Interval Data Classification under Partial Information: A Chance-Constraint Approach

This paper presents a Chance-constraint Programming approach for constructing maximum-margin classifiers which are robust to interval-valued uncertainty in training examples. The methodology ensures that uncertain examples are classified correctly with high probability by employing chance-constraints. The main contribution of the paper is to pose the resultant optimization problem as a Second Order Cone Program by using large deviation inequalities, due to Bernstein. Apart from support and mean of the uncertain examples these Bernstein based relaxations make no further assumptions on the underlying uncertainty. Classifiers built using the proposed approach are less conservative, yield higher margins and hence are expected to generalize better than existing methods. Experimental results on synthetic and real-world datasets show that the proposed classifiers are better equipped to handle interval-valued uncertainty than state-of-the-art.

Stochastic modelling of monthly rainfall

A transformation is suggested which can transform a non-Gaussian monthly hydrological time series into a Gaussian one. The suggested approach is verified with data of ten Indian rainfall time series. Incidentally, it is observed that once the deterministic trends are removed, the transformation leads to an uncorrelated process for monthly rainfall. The procedure for normalization is general enough in that it should be also applicable to river discharges. This is verified to a limited extent by considering data of two Indian river discharges.

Variability of Indian summer monsoon rainfall in daily data from gauge and satellite

It has long been thought that tropical rainfall retrievals from satellites have large errors. Here we show, using a new daily 1 degree gridded rainfall data set based on about 1800 gauges from the India Meteorology Department (IMD), that modern satellite estimates are reasonably close to observed rainfall over the Indian monsoon region. Daily satellite rainfalls from the Global Precipitation Climatology Project (GPCP 1DD) and the Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA) are available since 1998. The high summer monsoon (June-September) rain over the Western Ghats and Himalayan foothills is captured in TMPA data. Away from hilly regions, the seasonal mean and intraseasonal variability of rainfall (averaged over regions of a few hundred kilometers linear dimension) from both satellite products are about 15% of observations. Satellite data generally underestimate both the mean and variability of rain, but the phase of intraseasonal variations is accurate. On synoptic timescales, TMPA gives reasonable depiction of the pattern and intensity of torrential rain from individual monsoon low-pressure systems and depressions. A pronounced biennial oscillation of seasonal total central India rain is seen in all three data sets, with GPCP 1DD being closest to IMD observations. The new satellite data are a promising resource for the study of tropical rainfall variability.

Robust and High-resolution Voiced/Unvoiced Classification in Noisy Speech Using A Signal Smoothness Criterion

We propose a novel technique for robust voiced/unvoiced segment detection in noisy speech, based on local polynomial regression. The local polynomial model is well-suited for voiced segments in speech. The unvoiced segments are noise-like and do not exhibit any smooth structure. This property of smoothness is used for devising a new metric called the variance ratio metric, which, after thresholding, indicates the voiced/unvoiced boundaries with 75% accuracy for 0dB global signal-to-noise ratio (SNR). A novelty of our algorithm is that it processes the signal continuously, sample-by-sample rather than frame-by-frame. Simulation results on TIMIT speech database (downsampled to 8kHz) for various SNRs are presented to illustrate the performance of the new algorithm. Results indicate that the algorithm is robust even in high noise levels.

Feature extraction for fingerprint classification

This paper presents two algorithms for smoothing and feature extraction for fingerprint classification. Deutsch's(2) Thinning algorithm (rectangular array) is used for thinning the digitized fingerprint (binary version). A simple algorithm is also suggested for classifying the fingerprints. Experimental results obtained using such algorithms are presented.

