Johnny Koh Siaw Paw

Minimum Variance Distortionless Response Beamformer with Enhanced Nulling Level Control via Dynamic Mutated Artificial Immune System

In smart antenna applications, the adaptive beamforming technique is used to cancel interfering signals (placing nulls) and produce or steer a strong beam toward the target signal according to the calculated weight vectors. Minimum variance distortionless response (MVDR) beamforming is capable of determining the weight vectors for beam steering; however, its nulling level on the interference sources remains unsatisfactory. Beamforming can be considered as an optimization problem, such that optimal weight vector should be obtained through computation. Hence, in this paper, a new dynamic mutated artificial immune system (DM-AIS) is proposed to enhance MVDR beamforming for controlling the null steering of interference and increase the signal to interference noise ratio (SINR) for wanted signals.

Cognitive Map approach for mobility path optimization using multiple objectives genetic algorithm

This paper describes the evolutionary planning strategies for mobile robot to move along the streamlined collision-free paths in a known static environment. The Cognitive Map method is combined with genetic algorithm to derive the mobile robot optimal moving path towards its goal functions. In this study, multi-objectives genetic algorithm (MOGA) is utilized due to there are more than one objective need to be achieved while planning for the robot moving path. Goal-factor and obstacle-factor are the key parameters incorporated in the MOGA fitness functions. The simulation results showed that the hybrid Cognitive Map approach with MOGA is capable of navigating a robot situated among non-moving obstacles. The proposed hybrid method demonstrates good performance in planning and optimizing mobile robot moving path with stationary obstacles and goal.

Artificial immune system assisted Minimum Variance Distortionless Response beamforming technique for adaptive antenna system

In wireless applications, the radiation pattern of adaptive antenna system is smartly formed and steered to cancel interfering signals (placing nulls) and produces a strong peak towards the desired signal according to the calculated weight vectors. This paper proposes an enhanced beamforming technique based on Minimum Variance Distortionless Response (MVDR). The Clonal selection algorithm (Clonalg) of Artificial Immune System (AIS) has been incorporated to assist MVDR to more precisely steer its beam towards desired user and forming deeper nulls at the interfering signals. The proposed algorithm has been simulated by using uniform linear antenna with multiple array elements, with 0.5λ spacing between adjacent elements and operated in the frequency of 2.3 GHz with 20 dB noise power level. Simulation results show that AIS assisted MVDR adaptive beamforming technique is able to produce much better received SINR in comparison of conventional MVDR.

Dynamic social behavior algorithm for real-parameter optimization problems and optimization of hyper beamforming of linear antenna arrays

Abstract The ever evolving complexity of real-world problems had become an impetus for the development of many new and efficient optimization algorithms. Meta-heuristics based on evolutionary computation and swarm intelligence are successful examples of nature-inspired optimization techniques. In this work, a new Dynamic Social Behavior (DSB) algorithm is proposed to solve global optimization problems. The DSB algorithm is based on the simulation of cooperative behavior of animal groups. In the proposed algorithm, individuals emulate the interaction of individuals based on biological laws of cooperative colony. This algorithm partially adopts the foraging strategy of animal groups and utilizes recruitment signal as a means of information transfer among individuals. In order to illustrate the proficiency and robustness of the proposed algorithm, it is compared with other well-known evolutionary algorithms. The comparison examines several series of widely used benchmark functions and an engineering problem on hyper beamforming optimization. The results testifies the superior performance of DSB compared with other state-of-the-art meta-heuristics.

Prediction of NO2 Emission Concentration via Correlation of Multiple Big Data Sources Using Extreme Learning Machine

Increase of electricity demand and urbanization process has caused more power plants to be built to meet the demand of electricity. However, development of power plant will cause environmental issue for its surrounding. Necessary measures need to be taken to ensure social and environmental sustainability. Among the requirements in Malaysia, discharge of air pollution emission of a gas- or distillate-fired power plant has to comply with air pollution level as described in the Malaysian Ambient Air Quality Standards ((MAAQS) 2013 and the Environmental Quality (Clean Air) Regulations 2014. Pertaining to the environmental requirements, this paper is to investigate the ability of a regression based artificial intelligence tool, namely Extreme Learning Machine (ELM) in correlating multiple sources of big data sets and subsequently predicting the air pollution emission level from the chimney of a Combined Cycle Gas Turbine (CCGT) power plant. This emission data is later being used to ensure the clean air regulatory requirement is fulfilled. The big data sources that have been used in this work are meteorological data, terrain and land use data, historical emission data and power plant parameters particularly related to the point source emitter. With the correlation of multiple big data sources, Extreme Learning Machine (ELM) is then trained for the prediction of emission rate at certain targeted areas, which are classified as air sensitive receptors (ASR) surrounding the power plant. Nitrogen dioxide (NO2) is the key emission that has been studied in this paper due to its criticality towards environment. A standalone application program has been developed to employ ELM based big data analytics tool for the prediction of NO2 pollution emission. The output of ELM is analyzed to ensure the emission at ground level of ASR is maintained within allowable limit.

Optimization of array pattern for efficient control of adaptive nulling and side lobe level

The array synthesis problem is modeled as a nonlinear optimization problem with the constraints of a reduced side lobe level (SLL). The goal is to impose deeper nulls in the interference direction of an uniform linear antenna arrays. This paper focuses on the array synthesis of adaptive nulling and side lobe level control which is a highly nonlinear problem fit for an evolutionary optimization algorithm. The limitations with the available optimization algorithms are mainly subjected to premature convergence and stagnation problem hence resulting in a non satisfactory array synthesis results. Hence, a new optimization technique known as Collective Social Behavior (CSB) is developed with concepts adopted from evolution of social behavior to address the current limitations to achieve a better result in array synthesis problem. The optimal set of weight coefficients for the linear antenna arrays is determined by the CSB algorithm by evaluating the objective function for the array synthesis problem. To establish the CSB algorithm as an efficient optimization tool for adaptive nulling applications, several numerical benchmark tests have been conducted. The simulation results reveal that the proposed CSB algorithm enhances the performance of array pattern synthesis with precise deeper nulls and suppressed side lobe levels.

Improved combined mutation clonal selection algorithm

In this paper, the performance of a clonal selection optimization algorithm implementing a combined mutation strategy using Gaussian and Cauchy mutations was further improved with the addition of two new operators, namely the Cell Repair Operator (CPO) and Dynamic Mutation Size Operator (DMSO). The new and improved algorithm was tested using various unimodal and multimodal test functions to illustrate the improvements of the algorithm. The test results indicate that the added operators have significantly improved the performance of the algorithm in terms of accuracy and performance.

Improved Hierarchical Structure Poly-particle particle Swarm Optimization

In this paper, the Improved Hierarchical Structure Poly-particle Swarm Optimization (IHSPPSO) algorithm is proposed based on the Hierarchical Structure Poly-particle Swarm Optimization (HSPPSO) algorithm with the addition of three new operators, namely the Particle Repair Operator, Dynamic Acceleration Control Operator and Cauchy mutation operator to achieve better performance in terms of accuracy and rate of convergence. The performance of the IHSPPSO algorithm was tested and evaluated using four benchmark test functions. The test results of the IHSPPSO algorithm were compared with the ones of HSPPSO and significant improvements were shown. The addition of three new operators has significantly improved the performance of the IHSPPSO algorithm.