Sudhansu Kumar Mishra

A comparative performance assessment of a set of multiobjective algorithms for constrained portfolio assets selection

Abstract This paper addresses a realistic portfolio assets selection problem as a multiobjective optimization one, considering the budget, floor, ceiling and cardinality as constraints. A novel multiobjective optimization algorithm, namely the non-dominated sorting multiobjective particle swarm optimization (NS-MOPSO), has been proposed and employed efficiently to solve this important problem. The performance of the proposed algorithm is compared with four multiobjective evolution algorithms (MOEAs), based on non-dominated sorting, and one MOEA algorithm based on decomposition (MOEA/D). The performance results obtained from the study are also compared with those of single objective evolutionary algorithms, such as the genetic algorithm (GA), tabu search (TS), simulated annealing (SA) and particle swarm optimization (PSO). The comparisons of the performance include three error measures, four performance metrics, the Pareto front and computational time. A nonparametric statistical analysis, using the Sign test and Wilcoxon signed rank test, is also performed, to demonstrate the superiority of the NS-MOPSO algorithm. On examining the performance metrics, it is observed that the proposed NS-MOPSO approach is capable of identifying good Pareto solutions, maintaining adequate diversity. The proposed algorithm is also applied to different cardinality constraint conditions, for six different market indices, such as the Hang-Seng in Hong Kong, DAX 100 in Germany, FTSE 100 in UK, S&P 100 in USA, Nikkei 225 in Japan, and BSE-500 in India.

A novel method of designing LVDT using artificial neural network

This paper proposes a simple and novel method of designing and developing LVDT based sensing system. Conventionally, precise adjustment of windings is made to enhance the linearity range of LVDT. The tedious job of pitch adjustment of windings of LVDT can be overcome by use of the proposed method. Functional link artificial neural network has been successfully used in the paper for nonlinear compensation of LVDT. The effectiveness of the proposed method is demonstrated through computer simulation with the experimental data of a simple LVDT. The complete algorithm with practical set-up for development of LVDT is presented in the paper.

Constrained portfolio asset selection using multiobjective bacteria foraging optimization

Portfolio asset selection (PAS) is a challenging and interesting multiobjective task in the field of computational finance, and is receiving the increasing attention of researchers, fund management companies and individual investors in the last few decades. Selecting a subset of assets and corresponding optimal weights from a set of available assets, is a key issue in the PAS problem. A Markowitz model is generally used to solve this optimization problem, where the total profit is maximized, while the total risk is to be minimized. However, this model does not consider the practical constraints, such as the minimum buy in threshold, maximum limit, cardinality etc. The Practical constraints are incorporated in this study to meet a real world financial scenario. In the proposed work, the PAS problem is formulated in a multiobjective framework, and solved using the multiobjective bacteria foraging optimization (MOBFO) algorithm. The performance of the proposed approach is compared with a set of competitive multiobjective evolutionary algorithms using six performance metrics, the Pareto front and computational time. On examining the performance metrics, it is concluded that the proposed MOBFO algorithm is capable of identifying a good Pareto solution, maintaining adequate diversity. The proposed algorithm is also successfully applied to different cardinality constraint conditions, for six different market indices.

Multi-objective particle swarm optimization approach to portfolio optimization

The problem of portfolio optimization is a standard problem in financial world and has received a lot of attention. Selecting an optimal weighting of assets is a critical issue for which the decision maker takes several aspects into consideration. In this paper we consider a multi-objective problem in which the percentage of each available asset is selected such a way that the total profit of the portfolio is maximized while total risk to be minimized, simultaneously. Four well-known multi-objective evolutionary algorithms i.e. Parallel Single Front Genetic Algorithm (PSFGA), Strength Pareto Evolutionary Algorithm 2(SPEA2), Nondominated Sorting Genetic Algorithm II( NSGA II) and Multi Objective Particle Swarm Optimization (MOPSO) for solving the bi-objective portfolio optimization problem has been applied. Performance comparison carried out in this paper by performing different numerical experiments. These experiments are performed using real-world data. The results show that MOPSO outperforms other two for the considered test cases.