Classification of Nonenzymatic Homologues of Protein Kinases

Protein Kinase-Like Non-kinases (PKLNKs), which are closely related to protein kinases, lack the crucial catalytic aspartate in the catalytic loop, and hence cannot function as protein kinase, have been analysed. Using various sensitive sequence analysis methods, we have recognized 82 PKLNKs from four higher eukaryotic organisms, namely, Homo sapiens, Mus musculus, Rattus norvegicus, and Drosophila melanogaster. On the basis of their domain combination and function, PKLNKs have been classified mainly into four categories: (1) Ligand binding PKLNKs, (2) PKLNKs with extracellular protein-protein interaction domain, (3) PKLNKs involved in dimerization, and (4) PKLNKs with cytoplasmic protein-protein interaction module. While members of the first two classes of PKLNKs have transmembrane domain tethered to the PKLNK domain, members of the other two classes of PKLNKs are cytoplasmic in nature. The current classification scheme hopes to provide a convenient framework to classify the PKLNKs from other eukaryotes which would be helpful in deciphering their roles in cellular processes.

Vocalizations of wild Asian elephants (Elephas maximus): Structural classification and social context

Elephants use vocalizations for both long and short distance communication. Whereas the acoustic repertoire of the African elephant (Loxodonta africana) has been extensively studied in its savannah habitat, very little is known about the structure and social context of the vocalizations of the Asian elephant (Elephas maximus), which is mostly found in forests. In this study, the vocal repertoire of wild Asian elephants in southern India was examined. The calls could be classified into four mutually exclusive categories, namely, trumpets, chirps, roars, and rumbles, based on quantitative analyses of their spectral and temporal features. One of the call types, the rumble, exhibited high structural diversity, particularly in the direction and extent of frequency modulation of calls. Juveniles produced three of the four call types, including trumpets, roars, and rumbles, in the context of play and distress. Adults produced trumpets and roars in the context of disturbance, aggression, and play. Chirps were typically produced in situations of confusion and alarm. Rumbles were used for contact calling within and among herds, by matriarchs to assemble the herd, in close-range social interactions, and during disturbance and aggression. Spectral and temporal features of the four call types were similar between Asian and African elephants.

Pi-turns in proteins and peptides: Classification, conformation, occurrence, hydration and sequence.

The i + 5-->i hydrogen bonded turn conformation (pi-turn) with the fifth residue adopting alpha L conformation is frequently found at the C-terminus of helices in proteins and hence is speculated to be a "helix termination signal." An analysis of the occurrence of i + 5-->i hydrogen bonded turn conformation at any general position in proteins (not specifically at the helix C-terminus), using coordinates of 228 protein crystal structures determined by X-ray crystallography to better than 2.5 A resolution is reported in this paper. Of 486 detected pi-turn conformations, 367 have the (i + 4)th residue in alpha L conformation, generally occurring at the C-terminus of alpha-helices, consistent with previous observations. However, a significant number (111) of pi-turn conformations occur with (i + 4)th residue in alpha R conformation also, generally occurring in alpha-helices as distortions either at the terminii or at the middle, a novel finding. These two sets of pi-turn conformations are referred to by the names pi alpha L and pi alpha R-turns, respectively, depending upon whether the (i + 4)th residue adopts alpha L or alpha R conformations. Four pi-turns, named pi alpha L'-turns, were noticed to be mirror images of pi alpha L-turns, and four more pi-turns, which have the (i + 4)th residue in beta conformation and denoted as pi beta-turns, occur as a part of hairpin bend connecting twisted beta-strands. Consecutive pi-turns occur, but only with pi alpha R-turns. The preference for amino acid residues is different in pi alpha L and pi alpha R-turns. However, both show a preference for Pro after the C-termini. Hydrophilic residues are preferred at positions i + 1, i + 2, and i + 3 of pi alpha L-turns, whereas positions i and i + 5 prefer hydrophobic residues. Residue i + 4 in pi alpha L-turns is mainly Gly and less often Asn. Although pi alpha R-turns generally occur as distortions in helices, their amino acid preference is different from that of helices. Poor helix formers, such as His, Tyr, and Asn, also were found to be preferred for pi alpha R-turns, whereas good helix former Ala is not preferred. pi-Turns in peptides provide a picture of the pi-turn at atomic resolution. Only nine peptide-based pi-turns are reported so far, and all of them belong to pi alpha L-turn type with an achiral residue in position i + 4. The results are of importance for structure prediction, modeling, and de novo design of proteins.

