Showing papers by "Kalyani Mali published in 2016"

Fuzzy-based artificial bee colony optimization for gray image segmentation

Abstract: In this article, we have proposed an image segmentation algorithm FABC, which is a kind of unsupervised classification (clustering), where we combine the concept of artificial bee colony optimization (ABC) and the popular fuzzy C means (FCM) and named it as fuzzy-based ABC or FABC. In FABC, we have used fuzzy membership function to search for optimum cluster centers using ABC. FABC is more efficient than other optimization techniques such as genetic algorithm (GA), particle swarm optimization (PSO) and expectation maximization (EM) algorithms. FABC overcomes the drawbacks of FCM as it does not depend on the choice of initial cluster centers and it performs better in terms of convergency, time complexity, robustness and segmentation accuracy. FABC becomes more efficient as it takes the advantage of the randomized characteristics of ABC for the initialization of the cluster centers. The experiments with FABC, GA, PSO and EM have been done over various grayscale images including some synthetic, medical and texture images, and segmentation of such images is very difficult due to the low contrast, noise and other imaging ambiguities. The efficiency of FABC is proven by both quantitative and qualitative measures.

A Novel Lossless Image Encryption Method using DNA Substitution and Chaotic Logistic Map

Abstract: Presently, there is a growth in the transmission of image and video data. Security becomes a main issue. Very strong image cryptographic techniques are a solution to this problem. There is a use of a randomly generated public key and based on that there is an application of DNA algorithm. In the proposed method DNA algorithm based substitution is used for spatial domain bit permutation. Here the chaotic logistic map is used for generating a pseudorandom bit sequence. We have generated 48bit length sequences for every pixel. After the substitution operation, a final layer of security is imposed to make this process more fault tolerant. The For checking the strength of the work a series of tests are performed and various parameters are checked like Correlation Coefficient Analysis, analysis of NPCR and UACI values etc.

High Order Time Series Forecasting using Fuzzy Discretization

Abstract: In recent years, various methods for forecasting fuzzy time series have been presented in different areas, such as stock price, enrollments, weather, production etc It is observed that in most of the cases, static length of intervals/equal length of interval has been used Length of the interval has significant role on forecasting accuracy The objective of this present study is to incorporate the idea of fuzzy discretization into interval creation and examine the effect of positional information of elements within a group or interval to the forecast This idea outperforms the existing high order forecast methods using fixed interval Experiments are carried on three datasets including Lahi production data, enrollment data and rainfall data which deal with a lot of uncertainty

Clustering with vague set

Abstract: This article constitutes a new method of clustering. The classical concept of fuzzy logic provides the means to represent approximate knowledge. Therefore the elements which lie in the boundaries of several sets are forced to belong to any of the sets. Introduction to fuzzy sets undoubtedly increases the computational burden, so there is an extension into shadowed sets, which takes the essence of fuzzy sets and reduce the computational complexity of the fuzzy sets. Shadowed set is based on three valued logic which represents the concept of full exclusion(0), full participation(1) and uncertain. So a shadowed set comprises of the elements with full participation in the set and those which are uncertain of this set. Here we have used another set theoretic concept named as vague set, it changes the general concept of fuzzy set and it removes the uncertainty of the shadowed set. Each object of this vague set has a grade of membership whose value is a continuous sub interval of [0,1]. In this study we have proposed a set theoretic concept which combines the concept of shadowed set as well as vague set. We use the proposed concept for the clustering of synthetic data sets and real data sets. The experimental results are analyzed by both quantitative and qualitative measures.

Pixel variation problem identification in image segmentation for big image data set in cloud platform

Abstract: This paper describes problem regarding pixel identification for image segmentation methodologies for big image dataset for real robust applications. For medical, urban or satellite images, segmentation process can done through high computing nodes for high I/O performance, low computing time by considering low overhead of transmission rate. Multi thresholding segmentation may apply for large images must conduct due to features of different computing nodes for different images. For heterogeneity after reduction of a big image data set into image set there is a lack of information regarding pixel may arise in cloud platform. This paper identified the problem and shown how that one occurs.