Sasmita Kumari Padhy

Artificial Neural Network trained by Particle Swarm Optimization for non-linear channel equalization

Development of a learning method for optimization of network topology of ANN.Use of PSO trained ANN in channel equalization.PSO trained ANN equalizers performs better than PSO based equalizers as well as ANN based equalizers. In this paper, we apply Artificial Neural Network (ANN) trained with Particle Swarm Optimization (PSO) for the problem of channel equalization. Existing applications of PSO to Artificial Neural Networks (ANN) training have only been used to find optimal weights of the network. Novelty in this paper is that it also takes care of appropriate network topology and transfer functions of the neuron. The PSO algorithm optimizes all the variables, and hence network weights and network parameters. Hence, this paper makes use of PSO to optimize the number of layers, input and hidden neurons, the type of transfer functions etc. This paper focuses on optimizing the weights, transfer function, and topology of an ANN constructed for channel equalization. Extensive simulations presented in this paper shows that, as compared to other ANN based equalizers as well as Neuro-fuzzy equalizers, the proposed equalizer performs better in all noise conditions.

A novel algorithm for dynamic task scheduling

This paper deals with the problem of dynamic task scheduling in grid environment of multi-processors. First, this paper formulates task scheduling as an optimization problem and then optimizes with a novel hybrid optimization algorithm. The proposed algorithm combines the merits of Genetic Algorithm and Bacteria Foraging optimization. The simulation result proves the superior performance with the proposed algorithm.

Dynamic task scheduling using a directed neural network

This article is based on the problem of work flow scheduling in grid environment of multi-processors. We, in this paper, introduce three novel approaches for the task scheduling problem using recently proposed Directed Search Optimization (DSO). In the first attempt, task scheduling is framed as an optimization problem and solved by DSO. Next, this paper makes use of DSO as a training algorithm to train (a) a three layer Artificial Neural Network (ANN) and then (b) Radial Basis Function Neural Networks (RBFNN). These DSO trained networks are used for task scheduling and interestingly yield better performance than contemporary algorithms as evidenced by simulation results. Development of the learning method for ANN.Development of a method for optimization of RBFNN.Use of DSO in task scheduling.Use of DSO trained ANN in task scheduling.Use of DSO trained RBFNN in task scheduling.

Multiprocessor scheduling and neural network training methods using shuffled frog-leaping algorithm

Development of learning method for ANN.Development of a method for optimization of RBFNN.Use of SFLA in task scheduling.Use of SFLA trained ANN in task scheduling.Use of SFLA trained RBFNN in task scheduling. In this paper, we designed novel methods for Neural Network (NN) and Radial Basis function Neural Networks (RBFNN) training using Shuffled Frog-Leaping Algorithm (SFLA). This paper basically deals with the problem of multi-processor scheduling in a grid environment. We, in this paper, introduce three novel approaches for the task scheduling problem using a recently proposed Shuffled Frog-Leaping Algorithm (SFLA). In a first attempt, the scheduling problem is structured as a problem of optimization and solved by SFLA. Next, this paper makes use of SFLA trained Artificial Neural Network (ANN) and Radial Basis function Neural Networks (RBFNN) for the problem of task scheduling. Interestingly, the proposed methods yield better performance than contemporary algorithms as evidenced by simulation results.

Swarm intelligence based techniques for digital filter design

Two novel modifications to QPSO proposed.Time dependency of constriction factor taken care.Improved methods for IIR filter design proposed and validated. This paper deals with the problem of digital IIR filter design. Two novel modifications are proposed to Particle Swarm Optimization and validated through novel application for design of IIR filter. First modification is based on quantum mechanics and proved to yield a better performance. The second modification is to take care of time dependency character of the constriction factor. Extensive simulation results validate the superior performance of proposed algorithms.

Hybrid ANN reducing training time requirements and decision delay for equalization in presence of co-channel interference

Bayesian equalizer is known to be the optimum equalizer. This paper proposes a Hybrid Artificial Neural Network (Hybrid ANN) and an algorithm to modify Decision Feedback Equalizer (DFE) function of Bayesian equalizer while equalizing in presence of co-channel interference (CCI). A combination of Artificial Neural Network and Decision Feedback Equalizer (DFE) is termed as Neural-DFE (NDFE). The results show that the decision delay and training time requirement reduces significantly by use of NDFE. This creates an advantage specifically for a mobile environment where the CCI is varying in nature and the Bayesian equalizer requires a lot of training time.

Non-linear channel equalization using adaptive MPNN

In this paper the Modified Probabilistic Neural Network (MPNN) is used for dealing with the problem of channel equalization. Some improvements are suggested for the MPNN so that it is more suitable for the current problem. Firstly, the MPNN is extended to process complex signals. Secondly, a stochastic gradient adaptation technique is proposed, such that when the network is being employed to equalize a slowly varying channel, it can self-adapt to the changing environment. Simulations have shown that the MPNN is able to effectively equalize 4-QAM symbol sequences transmitted through a non-linear, slowly time-varying channel. Finally, methods that further reduce the size of the network are proposed. Simulations show that the proposed method is able to reduce the size of the network considerably.

Reduced Complexity Dynamic Systems Using Approximate Control Moments

This paper deals with reduction of computational complexities in dynamic systems. This paper develops a novel method of reducing complexities with use of control moments of the system. Though the proposed method is validated through channel estimation in this paper, the same can be equally applied to any other dynamic systems. Encouraging results given in this paper prove that the computational complexities can be reduced up to 104 with a marginal affordable loss of performance.

An Efficient Noise Generator for Validation of Channels Equalizers

This paper develops an efficient pseudo-random number generator for validation of digital communication channels and secure disc. Drives. Simulation results validates the effectiveness of the random number generator.

Complexity Reduction Using Two Stage Tracking

The Estimation of MIMO Channels becomes a tedious task in the non-stationary environment. This is because of pilot overhead and corresponding interference. To reduce this pilot overhead, QR decomposition is proposed in the literature. However, higher the rate of the QR decomposition will result in a computationally intensive system. In this paper, we propose a two stage estimation solution to reduce the complexity as well as to eliminate the interference arising out of pilot overhead. Advantages of this paper can be seen as separation of channel impulse response and interference, elimination of the interference arising out of pilot overhead, and reduction in computational complexity.