Classification Based on Hybridization of Parametric and Nonparametric Classifiers

Parametric methods of classification assume specific parametric models for competing population densities (e.g., Gaussian population densities can lead to linear and quadratic discriminant analysis) and they work well when these model assumptions are valid. Violation in one or more of these parametric model assumptions often leads to a poor classifier. On the other hand, nonparametric classifiers (e.g., nearest-neighbor and kernel-based classifiers) are more flexible and free from parametric model assumptions. But, the statistical instability of these classifiers may lead to poor performance when we have small numbers of training sample observations. Nonparametric methods, however, do not use any parametric structure of population densities. Therefore, even when one has some additional information about population densities, that important information is not used to modify the nonparametric classification rule. This paper makes an attempt to overcome these limitations of parametric and nonparametric approaches and combines their strengths to develop some hybrid classification methods. We use some simulated examples and benchmark data sets to examine the performance of these hybrid discriminant analysis tools. Asymptotic results on their misclassification rates have been derived under appropriate regularity conditions.     

ILP-assisted de novo drug design

The accurate and early detection of epileptic seizures in continuous electroencephalographic (EEG) data has a growing role in the management of patients with epilepsy. Early detection allows for therapy to be delivered at the start of seizures and for caregivers to be notified promptly about potentially debilitating events. The challenge to detecting epileptic seizures, however, is that seizure morphologies exhibit considerable inter-patient and intra-patient variability. While recent work has looked at addressing the issue of variations across different patients (inter-patient variability) and described patient-specific methodologies for seizure detection, there are no examples of systems that can simultaneously address the challenges of inter-patient and intra-patient variations in seizure morphology. In our study, we address this complete goal and describe a multi-task learning approach that trains a classifier to perform well across many kinds of seizures rather than potentially overfitting to the most common seizure types. Our approach increases the generalizability of seizure detection systems and improves the tradeoff between latency and sensitivity versus false positive rates. When compared against the standard approach on the CHB–MIT multi-channel scalp EEG data, our proposed method improved discrimination between seizure and non-seizure EEG for almost 83 % of the patients while reducing false positives on nearly 70 % of the patients studied.     

A revisit to non-maximally entangled mixed states: teleportation witness,noisy channel and discord

We constructed a class of non-maximally entangled mixed states (Adhikari et al. in Quantum Inf Comput 10:0398, 2010) and extensively studied their entanglement properties and also their usefulness as teleportation channels. In this article, we have revisited our constructed state and have studied it from three different perspectives. Since every entangled state is associated with a witness operator, we have found a suitable entanglement as well as teleportation witness operator for our non-maximally entangled mixed states. We considered the noisy channel’s effects on our constructed states to see how much it affects the states’ capacities as teleportation channels. For this purpose, we have mainly focussed on amplitude damping channel. A comparative study on concurrence and quantum discord of our constructed state of Adhikari et al. (2010) has also been carried out here.     

Surface modes of a sessile water drop: an optical tweezer based study

A high-precision method to study the dynamics of two-fluid interfaces using an optical tweezer and a phase-sensitive detection technique are described. The disturbances set up at the interface are studied by analyzing the motion of an optically trapped particle in the bulk of the fluid, i.e., away from the interface. The usefulness of the technique is demonstrated for the well-known problem of a horizontally vibrated sessile liquid drop. The vibrational modes of the liquid drop excited by sinusoidally vibrating the support in a horizontal plane appear as resonances in the motion of the trapped particle. The nature of the resonance is studied in detail by measuring the real part, the imaginary part, and the phase response of the motion of the particle as a function of the "effective" size of the liquid drop. Excellent quantitative agreement with the theoretically predicted values of the eigenfrequencies and damping of the surface modes is obtained.     

Algorithms for computing diffuse reflection paths in polygons

Let s be a point source of light inside a polygon P of n vertices. A polygonal path from s to some point t inside P is called a diffuse reflection path if the turning points of the path lie on edges of?P. A?diffuse reflection path is said to be optimal if it has the minimum number of reflections on the path. The problem of computing a diffuse reflection path from s to t inside P has not been considered explicitly in the past. We present three different algorithms for this problem which produce suboptimal paths. For constructing such a path, the first algorithm uses a greedy method, the second algorithm uses a transformation of a minimum link path, and the third algorithm uses the edge–edge visibility graph of?P. The first two algorithms are for polygons without holes, and they run in O(n+klogn) time, where k denotes the number of reflections in the constructed path. The third algorithm is for polygons with or without holes, and it runs in O(n ²) time. The number of reflections in the path produced by this third algorithm can be at most three times that of an optimal diffuse reflection path. Though the combinatorial approach used in the third algorithm gives a better bound on the number of reflections on the path, the first and the second algorithms stand on the merit of their elegant geometric approaches based on local geometric information.     

An inertia-adaptive particle swarm system with particle mobility factor for improved global optimization

Particle Swarm Optimization (PSO) has recently emerged as a nature-inspired algorithm for real parameter optimization. This article describes a method for improving the final accuracy and the convergence speed of PSO by firstly adding a new coefficient (called mobility factor) to the position updating equation and secondly modulating the inertia weight according to the distance between a particle and the globally best position found so far. The two-fold modification tries to balance between the explorative and exploitative tendencies of the swarm with an objective of achieving better search performance. We also mathematically analyze the effect of the modifications on the dynamics of the PSO algorithm. The new algorithm has been shown to be statistically significantly better than the basic PSO and four of its state-of-the-art variants on a twelve-function test-suite in terms of speed, accuracy, and robustness.     

