Amit Kumar Saxena

Evolutionary methods for unsupervised feature selection using Sammon’s stress function

In this paper, four methods are proposed for feature selection in an unsupervised manner by using genetic algorithms. The proposed methods do not use the class label information but select a set of features using a task independent criterion that can preserve the geometric structure (topology) of the original data in the reduced feature space. One of the components of the fitness function is Sammon’s stress function which tries to preserve the topology of the high dimensional data when reduced into the lower dimensional one. In this context, in addition to using a fitness criterion, we also explore the utility of unfitness criterion to select chromosomes for genetic operations. This ensures higher diversity in the population and helps unfit chromosomes to become more fit. We use four different ways for evaluation of the quality of the features selected: Sammon error, correlation between the inter-point distances in the two spaces, a measure of preservation of cluster structure found in the original and reduced spaces and a classifier performance. The proposed methods are tested on six real data sets with dimensionality varying between 9 and 60. The selected features are found to be excellent in terms of preservation topology (inter-point geometry), cluster structure and classifier performance. We do not compare our methods with other methods because, unlike other methods, using four different ways we check the quality of the selected features by finding how well the selected features preserve the “structure” of the original data.

A review of clustering techniques and developments

This paper presents a comprehensive study on clustering: exiting methods and developments made at various times. Clustering is defined as an unsupervised learning where the objects are grouped on the basis of some similarity inherent among them. There are different methods for clustering the objects such as hierarchical, partitional, grid, density based and model based. The approaches used in these methods are discussed with their respective states of art and applicability. The measures of similarity as well as the evaluation criteria, which are the central components of clustering, are also presented in the paper. The applications of clustering in some fields like image segmentation, object and character recognition and data mining are highlighted.

An Improved Polynomial Neural Network Classifier Using Real-Coded Genetic Algorithm

In this paper, a novel approach is proposed to improve the classification performance of a polynomial neural network (PNN). In this approach, the partial descriptions (PDs) are generated at the first layer based on all possible combinations of two features of the training input patterns of a dataset. The set of PDs from the first layer, the set of all input features, and a bias constitute the chromosome of the real-coded genetic algorithm (RCGA). A system of equations is solved to determine the values of the real coefficients of each chromosome of the RCGA for the training dataset with the mean classification accuracy (CA) as the fitness value of each chromosome. To adjust these values for unknown testing patterns, the RCGA is iterated in the usual manner using simple selection, crossover, mutation, and elitist selection. The method is tested extensively with the University of California, Irvine benchmark datasets by utilizing tenfold cross validation of each dataset, and the performance is compared with various well-known state-of-the-art techniques. The results obtained from the proposed method in terms of CA are superior and outperform other known methods on various datasets.

Vertical Collaborative Fuzzy C-Means for Multiple EEG Data Sets

Vertical Collaborative Fuzzy C-Means VC-FCM is a clustering method that performs clustering on a data set of having some set of patterns with the collaboration of some knowledge which is obtained from other data set having the same number of features but different set of patterns. Uncertain relationship lies in data between the data sets as well as within a dataset. Practically data of the same group of objects are usually stored in different datasets; in each data set, the data dimensions are not necessarily the same and unreal data may exist. Fuzzy clustering of a single data set would bring about less reliable results. And these data sets cannot be integrated for some reasons. An interesting application of vertical clustering occurs when dealing with huge data sets. Instead of clustering them in a single pass, we split them into individual data sets, cluster each of them separately, and reconcile the results through the collaborative exchange of prototypes. Vertical collaborative fuzzy C-Means is a useful tool for dealing collaborative clustering problems where a feature space is described in different pattern-sets. In this paper we use collaborative fuzzy clustering, first we cluster each data set individually and then optimize in accordance with the dependency of these datasets is adopted so as to improve the quality of fuzzy clustering of a single data set with the help of other data sets, taking personal privacy and security of data into consideration.

