Research papers can be visualized as a networked information space that contains a collection of information entities, interconnected by directed links, commonly known as citation graph. There is a possibility to enrich the citation graph with meaningful relations using semantic tags. We have discovered and evaluated more than 150 citations' reasons from the existing published literature to be represented as citation tags. Many of these reasons have overlapped and diffused meanings. Annotating such a large volume of citation graphs with citation's reasons manually is nearly impossible, giving rise to a need to discover the citation's reasons automatically with high accuracy. The first step towards this is developing a minimal set of citation's context and reasons that are disjoint in nature. It would be a great help to the reasoning system if these reasons are represented in a formal way in the form of an ontology. By adopting a welldefined scientific methodology to formulate an ontology of citation reasons, we have reduced 150 reasons into only eight disjoint reasons, using an iterative process of sentiment analysis, collaborative meanings, and experts' opinions. Based on our findings and experiments, we have proposed a citation's context and reasons ontology (CCRO) that provides abstract conceptualization required to organize citations' relations. CCRO has been verified, validated, and assessed by using the well-defined procedures and tools proposed in the literature for ontology evaluation. The results show that the proposed ontology is concise, complete, and consistent. For the instantiation and mapping of ontology classes on real data, we have developed a mapping graph among the verbs with predicative complements in the English Language, the verbs extracted from the selected corpus using the NLP and CCRO classes. Using this mapping graph, the mapping of ontology classes in each citation's sentiment is explained with a complete mapping on the selected dataset.

Motion Picture Production has always been a risky and pricey venture. Bollywood alone has released approximately 120 movies in 2017. It is disappointing that only 8% of the movies have made to box office and the remaining 92% failed to return the total cost of production. Studies have explored several determinants that make a motion picture success at box office for Hollywood movies including academy awards. However, same can't be said for Bollywood movies as there is significantly less research has been conducted to predict their success of a movie. Research also shows no evidence of using academy awards to predict a Bollywood movie's success. This paper investigates the possibility; does an academy award such as ZeeCine or IIFA, previously won by the actor, playing an important role in movie, impact its success or not? In order to measure, the importance of these academy awards towards a movie's success, a possible revenue for the movie is predicted using the academy awards information and categorizing the movie in different revenue range classes. We have collected data from multiple sources like Wikipedia, IMDB and BoxOfficeIndia. Various machinelearning algorithms such as Decision Tree, Random Forest, Artificial Neural Networks, Naïve Bayes and Bayesian Networks are used for the said purpose. Experiment and their results show that academy awards slightly increase the accuracy making an academy award a non-dominating ingredient of predicating movie's success on box office.

World’s second most occurring cancer is breast cancer. Prediction of disease is one of the most challenging tasks and there are many factors that effect this type of diagnosis like the ability of visual perception. This paper proposed a Convolutional Neural Network (CNN) based proper method for analyzing the earliest signs of breast cancer with the help of mammogram images. The main goal of proposed system is to identify the disease of breast cancer at early stages. Due to this reason, Mammographic image analysis society (MIAS) dataset is used. There are three hundred & twenty two (322) mammograms in the dataset, with 209 images of normal breasts and 133 images of abnormal breasts. While abnormal breasts are further classified as benign (62 images) and malignant (51 images). To implement this system, python library Keras and Tensor Flow libraries are used along with deep learning model CNN. Convolutional Neural Network (CNN) has been shown to be effective in detecting breast cancer in mammography images with 70% accuracy rate, according to promising testing data. The proposed system will enable the radiologist in detecting breast cancer in early stages.

With the versatility and exponential growth of IoT solutions, the probability of being attacked has increased. Resource constraint IoT devices raised a challenge for the security handler to track logs of different variety of attacks generated on them while performing the forensic analysis. Commonly forensic analysis is performed on the devices that calculate how much loss has occurred to the device due to the diversity of attacks. The main objective of this paper to develop a framework through which secueity can perfrom the forensic analysis on resource contraint IoT devices. In this paper, we have proposed a framework that intelligently performs forensic analysis and detects the different types of attacks performed on the endpoint (IoT device) using a node to node (N2N) framework. Furthermore, this proposed solution is a blend of different forensic tools and Machine learning techniques to identify different types of attacks. Using a third-party log server, the problem of evidence recovery from the endpoint under attack is addressed. To determine the nature and effect of the attack we have used the logs by using the security onion (forensic server). Additionally, this framework is equipped to automatically detect attacks by using the different machine learning algorithms. The efficiency of machine learning models is measured upon the values of (1) Accuracy, (2) Precision, (3) Recall, and (4) F-Measure. The results show that the decision tree algorithm stands out with the optimum performance compared to other ML models. Overall this framework can be used for the secuirty of IoT devices as well as the evidence collection from the IoT endpoint. For the validation of the proposed framework more detailed results and performance, analysis is presented in this paper.

No abstract