Informatics Publishing Limited

Yee Shin Chia ¹, Zhan Wei Siew ¹, Hoe Tung Yew ¹, Soo Siang Yang ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modeling, Simulation & Computing Laboratory, Material & Mineral Research Unit School of Engineering and Information Technology, Universiti Malaysia Sabah, MY

Abstract

The channel assignment problem in wireless mobile network is the assignment of appropriate frequency spectrum to incoming calls while maintaining a satisfactory level of electromagnetic compatibility (EMC) constraints. An effective channel assignment strategy is important due to the limited capacity of frequency spectrum in wireless mobile network. Most of the existing channel assignment strategies are based on deterministic methods. In this paper, an adaptive genetic algorithm (GA) based channel assignment strategy is introduced for resource management and to reduce the effect of EMC interferences. The most significant advantage of the proposed optimization method is its capability to handle both the reassignment of channels for existing calls as well as the allocation of channel to a new incoming call in an adaptive process to maximize the utility of the limited resources. It is capable to adapt the population size to the number of eligible channels for a particular cell upon new call arrivals to achieve reasonable convergence speed. The MATLAB simulation on a 49-cells network model for both uniform and nonuniform call traffic distributions showed that the proposed channel optimization method can always achieve a lower average new incoming call blocking probability compared to the deterministic based channel assignment strategy.

Keywords

Evolutionary Optimization, Genetic Algorithm, Hybrid Channel Assignment, Wireless Mobile Network.

Full Text

     

Zhan Wei Siew ¹, Chen How Wong ¹, Aroland Kiring ¹, Renee Ka Yin Chin ¹, Kenneth Tze Kin Teo ²

Affiliations
1 Modeling, Simulation & Computing Laboratory, Material & Mineral Research Unit School of Engineering and Information Technology, Universiti Malaysia Sabah, MY
2 Modeling, Simulation & Computing Laboratory, Material & Mineral Research Unit School of Engineering and Information Technology, Universiti Malaysia Sabah, MY

Abstract

Wireless sensor networks (WSNs) have been vastly developed due to the advances in microelectromechanical systems (MEMS) using WSN to study and monitor the environments towards climates changes. In environmental monitoring, sensors are randomly deployed over the interest area to periodically sense the physical environments for a few months or even a year. Therefore, to prolong the network lifetime with limited battery capacity becomes a challenging issue. Low energy adaptive cluster hierarchical (LEACH) is the common clustering protocol that aim to reduce the energy consumption by rotating the heavy workload cluster heads (CHs). The CHs election in LEACH is based on probability model which will lead to inefficient in energy consumption due to least desired CHs location in the network. In WSNs, the CHs location can directly influence the network energy consumption and further affect the network lifetime. In this paper, factors which will affect the network lifetime will be presented and the demonstration of fuzzy logic based CH selection conducted in base station (BS) will also be carried out. To select suitable CHs that will prolong the network first node dies (FND) round and consistent throughput to the BS, energy level and distance to the BS are selected as fuzzy inputs.

Keywords

Wireless Sensor Network, Cluster Head, First Node Dies, Fuzzy Logic.

Full Text

     

Wei Leong Khong ¹, Wei Yeang Kow ¹, Ismail Saad ¹, Chung Fan Liau ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modelling, Simulation and Computing Laboratory, Material and Mineral Research Unit, School of Engineering and Information Technology, Universiti Malaysia, Sabah, MY

Abstract

Optical sensors based vehicle tracking can be widely implemented in traffic surveillance and flow control. The vast development of video surveillance infrastructure in recent years has drawn the current research focus towards vehicle tracking using high-end and low cost optical sensors. However, tracking vehicles via such sensors could be challenging due to the high probability of changing vehicle appearance and illumination, besides the occlusion and overlapping incidents. Particle filter has been proven as an approach which can overcome nonlinear and non-Gaussian situations caused by cluttered background and occlusion incidents. Unfortunately, conventional particle filter approach encounters particle degeneracy especially during and after the occlusion. Particle filter with sampling important resampling (SIR) is an important step to overcome the drawback of particle filter, but SIR faced the problem of sample impoverishment when heavy particles are statistically selected many times. In this work, genetic algorithm has been proposed to be implemented in the particle filter resampling stage, where the estimated position can converge faster to hit the real position of target vehicle under various occlusion incidents. The experimental results show that the improved particle filter with genetic algorithm resampling method manages to increase the tracking accuracy and meanwhile reduce the particle sample size in the resampling stage.