Rainfall changes over tropical montane cloud forests of southern Western Ghats, India

The southern Western Ghats tropical montane cloud forest sites (Gavi, Periyar, High wavys and Venniyar), which are characterized by frequent or seasonal cloud cover at the vegetation level, are considered one of the most threatened ecosystems in India and the world. Three out of four montane cloud forest sites studied in the southern Western Ghats had experienced diminishing trends of seasonal average and total rainfall, especially during summer monsoon season. The highest level of reduction for summer monsoon season was observed at Gavi rainforest station (>20 mm/14 years) in Kerala followed by Venniyar (>20 mm/20 years) site in Tamil Nadu. Average annual and total precipitation increased during the study period irrespective of the seasons over Periyar area, and the greatest values were recorded for season 2 (>25 mm/28 years). Positive trends for winter monsoon rainfall has been observed for three stations (Periyar, High wavys and Venniyar) except Gavi, and the trend was positive and significant (90%) for Periyar and High wavys. Increase in summer monsoon rainfall was observed for Periyar site and the trend was found to be significant (95%).

Two-level k-means clustering algorithm for k-tau relationship establishment and linear-time classification

Partitional clustering algorithms, which partition the dataset into a pre-defined number of clusters, can be broadly classified into two types: algorithms which explicitly take the number of clusters as input and algorithms that take the expected size of a cluster as input. In this paper, we propose a variant of the k-means algorithm and prove that it is more efficient than standard k-means algorithms. An important contribution of this paper is the establishment of a relation between the number of clusters and the size of the clusters in a dataset through the analysis of our algorithm. We also demonstrate that the integration of this algorithm as a pre-processing step in classification algorithms reduces their running-time complexity.

Diurnal-scale signatures of monsoon rainfall over the Indian region from TRMM satellite observations

One of the most important modes of summer season precipitation variability over the Indian region, the diurnal cycle, is studied using the Tropical Rainfall Measuring Mission 3-hourly, 0.25 degrees x 0.25 degrees 3B42 rainfall product for nine years (1999-2007). Most previous studies have provided an analysis of a single year or a few years of satellite-or station-based rainfall data. Our study aims to systematically analyze the statistical characteristics of the diurnal-scale signature of rainfall over the Indian and surrounding regions. Using harmonic analysis, we extract the signal corresponding to diurnal and subdiurnal variability. Subsequently, the 3-hourly time period or the octet of rainfall peak for this filtered signal, referred to as the ``peak octet,'' is estimated, with care taken to eliminate spurious peaks arising out of Gibbs oscillations. Our analysis suggests that over the Bay of Bengal, there are three distinct modes of the peak octet of diurnal rainfall corresponding to 1130, 1430, and 1730 Indian standard time (IST), from the north central to south bay. This finding could be seen to be consistent with southward propagation of the diurnal rainfall pattern reported by earlier studies. Over the Arabian Sea, there is a spatially coherent pattern in the mode of the peak octet (1430 IST), in a region where it rains for more than 30% of the time. In the equatorial Indian Ocean, while most of the western part shows a late night/early morning peak, the eastern part does not show a spatially coherent pattern in the mode of the peak octet owing to the occurrence of a ual maxima (early morng and early/late afternoon). The imalayan foothills were found to have a mode of peak octet corresponding to 0230 IST, whereas over the Burmese mountains and the Western Ghats (west coast of India) the rainfall peaks during late afternoon/early evening (1430-1730 IST). This implies that the phase of the diurnal cycle over inland orography (e. g., Himalayas) is significantly different from coastal orography (e. g., Western Ghats). We also find that over the Gangetic plains, the peak octet is around 1430 IST, a few hours earlier compared to the typical early evening maxima over land.

