Ajit Kumar Sahoo

Exponential Functional Link Artificial Neural Networks for Denoising of Image Corrupted by Gaussian Noise

Here we have presented an alternate ANN structure called functional link ANN (FLANN) for image denoising. In contrast to a feed forward ANN structure i.e. a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which non-linearity is introduced by enhancing the input pattern with nonlinear function expansion. In this work three different expansions is applied. With the proper choice of functional expansion in a FLANN , this network performs as good as and in some case even better than the MLP structure for the problem of denoising of an image corrupted with Gaussian noise. In the single layer functional link ANN (FLANN) the need of hidden layer is eliminated. The novelty of this structure is that it requires much less computation than that of MLP. In the presence of additive white Gaussian noise in the image, the performance of the proposed network is found superior to that of a MLP .In particular FLANN structure with exponential function expansion works best for Gaussian noise suppression from an image

A GA-based pruning strategy and weight update algorithm for efficient nonlinear system identification

Identification of nonlinear static and dynamic systems plays a key role in many engineering applications including communication, control and instrumentation. Various adaptive models have been suggested in the literature using ANN and Fuzzy logic based structures. In this paper we employ an efficient and low complexity Functional Link ANN (FLANN) model for identifying such nonlinear systems using GA based learning of connective weights. In addition, pruning of connecting paths is also simultaneously carried out using GA to reduce the network architecture. Computer simulations on various static and dynamic systems indicate that there is more than 50% reduction in original model FLANN structure with almost equivalent identification performance.

Design and implementation of FPGA based linear all digital phase-locked loop

This paper presents a linear all-digital phase locked loop based on FPGA. In this ADPLL the phase detection system is realized by generating an analytic signal using a compact implementation of Hilbert transform and then simply computing the instantaneous phase using CORDIC algorithm in vectoring mode of operation. A 16-bit pipelined CORDIC algorithm is employed in order to obtain the phase information of the signal. All the components used in this phase detection system are realized as digital discrete time components. This design does not involve any class of multipliers thus reducing the complexity of the design. The loop filter of the ADPLL has been designed using PI controller which has a low pass behavior and is used to discard the higher order harmonics of the error signal. The CORDIC algorithm in its rotation mode of operation is used to compute sinusoidal values for the DDS. The ADPLL model has been implemented using Xilinx ISE 12.3 and ModelSim PE Student Edition 10.1a.

A Recurrent Neural Network Approach to Pulse Radar Detection

Matched filtering of biphase coded radar signals create unwanted sidelobes which may mask some of the desired information. This paper presents a new approach for pulse compression using recurrent neural network (RNN). The 13-bit and 35-bit barker codes are used as input signal codes to RNN. The pulse radar detection system is simulated using RNN. The results of the simulation are compared with the results obtained from the simulation of pulse radar detection using Multilayer Perceptron (MLP) network. The number of input layer neurons is same as the length of the signal code and three hidden neurons are taken in the present systems. The Simulation results show that RNN yields better signal-to-sidelobe ratio (SSR) and doppler shift performance than neural network (NN) and some traditional algorithms like auto correlation function (ACF) algorithm. It is also observed that RNN based system converges faster as compared to the MLP based system. Hence the proposed RNN provides an efficient means for pulse radar detection. Keywords—RNN, pulse compression, ACF, SSR, biphase code.

A novel phase detection system for linear all-digital phase locked loop

In this paper, a novel fast phase detection system for all-digital phase locked loop (ADPLL) is presented. The phase detection system is realized by generating an analytic signal using a compact implementation of Hilbert transform and then simply computing the instantaneous phase. 16-bit CORDIC algorithm is employed in order to obtain the phase information of the signal. All the components used in this phase detection system are realized as digital discrete time components. This design does not involve any class of multipliers thus reducing the complexity of the design. The phase detection system although providing a definite advantage over conventional analog phase detectors, the Hilbert filter implemented in this paper has been designed using a method based on complex, multiplier less sampling filters. A comparison has been drawn between the continuous PLL models phase detection system and the proposed method for effectiveness of the study. The studied system is modeled and tested in the MATLAB/Simulink environment.