Novel Approach for the use of Small World Theory in Particle Swarm Optimization

This paper introduces a novel particle swarm optimization (PSO) framework using concepts of small world theory. Here, the PSO algorithm is applied on the small world network model as given by Jon Kleinberg. The proposed methodology is applied to four standard test functions. The results obtained are compared with Kennedys method of applying PSO on the Watts-Strogatz small world network model and also with other PSO variants. The comparative study demonstrates the effectiveness of the proposed approach.

Collaborative fuzzy rule learning for Mamdani type fuzzy inference system with mapping of cluster centers

This paper demonstrates a novel model for Mamdani type fuzzy inference system by using the knowledge learning ability of collaborative fuzzy clustering and rule learning capability of FCM. The collaboration process finds consistency between different datasets, these datasets can be generated at various places or same place with diverse environment containing common features space and bring together to find common features within them. For any kind of collaboration or integration of datasets, there is a need of keeping privacy and security at some level. By using collaboration process, it helps fuzzy inference system to define the accurate numbers of rules for structure learning and keeps the performance of system at satisfactory level while preserving the privacy and security of given datasets.

A preprocessed induced partition matrix based collaborative fuzzy clustering for data analysis

Preprocessing is generally used for data analysis in the real world datasets that are noisy, incomplete and inconsistent. In this paper, preprocessing is used to refine the inconsistency of the prototype and partition matrices before getting involved in the collaboration process. To date, almost all organizations are trying to establish some collaboration with others in order to enhance the performance of their services. Due to privacy and security issues they cannot share their information and data with each other. Collaborative clustering helps this kind of collaborative process while maintaining the privacy and security of data and can still yield a satisfactory result. Preprocessing helps the collaborative process by using an induced partition matrix generated based on cluster prototypes. The induced partition matrix is calculated from local data by using the cluster prototypes obtained from other data sites. Each member of the collaborating team collects the data and generates information locally by using the fuzzy c-means (FCM) and shares the cluster prototypes to other members. The other members preprocess the centroids before collaboration and use this information to share globally through collaborative fuzzy clustering (CFC) with other data. This process helps system to learn and gather information from other data sets. It is found that preprocessing helps system to provide reliable and satisfactory result, which can be easily visualized through our simulation results in this paper.

A Novel Fuzzy Logic Model for Pseudo-Relevance Feedback-Based Query Expansion

In this paper, a novel fuzzy logic-based expansion approach considering the relevance score produced by different rank aggregation approaches is proposed. It is well known that different rank aggregation approaches yield different relevance scores for each term. The proposed fuzzy logic approach combines different weights of each term by using fuzzy rules to infer the weights of the additional query terms. Experimental results demonstrate that the proposed approach achieves significant improvement over individual expansion, aggregated and other related state-of-the-arts methods.

A sequential cosine similarity based feature selection technique for high dimensional datasets

Due to day to day use of information processing in society, the size of the databases has become tremendously high. It has been realized that most of the times, all parameters (called features precisely here) are not required to decide the outcome (or decision) of an instance. Therefore feature selection is an important step in data processing. In this paper, a novel method is presented to select features. In the method, cosine similarity of individual feature of the database with the respective class is computed and kept in an array in descending order. The first feature of this array is combined with rest of the features sequentially one by one. If the classification accuracy of the combination of features increases then the combination is accepted otherwise the responsible features are eliminated from the combination. In this manner all features are tested and a final subset of features is obtained. The results obtained after rigorous experiments on the proposed method on high dimensional databases and comparing with other methods reported so far are encouraging. It is therefore recommended that the proposed method can be applied for high dimensional data processing.

A Cosine-Similarity Mutual-Information Approach for Feature Selection on High Dimensional Datasets

A novel hybrid method based on Cosine Similarity and Mutual Information is presented to find out relevant feature subset. Initially, the supervised Cosine Similarity of each feature is calculated with respect to the class vector and then features are grouped based on the obtained cosine similarity values. From each group the best mutual informative feature is selected. The selected features subset is tested using the three classifiers namely Naive Bayes NB, K-Nearest Neighbor and Classification and Regression trees CART for getting classification accuracy. The proposed method is applied to various high dimensional datasets. Obtained results showed that the proposed method is capable of eliminating the redundant and irrelevant features.