A fast algorithm for finding frequent episodes in event streams

Frequent episode discovery is a popular framework for mining data available as a long sequence of events. An episode is essentially a short ordered sequence of event types and the frequency of an episode is some suitable measure of how often the episode occurs in the data sequence. Recently,we proposed a new frequency measure for episodes based on the notion of non-overlapped occurrences of episodes in the event sequence, and showed that, such a definition, in addition to yielding computationally efficient algorithms, has some important theoretical properties in connecting frequent episode discovery with HMM learning. This paper presents some new algorithms for frequent episode discovery under this non-overlapped occurrences-based frequency definition. The algorithms presented here are better (by a factor of N, where N denotes the size of episodes being discovered) in terms of both time and space complexities when compared to existing methods for frequent episode discovery. We show through some simulation experiments, that our algorithms are very efficient. The new algorithms presented here have arguably the least possible orders of spaceand time complexities for the task of frequent episode discovery.

Clustering Based Large Margin Classification: A Scalable Approach using SOCP Formulation

This paper presents a novel Second Order Cone Programming (SOCP) formulation for large scale binary classification tasks. Assuming that the class conditional densities are mixture distributions, where each component of the mixture has a spherical covariance, the second order statistics of the components can be estimated efficiently using clustering algorithms like BIRCH. For each cluster, the second order moments are used to derive a second order cone constraint via a Chebyshev-Cantelli inequality. This constraint ensures that any data point in the cluster is classified correctly with a high probability. This leads to a large margin SOCP formulation whose size depends on the number of clusters rather than the number of training data points. Hence, the proposed formulation scales well for large datasets when compared to the state-of-the-art classifiers, Support Vector Machines (SVMs). Experiments on real world and synthetic datasets show that the proposed algorithm outperforms SVM solvers in terms of training time and achieves similar accuracies.

Investigating Diproline Segments in Proteins: Occurrences, Conformation and Classification

The covalent linkage between the side-chain and the backbone nitrogen atom of proline leads to the formation of the five-membered pyrrolidine ring and hence restriction of the backbone torsional angle phi to values of -60 degrees +/- 30 degrees for the L-proline. Diproline segments constitute a chain fragment with considerably reduced conformational choices. In the current study, the conformational states for the diproline segment ((L)Pro-(L)Pro) found in proteins has been investigated with an emphasis on the cis and trans states for the Pro-Pro peptide bond. The occurrence of diproline segments in turns and other secondary structures has been studied and compared to that of Xaa-Pro-Yaa segments in proteins which gives us a better understanding on the restriction imposed on other residues by the diproline segment and the single proline residue. The study indicates that P(II)-P(II) and P(II)-alpha are the most favorable conformational states for the diproline segment. The analysis on Xaa-Pro-Yaa sequences reveals that the XaaPro peptide bond exists preferably as the trans conformer rather than the cis conformer. The present study may lead to a better understanding of the behavior of proline occurring in diproline segments which can facilitate various designed diproline-based synthetic templates for biological and structural studies. (C) 2011 Wiley Periodicals, Inc. Biopolymers 97: 54-64, 2012.

Multi-spectral satellite image classification using Glowworm Swarm Optimization

This paper investigates a new Glowworm Swarm Optimization (GSO) clustering algorithm for hierarchical splitting and merging of automatic multi-spectral satellite image classification (land cover mapping problem). Amongst the multiple benefits and uses of remote sensing, one of the most important has been its use in solving the problem of land cover mapping. Image classification forms the core of the solution to the land cover mapping problem. No single classifier can prove to classify all the basic land cover classes of an urban region in a satisfactory manner. In unsupervised classification methods, the automatic generation of clusters to classify a huge database is not exploited to their full potential. The proposed methodology searches for the best possible number of clusters and its center using Glowworm Swarm Optimization (GSO). Using these clusters, we classify by merging based on parametric method (k-means technique). The performance of the proposed unsupervised classification technique is evaluated for Landsat 7 thematic mapper image. Results are evaluated in terms of the classification efficiency - individual, average and overall.

Modelling and classification of respiratory volume wavefourms

A technique is proposed for classifying respiratory volume waveforms(RVW) into normal and abnormal categories of respiratory pathways. The proposed method transforms the temporal sequence into frequency domain by using an orthogonal transform, namely discrete cosine transform (DCT) and the transformed signal is pole-zero modelled. A Bayes classifier using model pole angles as the feature vector performed satisfactorily when a limited number of RVWs recorded under deep and rapid (DR) manoeuvre are classified.

Classification of road damage due to earthquakes

Earthquakes cause massive road damage which in turn causes adverse effects on the society. Previous studies have quantified the damage caused to residential and commercial buildings; however, not many studies have been conducted to quantify road damage caused by earthquakes. In this study, an attempt has been made to propose a new scale to classify and quantify the road damage due to earthquakes based on the data collected from major earthquakes in the past. The proposed classification for road damage due to earthquake is called as road damage scale (RDS). Earthquake details such as magnitude, distance of road damage from the epicenter, focal depth, and photographs of damaged roads have been collected from various sources with reported modified Mercalli intensity (MMI). The widely used MMI scale is found to be inadequate to clearly define the road damage. The proposed RDS is applied to various reported road damage and reclassified as per RDS. The correlation between RDS and earthquake parameters of magnitude, epicenter distance, hypocenter distance, and combination of magnitude with epicenter and hypocenter distance has been studied using available data. It is observed that the proposed RDS correlates well with the available earthquake data when compared with the MMI scale. Among several correlations, correlation between RDS and combination of magnitude and epicenter distance is appropriate. Summary of these correlations, their limitations, and the applicability of the proposed scale to forecast road damages and to carry out vulnerability analysis in urban areas is presented in the paper.

Hybrid Bayesian Classifier for Improved Classification Accuracy

The widely used Bayesian classifier is based on the assumption of equal prior probabilities for all the classes. However, inclusion of equal prior probabilities may not guarantee high classification accuracy for the individual classes. Here, we propose a novel technique-Hybrid Bayesian Classifier (HBC)-where the class prior probabilities are determined by unmixing a supplemental low spatial-high spectral resolution multispectral (MS) data that are assigned to every pixel in a high spatial-low spectral resolution MS data in Bayesian classification. This is demonstrated with two separate experiments-first, class abundances are estimated per pixel by unmixing Moderate Resolution Imaging Spectroradiometer data to be used as prior probabilities, while posterior probabilities are determined from the training data obtained from ground. These have been used for classifying the Indian Remote Sensing Satellite LISS-III MS data through Bayesian classifier. In the second experiment, abundances obtained by unmixing Landsat Enhanced Thematic Mapper Plus are used as priors, and posterior probabilities are determined from the ground data to classify IKONOS MS images through Bayesian classifier. The results indicated that HBC systematically exploited the information from two image sources, improving the overall accuracy of LISS-III MS classification by 6% and IKONOS MS classification by 9%. Inclusion of prior probabilities increased the average producer's and user's accuracies by 5.5% and 6.5% in case of LISS-III MS with six classes and 12.5% and 5.4% in IKONOS MS for five classes considered.

Fast Robust Pattern Classification Algorithms for Real Time Neuro-Motor Prosthetic Applications

In this paper, we give a brief review of pattern classification algorithms based on discriminant analysis. We then apply these algorithms to classify movement direction based on multivariate local field potentials recorded from a microelectrode array in the primary motor cortex of a monkey performing a reaching task. We obtain prediction accuracies between 55% and 90% using different methods which are significantly above the chance level of 12.5%.