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

Portfolio management assessment by four multiobjective optimization algorithm

The portfolio optimization aims to find an optimal set of assets to invest on, as well as the optimal investment for each asset. This optimal selection and weighting of assets is a multi-objective problem where total profit of investment has to be maximized and total risk is to be minimized. In this paper four well known multi-objective evolutionary algorithms i.e. Pareto Archived Evolution Strategy (PAES), Pareto Envelope-based Selection Algorithm (PESA), Adaptive Pareto Archived Evolution Strategy (APAES) algorithm and Non dominated Sorting Genetic Algorithm II (NSGA II) are chosen and successfully applied for solving the biobjective portfolio optimization problem. Their performances have been evaluated through simulation study and have been compared in terms of Pareto fronts, the delta, C and S metrics. Simulation results of various portfolios clearly demonstrate the superior portfolio management capability of NSGA II based method compared to other three standard methods. Finally NSGA II algorithm is applied to the same problem with some real world constraint.

Cat Swarm Optimization Based Functional Link Artificial Neural Network Filter for Gaussian Noise Removal from Computed Tomography Images

Gaussian noise is one of the dominant noises, which degrades the quality of acquired Computed Tomography CT image data. It creates difficulties in pathological identification or diagnosis of any disease. Gaussian noise elimination is desirable to improve the clarity of a CT image for clinical, diagnostic, and postprocessing applications. This paper proposes an evolutionary nonlinear adaptive filter approach, using Cat Swarm Functional Link Artificial Neural Network CS-FLANN to remove the unwanted noise. The structure of the proposed filter is based on the Functional Link Artificial Neural Network FLANN and the Cat Swarm Optimization CSO is utilized for the selection of optimum weight of the neural network filter. The applied filter has been compared with the existing linear filters, like the mean filter and the adaptive Wiener filter. The performance indices, such as peak signal to noise ratio PSNR, have been computed for the quantitative analysis of the proposed filter. The experimental evaluation established the superiority of the proposed filtering technique over existing methods.

Prediction based mean-variance model for constrained portfolio assets selection using multiobjective evolutionary algorithms

Abstract In this paper, a novel prediction based mean-variance (PBMV) model has been proposed, as an alternative to the conventional Markowitz mean-variance model, to solve the constrained portfolio optimization problem. In the Markowitz mean-variance model, the expected future return is taken as the mean of the past returns, which is incorrect. In the proposed model, first the expected future returns are predicted, using a low complexity heuristic functional link artificial neural network (HFLANN) model and the portfolio optimization task is carried out by using multi-objective evolutionary algorithms (MOEAs). In this paper, swarm intelligence based, multiobjective optimization algorithm, namely self-regulating multiobjective particle swarm optimization (SR-MOPSO) has also been proposed and employed efficiently to solve this important problem. The Pareto solutions obtained by applying two other competitive MOEAs and using the proposed PBMV models and Markowitz mean-variance model have been compared, considering six performance metrics and the Pareto fronts. Moreover, in the present study, the nonparametric statistical analysis using the Sign test and Wilcoxon rank test are also carried out, to compare the performance of the algorithms pair wise. It is observed that, the proposed PBMV model based approach provides better Pareto solutions, maintaining adequate diversity, and also quite comparable to the Markowitz model. From the simulation result, it is observed that the self regulating multiobjective particle swarm optimization (SR-MOPSO) algorithm based on PBMV model, provides the best Pareto solutions amongst those offered by other MOEAs.

Analysis of asymmetrical cascaded multilevel inverter for traction systems

Multilevel inverters when supplied from equal and constant DC sources does not have a practical sense of applications. For each of the specific harmonic profiles the variation of the DC sources affects the values of the switching angles. This increases the difficulty of the harmonic eliminations equations. This paper presents the application of the cascaded asymmetrical multilevel inverter in the railway traction drive. The total harmonic distortion (THD) reduces with the increase in the voltage level. Various modulation techniques such as Phase Shifted Modulation (PSM), Level Shifted Modulation (LSM) and Selective Harmonic Elimination Techniques (SHE) were implemented in order to find the best modulation techniques among them. Also it is shown that SHE technique resulted in low THD. Thus, an IGBT based-cascaded five level asymmetrical inverters with SHE method has been modelled to lower the supply voltage to a level convenient for the traction induction motors.

A comparative performance evaluation of evolutionary algorithms for optimal design of three-phase induction motor

The attribute of an induction motor vary with the number of parameters and the performance relationship between the parameters also is implicit. In this paper a multi-objective problem is considered in which three phase squirrel cage induction motor (SCIM) has been designed in such a way that the efficiency is maximized while power density to be minimized simultaneously keeping various constraints in mind. Three well-known single objective methods such as tabu search (TS), simulated annealing (SA) and Genetic algorithm (GA) for comparing Pareto solutions has also been applied. Performance comparison carried out in this paper by performing different numerical experiments. The result shows that NSGA-II outperforms other three for the considered test cases.