Shift of peak in summer monsoon rainfall over Korea and its association with El Nino-Southern Oscillation

The annual cycle of rainfall over the Korean Peninsula is marked by two peaks: one during July and the other during August. Since the mid-1970s, the maximum rainfall over the Korean Peninsula has shifted from July to August. This shift in rainfall peak was caused by a significant increase of August rainfall after the mid-1970s. The basic reason for this shift has been traced to a change in teleconnection between El Nino-Southern Oscillation (ENSO) and August rainfall. The relationship between August rainfall over Korea and ENSO changed from 1954-1975 (PI) to 1976-2002 (PII). The variability of August rainfall was significantly associated with sea surface temperature (SST) variation over the eastern equatorial Pacific during PI, but this relationship is absent during the PII period. In El Nino years during PI, low-level westerly and southerly wind anomalies are dominant around the East China Sea, which relates to strong August rainfall. In La Nina years during PI, easterly and northerly wind anomalies are dominant. During the PII period, however, westerly and southerly wind anomalies around the East China Sea were responsible for the high August rainfall over the East Asian region, even though La Nina SST conditions were in effect over the eastern Pacific.

Classification of Indian meteorological stations using cluster and fuzzy cluster analysis, and Kohonen artificial neural networks

The present study deals with the application of cluster analysis, Fuzzy Cluster Analysis (FCA) and Kohonen Artificial Neural Networks (KANN) methods for classification of 159 meteorological stations in India into meteorologically homogeneous groups. Eight parameters, namely latitude, longitude, elevation, average temperature, humidity, wind speed, sunshine hours and solar radiation, are considered as the classification criteria for grouping. The optimal number of groups is determined as 14 based on the Davies-Bouldin index approach. It is observed that the FCA approach performed better than the other two methodologies for the present study.

Kernels for large margin time-series classification

In this paper we propose a novel family of kernels for multivariate time-series classification problems. Each time-series is approximated by a linear combination of piecewise polynomial functions in a Reproducing Kernel Hilbert Space by a novel kernel interpolation technique. Using the associated kernel function a large margin classification formulation is proposed which can discriminate between two classes. The formulation leads to kernels, between two multivariate time-series, which can be efficiently computed. The kernels have been successfully applied to writer independent handwritten character recognition.

Relationship between annual rainfall and tree mortality in a tropical dry forest: Results of a 19-year study at Mudumalai, southern India

Variability in rainfall is known to be a major influence on the dynamics of tropical forests, especially rates and patterns of tree mortality. In tropical dry forests a number of contributing factors to tree mortality, including dry season fire and herbivory by large herbivorous mammals, could be related to rainfall patterns, while loss of water potential in trees during the dry season or a wet season drought could also result in enhanced rates of death. While tree mortality as influenced by severe drought has been examined in tropical wet forests there is insufficient understanding of this process in tropical dry forests. We examined these causal factors in relation to inter-annual differences in rainfall in causing tree mortality within a 50-ha Forest Dynamics Plot located in the tropical dry deciduous forests of Mudumalai, southern India, that has been monitored annually since 1988. Over a 19-year period (1988-2007) mean annual mortality rate of all stems >1 cm dbh was 6.9 +/- 4.6% (range = 1.5-17.5%); mortality rates broadly declined from the smaller to the larger size classes with the rates in stems >30 cm dbh being among the lowest recorded in tropical forest globally. Fire was the main agent of mortality in stems 1-5 cm dbh, elephant-herbivory in stems 5-10 cm dbh, and other natural causes in stems > 10 cm dbh. Elephant-related mortality did not show any relationship to rainfall. On the other hand, fire-related mortality was significantly negatively correlated to quantity of rainfall during the preceding year. Mortality due to other causes in the larger stem sizes was significantly negatively correlated to rainfall with a 2-3-year lag, suggesting that water deficit from mild or prolonged drought enhanced the risk of death but only with a time lag that was greater than similar lags in tree mortality observed in other forest types. In this respect, tropical dry forests growing in regions of high rainfall variability may have evolved greater resistance to rainfall deficit as compared to tropical moist or temperate forests but are still vulnerable to drought-related mortality.