Journals Articles

Permanent URI for this collection

https://hdl.handle.net/20.500.14170/1995

Browse

Browsing Journals Articles by Department "Universiti Malaysia Perlis"
  • Publication
    2-SAT discrete Hopfield neural networks optimization via Crow search and fuzzy dynamical clustering approach
    ( 2024)
    Caicai Feng
    ;
    Saratha Sathasivam
    ;
    Nurshazneem Roslan
    ;
    Muraly Velavan
    Within the swiftly evolving domain of neural networks, the discrete Hopfield-SAT model, endowed with logical rules and the ability to achieve global minima of SAT problems, has emerged as a novel prototype for SAT solvers, capturing significant scientific interest. However, this model shows substantial sensitivity to network size and logical complexity. As the number of neurons and logical complexity increase, the solution space rapidly contracts, leading to a marked decline in the model's problem-solving performance. This paper introduces a novel discrete Hopfield-SAT model, enhanced by Crow search-guided fuzzy clustering hybrid optimization, effectively addressing this challenge and significantly boosting solving speed. The proposed model unveils a significant insight: its uniquely designed cost function for initial assignments introduces a quantification mechanism that measures the degree of inconsistency within its logical rules. Utilizing this for clustering, the model utilizes a Crow search-guided fuzzy clustering hybrid optimization to filter potential solutions from initial assignments, substantially narrowing the search space and enhancing retrieval efficiency. Experiments were conducted with both simulated and real datasets for 2SAT problems. The results indicate that the proposed model significantly surpasses traditional discrete Hopfield-SAT models and those enhanced by genetic-guided fuzzy clustering optimization across key performance metrics: Global minima ratio, Hamming distance, CPU time, retrieval rate of stable state, and retrieval rate of global minima, particularly showing statistically significant improvements in solving speed. These advantages play a pivotal role in advancing the discrete Hopfield-SAT model towards becoming an exemplary SAT solver. Additionally, the model features exceptional parallel computing capabilities and possesses the potential to integrate with other logical rules. In the future, this optimized model holds promise as an effective tool for solving more complex SAT problems. </abstract>
      25  2
  • Publication
    Analytical and numerical solutions of fuzzy differential equations
    ( 2013-02-26)
    Muhammad Zaini Ahmad
    ;
    M.K. Hasan
    ;
    B. De Baets
    In this paper, we study analytical and numerical solutions of fuzzy differential equations based on the extension principle. For linear fuzzy differential equations, we state some results on the behaviour of the solutions and study their relationship with the generalised Hukuhara derivative. In order to approximate the solutions of linear and non-linear fuzzy differential equations, we propose a new fuzzification of the classical Euler method and then incorporate an unconstrained optimisation technique. This combination offers a powerful tool to tackle uncertainty in any numerical method. An efficient computational algorithm is also provided to guarantee the convexity of fuzzy solutions on the time domain. Several illustrative examples are given.
      24  2
  • Publication
    Application of hybrid cubic B-Spline collocation approach for solving a generalized nonlinear Klien-Gordon equation
    ( 2014)
    Shazalina Mat Zin
    ;
    Ahmad Abd Majid
    ;
    Ahmad Izani Md. Ismail
    ;
    Muhammad Abbas
    The generalized nonlinear Klien-Gordon equation is important in quantum mechanics and related fields. In this paper, a semi-implicit approach based on hybrid cubic B-spline is presented for the approximate solution of the nonlinear Klien-Gordon equation. The usual finite difference approach is used to discretize the time derivative while hybrid cubic B-spline is applied as an interpolating function in the space dimension. The results of applications to several test problems indicate good agreement with known solutions.
      3  16
  • Publication
    Application of resampling techniques in Orthogonal regression
    (International Research Publication House, 2020)
    Fitrianto, Anwar
    ;
    Yun, Tan Sin
    ;
    Wan Zuki Azman Wan Muhamad
    The classical Orthogonal Regression analysis relies heavily on the normality assumption. However, sometimes we might be uncertain of the underlying distribution of our dataset or the sample size might be small, which would cause an inaccurate inference on the parameter if the data is not normally distributed. This leads to the main objective of this paper which is to examine alternative methods to the parametric OR analysis which do not rely on the normality assumption. In this paper, the nonparametric jackknife and bootstrap resampling techniques were applied to assess the bias, standard errors and confidence intervals for the parameters of the model. We studied on the method of delete-one jackknife and bootstrapping the observations and made comparisons between the two methods as well. Under bootstrapping, three methods were considered to construct the confidence intervals which include percentile interval, bias-corrected (BC) interval and bias-corrected and accelerated (BCa) interval. Based on the results, it was found that the bootstrap estimators were closer to the values of classical OR analysis compared to jackknifed estimators. Besides, the jackknife estimates of bias and standard errors were slightly larger than that of bootstrap. Furthermore, we also found that the confidence intervals for the parameters constructed from jackknife have longer lengths and closer to that of OR. This showed that jackknife performed better in constructing confidence interval than the bootstrap.
