Lim Eng Aik
Thumbnail Image
Preferred name
Lim Eng Aik
Official Name
Lim, Eng Aik
Alternative Name
Aik, Limeng
Lim, E. A.
Main Affiliation
Scopus Author ID
23491376300
Researcher ID
EKL-8415-2022

Research Output

Filters

5 1
1
5
Reset filters

Settings
Now showing 1 - 5 of 5
  • Publication
    The SIR model of Zika virus disease outbreak in Brazil at year 2015
    ( 2017-05-19)
    Lim Eng Aik
    ;
    Lam Chee Kiang
    ;
    Tan Wei Hong
    ;
    Mohd Syafarudy Abu
    This research study demonstrates a numerical model intended for comprehension the spread of the year 2015 Zika virus disease utilizing the standard SIR framework. In modeling virulent disease dynamics, it is important to explore whether the illness spread could accomplish a pandemic level or it could be eradicated. Information from the year 2015 Zika virus disease event is utilized and Brazil where the event began is considered in this research study. A three dimensional nonlinear differential equation is formulated and solved numerically utilizing the Euler's method in MS excel. It is appeared from the research study that, with health intercessions of public, the viable regenerative number can be decreased making it feasible for the event to cease to exist. It is additionally indicated numerically that the pandemic can just cease to exist when there are no new infected people in the populace.
  • Publication
    In-situ Noise Measurement and Analysis for the Motorcycle Muffler
    ( 2020-01-01)
    Tan Wei Hong
    ;
    Chuah H.G.
    ;
    Cheng Ee Meng
    ;
    Lim Eng Aik
    ;
    Lok, Chip Hao
    Noise from the vehicles is one of the noise pollutions to the environment. The noises emitted by the vehicles have to obey the requirement of regulation of maximum sound pressure level permitted for respective vehicles. In this study, the aim is to reduce the noise emitted from the motorcycle muffler. The noise emitted from the motorcycle muffler is analyzed and measured using a sound level meter. The average sound pressure level of the motorcycle muffler is determined in certain conditions. The sound pressure levels for original installed muffler are recorded as 76.4dB, 79.5dB and 82.3dB under the constant speed of 10km/hr, 20km/hr and 30km/hr respectively by engaging 2nd gear. For the acceleration with the scope of 0 km/hr to 30 km/hr, the difference of sound pressure level between 2nd and 4th gear engaged is 5.4dB. The study is continued by using a modified muffler which contains sound absorptive materials. The absorptive materials chosen are glass wool, cotton and Styrofoam and they are taking turn to be placed into the modified muffler to reduce the sound pressure level. Then the experiment is repeated. By applying 100g absorptive materials in the modified muffler, the reduction of sound pressure level are recorded as 12.6% (glass wool), 7.5% (cotton) and 4.4% (Styrofoam) compared with original installed muffler while 2nd gear engaged. Styrofoam is observed does not perform significantly in absorbing sound or noise in this study. Glass wool demonstrates relatively better sound energy absorption compared with cotton. In general, soft and porous materials are considered good performance in sound absorption. Denser materials are better at soundproofing or sound blocking. Therefore, glass wool with relatively higher density among the investigated absorptive materials in this study has the greatest sound absorption performance.
  • Publication
    New algorithm for improving prediction performance in modified radial basis function network
    ( 2020)
    Lim Eng Aik
    In neural networks, the accuracies of the networks are primarily relying on two critical factors, which are the centers and networks weight values. The feed-forward network known as Radial basis function network (RBFN) capable of performing nonlinear approximation on an unknown dataset, classification, pattern recognition, control system, and image processing. However, there are some disadvantages of the RBFN network, such as longer computation time for large datasets, less efficient weight updating, and center selection algorithms that cause low accuracy are identified. Limited data points or overload data points can affect the training of RBFN. Hence, proper size for dataset is required to ensure RBFN is trained using suitable dataset size to lessen the computational time without a significant influence on the accuracy. For RBFN weight updating, the gradient descent (GD) algorithm easily trapped in local minima by random weight generated during the initial stage of training. Meanwhile, the center's selection using the K-means algorithm is known for its sensitivity and high dependency to initial center selection from the input dataset. Therefore, this work proposed solutions for these mentioned disadvantages through modification on a few parts of the RBFN algorithm to improve their performance. First, this work proposed a new dataset reduction formula to obtain a suitable number of a dataset for network training. Next, a modified steepest descent algorithm was proposed for RBFN weight updating during training. Then, a new distance-weighted K-means algorithm is proposed for obtaining more accurate initial centers for RBFN. Finally, this work proposed a new model through a combination of quantum evolutionary algorithm (QEA) and RBFN known as QRBFN. This proposed RBFN demonstrated its abilities in global search and local optimization to effectively provide better accuracy in prediction results. All proposed modified RBFN was tested against the standard RBFN in predictions accuracy on four nonlinear models from literature, and four real-world datasets that consist two time-series datasets (Air pollutant dataset and forex pair EURUSD dataset), and other two datasets are Biochemical Oxygen Demand (BOD) dataset, and Phytoplankton growth dataset. The proposed dataset reduction formula was conducted through experiments where data was tested by a 5 percent step size reduction. The results of this proposed RBFN are compared for root mean square error (RMSE) and area under curve (AUC) values with standard RBFN. The proposed dataset reduction case yielded average results over a 50 percent decrease in time usage and a 20 percent reduction in RMSE. Meanwhile, all proposed RBFN yielded better results and robustness with an average improvement percentage of more than 40 percent in RMSE and AUC results.
  • Publication
    MICROWAVE ABSORPTION ANALYSIS ON HEATED EDIBLE SPIRULINA WITH VARIOUS TEMPERATURES
    ( 2023-05-01)
    Cheng Ee Meng
    ;
    Tan Wei Hong
    ;
    Tan Wee Choon
    ;
    Lim Eng Aik
    This paper discusses the microwave absorption analysis of edible Spirulina by using WR62 and WR90 rectangular waveguides in conjunction with Agilent P-series Vector Network Analyzer (PNA). Heat might lead to the degradation of spirulina. This phenomenon involves the chemical and physical reaction that is associated with the variation of dielectric properties. These properties determine the propagation mechanism of microwaves within the sample or material. Hence, an assessment method to detect a nutrient change in spirulina due to heat is necessary. In this context, a microwave absorption measurement system was developed to study the reflection coefficient, transmission coefficient, and absorption coefficient of Spirulina tablets over temperature. The transmission/Reflection line method is well-known because it is non-destructive and rapid in analyzing chemical and physical properties. In this work, Spirulina tablet is used since it is a popular food supplement that is believed to be able to treat diseases is and good for health. The reflection, transmission, and absorption measurements were conducted on Spirulina from 12.4GHz to 18GHz.
  • Publication
    K-means Algorithm Based on Flower Pollination Algorithm and Calinski-Harabasz Index
    ( 2023-01-01)
    Lim Eng Aik
    ;
    Tan Wee Choon
    ;
    Mohd Syafarudy Abu
    Aiming at the problems that the Flower Pollination (FP) algorithm is easy to fall into the local optimum, the searchability is weak, and the k-means algorithm is easily affected by the selection of the initial clustering centre, a k-means algorithm based on the FP algorithm is proposed. Six benchmark functions test the improved FP algorithm. The effectiveness of the k-means algorithm based on the improved FP algorithm was tested and verified with UCI machine learning and artificial datasets. The verification results showed that the improved FP algorithm improved based on ensuring a faster convergence speed. Compared with other algorithms, the performance of this algorithm has been significantly improved in all aspects.