IJETE
Call for papers , Manuscript submission last date 30th April 2018. Send to ijete.editor@ijete.org

Volume 2 Issue 3 March 2015 Edition

COPY-MOVE FORGERY DETECTION USING DCT
NEHA JADHAV, SUVARNA KHARAT, PUNAM NANGARE
pp 38-42
Abstract: In today’s day today life digital images are available everywhere and it is very easy to manipulate these digital images by using powerful editing software. Now a day’s many people add, crop or remove important features from an image without leaving any proof of fake images. There are many techniques used for forgery detection. One of the technique most commonly used is Copy-Move forgery in which coping a some part of image and pasting it into the same image in order to hide some data or part of an image and other most commonly used technique is staganalysis in which some message is hidden inside the image which is not easily possible to see with naked human eye. In this paper we search the problem of detecting the forgery and describe robust detection method. this method successfully detect the forged part even when the copied area is edited to combine it with the background of an image and even if the forged image is saved in the JPEG format.
DIGITAL WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
NEHA JADHAV, SUVERNA KHARAT, PUNAM NAGARE
pp 43-45
Abstract: Digital watermarking is one of the types of digital signal which hidden directly in digital content. It helps to make the distribution of digital material more secure. Digital watermarking has the properties like strongness, security, transparency, complexity, capacity, and verification. A Digital Watermarking is a form of steganography in which copy-move and other source information is hidden inside a document, image or sound file without the user’s knowledge. Many companies involved in digital watermarking activities with different types of watermarks. It discusses different techniques for images, text and other applications of digital watermarking.
ANDROID APPLICATION FOR FORENSIC IMAGE IDENTIFICATION
PROF. SANJAY AGRAWAL, SHUBHAM WANKHADE, SIDDHESH RATHI, BHAUSAHEB SHINDE
pp 46-48
Abstract: We present an image processing software suite-SmartCop, based on the Android environment, specifically designed to be applied as a forensic tool by law enforcement personnel in the analysis of images of the criminal. Utilizing an image, refining it for further image recognition purpose is the central theme of in this paper. SURF algorithm involves Image enhancement and Image matching as salient features. The images from videos can be captured and compared to determine the resultant match. Our bearing is to overcome some drawbacks which normally look when using standard image processing tools for this application, i.e. mainly the less control & documentation of the operations which have been performed on the images, and provide improved operations and earn the difference in critical instances.
QUALITIES OF TIGER NUT OIL AS INFLUENCED BY HEATING TEMPERATURE
Adejumo, B. A., Olorunsogo, S. T. and Omodaiye, S. I.
pp 49-52
Abstract: The effect of heating temperature on the oil yield and characteristics of tiger nut was investigated. The tiger nut samples was divided into four portions A, B, C and D. Samples B, C and D were heated at 100oC, 120oC and 140oC respectively for 30 minutes, while sample A, which was not heated served as the control for the experiment. The oil extraction was done using solvent extraction method and the extracted oil was characterized using standard methods. The results showed a percentage oil yield of 28.18%, 26.83%, 24.14% and 21.19% for samples A, B, C and D respectively. The acid (mg/KOH/g) and peroxide (m/mol/kg) values are 2.81, 2.53, 2.24, 1.40 and 2.8, 2.0,1.0, 2.0 for samples A, B, C and D respectively. The free fatty acid (mg/KOH/kg) values are 5.61, 5.05, 4.49, 2.81 for samples A, B, C and D respectively for oil samples extracted. The oil yield, acid value, peroxide value and free fatty acid decreases with increase in heating temperature.The heating temperature however had no significant effect on the specific gravity, density, refractive index, saponification value and iodine value of the extracted oil. It can be concluded that tiger nut should not be heat treated above 100oC prior to oil extraction for optimum oil yield and reduction in peroxide value. However further research work should be carried out on tiger nut by heating at temperature below 100oC prior to oil extraction.
