issue. TROBP algorithm constructs an optimal backbone path based on multi-criterion approach to minimize power consumption during transmission mode. Multi-Criterion approach is designed based on the periodic estimation of criteria's that includes transmission range and residual energy of optimal node, link stability of optimal backbone path and also the load distribution during transmission. TROBP algorithm implements a scheduling scheme for optimizing energy consumption in a high mobility environment.

The currently going on demand for digitalization public supply chains in cooperative sectors motivates to go for metrics which raise the fairness and at the same time the standards of the Government either regional or federal synchronizing with their policies and legislation towards economic growth and citizen welfare.The involved decision makers cannot be rigid/discrete in measuring the parameters in such systems and hence fuzzy logic is identified suitable for them.Though there are many research works in the literature, still their focus is on particularly on systems managing safety, risk and profit outputs.The lack of availability of this approach in cooperative sectors for public food distribution makes the authors to propose a fuzzy inference system accommodating fuzzy rules mapping to Farmers yield , Government approval rate and customer Demand

Shallow parsing is one of the natural language processing tasks, where various syntactic phrases such as noun phrases, verb phrases, and others, are identified. Here shallow parsing is considered as a sequence tagging task, and this paper presents the application of deep learning approach using recurrent neural networks (RNN) for shallow parsing. Specifically, gated recurrent unit (GRU), and bidirectional gated recurrent unit (BiGRU) are applied in parsing Khasi, an Austro-Asiatic language. These variants of the RNN address the vanishing gradient problem and the dependency of the chunk tags on both preceding and subsequent information from the sequential input data. The results have shown an improved performance compared to an existing shallow parser for Khasi.

Diabetic Retinopathy (DR) is an eye-related complication experienced by individuals with longstanding diabetes. Usually diagnosed by the healthcare professional by retinal fundus examination during Medical check-ups or mass screenings. Early detection of diabetic retinopathy will avoid vision loss and other issues. The objective of this work is to diagnose the Diabetic Retinopathy from retinal fundus images using deep learning (DL) techniques for better detection accuracy.The proposed fine-tunedVGG19 CNN architecture is performing well with the Kaggle data set and effectively dealing with this multi-class classification problem. The proposed model uses pre-trained weights from image net data which lessens the training time and improves the performance in detecting DR from retinal fundus images in terms of sensitivity, specificity, and accuracy. Deep transfer learning with fine-tuning method implementation was carried out to get the highest test accuracy of 73.60%.

Machine-Type Communications (MTC) is one of the primary aspects of Internet of Things (IoT) which has gained vast markets and application scenarios.In the recent times, an enormous surge in the number of low cost and low-powered Machine Type Communicating Devices (MTCDs) is observed that tend to connect and cause severe congestions, at times, in the network thus bringing down network's quality of service drastically.Conditionally, all the MTCDs must be mutually authenticated successfully for the corresponding application to be reliable.In the process of authentication and key agreement, the participating MTCDs, high or low configured, need to exchange several control messages with the other participating entities and the servers of the network, leading to overburden and ineffective service delivery.As most of the MTCDs are the constrained devices, lightweight computations are desirable for them without any compromise in its security aspect.In our paper, we have proposed the Secure and Lightweight Group Based Authentication and Key Agreement (SL-Grp-AKA) protocol based on Elliptic-Curve Diffie-Hellman cryptography, where the group of such MTCDs is authenticated simultaneously by the authorized Home Subscriber Server (HSS), also responsible for authentication in the wireless networks.Also, the independent session keys are established with the individual MTCD, to be used for further data transmission securely in our protocol.SL-Grp-AKA guarantees the efficient usage of bandwidth by reducing the congestions caused by the exchange of the control signals.The formal analysis is also performed on SL-Grp-AKA using the well-known AVISPA tool and achieved desirable results and enlisted.The cryptanalysis is performed for establishing its strength as well as the performance evaluation for its computational speed and bandwidth consumption.Towards the end of the paper, we have explored and presented the future scope in this direction.