      1  9
  • Publication
    Applications of the fuzzy sumudu transform for the solution of first order fuzzy differential equations
    ( 2015)
    Norazrizal Rahman
    ;
    Muhammad Zaini Ahmad
    In this paper, we study the classical Sumudu transform in fuzzy environment, referred to as the fuzzy Sumudu transform (FST). We also propose some results on the properties of the FST, such as linearity, preserving, fuzzy derivative, shifting and convolution theorem. In order to show the capability of the FST, we provide a detailed procedure to solve fuzzy differential equations (FDEs). A numerical example is provided to illustrate the usage of the FST.
  • Publication
    Boundary layer flow and heat transfer over a permeable stretching/shrinking sheet with a convective boundary condition
    ( 2015)
    Wan Mohd Khairy Adly Wan Zaimi
    ;
    Anuar Ishak
    This paper concerns with the boundary layer flow and heat transfer over a permeable stretching/shrinking sheet in a viscous fluid, with the bottom surface of the plate is heated by convection from a hot fluid. The partial differential equations governing the flow and heat transfer are converted into ordinary differential equations using a similarity transformation, before being solved numerically. The effects of the suction, convection and stretching/shrinking parameters on the skin friction coefficient and the local Nusselt number are examined and graphically illustrated. Dual solutions are found to exist for a certain range of the suction and stretching/shrinking parameters. The numerical results also show that suction widens the range of the stretching/shrinking parameter for which the solution exists.
      2  13
  • Publication
    Computational study of magnetite-ethylene glycol–water-based hybrid nanofluid dynamics on an exponential shrinking/stretching Riga surface under radiative heat flux
    (Springer, 2024-10)
    Ubaidullah Yashkun
    ;
    Liaquat Ali Lund
    ;
    Wan Mohd Khairy Adly Wan Zaimi
    ;
    Zahir Shah
    ;
    Mansoor H. Alshehri
    ;
    Narcisa Vrinceanu
    ;
    Elisabeta Antonescu
    The exceptional heat transfer capabilities of hybrid base ferrofluids have attracted numerous researchers, prompting an increase in investigations into these working fluids. In various applications, hybrid base nanofluids have demonstrated superior heat transfer performance. However, further research is needed to expand their range of applications. To address this need, the current study aims to explore the flow of a hybrid base nanofluid (magnetite with ethylene glycol and water as the base fluid) on an exponential shrinking/stretching Riga plate with radiative heat flux. The Riga plate, an electromagnetic actuator, consists of a spanwise-aligned array of alternating electrodes attached to a flat surface and permanent magnets. This setup enables the examination of heat transfer with Hartmann number, thermal radiation, and nanoparticle volume fraction. The governing PDE systems are transformed into ODE systems using similarity transformations, and the developed model is solved numerically using the bvp4c technique in MATLAB software. A comprehensive convergence analysis and comparative investigation of numerical data are conducted to ensure the accuracy of the results. Finally, the effects of physical parameters on skin frictional force, Nusselt number, velocity field, and temperature field are investigated, and the results are presented graphically and discussed in detail. The numerical values for the skin frictional quantity variation along suction with different Hartmann quantity obtained. The critical values Sci,i=1,2, and 3 observed are 2.2396,2.3795, and 2.7714 corresponding to the values of M = 0,0.02, and 0.04, respectively. Research suggests that dual solutions are present within a specific spectrum of suction and stretching/shrinking parameters. Additionally, the stability analysis of these dual solutions indicates that the primary solution is stable.