TESTING OF VARIOUS IP USING DIGITAL TECHNIQUE FOR ANALOG BIST
KHANGEMBAM RAHUL SINGH,M.R BIBIN
pp 53-58
Abstract: Work on analog testing has focused on diagnosing faults in board designs. Recently, with increasing levels of integration, not just diagnosing faults, but distinguishing between faulty and good circuits has become a problem. This paper aims to develop an approach to test analog signal of various IP using only one built-in-self-test (BIST) and check this various input by using assertion algorithm. A major advantage of using single BIST is it requires less power and has less complexity. This paper helps us to find faults using this assertion algorithm.
CLUSTERING OF HIGH DIMENSIONAL DATA USING FAST ALGORITHM
MISS. SHAIKH SANA, MISS. POOJA THORAT, MR. DEVADHE GAURAVE, PROF: SONAWNE V.D.
pp 59-61
Abstract: The Feature selection is a process of identifying & removing as many relevant and redundant feature as possible. Feature selection involves identifying a subset of the most useful features that produces compatible results as the original entire set of features. A feature selection algorithm may be generated from both the efficiency and effectiveness points of view. First efficiency related with the time required to find a subset of features, the second effectiveness is related to the quality of the subset of features. Based on these criteria, a fast clustering-based feature selection algorithm (FAST) is proposed and experimentally evaluated in this paper. The FAST algorithm works in two steps. In the first step, features are divided into clusters by using graph-theoretic clustering methods. In the second step, the most representative feature that is strongly related to target classes is selected from each cluster to form a subset of features.Features in different clusters are relatively independent; the clustering-based strategy of FAST has a high probability of producing a subset of useful and independent features. To ensure the efficiency of FAST, we adopt the efficient minimum-spanning tree (MST) clustering method. The efficiency and effectiveness of the FAST algorithm are evaluated through an empirical study. Extensive experiments are carried out to compare FAST and several representative feature selection algorithms, namely, FCBF, Relief F, CFS, Consist, and FOCUS-SF, with respect to four types of well-known classifiers, namely, the probability based Naive Bayes, the treebased C4.5, the instance-based IB1, and the rule-based RIPPER before and after feature selection. The results, on 35 publicly available real-world high-dimensional image, microarray, and text data, demonstrate that the FAST not only produces smaller subsets of features but also improves the performances of the four types of classifiers.
TAXI-FINDER: ONLINE RECOMMENDER SYSTEM
RESHMA SUPUGADE,PRIYANKA THAKUR,NAMRATA JAGTAP
pp 62-65
Abstract: A recommender system for both taxi drivers and people expecting to take a taxi, using the knowledge of passengers’ mobility patterns and taxi drivers’ picking-up/dropping-off behaviors learned from the GPS trajectories of taxicabs. First, this recommender system provides taxi drivers with some locations and the routes to these locations, towards which they are more likely to pick up passengers quickly (during the routes or in these locations) and maximize the profit of the next trip. Second, it recommends people with some locations (within a walking distance) where they can easily find vacant taxis. In our method, we learn the above-mentioned knowledge (represented by probabilities) from GPS trajectories of taxis. Then, we feed the knowledge into a probabilistic model which estimates the profit of the candidate locations for a particular driver based on where and when the driver requests the recommendation. We build our system using historical trajectories generated by over 12,000 taxis during 110 days and validate the system with extensive evaluations including in-the-field user studies.
PMSE: PERSONALIZED MOBILE SEARCH ENGINE USING LOCATION CONCEPT
MISS. BELGE PRIYANKA, MISS. CHAUHAN MANISHA, MISS. DHOBALE YOGITA, PROF: PATIL S.S.
pp 66-68
Abstract: We propose a personalized mobile search engine, PMSE, that captures the users’ preferences in the form of concepts by mining their click through data. Observing the need for different types of conccepts, we separate concepts into location concepts and content concepts. In addition, users’ locations (positioned by GPS) are used to supplement the location concepts in PMSE. The user preferences are organized in an ontology-based, multi-facet user profile, which are used to adapt a personalized ranking function for rank adaptation of future search results.Based on the client-server model, we also present a detailed architecture and design for implementation of PMSE. In our design, the client collects and stores locally the click through data to protect privacy, whereas heavy tasks such as concept extraction, training and are performed at the PMSE server.Moreover, we address the privacy issue by restricting the information in the user profile exposed to the PMSE server with two privacy parameters.We prototype PMSE on the Google platform.