Generation of Pulse Compression Codes Using NSGA-II

Pulse compression technique avoids the transmission of a signal having small pulse width and high peak power for better range resolution by transmitting phase or frequency modulated large pulse width signal having comparatively low peak power signal. This paper demonstrates an application of non dominated sorting genetic algorithm-II (NSGA-II), a multiobjective algorithm, to generate biphase pulse compression codes from length 49 to 59. But the aperiodic autocorrelation function(ACF) of the phase coded signals contains range sidelobes which act as self clutter in radar target detection. The efficiency of these codes depends upon the energy content in the range sidelobes of their autocorrelation functions. Peak sidelobe level (PSL) and integrated side lobe level (ISL) are the two performance measures for pulse compression codes. A code is chosen for an application if the ISL and PSL value is within tolerable limits. In this work PSL and ISL are chosen as the objective functions for generating biphase code. keywords—NSGA-II, pulse compression, PSL, ISL, biphase code.

Diffusion minimum-Wilcoxon-norm over distributed adaptive networks

This paper deals with the development of robust diffusion strategy for wireless sensor networks using minimum-Wilcoxon-norm. The Wilcoxon norm based robust estimation now-a-days has drawn the attention of the signal processing community for its scale equivariant property and simplicity. Exhaustive mathematical analysis has been presented to obtain the proposed diffusion minimum-Wilcoxon-norm (dMWN) algorithm. Steady state performance analysis of the algorithm has also been carried out to show the stability of the proposed method. Asymptotic linearity of rank test 1 is used for the convergence analysis of the proposed method. Extensive simulations have been given to demonstrate the efficacy of the proposed algorithm.

Distributed Incremental Leaky LMS

Adaptive algorithms are applied to distributed networks to endow the network with adaptation capabilities. Incremental Strategy is the simplest mode of cooperation as it needs less amount of communication between the nodes. The adaptive incremental strategy which is developed for distributed networks using LMS algorithm, suffers from drift problem, where the parameter estimate will go unbounded in non ideal or practical implementations. Drift problem or divergence of the parameter estimate occurs due to continuous accumulation of quantization errors, finite precision errors and insufficient spectral excitation or ill conditioning of input sequence. They result in overflow and near singular auto correlation matrix, which provokes slow escape of parameter estimate to go unbound. The proposed method uses the Leaky LMS algorithm, which introduces a leakage factor in the update equation, and so prevents the weights to go unbounded by leaking energy out.

Block diffusion adaptation over distributed adaptive networks under imperfect data transmission

A distributed Block LMS estimate strategy is developed by appealing to collaboration techniques that exploits both space and time structures of data. In diffusion strategies, information are exchanged among the nodes, usually containing noisy links. The weight combination of the neighboring nodes play a crucial role in adaptation and tracking ability of the network. The paper investigates for general adaptive diffusion algorithm, in presence of various sources of imperfect information exchange, then moves on to investigate for BLMS diffusion method, which plays a crucial role in reducing the burden of communication by a factor of block length.

Efficient design of pulse compression codes using multiobjective genetic algorithm

Binary sequences having good aperiodic autocorrelation functions (ACFs) with low range sidelobes are required for many communication applications. However, few such good binary sequences are available having large sequence length. In this paper nondominated sorting genetic algorithm-II (NSGA-II) is used to generate biphase pulse compression codes from length 49 to 100. Pulse compression technique avoids the transmission of a signal having small pulse width and high peak power for better range resolution. The efficiency of these codes depends upon the energy content in the range sidelobes of their autocorrelation functions. Peak sidelobe level (PSL) and integrated side lobe level (ISL) are the two performance measures for pulse compression codes. In this paper the multi objective problem is designed by taking PSL and ISL as the objective functions.