  • Publication
    Conditional random k satisfiability modeling for k =1,2 (CRAN2SAT) with non-monotonic Smish activation function in discrete Hopfield neural network
    ( 2024)
    Nurshazneem Roslan
    ;
    Saratha Sathasivam
    ;
    Farah Liyana Azizan
    <abstract> <p>The current development of logic satisfiability in discrete Hopfield neural networks (DHNN)has been segregated into systematic logic and non-systematic logic. Most of the research tends to improve non-systematic logical rules to various extents, such as introducing the ratio of a negative literal and a flexible hybrid logical structure that combines systematic and non-systematic structures. However, the existing non-systematic logical rule exhibited a drawback concerning the impact of negative literal within the logical structure. Therefore, this paper presented a novel class of non-systematic logic called conditional random <italic>k</italic> satisfiability for <italic>k</italic> = 1, 2 while intentionally disregarding both positive literals in second-order clauses. The proposed logic was embedded into the discrete Hopfield neural network with the ultimate goal of minimizing the cost function. Moreover, a novel non-monotonic Smish activation function has been introduced with the aim of enhancing the quality of the final neuronal state. The performance of the proposed logic with new activation function was compared with other state of the art logical rules in conjunction with five different types of activation functions. Based on the findings, the proposed logic has obtained a lower learning error, with the highest total neuron variation <italic>TV</italic> = 857 and lowest average of Jaccard index, <italic>JSI</italic> = 0.5802. On top of that, the Smish activation function highlights its capability in the DHNN based on the result ratio of improvement <italic>Zm</italic> and <italic>TV</italic>. The ratio of improvement for Smish is consistently the highest throughout all the types of activation function, showing that Smish outperforms other types of activation functions in terms of <italic>Zm</italic> and <italic>TV.</italic> This new development of logical rule with the non-monotonic Smish activation function presents an alternative strategy to the logic mining technique. This finding will be of particular interest especially to the research areas of artificial neural network, logic satisfiability in DHNN and activation function.</p> </abstract>
      1  19
  • Publication
    Decay properties of 253, 255Rf using the relativistic Mean-Field framework within the preformed Cluster-Decay model
    (Pleiades Publishing Ltd., 2023)
    Joshua T. Majekodunmi
    ;
    Nishu Jain
    ;
    Khairul Anwar Mohamad Khazali
    ;
    Nooraihan Abdullah
    ;
    Raj Kumar
    ;
    Muruthujaya Bhuyan
    Most neutron-deficient α emitters are known to be of great relevance to the astrophysical rapid neutron capture process in superheavy nuclei. Therefore, in the present work, the decay properties of newly observed superheavy nuclei with Z = 102, i.e., 249No isotope from the α-decay of 253Rf is theoretically investigated using the relativistic mean field (RMF) framework and the NL3* parameter set within the preformed cluster-decay model (PCM). The α-decay chain of 255f is also considered. The RMF densities are folded with the R3Y nucleon-nucleon (NN) potential to deduce the nuclear interaction potential between the decaying fragments. A complete understanding of the penetration of an α-particle across the nuclear Coulomb barrier gives outstanding credence to the assumptions of quantum mechanics. The presence of shell/sub-shell closure is indicated by the formation of peaks along the decay chain and was found to alter the conventional scaling factor observed earlier in the results of the PCM. The calculated half-lives are in close agreement with recent experimental measurements.
      1  22
  • Publication
    Dual solutions of boundary layer flow and heat transfer in hybrid nanofluid over a stretching/shrinking cylinder
    (Semarak Ilmu Publishing, 2023)
    Nor Ashikin Abu Bakar
    ;
    Rohana Abdul Hamid
    ;
    Najwa Najib
    The boundary layer flow over a stretching/shrinking cylinder in hybrid nanofluid with the effects of suction, partial slip and convective boundary condition is studied. Hybrid nanoparticles Al2O3 and TiO2 with water as based fluid are considered in the study. The partial differential equations are transformed to ordinary differential equations by employing the similarity variables. The numerical results are obtained using the bvp4c solver in MATLAB software. The influence of nanoparticles volume fraction (Al2O3-TiO2 in water-based fluid), curvature parameter, suction parameter, partial slip parameter and Biot number on the velocity profile, temperature profile, skin friction coefficient and heat transfer rate are discussed. The numerical results indicate that for shrinking surface case, the dual solutions exist for a certain range of curvature parameter and suction parameter.