Keywords

Vehicle Tracking, Particle Filter, Genetic Algorithm, Resampling, Occlusion.

Full Text

     

Lorita Angeline ¹, Hou Pin Yoong ¹, Hui Keng Lau ¹, Ismail Saad ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modelling, Simulation and Computing Laboratory, Material and Mineral Research Unit, School of Engineering and Information Technology, Universiti Malaysia, Sabah, MY

Abstract

A new algorithm for license plate localisation and identification is proposed on the basis of Signature analysis. Signature analysis has been used to locate license plate candidate and its properties can be further utilised in supporting and affirming the license plate character recognition. This paper presents Signature Analysis and the improved conventional Connected Component Analysis (CCA) to design an automatic license plate localisation and identification. A procedure called Euclidean Distance Transform is added to the conventional CCA in order to tackle the multiple bounding boxes that occurred. The developed algorithm, SAICCA achieved 92% successful rate, with 8% failed localisation rate due to the restrictions such as insufficient light level, clarity and license plate perceptual information. The processing time for a license plate localisation and recognition is a crucial criterion that needs to be concerned. Therefore, this paper has utilised several approaches to decrease the processing time to an optimal value. The results obtained show that the proposed system is capable to be implemented in both ideal and non-ideal environments.

Keywords

Vehicle Localisation, Automatic License Plate Recognition, Signature Analysis, Adaptive Searching, Euclidean Distance Transform.

Full Text

     

Chia Seet Chin ¹, Bih Lii Chua ¹, Pei Yi Lim ¹, Hui Hwang Goh ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modeling, Simulation & Computing Laboratory, Material & Mineral Research Unit School of Engineering and Information Technology, Universiti Malaysia Sabah, MY

Abstract

The photovoltaic (PV) array controlled by Maximum Power Point Tracking (MPPT) method for optimum PV power generation, particularly when the PV array is under partially shaded condition is presented in this paper. The system modelling is carried out in MATLAB-SIMULINK where the PV array is formed by five series connected identical PV modules. Under uniform solar irradiance conditions, the PV module and the PV array present nonlinear P-V characteristic but the maximum power point (MPP) can be easily identified. However, when the PV array is under shaded conditions, the P-V characteristic becomes more complex with the present of multiple MPP. While the PV array operated at local MPP, the generated power is limited. Thus, the investigation on MPPT approach is carried out to maximize the PV generated power even when the PV array is under partially shaded conditions (PSC). Fuzzy logic is adopted into the conventional MPPT to form fuzzy logic based MPPT (FMPPT) for better performance. The developed MPPT and FMPPT are compared, particularly the performances on the transient response and the steady state response when the array is under various shaded conditions. FMPPT shows better performance where the simulation results demonstrate FMPPT is able to facilitate the PV array to reach the MPP faster while it helps the PV array to produce a more stable output power.

Keywords

Photovoltaic, Partially Shaded Conditions, MPPT, Fuzzy Logic, Perturb and Observe.

