Time filter

Source Type

Kolkur S.,Thadomal Shahani Engineering College
ACM International Conference Proceeding Series | Year: 2016

ESD is an acronym for Erythemato-Squamous Diseases, which is a set of six skin diseases [6]. The Erythemato-Squamous Diseases (ESDs) require huge computational efforts to predict the diseases because all the six diseases studied in this group have more than 90% common features. The main focus of this paper is to study the use of machine learning algorithms in R software for prediction of ESD Diseases. In this paper, different algorithms are studied and implemented in R. Accuracy of these algorithms is compared. © 2016 ACM.

Dhannawat R.,Usha Mittal Institute of Technology | Patankar A.B.,Thadomal Shahani Engineering College
Procedia Computer Science | Year: 2016

Image denoising without any idea about kind of noise is very cumbersome as compared to known noise. This paper proposed a novel technique for blind image denoising using SVD and local pixel grouping. The technique is checked against salt & pepper noise and Gaussian noise for gray as well as color images and compared with state of art algorithm LPGPCA. It is found that the proposed technique gives better results when compared using objective criteria. © 2016 The Authors.

Antony N.,Thadomal Shahani Engineering College | Deshpande A.,G.H. Raisoni College of Engineering
Advances in Intelligent Systems and Computing | Year: 2016

Due to increasing demand to derive knowledge from data, there is need for efficient data mining algorithms. We have proposed an algorithm to get clusters of arbitrary shapes with the help of Density Based clustering algorithms. Density Based clustering algorithms need Epsilon Value (Eps) and Minimum Points Value (MinPt) to create clusters. Hence in this paper, a method is proposed which accepts the domain knowledge about the dataset as an input and calculation of Eps and MinPt is automated which helps to make the data certain to some extent. Domain knowledge adds some relevance to data, hence this data with knowledge will never be ignored during clustering. In this method, we first create grids for dataset as per user’s requirement then it derives the default Eps and MinPt which are inputs for Density Based Clustering Algorithm for Large Datasets (DBSCALE) algorithm. The results taken after implementation shows the proposed method gives better clusters. © Springer Science+Business Media Singapore 2016.

Gupta J.,Thadomal Shahani Engineering College | Gadge J.,Thadomal Shahani Engineering College
2014 International Conference on Circuits, Systems, Communication and Information Technology Applications, CSCITA 2014 | Year: 2014

Recommendation systems attempt to predict the preference or rating that a user would give to an item. Knowledge discovery techniques can be applied to the problem of making personalized recommendations about items or information during a user's visit to a website. Collaborative Filtering algorithms give recommendations to a user based on the ratings of other users in the system. Traditional collaborative filtering algorithms face issues such as scalability, sparsity and cold start. In the proposed framework, prediction using item based collaborative filtering is combined with prediction using demographics based user clusters in an adaptive weighted scheme. The proposed solution will be scalable while addressing user cold start. © 2014 IEEE.

Pathak R.K.,Thadomal Shahani Engineering College
Asian Journal of Microbiology, Biotechnology and Environmental Sciences | Year: 2012

Protease are among the oldest enzyme known to human being with the molecular weight ranging from 18 to 90 Kda. They are the enzymes that catalyzes the splitting of proteins into smaller peptide fractions and amino acids by a process known as proteolysis. These are found in wide diversity of sources like plant, animals and microorganisms. The microorganisms being the major source. Protease catalyzes the total hydrolysis of protein and have broad scope of usage in the industries. The increasing demand of protease in industries led to isolation of microorganisms producing protease. In the present study the microorganisms were isolated from alkaline soil collected from beach. The serial dilution was performed and 5 bacterial strains were isolated. The growth characteristics were studied. The microorganisms producing protease were screened using folin- lowry method and the activity of enzyme was determined. © Global Science Publications.