  • Publication
    Dynamic modelling of the spine for the estimation of vertebral joint torques using Gordon’s method
    (Semarak Ilmu Publishing, 2025-01)
    Munawwarah Solihah Muhammad Isa
    ;
    Nurhidayah Omar
    ;
    Saidatul Ardeenawatie Awang
    ;
    Mohammad Shahril Salim
    ;
    Suhizaz Sudin
    World Health Organization (WHO) recognised musculoskeletal disorder (MSD) as the main contributor to disability worldwide, with low back pain as the major disorder globally. The occupational disorder normally occurs during lifting. The weight of the load and manual handling tasks during lifting has an impact on the spine and joint torque. The purpose of this study is to propose a dynamic model of the spine that can estimate the vertebral joint torques. This study is a bimodal approach that consists of the experimental and theoretical parts. Ten healthy UniMAP students (10 males) participated in this study. The subjects were required to lift a 3kg weight plate for kinematics and EMG data collection. Retro-reflective markers were attached to the subject body, and then, the data was collected and stored in QTM software. Kinematic data was processed using C-Motion Visual3D. Eight Trigno Wireless Sensors were attached on the back muscles (left and right erector spinae, latissimus dorsi, external oblique and internal oblique). The EMG data were stored in EMG Acquisition software and subsequently, were processed using EMG Analysis software. Gordon’s method was used to develop a mathematical model of the spine. The model comprises of five kinematic chains which connected three lumbar, two thoracic and one cervical. The model calculated the value of joint torque on flexion/extension movement using Matlab and Microsoft Excel. When calculated on L5, the model gives an estimation within 0 – 30 kgm2s-2. The model was further used to estimate value of L3, L1, MAI and T2. The estimate average value of joint torque at L3 is within 5 – 25 kgm2s-2, MAI is within 0 – 6 kgm2s-2 and T2 is within 0 – 1 kgm2s-2. The average RMS values show the highest muscle activity on the right internal oblique muscle (1519 µV), followed by the right external oblique (1166 µV) and left external oblique (418 µV). The results obtained gives an insight on the value of joint torque that have been applied by the spine and the most activated back muscles during lifting.
      1  2
  • Publication
    Effect of extraction conditions on the phytochemical properties of Clinacanthus nutans using Pressurized Hot Water Extraction (PHWE) technique
    (IOP Publishing Ltd, 2020)
    M.K. Abduljabbar
    ;
    Khairul Farihan Kasim
    ;
    Akmal Hadi Ma’Radzi
    ;
    N.S. Sofian-Seng
    Clinacanthus nutan is an important herb species from the family Acanthaceae and is commonly found in Southeast Asia. It is also known as snake grass, or 'belalai gajah' in malay. The leaves of C. nutan can be used to make a refreshing juice or tea, or even consumed raw as 'ulam', a traditional malay salad. In this work, the leaves, stems, and a mixture of both leaves and stems of C. nutan are first dried in an oven at 50 C for 24 hours and then grounded into a powder. Then, pressurized hot water extraction (PHWE) is used to extract phytochemicals from the powdered samples at 120 C for 20 minutes. This work investigates the effects of three important parameters for extraction; the sample particle size (<63 to 500μm), solventto-sample ratio (10:2 to 50:2 v/w), and sample weight (0.5 to 3.0g) on the extracted phytochemicals' total phenolic compounds (TPC), total flavonoid compounds (TFC), and 2,2-dipheny1-1picrylhydrazyl (DPPH) scavenging activity. The experiments are carried out in triplicate and the results are analyzed using Minitab. Phytochemicals extracted from 2g leaf powder samples of particle size <63μm using a solvent-tosample ratio of 50:2 (v/w) resulted in the most favorable results for TPC, TFC, and DPPH scavenging activity.
      2  27
  • Publication
    Effect of water-based Alumina-copper MHD hybrid nanofluid on a power-law form stretching/shrinking sheet with joule heating and slip condition: dual solutions study
    (Semarak Ilmu Publishing, 2024-04)
    Adnan Asghar
    ;
    Mallika Vasugi Govindarajoo
    ;
    Hussan Ara
    ;
    Wan Mohd Khairy Adly Wan Zaimi
    ;
    Teh Yuan Ying
    ;
    Liaquat Ali Lund
    The application of hybrid nanofluid is now being employed to augment the efficiency of heat transfer rates. A numerical study was conducted to investigate the flow characteristics of water-based-alumina copper hybrid nanofluids towards a power-law form stretching/shrinking sheet. This study also considered the influence of magnetic, Joule heating, and thermal slip parameters. This study is significant because it advances our understanding of hybrid nanofluids in the presence of magnetic fields, power-law form stretching/shrinking sheet, and heat transfer mechanisms, providing valuable insights for optimizing and innovating thermal management systems in various industrial applications such as polymers, biological fluids, and manufacturing processes like extrusion, plastic and metal forming, and coating processes. The main objective of this study is to examine the impact of specific attributes, including suction and thermal slip parameters on temperature and velocity profiles. In addition, this exploration examined the reduced skin friction and reduced heat transfer in relation to the solid volume fraction copper and magnetic effects on shrinkage sheet and thermal slip parameter on suction effect. To facilitate the conversion of a nonlinear partial differential equation into a collection of ordinary differential equations, it is necessary to incorporate suitable similarity variables into the transformation procedure. The MATLAB bvp4c solver application is utilized in the conclusion process to solve ordinary differential equations. No solution was found in the sort of when , and . As the intensity of the Eckert number increases, the temperature profile and boundary layer thickness also increase. The reduced heat transfer rate upsurged in both solutions for solid volume fraction copper for shrinking sheet, while the opposite actions can be noticed in both solutions for thermal slip parameter for suction effect. Finally, the study conducted an analysis to identify two distinct solutions for shrinking sheet and suction zone, while considering different parameter values for the copper volume fractions, magnetic and thermal slip condition effect.