Full Text

     

Yit Kwong Chin ¹, Heng Jin Tham ¹, N. S. V. Kameswara Rao ¹, Nurmin Bolong ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modeling, Simulation & Computing Laboratory, Material & Mineral Research Unit School of Engineering and Information Technology, Universiti Malaysia Sabah, MY

Abstract

Congestions of the traffic flow within the urban traffic network have been a challenging task for all the urban developers. Many approaches have been introduced into the current system to solve the traffic congestion problems. Reconfiguration of the traffic signal timing plan has been carried out through implementation of different techniques. However, dynamic characteristics of the traffic flow increase the difficulties towards the ultimate solutions. Thus, traffic congestions still remain as unsolvable problems to the current traffic control system. In this study, artificial intelligence method has been introduced in the traffic light system to alter the traffic signal timing plan to optimize the traffic flows. Q-learning algorithm in this study has enhanced the traffic light system with learning ability. The learning mechanism of Q-learning enables traffic light intersections to release itself from traffic congestions situation. Adjacent traffic light intersections will work independently and yet cooperate with each others to a common goal of ensuring the fluency of the traffic flows within the traffic network. The simulated results show that the Q-Learning algorithm is able to learn from the dynamic traffic flow and optimize the traffic flow accordingly.

Keywords

Reinforcement Learning, Q-Learning, Traffic Networks, Traffic Signal Timing Plan Management, Multi-Agents Systems.

Full Text

     

Kit Guan Lim ¹, Chun Hoe Lee ¹, Renee Ka Yin Chin ¹, Kiam Beng Yeo ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Simulation and Computing Laboratory, Universiti Malaysia Sabah, MY

Abstract

It is normal that every family is having at least one vehicle at their home as vehicles have become a daily needs for all of us. However, this also leads to the increased of road accidents where major causes are related to human errors which can be prevented. To tackle with this problem, vehicular ad hoc network (VANET) is introduced with the aim to make vehicles intelligent. In order to study the algorithm in VANET, a mobility simulator is needed for simulation purpose. In this case, SUMO is proved to be a good simulation tool in generating VANET environment while MATLAB is good for algorithm development. Yet, to develop a good simulation platform, modification on SUMO files are necessary. This paper discusses on the procedures in creating a left-hand traffic (LHT) simulation file that is suitable to be used in Malaysia. LHT simulation is not easy to achieve as modification on the road connection and traffic light files are required. This paper also showed the results of the simulation after SUMO files modification. Apart from that, this paper also showed the simulation of VANET environment using SUMO and MATLAB through a third party interfacing named TraCI4Matlab, which allows communication between MATLAB and SUMO simulator.

Keywords

Mobility Simulator, SUMO, MATLAB, SUMO Files Modification.

Full Text

     

Chun Hoe Lee ¹, Kit Guan Lim ¹, Min Keng Tan ¹, Renee Ka Yin Chin ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Simulation and Computing Laboratory, Universiti Malaysia Sabah, MY

Abstract

Intelligent Transportation Systems (ITS) plays a vital role in providing different means of traffic management and enables users to be better informed of traffic condition, promoting safer, coordinated and efficient use of transport network. Vehicular Ad Hoc Network (VANET) shows promising reliability and validity in ITS. But, it poses challenges to researchers in designing protocol specifically for VANET as the deployment of VANET in real world will incur high cost. Therefore, simulation and non-physical testbed implementation have been widely adopted by the VANET research community in the development and assessment of the new or improved system and protocol of VANET. This paper presents a viable simulation platform for network development. Besides, a code cast or better known as network coding, a data packet transmission method has been developed and introduced into VANET protocol using the presented platform to assess and determine the potential of the introduced simulation platform.

Keywords

Vehicular Ad hoc Network, Traffic Simulation, Network Simulation, Intelligent Transportation System, Network Coding.

Full Text

     

Nurul Izyan Kamaruddina ¹, Ahmad Razani Haron ¹, Bih Lii Chua ¹, Min Keng Tan ¹, Kit Guan Lim ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modelling, Simulation and Computing Laboratory, Artificial Intelligence Research Unit, Faculty of Engineering, Universiti Malaysia Sabah, MY

