The growth in population all over the world and in particular in India causes an increase in the number of vehicles which, create complications regarding traffic jam and traffic safety. The primary solution to recover the jam condition is the expansion of capacities of roads by building new streets. However, this requires extra efforts and more time that is a costly and ineffective solution. Therefore, there is a need for alternative solution methodologies that are being implemented. Intelligent traffic monitoring is a branch of intelligent transportation systems that focuses on improving traffic signal conditions. The key goal of such an intelligent monitoring system is to improve the traffic system in a way that reduces delays. Many cities facing these delays because of the inefficient configuration of traffic light systems which are mostly fixed-cycle protocol based. Therefore, there is a profound need to improve and automate these traffic light systems. The establishment of a mixed technique of artificial intelligence (AI) and computer vision (CV) can be desirable to develop an authenticated and scalable traffic system which can aid to solve such problems. Proposed work supports the use of computer vision technology to build a resource-efficient, synchronous and automated traffic analysis. Video samples were collected from multiple areas to use in the system. The system applied and the vehicle was counted and classified into different classes. Manually and automatically annotated patterns were used for the classification. The multi-reference-line mechanism employed to find the speed of the vehicle and analyze traffic. The system makes its decision based on a number of vehicles, backwards-forward synchronous data and emergency conditions.

Data mining and machine learning is one of the most essential tools in new generation technology. That is used in a number of applications i.e. security, banking and decision making. In this paper, data mining application of web data security is described in details. In this context the domain of phishing URL detection and classification is key aim of the proposed work. This paper includes the different aspects of phishing and recently made contributions for accurately classification of phishing URLs. In addition of that a data mining based model is also proposed that is help to classify the phishing URLs more accurately. Finally the paper provides the future extension of the work.

No abstract

Image inpainting is an emerging area of image processing; with the help of this we can fill the misplaced or lost regions of a given image. In real life for example in the museum world the job of inpainting of precious images or paintings is fulfilled with the help of an expert of arts. Like this in the digital world the job of image inpainting is fulfilled with the help of inpainting algorithms. Various algorithms have presented in the past to achieve the task of image inpainting. In this paper, we have suggested a novel exemplar based image inpainting technique. The suggested technique will remove whole object from a given image or a portion of the object & it will offer high quality outcomes.

Data mining is readily growing and accepted technology in recent years. It is utilized for finding instant decisions by analyzing the historical records. A formal decision making technique can also be helpful for information security. In this presented work the demonstration of a data mining application is provided. The proposed data mining application contributes on the information security. Therefore URL classification problem is taken in consideration. In this context we can apply here the any supervised learning algorithm but in this work the association rule mining based technique is proposed for solving the URL classification. That technique is used for analyzing the URL patterns of two kinds of class labels i.e. phishing and legitimate. In this context a rule based classification technique is proposed. That technique is computing the association rules and we can use these patterns to classify the URL data. The Idea is taken from [1] where apriori algorithm is implemented for generation and classification of phishing URLs. Apriori algorithm is computationally complex and requires significant amount of time and memory for generating candidate sets. Therefore we usages the FP-Tree algorithm which efficient develops the association rules with less resource requirements. The system can be used for designing the phishing tool bars. This technique is used with the phish tank dataset with different set of data for experimentations. The obtained results shows the proposed technique requires less amount of time and memory. In near future it is tried to reduce time and improve the accuracy of the proposed phishing URL classification system.