      3
  • Publication
    Engineering students' performances in mathematics through project-based learning
    (Horizon Research Publishing, 2020)
    N. Razali
    ;
    N. A. Zainuri
    ;
    H. Othman
    ;
    Z. M. Nopiah
    ;
    Nor Ashikin Abu Bakar
    Project-based learning is an example of active learning and is student-driven, interdisciplinary, collaborative and technology-based. To test the hypothesis that project-based learning maximises course performance, we analysed a difficulty index of examination scores or failure rates and compared between 422 students in the 2016/2017 session, who took the Vector Calculus course and project-based learning with 342 students from the 2015/2016 session without project-based learning. The analysis of the difficulty index is used to investigate the achievement of the course outcome and the analysis on the correlation between the project-based learning scores and the final exam scores are identified using Pearson's product-moment correlation. The effect sizes indicate that on average examination scores improved by about 12% with project-based learning and students in classes with project-based learning were 3.4 times more likely to get as than students in classes without project-based learning. It is observed that the difficulty index for all course outcomes are achieved and distributed between a good range of 0.3–0.8. It is also proven that the students find it easier to answer the exam questions after the project-based learning is implemented based on the results of their mid and final semester exams.
      17  1
  • Publication
    Exploring the systematics of cluster decay half-lives in heavy actinides within the range 234 ≤ A ≤ 252
    (Semarak Ilmu Publishing, 2025)
    Khairul Anwar Mohamad Khazali
    ;
    Nooraihan Abdullah
    This study explores the cluster decay half-lives in both experimentally measured and undetected radioactive nuclei within the mass number range The investigation employs the recently proposed preformation probability formula, focusing on the systematic behaviours governing cluster emissions. Emphasis is placed on the contribution of the Q-value during both preformation and decay processes. Experimental binding energy data are used to estimate Q-values, and the cluster penetration process is discussed using the M3Y and R3Y nuclear potentials. The interaction potential between the cluster and the daughter nucleus is obtained by folding the relativistic mean-field (RMF) densities with R3Y NN potential using the NL3* parameter set and compared with the phenomenological M3Y NN potential. The penetration probabilities are calculated from the WKB approximation. The formula is found to be a useful tool for understanding cluster radioactivity in heavy actinides. The result provides valuable insights into the systematics of cluster decay half-lives, highlighting the influence of neutron magic shell closures and interaction potentials on different cluster decay properties.
  • Publication
    Flow past a permeable stretching/shrinking sheet in a nanofluid using two-phase model
    ( 2014-11)
    Wan Mohd Khairy Adly Wan Zaimi
    ;
    Anuar Ishak
    ;
    Ioan Pop
    ;
    James P. Brody
    The steady two-dimensional flow and heat transfer over a stretching/shrinking sheet in a nanofluid is investigated using Buongiorno’s nanofluid model. Different from the previously published papers, in the present study we consider the case when the nanofluid particle fraction on the boundary is passively rather than actively controlled, which make the model more physically realistic. The governing partial differential equations are transformed into nonlinear ordinary differential equations by a similarity transformation, before being solved numerically by a shooting method. The effects of some governing parameters on the fluid flow and heat transfer characteristics are graphically presented and discussed. Dual solutions are found to exist in a certain range of the suction and stretching/shrinking parameters. Results also indicate that both the skin friction coefficient and the local Nusselt number increase with increasing values of the suction parameter.
