Legal documents data analytics is a very significant process in the field of computational law. Semantically analyzing the documents is more challenging since they are often more complicated than open domain documents. Efficient document analysis is crucial to current legal applications, such as case-based reasoning, legal citations, and so on. Due to the extensive growth of documents of data, several statistical machine learning methods have been developed for Legal documents data analytics. However, documents are large and highly complex, so traditional machine learning-based classification models are inefficient for accurate data analytics with minimum time. In order to improve accurate legal documents data analytics with minimum time, an efficient technique called Probit Regressive Tversky Indexed Rocchio Convolutive Deep Neural Learning (PRTIRCDNL) is introduced. The PRTIRCDNL technique uses the Convolutive Deep neural learning concept to learn the given input with the help of many layers and provides accurate classification results. Convolutive Deep Neural Learning uses two different processing steps such as keyword extraction and classification in different layers such as input, two hidden layers, and an output layer. Initially, large numbers of legal documents are collected from the dataset. Then, the collected legal documents are sent to the input layer of the convolutive deep neural learning. The input legal documents are transferred into the first hidden layer where the keyword extraction process is carried out by applying the Target projective probit Regression. Then, the regression function extracts the keywords based on frequent occurrence scores. Next, the extracted keywords are transferred into the second hidden layer where the document classification is performed using the Tversky similarity indexive Rocchio classifier. Likewise, all the legal documents are classified into different classes. The experimental evaluation is carried out using different performance metrics such as accuracy, precision, recall, F-measure, and computational time with respect to the number of legal documents collected from the dataset. The observed results confirmed that the presented PRTIRCDNL technique provides better performance in terms of achieving higher accuracy, precision, recall, and F-measure with minimum computation time.

Vehicle Routing is a highly investigated problem in the field of logistics, informatics, management, and engineering. Several Vehicle Routing Problem variants have appeared since the first paper was published in 1959 by Dantzig and Ramster. In this paper, the neutrality analysis of a complex Vehicle Routing Problem is presented. Neutrality analysis is a special method in the general fitness landscape analysis. The fitness landscape analysis is aimed at the examination of the complexity analysis in regard to the objective function of the optimization problem including the efficiency of the representation space and the operators. In the neutrality analysis, we select the neighbors of the solutions that are closest to them. In this paper, we present the analysis of four neighborhood operators: the 2-opt, partially matched crossover, order crossover and the cycle crossover. Based on the performed numerical analysis, the 2-opt and partially matched crossover methods dominate the other operators.

This research conducts the assessment of the real TAM project implementation in the process industry in Indonesia based on the measurement criteria developed by previous research. The goal of this research is to show the general pictures of the TAM project implementation in Indonesia’s process industry and to evaluate the criteria given to aid in the success of TAM in the process industry. The questionnaire, interview, and direct observation in this research was conducted with TAM experts in one of the biggest petrochemical industries in Indonesia. Some possible improvements on TA management and control have also been discussed. For future research, the proposed decision support system to assist the decision-making on the management and control of TA, scheduling TA, and filtering the unnecessary TA task can be very useful for a more effective and efficient TAM practice.

The OpenDayLight (ODL) clusters strengthened the Software-Defined Network (SDN) centralized controller environment because in any case one controller (leader) collapses or stops working other controllers (followers) will come into play and perform the functionality. This multi-controller environment capability enhances more flexibility and less dependency on external factors. But DDoS attacks are nowadays dynamic and more powerful. In this paper, the implementation of a 3-node ODL cluster along with its vulnerability analysis against DDoS attacks is achieved. Different DDoS traffic penetration tools are being used to launch a huge amount of traffic. This bombardment of the network traffic makes the controller down and the overall functionality of the network also stops.

WBNs are the sensors that are used for extracting patient health related information. But due to less computational power and limited storage of these devices, these devices are amalgamated with cloud for storage that further helps in real time monitoring of the patient’s health. This in turn helps in providing early diagnosis of the patient and saves the patient’s life. This transmission of sensitive data to cloud faces various security challenges. This research focuses on designing and implementation of Certificateless Secured Signature Scheme (CSSS) which provides a great level of security to the sensitive data in transit. Signcryption scheme is implemented which performs encryption and signing in a single logical step. As small key size in ECC provides a high level of security so keys are generated using ECC and data is encrypted using AES algorithm. Our secured scheme is proficient to achieve various security parameters such as confidentiality, authentication, integrity, unforgeability and forward secrecy and non-repudiation. Our scheme improves computational cost and provides a high level of security.

Aggressive driving is a significant contributor to traffic accidents. One of the major applications in the area of intelligent transportation systems is identification of aggressive driving behavior. Several deep learning algorithms have been designed for driver behavior prediction, but the unoptimized parameters of Neural Network algorithms suffer to obtain an effective and accurate solution for the prediction of a driver’s aggressive behavior. The unoptimized parameters of aa LSTM model minimize the accuracy and increase the computational cost. Therefore, an intelligent model using the Genetic Algorithm (GA) optimized Long Short Term Memory (LSTM) has been proposed for the prediction of a driver’s aggressive behavior, which maximizes the efficiency of the driver behavior prediction system. The proposed model optimizes the window size of LSTM, total number of hidden layers and hidden units, and learning rate of LSTM model. The result reveals that the proposed driver’s aggressive behavior prediction model achieves an accuracy of 98.2% and outperforms state of art models. The proposed model minimizes the computational cost drastically. The proposed model supports drivers to avoid collisions by presenting alerts to aggressive drivers. In addition, it minimizes the total number of accidents considerably by predicting aggressive behaviors of drivers and presenting alerts before an accident happens.

The potential benefits and enhancement of services have made cloud computing an attractive field in the current era. Cloud computing has various benefits that has grabbed a focal point among researchers. Cloud service providers pose numerous security challenges and are highly susceptible to attacks. In the context of cloud computing, the anomalies and insiders attacks will deactivate the service providers, which results in the malfunctioning of the entire system. Traditional defense systems in the network are not efficient in handling insider attacks and intrusion. In this work, the anomaly identification technique is developed to identify the attack incidence, and the proposed approach uses the fuzzy min-max neural network (FMM-NN). The classification accuracy is enhanced by the effective identification of features using a neural network. The performance investigation and outcome of the FMM-NN identifies and classifies the real-time attacks in the cloud environment with high identification accuracy.

Abstract Text Summarization can be understood as the task of constructing a summary from a relatively larger text. This summary would comprise of only a comparatively much smaller number of sentences than the actual text and would still express the main idea. Its applications lie in sentiment analysis, document summarization, search engine queries, business analysis, etc. Over time, a lot of research has happened on the topic of abstract text summarization, especially with the emergence of pre-trained models proposed by researchers. In this research a pre-trained model was fine-tuned on Xsum and Gigaword datasets and produced state-of-the-art performance in the abstractive summarization.