Gender Classification on Skeletal Remains: Efficiency of Metaheuristic Algorithm Method and Optimized Back Propagation Neural Network

Hairuddin, Nurul Liyana; Yusuf, Lizawati Mi; Othman, Mohd Shahizan

doi:10.32890/jict2020.19.2.5

Cited by 6 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The well-known k-fold cross-validation test was used to partition the dataset into ten parts Gupta et al, 2016;Hairuddin et al, 2020) In each test, one part was used for the testing set, while the rest was used for the training set. The test was repeated ten times, with different datasets for testing each time.…”

Section: Resultsmentioning

confidence: 99%

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

Al-Behadili

Ku-Mahamud

2021

Journal of Information and Communication Technology

View full text Add to dashboard Cite

Diabetes classification is one of the most crucial applications of healthcare diagnosis. Even though various studies have been conducted in this application, the classification problem remains challenging. Fuzzy logic techniques have recently obtained impressive achievements in different application domains especially medical diagnosis. Fuzzy logic technique is not able to deal with data of a large number of input variables in constructing a classification model. In this research, a fuzzy logic technique using greedy hill climbing feature selection methods was proposed for the classification of diabetes. A dataset of 520 patients from the Hospital of Sylhet in Bangladesh was used to train and evaluate the proposed classifier. Six classification criteria were considered to authenticate the results of the proposed classifier. Comparative analysis proved the effectiveness of the proposed classifier against Naive Bayes, support vector machine, K-nearest neighbour, decision tree, and multilayer perceptron neural network classifiers. Results of the proposed classifier demonstrated the potential of fuzzy logic in analyzing diabetes patterns in all classification criteria.

show abstract

Section: Resultsmentioning

confidence: 99%

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

Al-Behadili

Ku-Mahamud

2021

Journal of Information and Communication Technology

View full text Add to dashboard Cite

show abstract

“…SVR and RBFNN models can control nonlinear problems better and have faster training speeds than the BPNN model; however, they are mainly applicable to low-dimensional datasets, and their training time and computational cost are higher for high-dimensional datasets, which may affect the accuracy of SVR and RBFNN models [51,52]. The higher BPNN model accuracy may be attributed to its high nonlinear function approximation capability, self-learning and self-adaptive capabilities, and fault tolerance to cope with measurement errors, making it more suitable for the inversion of CGMI of C. camphora than other models [53].…”

Section: Plos Onementioning

confidence: 99%

An integrated UAV growth monitoring model of Cinnamomum camphora based on whale optimization algorithm

Gong,

Zhang,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

To explore an effective analysis model and method for estimating Cinnamomum camphora’s (C. camphora’s) growth using unmanned aerial vehicle (UAV) multispectral technology, we obtained C. camphora’s canopy spectral reflectance using a UAV-mounted multispectral camera and simultaneously measured four single-growth indicators: Soil and Plant Analyzer Development (SPAD)value, aboveground biomass (AGB), plant height (PH), and leaf area index (LAI). The coefficient of variation and equal weighting methods were used to construct the comprehensive growth monitoring indicators (CGMI) for C. camphora. A multispectral inversion model of integrated C. camphora growth was established using the multiple linear regression (MLR), partial least squares (PLS), support vector regression (SVR), random forest (RF), radial basis function neural network (RBFNN), back propagation neural network (BPNN), and whale optimization algorithm (WOA)-optimized BPNN models. The optimal model was selected based on the coefficient of determination (R2), normalized root mean square error (NRMSE) and mean absolute percentage error (MAPE). Our findings indicate that apparent differences in the accuracy with different model, and the WOA–BPNN model is the best model to invert the growth potential of C. camphora, the R2 of the model test set was 0.9020, the RMSE was 0.0722, and the MAPE was 7%. The R2 of the WOA–BPNN model improved by 18%, the NRMSE decreased by 33%, and the MAPE decreased by 9% compared with the BPNN model. This study provides technical support for the modern field management of C. camphora essential oil and other dwarf forestry industries.

show abstract

“…Classification tasks are applicable in various domains (Hairuddin et al, 2020;Roy et al, 2018). In a binary classification, Gaussian-based Bayes rule assigns an object with variables, to group  1 if the probability density of x in  1 is larger than that in  2 :…”

Section: Related Workmentioning

confidence: 99%

“…mains (Hairuddin et al, 2020;Roy et al, 2018). In a assigns an object with variables, to group  1 if the  2 :…”

Section: Ted Workmentioning

confidence: 99%

Validation Assessments on Resampling Method in Imbalanced Binary Classification for Linear Discriminant Analysis

Jamaluddin

Mahat

2020

Journal of Information and Communication Technology

View full text Add to dashboard Cite

The curse of class imbalance affects the performance of many conventional classification algorithms including linear discriminant analysis (LDA). The data pre-processing approach through some resampling methods such as random oversampling (ROS) and random undersampling (RUS) is one of the treatments to alleviate such curse. Previous studies have attempted to address the effect of a resampling method on the performance of LDA. However, some studies contradicted with each other based on different performance measures as well as validation strategies. This manuscript attempted to shed more light on the effect of a resampling method (ROS or RUS) on the performance of LDA based on true positive rate and true negative rate through five validation strategies, i.e. leave-one-out cross-validation, k-fold cross-validation, repeated k-fold cross-validation, naive bootstrap, and .632+ bootstrap. 100 two-group bivariate normally distributed simulated and four real data sets with severe class imbalance ratio were utilised. The analysis on the location and dispersion statistics of the performance measures was further enlightened on: (i) the effect of a resampling method on the performance of LDA, and (ii) the enhancement in the learning fairness of LDA on objects regardless of sample size, hence reducing the effect of the curse of class imbalance.

show abstract

Gender Classification on Skeletal Remains: Efficiency of Metaheuristic Algorithm Method and Optimized Back Propagation Neural Network

Cited by 6 publications

References 17 publications

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

Fuzzy Unordered Rule Using Greedy Hill Climbing Feature Selection Method: An Application to Diabetes Classification

An integrated UAV growth monitoring model of Cinnamomum camphora based on whale optimization algorithm

Validation Assessments on Resampling Method in Imbalanced Binary Classification for Linear Discriminant Analysis

Contact Info

Product

Resources

About