      2  23
  • Publication
    Fuzzy method based on the removal effects of criteria (MEREC) for determining objective weights in multi-criteria decision-making problems
    (MDPI, 2023)
    Mohamad Shahiir Saidin
    ;
    Lai Soon Lee
    ;
    Siti Mahani Marjugi
    ;
    Muhammad Zaini Ahmad
    ;
    Hsin-Vonn Seow
    In multi-criteria decision-making (MCDM) research, the criteria weights are crucial components that significantly impact the results. Many researchers have proposed numerous methods to establish the weights of the criterion. This paper provides a modified technique, the fuzzy method based on the removal effects of criteria (MEREC) by modifying the normalization technique and enhancing the logarithm function used to assess the entire performance of alternatives in the weighting process. Since MCDM problems intrinsically are ambiguous or complex, fuzzy theory is used to interpret the linguistic phrases into triangular fuzzy numbers. The comparative analyses were conducted through the case study of staff performance appraisal at a Malaysian academic institution and the simulation-based study is used to validate the effectiveness and stability of the presented method. The results of the fuzzy MEREC are compared with those from a few different objective weighting techniques based on the correlation coefficients, outlier tests and central processing unit (CPU) time. The results of the comparative analyses demonstrate that fuzzy MEREC weights are verified as the correlation coefficient values are consistent throughout the study. Furthermore, the simulation-based study demonstrates that even in the presence of outliers in the collection of alternatives, fuzzy MEREC is able to offer consistent weights for the criterion. The fuzzy MEREC also requires less CPU time compared to the existing MEREC techniques. Hence, the modified method is a suitable alternative and efficient for computing the objective criteria weights in the MCDM problems.
      17  1
  • Publication
    Hybrid deep learning for estimation of state-of-health in lithium-ion batteries
    (Institute of Advanced Engineering and Science (IAES), 2025-02)
    Denis Eka Cahyani
    ;
    Langlang Gumilar
    ;
    Arif Nur Afandi
    ;
    Aji Prasetya Wibawa
    ;
    Ahmad Kadri Junoh
    Lithium-ion (li-ion) batteries have a high energy density and a long cycle life. Lithium-ion batteries have a finite lifespan, and their energy storage capacity diminishes with use. In order to properly plan battery maintenance, the state of health (SoH) of lithium-ion batteries is crucial. This study aims to combine two deep learning techniques (hybrid deep learning), namely convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), for SoH estimation in li-ion batteries. This study contrasts hybrid deep learning methods to single deep learning models so that the most suitable model for accurately measuring the SoH in lithium-ion batteries can be determined. In comparison to other methodologies, CNN-BiLSTM yields the best results. The CNN-BiLSTM algorithm yields RMSE, mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) in the following order: 0.00916, 0.000084, 0.0048, and 0.00603. This indicates that CNN-BiLSTM, as a hybrid deep learning model, is able to calculate the approximate capacity of the lithium-ion battery more accurately than other methods.
  • Publication
    Hybrid Mahalanobis Taguchi System with Binary Whale Optimisation Feature Selection for the Wisconsin Breast Cancer Dataset
    (Semarak Ilmu Publishing, 2023)
    Chow Yong Huan
    ;
    Wan Zuki Azman Wan Muhamad
    ;
    Zainor Ridzuan Yahya
    ;
    Nor Hizamiyani Abdul Azziz
    ;
    Tan Chye Lih
    ;
    Tan Xiao Jian
    The Mahalanobis-Taguchi System (MTS) is a statistical approach used in breast cancer research to facilitate early detection and promote efficient treatment. The technique analyses mammogram images for significant features using a multivariate statistical analysis technique. It combines the Mahalanobis distance (MD) and Taguchi's method to determine the differences between benign and malignant samples. While orthogonal array (OA) has been widely used in MTS, it has been criticised for providing suboptimal results due to insufficient coverage of feature combinations during the feature optimisation process. To address this issue, the Binary Whale Optimisation Algorithm (BWOA) is proposed as an improved search algorithm for MTS. This paper aims to develop a novel hybrid method that enhances the efficiency of the Mahalanobis Taguchi System (MTS). The performance of feature selection ability due to different MTS hybrid algorithms were also compared. BWOA simulates the hunting behaviour of humpback whales and works by exploring new regions of the solution space, gradually narrowing the search space, and fine-tuning the solution. MTS-BWOA demonstrated its enhanced capability in feature optimisation compared to traditional MTS methods and has the potential to be applied in other medical imaging domains.
      16  2