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.

Modeling and Analysis of Noise Margin in SET Logic

In this paper the static noise margin for SET (single electron transistor) logic is defined and compact models for the noise margin are developed by making use of the MIB (Mahapatra-Ionescu-Banerjee) model. The variation of the noise margin with temperature and background charge is also studied. A chain of SET inverters is simulated to validate the definition of various logic levels (like VIH, VOH, etc.) and noise margin. Finally the noise immunity of SET logic is compared with current CMOS logic.

The British Intervention in South Russia 1918-1920

Soon after the Bolshevik Revolution of 1917, a three-year civil war broke out in Russia. As in many other civil wars, foreign powers intervened in the conflict. Britain played a leading role in this intervention and had a significant effect on the course of the war. Without this intervention on the White side, the superiority of numbers in manpower and weaponry of the Bolsheviks would have quickly overwhelmed their opponents. The aim of this dissertation is to explain the nature and role of the British intervention on the southern, and most decisive, front of the Civil War. The political decision making in London is studied as a background, but the focus of the dissertation is on the actual implementation of the British policy in Russia. The British military mission arrived in South Russia in late 1918, and started to provide General Denikin s White army with ample supplies. General Denikin would have not been able to build his army of more than 200,000 men or to make his operation against Moscow without the British matériel. The British mission also organized the training and equipping of the Russian troops with British weapons. This made the material aid much more effective. Many of the British instructors took part in fighting the Bolsheviks despite the orders of their government. The study is based on primary sources produced by British departments of state and members of the British mission and military units in South Russia. Primary sources from the Whites, including the personal collections of several key figures of the White movement and official records of the Armed Forces of South Russia are also used to give a balanced picture of the course of events. It is possible to draw some general conclusions from the White movement and reasons for their defeat from the study of the British intervention. In purely material terms the British aid placed Denikin s army in a far more favourable position than the Bolsheviks in 1919, but other military defects in the White army were numerous. The White commanders were unimaginative, their military thinking was obsolete, and they were incapable of organizing the logistics of their army. There were also fundamental defects in the morale of the White troops. In addition to all political mistakes of Denikin s movement and a general inability to adjust to the complex situation in Revolutionary Russia, the Whites suffered a clear military defeat. In South Russia the Whites were defeated not because of the lack of British aid, but rather in spite of it.

Maximum Margin Classifiers with Specified False Positive and False Negative Error Rates

This paper addresses the problem of maximum margin classification given the moments of class conditional densities and the false positive and false negative error rates. Using Chebyshev inequalities, the problem can be posed as a second order cone programming problem. The dual of the formulation leads to a geometric optimization problem, that of computing the distance between two ellipsoids, which is solved by an iterative algorithm. The formulation is extended to non-linear classifiers using kernel methods. The resultant classifiers are applied to the case of classification of unbalanced datasets with asymmetric costs for misclassification. Experimental results on benchmark datasets show the efficacy of the proposed method.

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.

Learning from positive and unlabelled examples using maximum margin clustering

Learning from Positive and Unlabelled examples (LPU) has emerged as an important problem in data mining and information retrieval applications. Existing techniques are not ideally suited for real world scenarios where the datasets are linearly inseparable, as they either build linear classifiers or the non-linear classifiers fail to achieve the desired performance. In this work, we propose to extend maximum margin clustering ideas and present an iterative procedure to design a non-linear classifier for LPU. In particular, we build a least squares support vector classifier, suitable for handling this problem due to symmetry of its loss function. Further, we present techniques for appropriately initializing the labels of unlabelled examples and for enforcing the ratio of positive to negative examples while obtaining these labels. Experiments on real-world datasets demonstrate that the non-linear classifier designed using the proposed approach gives significantly better generalization performance than the existing relevant approaches for LPU.

Influence of the upwelling events on the delta C-13 and delta O-18 of the benthic bivalve shells of the South Western Continental Margin of India

In this study, the influence of the spatial and temporal variability of upwelling intensity and the associated biological productivity observed during different phases of summer monsoon along the southwestern continental margin of India (SWCMI) on the delta C-13 and delta O-18 of the inorganic biogenic carbonate shells was investigated. Multispecies benthic bivalve shells (1-5 mm) separated from ten surface sediment samples of SWCMI (off 12 degrees N, 10 degrees N and 9 degrees N) collected during the onset (OSM) and peak (PSM) phase of the summer monsoon of 2009 were analysed for delta C-13 and delta O-18. Sea surface temperature along the study region indicates prominent upwelling in PSM than in OSM. A comparison of analytical and predicted values for delta O-18 in the bivalve shells confirmed their in situ origin during both the sampling periods. During PSM, the delta C-13 values in the benthic bivalve shells were more depleted in C-13 than during OSM which recorded lower values of delta C-13 in dissolved inorganic carbon of bottom waters expected in the study region in PSM due to the upwelled waters, high surface productivity and the associated high degradation of the organic matter in the subsurface and bottom waters. However, this depletion of delta C-13 was not observed in benthic bivalve shells obtained from 10 degrees N, since it is influenced by high export fluxes of carbon from the Cochin estuary since early monsoon months.

Reconnaissance of the geology and ground-water resources of Columbia County, Florida

The Floridan aquifer was found to be principal source of ground water in the area, containing artesian water in the northern part of Columbia County, and being recharged in the southern part of the county. A few wells in the northern part of the county tap water present in sediments that lie above the Floridan aquifer. These shallow waters are generally high in iron and tannic acid. The details on the geology and hydrology necessary to conserve and utilize the water available to the residents of Columbia County are presented in this study. (PDF contains 86 pages)

Emerging technologies for reef fisheries research and management [held during the 56th annual Gulf and Caribbean Fisheries Institute meeting in Tortola, British Virgin Islands, November 2003]

This publication of the NOAA Professional Paper NMFS Series is the product of a special symposium on “Emerging Technologies for Reef Fisheries Research and Management” held during the 56th annual Gulf and Caribbean Fisheries Institute meeting in Tortola, British Virgin Islands, November 2003. The purpose of this collection is to highlight the diversity of questions and issues in reef fisheries management that are benefiting from applications of technology. Topics cover a wide variety of questions and issues from the study of individual behavior, distribution and abundance of groups and populations, and associations between habitats and fish and shellfish species.(PDF files contains 124 pages.)

Survey of fish protective facilities at water withdrawal sites on the Snake and Columbia Rivers

Proliferation of water withdrawals and new pump intake and screen designs has occurred with the growth of irrigated agriculture along the Columbia and Snake Rivers. Concern for the protection of anadromous and resident fish populations resulted in formulation of a survey of the water withdrawal systems. The survey included distribution studies of juvenile fish near pump sites and field inspection of those sites to determine adequacy of screening for protection of fish. A total of 225 sites were inspected in 1979 and 1980, with a follow-up inspection of 95 sites in 1982. Results indicated a definite trend toward lack of concern for the condition of fish protective facilities. Only 4 out of 22 sites not meeting criteria in 1979 had been upgraded to acceptable conditions. Of more concern, 13 of the sites meeting criteria in 1979 were below criteria when reinspected in 1982. Some of the discrepancies included lack of protective screens, poorly maintained screens, and screens permitting excessive velocity that could result in impingement of larvae or small fish. A conclusion from these surveys is that if adequate protection for fish is to exist, screens for water withdrawals need to be properly installed, inspected, and maintained. (PDF file contains 40 pages.)

Geometric multiplicity margin for a submatrix

AMS Classification: 15A18, 15A21, 15A60.