The chemistry of dicalcium silicate mineral

Dicalcium silicate is of vital importance in several fields of silicate science. It exists in several polymorphic forms, of which one (the-form) is stable at room temperature without any stabilizer. The-form is commonly found in ordinary portland cement (OPC) in association with stabilizing ions. Stabilization of other forms,,_L,_H and_m for structural and other studies have been reported. Theoretical structural analysis using topology has been reported to be of value in understanding the stabilization process of the polymorphs. The conversion of form is at times a problem in the cement industry, in addition to the formation of unwanted compounds, such as spurrite. The-form is low in hydraulic properties but in the presence of impurities such as excess CaO over the stoichiometric ratio, shows fairly high hydraulic properties. Of the other phases, the hydraulic properties of the a forms are quite encouraging but the choice of stabilizers etc. plays a dominant role. Correlation of hydraulicity with structural properties such as crystal defects, etc., has been reported but satisfactory explanation is yet to come. The hydration products of-C₂S are quite similar to those of C₃S but the kinetics are fairly slow. In the presence of active silica, and at elevated temperatures, even the-form hydrates at a faster rate. The influence of chemical accelerators on the hydration of C₂S at room temperature is well studied and NaF is found to be one of the best accelerators. The formation of reactive-C₂S by different preparative methods shows a quite interesting trend for potential manufacture of low-temperature inorganic cement or OPC with low C₃S; even utilization of low-grade limestone could be possible. The role of C₂S in the hydration of aluminous cements is being increasingly recognized and, in fact, a newer class of cements called alumina-belite cement, etc., are being developed in which C₂S is purposely maintained as a major phase.     

Ferromagnetic mixed tribridged dinuclear copper(II) complex [Cu2(OAc)2(OH)(dpa)2]PF6 · H2O (dpa = 2,2′-dipyridylamine): 3D superstructure based on hydrogen bond and π…π interaction

A new dinuclear complex [Cu₂(OAc)₂(OH)(dpa)₂] PF₆ · H₂O (1) is prepared and structurally and magneto-structurally characterized. The monocationic core contains one acetate in familiar bidentate η¹:η¹:μ₂-bridge and another in the rare monoatomic bridge along with one hydroxo intermediary. 1 packs through N–H…O and O–H…O hydrogen bonds and π…π interaction resulting a 3D supramolecular continuum and displays high-energy intraligand ¹(π − π^*) fluorescence and intraligand ³(π − π^*) phosphorescence in glassy solution.     

Polyaniline and polypyrrole modified conductive nanocomposites of polyfuran and polythiophene with montmorillonite clay

Nanocomposites of polyfuran (PF) and polythiophene (PTP) with montmorillonite clay (MMT) were prepared and modified by loading of polyaniline (PANI) and polypyrrole (PPY) moieties via polymerization of aniline (ANI) and pyrrole (PY) in aqueous dispersions of PF-MMT and PTP-MMT nanocomposites. Formation of PANI and PPY and their subsequent incorporation in the PF-MMT and PTP-MMT composites was confirmed by FTIR absorption studies. X-ray diffraction (XRD) patterns of PANI and PPY modified PF-MMT and PTP-MMT composites showed that PF-MMT and PTP-MMT intercalates were still present in the modified composites. Scanning electron microscopic analysis revealed distinctive morphological patterns of the various composite particles. The dc conductivity values of PANI and PPY modified PF-MMT and PTP-MMT composites were in the order of 10⁻² S/cm in either system – a value much improved compared to the same for both of the unmodified PF-MMT (10⁻⁷ S/cm) and PTP-MMT (10⁻⁵ S/cm) nanocomposites respectively.     

Novel wet-chemical synthesis and characterization of nanocrystalline CeO2 and Ce0.8Gd0.2O1.9 as solid electrolyte for intermediate temperature solid oxide fuel cell (IT-SOFC) applications

Novel wet-chemical methods of synthesis have been adopted to synthesize nano-crystalline CeO₂ and Gd-substituted compositions aiming to explore an efficient oxide ion conducting solid electrolyte for intermediate temperature solid oxide fuel cell (IT-SOFC) applications. Nano-crystalline CeO₂ powders were synthesized by combustion method using redox mixture of cerric ammonium nitrate or cerium nitrate and maleic acid or 1,3-dimethylurea and compared with high surface area CeO₂ powders prepared by hydrothermal technique with microwave precipitated precursor from aqueous solutions of (NH₄)₂Ce(NO₃)₆ and urea. The grain size achieved by the hydrothermal technique is ∼7 nm which is smaller than that of commercial nano CeO₂ powders. Conventional or microwave sintering was used to prepare dense Ce_0.8Gd_0.2O_1.9 pellets from the ceria powders made of redox mixture of cerium nitrate, 1,3-dimethylurea (DMU) and Gd₂O₃ as the starting ingredients. The samples were characterized by X-ray diffractometry (XRD), transmission electron microscopy (TEM), diffuse reflectance spectroscopy (DRS), scanning electron microscopy (SEM), and ac impedance spectroscopy. The ionic conductivity measured for the pellet sintered at 1400 °C is 1 × 10⁻² and 2.4 × 10⁻² S/cm at 700 °C and 800 °C respectively.