Menghani G.,Thadomal Shahani Engineering College
2010 1st International Conference on Parallel, Distributed and Grid Computing, PDGC - 2010 | Year: 2010

Scheduling of tasks in a heterogeneous computing (HC) environment is a critical task. It is also a well-known NP-complete problem, and hence several researchers have presented a number of heuristics for the same. The paper begins with introducing a new heuristic called Sympathy, and later a variant called Segmented Sympathy. A new Genetic Algorithm based heuristic using the Segmented Sympathy heuristic is proposed, which is aimed at improving over the speed and makespan of the implementation by Braun et al. Finally, the results of Simulation reveal that the proposed Genetic Algorithm gave up to 8.34% and on an average 3.42% better makespans. The new heuristic is also about 160% faster with respect to the execution time. © 2010 IEEE.

Khan S.,Thadomal Shahani Engineering College | Kulkarni A.,Thadomal Shahani Engineering College
Proceedings of the 2010 International Conference on Signal and Image Processing, ICSIP 2010 | Year: 2010

There is various forgeries possible on digital images such as image tampering, copy-move forgery and image compositing. Out of these, copy-move forgery is a type of image forgery, in which a part of original digital image is copied and pasted to another part in the same original image to make it, forged one. This paper describes blind image forensics approach for detecting copy-move forgery. In this technique forged image is reduced in dimension using DWT (Discrete Wavelet Transform) [1]. Then the compressed image is divided into overlapping blocks of fixed size. These blocks are sorted using lexicographic sorting and duplicated blocks are identified using Phase Correlation as similarity criterion. Detected forgery is displayed with the help of duplication map that gives count of pixels forged. This approach drastically reduces the time needed for the detection process and improves the accuracy of detection. ©2010 IEEE.

Pathak R.K.,Thadomal Shahani Engineering College
Asian Journal of Microbiology, Biotechnology and Environmental Sciences | Year: 2011

Immobilization, has emerged since last decade as a very powerful tool to improve almost all enzyme properties like stability, activity, specificity and selectivity, and reduction of inhibition. The immobilization may help to solve some of the problems of enzymes as industrial biocatalysts like enzyme recovery for reuse. In the present study 5 bacterial strains were isolated from alkaline soil collected from a beach. These cells were screened for protease activity. The initial activity of the cell was measured. The strain having high activity was selected for immobilization. The microorganisms were immobilized in various matrices, such as ca-alginate, polyacrylamide, agar-agar, and gelatin. The batch of 36 hrs was performed and the activity of the enzyme was measured for different matrices. The Polyacrylamide showed the maximum enzyme activity. The batches were performed for 9 days to check the potential application and it was observed that the enzyme activity was high for first 6 days and later it started reducing. © Global Science Publications.

Mandal N.,Thadomal Shahani Engineering College | Jadhav S.,Thadomal Shahani Engineering College
2016 IEEE International Conference on Current Trends in Advanced Computing, ICCTAC 2016 | Year: 2016

Providing security to the network in an open source has become a major challenge nowadays. Data transmitted through the network is not considered to be safe. Various threats like sniffing, spoofing, phishing exist. This paper presents an overview of various network threats and attacks to the network. There are many tools in the open source which are developed as a counter measure to these attacks. Tools like nmap, tcpdump, firewall, wireshark has been discussed in this paper. © 2016 IEEE.

Dixit S.,Thadomal Shahani Engineering College | Padmadas V.,Thadomal Shahani Engineering College
Advances in Intelligent Systems and Computing | Year: 2016

Evaluating the usability of web applications in terms of their learn-ability and navigability with the current design principles is a prospective area where improvement in the web designing principles should be revolutionised. The availability of any help system while navigating the web applications could be a progressive change towards providing better experience to the end users. Providing such system would be cost effective rather than suggesting the improvements in the design process which might not comply evenly with the web application developers across the globe. The research work presented here aims at providing such a help system to users which improves the user’s experience of the web application in terms of two factors: learn-ability and navigability. The proposed help system provides the suggestions in the form of links to be clicked next according to the user goal. The test-bed for the experiments conducted is Virtual Labs web application which is designed as a set of virtual laboratories aimed at users who are deprived of physical infrastructure for carrying out laboratory experiments in their institutes. © Springer Science+Business Media Singapore 2016.

Loading Thadomal Shahani Engineering College collaborators
Loading Thadomal Shahani Engineering College collaborators