No abstract

Web applications are taking popularity in number of ways. Monitoring the client side data allow for gathering valuable information about its behaviour. In this paper an intelligent and integrated system for user activity monitoring for both computer and internet movement is proposed. The system provides on-line and off-line monitoring and allows detecting user behaviour. On-line monitoring is carried in real time and is used to predict user actions. Off-line monitoring is carried out after user has ended his work, and is based on the analysis of statistical parameters of user behaviour. A method for the identifying the category of web sites is also presented. Our system performs clustering on the basis of URL. The URL clustering is very informative, making techniques based on it faster than that make use of text information as well.

A model is created for  blind people that can guide and support them while traveling on the highways just with the help of a smartphone application. This can be accomplished by first converting the scene in front of the user into text and  then converting text into voice output. Then a method for the generation of image legends based on deep neural networks. With an image as an entry, the method can display an English sentence describing the contents of the image. The user first provides a voice command, then a quick snapshot is captured by the camera or webcam. This image is then fed as input to the image caption generator template that generates a caption for the image. Next, this caption text is converted to speech, which gives rise to a voice message on the description of the image.

In the modern world, facial recognition is playing a vital role in the field of biometric technologies. The reason being simple, it’s a very efficient and developed method compared to the other methods. Its being so precise, errorless and effective gives it an edge over other technologies. There are lot of fields where this fast growing technology is yet to show its effectiveness, one of which is examinations, the identification of the students during examinations. Different kinds of biometric technologies are used in the examination sector in order to identify the students appearing for the exams. Biometric technologies use physical features to identify the person appearing in the exam but many of these traditional methods create room for errors and cheating which can be improved by execution of facial technology.In this research, the approach of Eigenface and fisherface has been used. These techniques are recent and have apparently promising performances, and are representing new trends in this field. Based on previous research that has been done by other researchers about the Eigen face and Fisher face algorithms, where facial image recognition uses Eigenface with different conditions of differentiation from expression, with success rates up to 75%. Ada-boost face recognition, Eigen face PCA and MySQL produce 80% of various different conditions. Face recognition with 93% success with Fisher face by 73 face trials of different expressions and different positions. From previous research, the author wanted to know which algorithm has speed in terms of time, distance and accuracy of photosensitivity in the facial recognition process. By tests of the two algorithms, it produces success percentages and accuracy charts. The Fisherface algorithm is faster than the  Eigenface algorithm has an accuracy of 96% and the Fisherface algorithm has an accuracy of 97%.

No abstract