Kalyani Mali

Clustering and its validation in a symbolic framework

Clustering of symbolic data, using different validity indices, is proposed for determining the optimal number of meaningful clusters. Symbolic objects include linguistic, nominal, boolean, and interval-type of features, along with quantitative attributes. Clustering in this domain involves the use of symbolic dissimilarity between the objects. The novelty of the method lies in transforming the different clustering validity indices, like Normalized Modified Huberts statistic, Davies-Bouldin index and Dunns index, from the quantitative domain to the symbolic framework. The effectiveness of symbolic clustering is demonstrated on several real life benchmark data sets.

Symbolic classification, clustering and fuzzy radial basis function network

Symbolic fuzzy classification is proposed using fuzzy radial basis function network, with fuzzy c-medoids clustering at the hidden layer. Symbolic objects include linguistic, nominal, boolean and interval-type of features, along with quantitative attributes. Classification and clustering in this domain involve the use of symbolic dissimilarity between the objects. Fuzzy memberships are used for appropriately handling uncertainty inherent in real-life decisions. The fuzzy radial basis function (FRBF) network here comprises an integration of the principles of radial basis function (RBF) network and fuzzy c-medoids clustering, for handling non-numeric data. The optimal number of hidden nodes is determined by using clustering validity indices, like normalized modified Huberts statistic and Davies-Bouldin index, in the symbolic framework. The effectiveness of the symbolic fuzzy classification is demonstrated on real-life benchmark data sets. Comparison is provided with the performance of a decision tree.

Fuzzy-based artificial bee colony optimization for gray image segmentation

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.

Clustering of Symbolic Data and Its Validation

Categorical clustering of symbolic data and its validation has been studied. Symbolic objects include linguistic, nominal, boolean, and interval-type data. Clustering in this domain involves the use of symbolic similarity and dissimilarity between the objects. The optimal number of meaningful clusters are determined in the process. The effectiveness of the symbolic clustering is demonstrated on a real life benchmark dataset.

Modified cuckoo search algorithm in microscopic image segmentation of hippocampus

Microscopic image analysis is one of the challenging tasks due to the presence of weak correlation and different segments of interest that may lead to ambiguity. It is also valuable in foremost meadows of technology and medicine. Identification and counting of cells play a vital role in features extraction to diagnose particular diseases precisely. Different segments should be identified accurately in order to identify and to count cells in a microscope image. Consequently, in the current work, a novel method for cell segmentation and identification has been proposed that incorporated marking cells. Thus, a novel method based on cuckoo search after pre‐processing step is employed. The method is developed and evaluated on light microscope images of rats’ hippocampus which used as a sample for the brain cells. The proposed method can be applied on the color images directly. The proposed approach incorporates the McCullochs method for lévy flight production in cuckoo search (CS) algorithm. Several objective functions, namely Otsus method, Kapur entropy and Tsallis entropy are used for segmentation. In the cuckoo search process, the Otsus between class variance, Kapurs entropy and Tsallis entropy are employed as the objective functions to be optimized. Experimental results are validated by different metrics, namely the peak signal to noise ratio (PSNR), mean square error, feature similarity index and CPU running time for all the test cases. The experimental results established that the Kapurs entropy segmentation method based on the modified CS required the least computational time compared to Otsus between‐class variance segmentation method and the Tsallis entropy segmentation method. Nevertheless, Tsallis entropy method with optimized multi‐threshold levels achieved superior performance compared to the other two segmentation methods in terms of the PSNR.

A wavelet based image retrieval

An wavelet based image retrieval scheme is described. Wavelet transforms are applied to compress the image space, thereby reducing noise. A combination of texture, shape, topology and fuzzy geometric features, that is invariant to orientation, scale and object deformation, are extracted from this compressed image. The use of wavelet based compression eliminates the need for any other preprocessing. The extracted features serve as the signature of the compressed images, in terms of their content. Their use in content based image retrieval is demonstrated.

A novel data partitioning and rule selection technique for modeling high-order fuzzy time series

Abstract Fuzzy time series forecasting is an emergent research topic. In fuzzy time series model design, accuracy of forecast is dependent on two major issues: (1) Efficient data partitioning (2) Establishing Fuzzy logical relationships for Prediction. In this study, a new data partitioning technique based on rough-fuzzy approach has been proposed. Then, for the prediction purpose, a novel rule selection criterion has been adopted. In addition to that a mechanism is devised to deal with the situation when there is no matching rule present in the training data. Motivation for the present work is to overcome the drawback of existing high-order fuzzy time series models by avoiding the computations of complicated fuzzy logical relationship considering all previous states at a time and then explicit matching of those rules. The proposed work produces output of improved accuracy with selective rules only. In this high order model fuzzy logical relationships for each time lag are established separately and predictions are combined at the end to produce final result. Performance of the model is evaluated using TAIEX dataset. This idea also outperforms the some of the recent fuzzy time series forecasting models using the same dataset, in terms of forecast accuracy.

Biomedical image enhancement based on modified Cuckoo Search and morphology

This work describes an method for biomedical image enhancement using modified Cuckoo Search Algorithm with some Morphological Operation. In recent years, various digital image processing techniques are developed. Computer Vision, machine interfaces, manufacturing industry, data compression for storage, vehicle tracking and many more are some of the domains of digital image processing application. In most of the cases, digital biomedical images contains various types of noise, artifacts etc. and are not useful for direct applications. Before using it in any process, the input image has to be gone through some preprocessing stages; such preprocessing is generally called as image enhancement. In this work, a new technique has been proposed to enhance biomedical images using modified cuckoo search algorithm and morphological operation. Presence of noise and other unwanted objects generates distortion in an image and it will affect the ultimate result of the process. In case of biomedical images, accuracy of the results is very important. It may also decrease the discernibility of many features inside the images. It can affect the classification accuracy. In this work, this issue has been targeted and improved by obtaining better contrast value after converting the color image into grayscale image. The basic property of the cuckoo search algorithm is that the amplitudes of its components are capable to objectively describe the contribution of the gray levels to the formation of image information for the best contrast value of a digital image. The proposed method modified the conventional cuckoo search method by employing the McCullochs method for levy flight generation. After computing the best contrast value, morphological operation has been applied. In morphological operation based phase, the intensity parameters are tuned for quality enhancement. Experimental results illustrate the effectiveness of this work.

Detection of skin disease using metaheuristic supported artificial neural networks

Automated, efficient and accurate classification of skin diseases using digital images of skin is very important for bio-medical image analysis. Various techniques have already been developed by many researchers. In this work, a technique based on meta-heuristic supported artificial neural network has been proposed to classify images. Here 3 common skin diseases have been considered namely angioma, basal cell carcinoma and lentigo simplex. Images have been obtained from International Skin Imaging Collaboration (ISIC) dataset. A popular multi objective optimization method called Non-dominated Sorting Genetic Algorithm — II is employed to train the ANN (NNNSGA-II). Different feature have been extracted to train the classifier. A comparison has been made with the proposed model and two other popular meta-heuristic based classifier namely NN-PSO (ANN trained with Particle Swarm Optimization) and NN-GA (ANN trained with Genetic algorithm). The results have been evaluated using various performances measuring metrics such as accuracy, precision, recall and F-measure. Experimental results clearly show the superiority of the proposed NN-NSGA-II model with different features.

High Order Time Series Forecasting using Fuzzy Discretization

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.