Krishnan Chemmangat

A cognitive QoS management framework for WLANs

Due to the precipitous growth of wireless networks and the paucity of spectrum, more interference is imposed to the wireless terminals which constraints their performance. In order to preserve such performance degradation, this paper proposes a framework which uses cognitive radio techniques for quality of service (QoS) management of wireless local area networks (LANs). The framework incorporates radio environment maps as input to a cognitive decision engine that steers the network to optimize its QoS parameters such as throughput. A novel experimentally verified heuristic physical model is developed to predict and optimize the throughput of wireless terminals. The framework was applied to realistic stationary and time-variant interference scenarios where an average throughput gain of 344% was achieved in the stationary interference scenario and 70% to 183% was gained in the time-variant interference scenario.

Optimization of high-speed electromagnetic systems with accurate parametric macromodels generated using sequential sampling of the design space

This paper presents a design optimization approach for electromagnetic systems using parametric macromodels. The parametric macro-models are generated using an efficient sequential sampling of the design space of interest which ensures optimal sample selection for a required level of accuracy. The proposed method is validated on a microwave notch filter example for which the parametric macromodel is used in a minimax optimization algorithm so that the design parameters are optimized for some specific electrical design performances.

Parametric Macromodeling for Sensitivity Responses From Tabulated Data

This letter presents a parametric macromodeling technique which accurately describes the parameterized frequency behavior of electromagnetic systems and their corresponding parameterized sensitivity responses with respect to design parameters. The technique is based on the interpolation of a set of state-space matrices with a proper choice of the interpolation scheme, so that parametric sensitivity macromodels can be computed. Pertinent numerical results validate the proposed parametric macromodeling approach.

A novel pre-processing procedure for enhanced feature extraction and characterization of electromyogram signals

Abstract In the analysis of electromyogram signals, the challenge lies in the suppression of noise associated with the measurement and signal conditioning. The main aim of this paper is to present a novel pre-processing step, namely Minimum Entropy Deconvolution Adjusted (MEDA), to enhance the signal for feature extraction resulting in better characterization of different upper limb motions. MEDA method is based on finding the set of filter coefficients that recover the output signal with maximum value of kurtosis while minimizing the low kurtosis noise components. The proposed method has been validated on surface electromyogram dataset collected from seven subjects performing eight classes of hand movements (wrist flexion, wrist radial deviation, hand close, tripod, wrist extension, wrist ulnar deviation, cylindrical and key grip) with only two pairs of electrodes recorded from flexor carpi radialis and extensor carpi radialis on the forearm. The performance of the MEDA has been compared across four classifiers namely J-48, k-nearest neighbours (KNN), Naives Bayes and Linear Discriminant Analysis (LDA) attaining the classification accuracy of 85.3 ± 4%, 85.67 ± 5%, 76 ± 6% and 91.2 ± 2% respectively. Practical results demonstrate the feasibility of the approach with mean percentage increase in classification accuracy of 20.5%, without significant increase in computational time across seven subjects demonstrating the significance of MEDA in classification.

Surrogate modeling based cognitive decision engine for optimization of WLAN performance

Due to the rapid growth of wireless networks and the dearth of the electromagnetic spectrum, more interference is imposed to the wireless terminals which constrains their performance. In order to mitigate such performance degradation, this paper proposes a novel experimentally verified surrogate model based cognitive decision engine which aims at performance optimization of IEEE 802.11 links. The surrogate model takes the current state and configuration of the network as input and makes a prediction of the QoS parameter that would assist the decision engine to steer the network towards the optimal configuration. The decision engine was applied in two realistic interference scenarios where in both cases, utilization of the cognitive decision engine significantly outperformed the case where the decision engine was not deployed.

Selfie Detection by Synergy-Constraint Based Convolutional Neural Network

Categorisation of huge amount of data on the multimedia platform is a crucial task. In this work, we propose a novel approach to address the subtle problem of selfie detection for image database segregation on the web, given rapid rise in the number of selfies being clicked. A Convolutional Neural Network (CNN) is modeled to learn a synergy feature in the common subspace of head and shoulder orientation, derived from Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG) features respectively. This synergy was captured by projecting the aforementioned features using Canonical Correlation Analysis (CCA). We show that the resulting networks convolutional activations in the neighbourhood of spatial keypoints captured by SIFT are discriminative for selfie-detection. In general, proposed approach aids in capturing intricacies present in the image data and has the potential for usage in other subtle image analysis scenarios apart from just selfie detection. We investigate and analyse the performance of the popular CNN architectures (GoogleNet, Alexnet), used for other image classification tasks, when subjected to the task of detecting the selfies on the multimedia platform. The results of the proposed approach are compared with these popular architectures on a dataset of ninety thousand images comprising of roughly equal number of selfies and non-selfies. Experimental results on this dataset shows the effectiveness of the proposed approach.

Word boundary estimation for continuous speech using higher order statistical features

Detection of the start and the end time of words in a continuous speech plays a crucial role in enhancing the accuracy of Automatic Speech Recognition (ASR). Hence, addressing the problem of efficiently demarcating word boundaries is of prime importance. In this paper, we introduce two new acoustic features based on higher order statistics called Density of Voicing (DoV) and Variability of Voicing (VoV) obtained from the bispectral distribution, which when used along with the popular prosodic cues helps in drastically reducing the recognition error rate in- volved. An ensemble of three different models has been designed to minimize the false alarms, during word boundary detection, by maximizing the uncorrelatedness in prediction from each model. Finally, the majority-voting rule was used to decide if the given frame encompasses a word boundary. The contribution of the work lies in: (i) Converting word boundary detection into a supervised learning problem (ii) Introduction of two new higher order statistical features (iii) Using ensemble methods to find the best model for prediction. Experimental results for NTIMIT Database shows the efficacy of the proposed method and its robustness to noise added during telephonic transmission.

Auto-generation of passive scalable macromodels for microwave components using scattered sequential sampling

This paper presents a method for automatic construction of stable and passive scalable macromodels for parameterized frequency responses. The method requires very little prior knowledge to build the scalable macromodels thereby considerably reducing the burden on the designers. The proposed method uses an efficient scattered sequential sampling strategy with as few expensive simulations as possible to generate accurate macromodels for the system using state-of-the-art scalable macromodeling methods. The scalable macromodels can be used as a replacement model for the actual simulator in overall design processes. Pertinent numerical results validate the proposed sequential sampling strategy.

Fast optimization of microwave filters using surrogate-based optimization methods

This paper investigates the use of surrogate-based optimization to optimize the behavioral response of broadband microwave filters. The proposed method makes use of an efficient infill criterion (called expected improvement) that sequentially samples the response of the device at well-chosen regions in the design space. Based on these data samples, successive global surrogate models are built that become increasingly accurate near the optimum solution. A microwave filter example confirms that this approach significantly accelerates device optimization when compared to standard gradient-based methods.

Partial Element Equivalent Circuit models in the solution of the electric field integral equation

3-D electromagnetic methods are fundamental design tools for complex high-speed systems. Among the integral equation-based techniques, the Partial Element Equivalent Circuit (PEEC) method has received a special attention in interconnect modeling, where mixed electromagnetic/circuit problems need to be solved. Retardation effects and the resulting delays must be taken into account and included in the modeling, when signal waveform rise times decrease and the corresponding frequency content increases or the geometric dimensions become electrically long. In this case, the enforcement of the Kirchhoff laws to PEEC delayed models leads to a set of delayed differential equations in a neutral form. The aim of this contribution is to present an overview of the PEEC method with special focus on the analysis of electrically long structures that require taking delays into account.