Nitte Meenakshi Institute of Technology

About: Nitte Meenakshi Institute of Technology is a based out in . It is known for research contribution in the topics: Computer science & Ultimate tensile strength. The organization has 846 authors who have published 644 publications receiving 2702 citations.

Modelling Fade Transition in a Video Using Texture Methods

Abstract: A video shot is an uninterrupted frame captured from a single video recorder. Shot transition is the change from one shot to another. Shot transitions are of two types: abrupt transition (cut) and gradual transition. The cut transition occurs in just one frame. Many methods have been proposed to detect cut transitions and have given good results. Gradual transitions, on the contrary, are not so easy to detect as the transition occurs over a number of frames. Gradual transition is of three types, fade, dissolve and wipe. In this paper, the authors have focused on Fade Transition, making use of well-known texture methods: Grey level Co-occurrence Matrix (GLCM), Statistical and Laws Texture methods to transform the video into texture domain and detect the transition using the response of characteristic properties of the histogram on texture frames. For the obtained responses, a polynomial equation is fit to give a mathematical justification to this work. This polynomial obtained is used in the Identification Phase to detect the kind of transition a raw input video belongs to. Quality of fit is used to determine the best polynomial fit among the polynomials obtained.

Smart Sensing for Vehicular Approach

Abstract: Every day around the world, a humongous amount of people die from road accident and the subsequent injuries. There are many problems which are largely prevalent in the everyday life of a driver around the globe. Some of the techniques that are available in the market are too expensive to implement on a common vehicle. If we take a look around the common household in an Indian society, most of the people are using average cost vehicles and they are not able to afford the existing techniques which can detect the obstacle to prevent from the road accident. The survey has been conducted on the problems which are being faced by the driver at the time of driving and we have proposed a suitable and less expensive ways to implement the solutions of, not all the problems, but few of them to detect the causes of road accident by using some sensors like ultrasonic sensor, ldr sensor, ir sensor and prevention from collision. As smart-driver assistance system, invisibility problem is our main focus in this project. The concept is that it assists the driver with information and actions. In our proposed work, the smart-driver assistant system will provide the information after analyzing results of various sensors existing in the system and then if the driver is unable with actions necessary to ensure the driver’s safety. Invisibility in fog is one of the major reasons of road accidents, various approaches have been made to counter this problem. We have found that ultrasonic sensor can be used to counter this problem. The sensed information is provided to the driver who takes appropriate action depending on the information. However, there are cases where the driver is incapacitated or unable or there are cases where the driver actually needs to drive faster for some urgency. In such cases, the smart-driver assistant system comes in play and slows down the vehicle for the drive, which changes their direction. If unable, the system slows the vehicle itself and if still not stopped, it stops the vehicle at 20 cm away from the obstacle. The proposed work has been tested with four parameters and found to be a better solution.

An Improved Stacked Sparse Auto-Encoder Method for Network Intrusion Detection

Abstract: Intrusion detection is very much needed in today's scenario in many application areas of network security. The development of effective, efficient, and flexibly adaptable security mechanisms has become more critical in today's network. The traditionally existing security mechanisms including NAT, firewall, user authentication, and information encryption, etc., are not enough insufficiently covering today's network. In this research, proposed the improved stacked sparse auto-encoder (ISSAE) method for dimensionality reduction and classifiers used for intrusion detection. We have used the principal component analysis, support vector machine, random forest classifiers on KDD-cup 99, NSL-KDD, UNSW-15nb, and NMITIDS datasets for result analysis of precision, recall, F-score, and false-positive rate. With minimum cost function and training epoch can get better results compared to existing methods. In this research best result obtained through random forest method with a less false positive rate compared to other classifiers.

The Recapitulate Analysis of Image Mining Techniques Applications and Challenges Associated

Abstract: In today’s world, multimedia plays a very vital role. The mining of images is strategically the most complicated yet interesting field for the researchers. Multimedia mining and knowledge discovery deal with non-structured information. Texts are embedded in real-world objects or scenes; examples are street image and its name, car license number, and the number/name on the back of a soccer player. The problems of accurately detecting and extracting the graph image recognition need to be addressed. Since image mining is more or less an extension of data mining, all the concepts of data mining work well with image mining as well. Image mining works with hidden knowledge extraction, image data association, and additional patterns that are dispersed locally in the images. This paper presents a survey of various image mining techniques and challenges related to them. Web image mining facilitates using a complementary textual resource available in the image.

Bounds of Some Topological Indices of the Cartesian Product of F-sum Graphs

Abstract: Lower and upper bounds of Randic index(R), sum-connectivity index (SCI), arithmetic geometric index (AG 1 ), Harmonic index (H) and multiplicative indices of Cartesian productof F-sum of connected graphs are obtained.