Abstract

Photovoltaic system (PV) is an important technological asset for renewable energy production. It works by converting solar cell energy from the sun into electrical direct current. In reality, the photovoltaic module usually receives non-uniform solar irradiance at different light intensity due to non-atmospheric hindrance. Under such conditions, the PV system exhibits multiple peaks on the energy characteristic curve, generally known as the partial shading condition (PSC). Therefore, in order to maximize the energy harvested by the photovoltaic system (PV), maximum power point tracking (MPPT) method is suggested to extract all possible maxima that have been produced by the PV system under various circumstances through the non-uniform irradiance of the sunlight. Based on previous researches, it is found that conventional method such as perturb and observed (P&O) method failed to track the maximum power and was trapped at the local maximum power (LMPP). This paper focuses on exploring a metaheuristic method which is the differential evolution (DE) algorithm in optimizing the energy harvested by the PV system. The platform chosen for modelling in this paper is a 3 × 3 PV array. The PV array is tested with different conditions of partial shading where random irradiance values are set. Comparing the performance of PV between P&O and DE based MPPT controller, the DE based MPPT controller is inferred to have a higher success rate to escape from being trapped in LMPP and thus produce more total energy.

Keywords

Photovoltaic system, Maximum Power Point Tracking, Partial Shading Condition, Perturb and Observed, Differential Evolution.

Full Text

     

Min Keng Tana ¹, Helen Sin Ee Chuo ¹, Kit Guan Lim ¹, Renee Ka Yin Chin ¹, Soo Siang Yang ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Modelling Simulation and Computing Laboratory, Artificial Intelligence Research Unit, Faculty of Engineering, Universiti Malaysia Sabah, MY

Abstract

Traffic congestion is a perennial issue for most cities. Various artificial intelligence (AI) algorithms, which can categorize as deterministic and metaheuristic algorithms have been suggested to mitigate congestion. Although traffic flow is dynamic and stochastic in nature, most of the previous works evaluated the algorithms with a deterministic or non-stochastic traffic flow pattern. As such, the adaptiveness of those AI algorithms in dealing with stochastic traffic flow patterns is yet to be investigated. Therefore, this paper aims to explore the feasibility of both algorithm types in controlling stochastic traffic flow. In this work, a benchmarked traffic flow model is modified and developed as the simulation platform with the parameters extracted from the guidelines of Public Works Department Malaysia (JKR). Normal distribution function is embedded in the developed model to simulate non-uniform headway for inflow and outflow vehicles. Two commonly used algorithms, namely Fuzzy Logic and Genetic Algorithm are proposed as the adaptive controller to optimize the traffic signalization based on the instant stochastic traffic demand. The simulation results show the metaheuristic algorithm performs better than the deterministic algorithm. The mutation mechanism of the metaheuristic algorithm improves the exploration ability of the algorithm in seeking the optimum solution within the solution space without bounded by a set of fixed-computational rules.

Keywords

Genetic Algorithm, Fuzzy Logic, Signal Optimization, Stochastic Flow, Saturated Condition.

Full Text

     

Vincent Chung ¹, Hamzarul Alif Hamzah ¹, Norah Tuah ², Kit Guan Lim ¹, Min Keng Tan ¹, Kenneth Tze Kin Teo ¹

Affiliations
1 Simulation and Computing Laboratory, Faculty of Engineering, Universiti Malaysia Sabah, MY
2 Faculty of Computer Science and Mathematics, Universiti Teknologi MARA, MY

Abstract

Wireless sensor network (WSN) is an embedded system comprises of spatially distributed sensor nodes where an energy-efficient mechanism is needed to prolong the network lifetime. Existing approaches for this optimization problem have several drawbacks, including non-adaptive network configuration that may cause premature death of sensor nodes. Genetic-based evolutionary algorithms such as Genetic Algorithm (GA) and Differential Evolution (DE) have been popularly used to optimize cluster head selection in WSN to improve energy efficiency for the extension of network lifetime. Therefore, the performances of GA and DE are evaluated through comparative analysis to determine their efficiency in cluster head selection optimization. Simulation results show that GA outperforms DE with higher round number for first node dies (FND) but lower round number for last node dies (LND) in terms of network lifetime. Besides, GA also leads to a network with lower number of transmission failures than DE. On the other hand, fitness convergence of GA is slower but it has higher fitness value of population.

Keywords

Brent’s Method, Optimal Power Allocation, Ant Colony Optimization, Secrecy Rate.

Full Text