Intelligent video surveillance system are extensively used in each and every sector of business.Ranging from small shops to safety systems, surveillance has become an integral part.In these fielded systems, a variety of factors can cause camera obstructions and persistent view change.The view change may adversely affect their performance.Examples include intentional blockage, noise, frame freeze, etc. which might warrant alarms.Considering the fact that the intelligent surveillance system is with very less human intervention, it is important to efficiently classify the tampered video.Analysis of the tampered videos helps in further scene investigation.The goal of the project is to use Support Vector Machines (SVM) a machine learning technique which classifies the real-time videos based on features extracted.The features selected are histogram gradients, HSV (Hue Saturation Value) and RGB (Red Blue Green) for the color based classification and edges (edge weight and direction) for the texture based classification.Further improvements are done using a deep learning technique such as CNN.Convolution neural networks make use of large amount of training data and use tensorflow framework for classification.The system accepts video inputs in mp3 or avi format.The output is the classification of tampered videos and alarm generation.Comparison between the two methodologies is done.Support vector machines gives an accuracy of 75% and convolutional neural networks give accuracy of 93%.The system is very useful to monitor all the surveillance activities.
: The major objective of this research is to identify the presence of brain cancer along with the incidence levels of beginning stage to advanced stage using collaborative analysis of big data and data mining techniques. The dataset collected from secondary sources had few errors and rectified using preprocessing techniques in MATLAB. Further, the testing dataset is processed with k-means algorithm to form cluster analysis and identify the presence of brain cancer in three levels of well, fair and poor levels using degree of difference between the normal and cancer cells in brain. The algorithm is modified according to the needs of the medical analysis of the current dataset. The results indicates the presence of brain cancer in various three levels under cluster values of initial stage (54%), Curable stage (38%) and incurable stage (8%), respectively. The accuracy of prediction is 93.4% and the error identification is 9.3% whereas the sensitivity and specificity accounts to 0.8 and 0.7, respectively. Hence, further analysis is conducted in tableau big data tool and the sheets with story boards are formed. This research indicates the occurrence of brain cancer is influenced by gender and age factors along with regular activities and streams. Thus, brain cancer is considered as one of the challenging prediction as the cell contains mixed patterns with variations according to gender and age of human beings.
Page No.: 33-43 Volume: 14, Issue 2, 2019 ISSN: 1816-9503 International Journal of Soft Computing Copy Right: Medwell Publications Abstract: Nowadays, the Online Social Networks OSN emergence has expanded the scope of these needs. In fact, besides the direct links between users, the OSN have various important information about user profiles, tastes and interactions or activities. This information richness has been exploited in the literature in particular social mining techniques to answer new analytical purposes such as influence analysis, trust analysis, opinion mining, recommendation, e-reputation, protection of privacy and detection of experts.
