Binary Bitwise Artificial Bee Colony as Feature Selection Optimization Approach within Taguchi’s T-Method

Harudin, Nolia; Ramlie, Faizir; Muhamad, Wan Zuki Azman Wan; Muhtazaruddin, Mohd Nabil; Jamaludin, Khairur Rijal; Abu, Mohd Yazid; Marlan, Zulkifli Marlah

doi:10.1155/2021/5592132

Cited by 11 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objective function of the proposed T-method with the NIBBA algorithm is to maximize the integrated estimate SNR value, which returns the optimal combination of input features. The selection of the final optimal feature combination is based on the 50% and more feature appearance in the optimal combination of every run, as practiced in [14].…”

Section: Experimental Designmentioning

confidence: 99%

“…The result shows an improvement in prediction accuracy as compared to the conventional OA approach. In a different study, Harudin et al [14] utilized a modified artificial bee colony algorithm with a binary bitwise operator as the feature selection approach, and the outcome recorded an enhancement in prediction accuracy. These studies have shown practicality in employing metaheuristic algorithms as the T-method feature selection optimization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Taguchi's T-method with nearest integer-based binary bat algorithm for prediction

Marlan

Jamaludin²,

Ramlie³

et al. 2022

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

Taguchi’s T-method is a new prediction technique under the Mahalanobis-Taguchi system to predict unknown output or future states based on available historical information. Conventionally, in optimizing the T-method prediction accuracy, Taguchi’s orthogonal array is utilized to determine a subset of significant features to be used in formulating the optimal prediction model. This, however, resulted in a sub-optimal prediction accuracy due to its fixed and limited feature combination offered for evaluation and lack of higher-order feature interaction. In this paper, a swarm-based binary bat optimization algorithm with a nearest integer discretization approach is integrated with the Taguchi’s T-method. A comparative study is conducted by comparing the performance of the proposed method against the conventional approach using mean absolute error as the performance measure on four benchmark case studies. The results from experimental studies show a significant improvement in the T-method prediction accuracy. A reduction in the total number of features results in a less complex model. Based on the general observation, the nearest integer-based binary bat algorithm successfully optimized the selection of significant features due to recursive and repetitive searchability, in addition to its adaptive element in response to the current best solution in guiding the search process towards optimality.

show abstract

Section: Experimental Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Taguchi's T-method with nearest integer-based binary bat algorithm for prediction

Marlan

Jamaludin²,

Ramlie³

et al. 2022

Bulletin EEI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ramlie et al [40] concluded that none of the four thresholding methods outperformed one over the others in (if it is not for all) most of the datasets. Harudin et al [41] proved that incorporating Bitwise Artificial Bee Colony (BitABC) techniques into Taguchi's T-Method methodology effectively improved prediction accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of the Mahalanobis-Taguchi System in Renal Profile of the Methadone Flexi Dispensing Program

Saad

Zaini

Abu

2022

jti

View full text Add to dashboard Cite

Patients under the methadone Flexi dispensing (MFlex) program are required to do blood tests like renal profile. To ensure the patient has a kidney failure, a doctor assesses one parameter like creatinine. Unfortunately, the existing system does not have a stable ecosystem towards classification and optimization due to inaccurate measurement methods and lack of justification of significant parameters, which will influence the accuracy of diagnosis. The objective is to apply the Mahalanobis-Taguchi system (MTS) in the MFlex program. The data is collected at Bandar Pekan clinic with 34 parameters. Two types of MTS methods are used, such as RT-Method and T-Method, for classification and optimization. As a result, the RT-Method can classify healthy and unhealthy samples, while the T-Method can evaluate the significant parameters in terms of the degree of contribution. Fifteen unknown samples have been diagnosed with different positive and negative degrees of contribution to achieving lower MD. The best-proposed solution is type 5 of 6 modifications because it shows the highest MD value than others. In conclusion, a pharmacist from Bandar Pekan clinic confirmed that MTS could solve a problem in the classification and optimization of the MFlex program.

show abstract

“…According to [38], none of the four thresholding approaches outperformed the others in almost all of the datasets. [39] showed that combining Bitwise Artificial Bee Colony (BitABC) methods along with Taguchi's T-Method greatly improved the accuracy of predictions.…”

Section: Introductionmentioning

confidence: 99%

Methadone Flexi Dispensing (MFlex) Intelligence System utilizing the Mahalanobis-Taguchi System

Pinueh,

Abu,

Saad

et al. 2024

JMMST

View full text Add to dashboard Cite

Patients who are participating in the methadone flexi dispensing (MFlex) program are obliged to provide their blood samples for various testing, such as lipid profiles. A doctor evaluates three parameters, including cholesterol, HDL cholesterol, and LDL cholesterol to determine whether or not the patient has a lipid issue. Since, the current structure lacks an ideal atmosphere for classification and optimization caused by inaccuracies in measurement methodologies and a lack of explanation for significant aspects that have an effect on the accuracy of diagnostics. The objective is to implement the Mahalanobis-Taguchi system (MTS) in the MFlex program. Utilizing a total of 34 parameters, there are two different types of MTS techniques used for classification and optimization: the RT method and T method. The average Mahalanobis distance (MD) for healthy conditions is 1.0000 whereas for unhealthy is 79.5876. As a result, there is 19 parameters indicate a positive degree of contribution. 15 unknown samples were diagnosed with a variety of positive and negative degree of contribution to achieving a lower MD. Type 5 of 6 alterations was chosen as the best suggested possibility. In conclusion, MTS is able to be applied in medical environment.

show abstract

Binary Bitwise Artificial Bee Colony as Feature Selection Optimization Approach within Taguchi’s T-Method

Cited by 11 publications

References 35 publications

Taguchi's T-method with nearest integer-based binary bat algorithm for prediction

Taguchi's T-method with nearest integer-based binary bat algorithm for prediction

Application of the Mahalanobis-Taguchi System in Renal Profile of the Methadone Flexi Dispensing Program

Methadone Flexi Dispensing (MFlex) Intelligence System utilizing the Mahalanobis-Taguchi System

Contact Info

Product

Resources

About