CSE&ISE

With the advent and popularity of social network, more and more users like to share their experiences, such as ratings, reviews, and blogs. The new factors of social network like interpersonal influence and interest based on circles of friends bring opportunities and challenges for recommender system (RS) to solve the cold start and sparsity problem of datasets. Some of the social factors have been used in RS, but have not been fully considered. In this paper, three social factors, personal interest, interpersonal interest similarity, and interpersonal influence, fuse into a unified personalized recommendation model based on probabilistic matrix factorization. The factor of personal interest can make the RS recommend items to meet users' individualities, especially for experienced users. Moreover, for cold start users, the interpersonal interest similarity and interpersonal influence can enhance the intrinsic link among features in the latent space. We conduct a series of experiments on three rating datasets: Yelp, MovieLens, and Douban Movie. Experimental results show the proposed approach outperforms the existing RS approaches.

A detailed study on feature extractors in spatial and transformed domain is carried out in this work. The survey in Spatial domain include most of the traditional detectors until recently the SIFT and its variants. In the transformed domain, the detectors developed using the Fourier transforms to wavelet transforms have been explored. The advantages and the limitations of each one of them is explained along with the results. Depending upon the application in hand together with time complexity and accuracy, an appropriate choice of the suitable detector has to be made.

Vison based tracking in aerial images has its own significance in the areas of both civil and defense applications.  A novel algorithm called aerial tracking learning detection which works on the basis of the popular tracking learning detection algorithm to effectively track single and multiple objects in aerial images is proposed in this study. Tracking learning detection (TLD) considers both appearance and motion features for tracking. It can handle occlusion to certain extent, and can work well on long duration video sequences. However, when objects are tracked in aerial images taken from platforms like unmanned air vehicle, the problems of frequent pose change, scale and illumination variations arise adding to low resolution, noise and jitter introduced by motion of the camera.  The proposed algorithm incorporates compensation for the camera movement, algorithmic modifications in combining appearance and motion cues for detection and tracking of multiple objects and enhancements...

In a world filled with busy schedules it becomes almost certain that a person is not able to keep up with his commitments on time due to a number of reasons. One of the main reasons being the inability to commute on time, i.e. we might be late to catch the vehicle or the vehicle might be delayed due to traffic, roadblock or a breakdown. Due to this very reason a lot of work is left unfinished and considerable amount of valuable time is lost. In this work we address this very problem which is quite prominent in institution, due to which a lot of teachers and students are unable to arrive in time and proceed with their classes. This prompted us to come up with an application that allows us to track all of the busses in institution, providing an alternate bus, along with the shortest route from the user to the bus and also informing the student or faculty when the bus is missed.

Hypothyroidism or hyperthyroidism is a major disease in India which arises due to malfunctioning of thyroid hormones. Medical industry has enormous quantity of data, but the bulk of this data is not processed. For proper diagnosis data must be processed accurately. For accurate processing intelligent Machine Learning techniques are widely used. In this paper an attempt is made to analyze Logistic regression and Support Vector Machine (SVM) for multiclass classification of thyroid dataset.Performance of these techniques ison basis of Precision, Recall, F measure, ROC, RMS Error and accuracy. Our analysis shows that logistic regression is more efficient than SVM for multiclass classification of thyroid dataset.

Disclaimer : This statement is based on the information available with us, and is only for your reference.The statement from the respective fund reflects the exact information for the respective folio. Any discrepancy may please be reported to us.All investments in Mutual Funds carry risk of loss of principal.No returns are guaranteed, all projections are indicative and subject to market fluctuations.Tax is payable on all your debt and equity transactions.

This project is an innovative solution that allows a patients to intract with all their health related problems.Here we are highlighting about the communication between the doctor and the pharmacist regarding appointments,medical procedure,treatement regiments and other health information of the patients .The patients are unable to bare the drastic situations when they are unwell.It also signifies the major portion and relationship between the physician and the pharmacists.It consists of various individual legacy application that have to be integrated to deliver a more unified solution.This article also aims to specify an approach to the doctor and the pharmacists.Here the doctor will send the prescription of a patient directly to a pharmacist of through a automated display.All the details of the patients related to their health and diet chart should also be sent to the patients.In case if the tablet given by the doctor is not available in the medical store,then the pharmacist have to immediately inform to the doctor.The doctor then will send the alternative tablet.The growing number of waiting lists, rising pressure on medical professionals and accountability for medical negligence are only part of the motivation to take initiative towards holds a core model integration strategy in various legacy infrastructure system.

Looking at the current situation faced by farmers, there is an increase in suicide rate over the years. Main reason behind it includes poverty, unpredictable weather, financial problem, parental issue and frequent change in Indian government norms. Education also plays an important role because due to lack of education they are not aware of the soil quality and the climatic change and sometimes farmer was not aware about the feasible crops. Because of lack of knowledge they are not aware of the soil quality, soil nutrients and soil composition. This paper focused on prediction of crop based on the existing data by Artificial Neural Network. We are implementing Artificial Neural Network which is used for classification and prediction as most of intense computation takes place during training phase only, there is no requires of testing phase.

Security of websites and online systems is of paramount concern today. A significant threat comes from malicious automated programs designed to take advantage of online facilities, resulting in wastage of resources and breach of web security. To counter them, CAPTCHAS are employed as a means of differentiating these bots from humans. However, highly sophisticated computer programs evolved over time have

Sophisticated and evolving CAPTCHA breaking algo-rithms as mentioned in [1, 4, 7] have successfully broken currently employed CAPTCHAs. This has resulted in a con-tinuous requirement for more robust CAPTCHAs. In light of this, STC generation scheme was introduced in [3] to stay ...