USUmu Sa'ADah

Umu Sa'ADah

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Umu Sa'ADah has a total of 26 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Optimization of Imbalanced Class Using CTGAN and RSCV-Ensemble Learning for Clean Water Quality Classification

    by Favian Sis Bagus Febrianto, Umu Sa'ADah, Imam Nurhadi Purwanto

    Class imbalance is a common challenge in classification learning. This condition often leads to poor model performance in identifying minority class observations. This study aims to evaluate the performance of an Ensemble Learning model optimized using Randomized Search CV (RSCV) to classify clean water quality under imbalanced class distributions. To address the imbalance problem, the CTGAN technique is applied and compared with other oversampling methods like SMOTENC that also can handle mix data. The model performance is assessed using two sided independent t-test form different mean (accuracy, precision, recall, F1-score, and AUC-ROC) two models. The best model performance from Data Testing in this study is the Ensemble Learning model with RSCV combined with CTGAN oversampling followed by mean Accuracy of 92,8%, mean Precision of 90,23%, mean Recall of 90,98%, mean f1-score of 90,82%, and mean AUC-ROC 96,80% from 25 split data experiment. Almost all accuracy metrics showed statistically significant differences when tested using a two-sided independent t-test. Overall, the results indicate that CTGAN outperforms SMOTENC, and RSCV optimization improves performance compared to models without optimization. Not only accuracy, all different mean Recall metrics is significant, further supporting the superiority of CTGAN and RSCV-enhanced models.

  • Open Access

    Optimizing Deep Neural Networks for Water Quality Prediction Using Spider Monkey Optimization and Permutation Importance-Based Feature Selection: A Comparative Heuristic Approach

    by Desy Lusiyanti, Syaiful Anam, Wayan Firdaus Mahmudy, Umu Sa'ADah

    In this study, a novel integration of Spider Monkey Optimization (SMO) with deep neural networks (DNNs) has been proposed for hyperparameter tuning in the context of water potability classification. To the best of the authors’ knowledge, this represents one of the first systematic applications of SMO for this task. The proposed framework incorporates a comprehensive data preprocessing pipeline, which includes missing value imputation using a K-Nearest Neighbors (KNN) imputer, feature normalization through min–max scaling, and class balancing via the Synthetic Minority Oversampling Technique (SMOTE). The SMO optimized DNN has been benchmarked against three established metaheuristic algorithms, Particle Swarm Optimization (PSO), GreyWolf Optimizer (GWO), and the Firefly Algorithm (FA), under a uniform Receiver Operating Characteristic Area Under the Curve (ROC-AUC) based objective function and hyperparameter search space. The SMO-DNN yielded competitive performance, attaining an average accuracy of 0.6947 and a ROC-AUC score of 0.6955 under 10-fold cross-validation, while reducing total computation time to 1347.41 minutes, which is 35% faster than GWO. Permutation Feature Importance (PFI) analysis identified sulfate, pH, and hardness as the most influential features. Further training using this reduced feature set led to improvements in both F1-score and ROC-AUC, highlighting the robustness and efficiency of the approach. Overall, the proposed method provides a scalable and computationally efficient strategy for deep learning based water quality assessment and demonstrates the potential of SMO as a viable alternative for deploying interpretable and accurate potability classification models, particularly in resource-constrained monitoring environments.

  • Open Access

    Heart Disease Classification Using Random Forest and Fox Algorithm as Hyperparameter Tuning

    by Afidatul Masbakhah, Umu Sa'ADah, Mohamad Muslikh

    Heart disease remains the leading cause of death worldwide, making early and accurate diagnosis crucial for reducing mortality and improving patient outcomes. Traditional diagnostic approaches often suffer from subjectivity, delay, and high costs. Therefore, an effective and automated classification system is necessary to assist medical professionals in making more accurate and timely decisions. This study aims to develop a heart disease classification model using Random Forest, optimized through the FOX algorithm for hyperparameter tuning, to improve predictive performance and reliability. The main contribution of this research lies in the integration of the FOX metaheuristic optimization algorithm with the RF classifier. FOX, inspired by fox hunting behavior, balances exploration and exploitation in searching for the optimal hyperparameters. The proposed RF-FOX model is evaluated on the UCI Heart Disease dataset consisting of 303 instances and 13 features. Several preprocessing steps were conducted, including label encoding, outlier removal, missing value imputation, normalization, and class balancing using SMOTE-NC. FOX was used to optimize six RF hyperparameters across a defined search space. The experimental results demonstrate that the RF-FOX model achieved superior performance compared to standard RF and other hybrid optimization methods. With a training accuracy of 100% and testing accuracy of 97.83%, the model also attained precision (97.83%), recall (97.88%), and F1-score (97.89%). It significantly outperformed RF-GS, RF-RS, RF-PSO, RF-BA, and RF-FA models in all evaluation metrics. In conclusion, the RF-FOX model proves highly effective for heart disease classification, providing enhanced accuracy, reduced misclassification, and clinical applicability. This approach not only optimizes classifier performance but also supports medical decision-making with interpretable and reliable outcomes. Future work may involve validating the model on more diverse datasets to further ensure its generalizability and robustness.


  • Open Access

    Ensemble Bagging in Binary Logistic Regression for Transportation Mode Selection

    by Nuzulul Laili Nabila, Sobri Abusini, Umu Sa'ADah

    This study examines train versus bus transportation mode choice on the Malang–Blitar route using binary logistic regression combined with ensemble bagging. Data from 100 respondents were analyzed using 80% for training and 20% for testing with k-fold cross-validation. Variables included travel cost differences, time, safety, comfort, and ease of access. Bagging was selected over other ensemble methods due to its effectiveness in reducing variance and overfitting with small datasets. Results showed the standard logistic regression achieved 85% accuracy on test data, while ensemble bagging with 200 replications improved accuracy to 90.83% (confidence interval: 90.379%–91.187%). McNemar’s test confirmed a statistically significant improvement (p 0.01). Under equivalent conditions, 20.6% of respondents preferred trains while 79.4% chose buses. Ease of access emerged as the primary decision factor, outweighing cost and time considerations. The optimal replication number was 200; exceeding 300 replications decreased model performance. This research contributes an optimized ensemble methodology for transportation mode prediction in developing countries, demonstrating that accessibility infrastructure significantly influences passenger preferences over traditional economic factors.

  • Open Access

    Exploring DenseNet architectures with particle swarm optimization: efficient tomato leaf disease detection

    by Cynthia Ayu Dwi Lestari, Syaiful Anam, Umu Sa’aDah

    The critical challenge of tomato leaf disease demands effective solutions surpassing manual detection limitations, ensuring rapid intervention, optimal crop health, and maximizing yield for farmers. DenseNet, a convolutional neural network (CNN) architecture, is lauded for its adept handling of gradient flow issues by extensive interlayer connectivity. Its application holds significant promise in tackling the intricate task of identifying tomato leaf diseases. This research introduces an innovative methodology employing particle swarm optimization (PSO) to fine-tune the DenseNet architecture and hyperparameter. The proposed approach efficiently converges on optimal configurations encompassing parameters, such as the number of layers in dense blocks, growth rates, dropout rates, activation functions, and optimizers tailored for DenseNet. The DenseNet-PSO model achieves remarkable accuracy and precision in classifying various tomato leaf diseases, outperforming alternative architectures in total parameters, computational efficiency, and overall performance compared with six other architecture models. These outcomes elucidate DenseNet-PSO's efficacy in tomato leaf disease detection and demonstrate.

  • Open Access

    Hybrid methods to identify ovarian cancer from imbalanced high-dimensional microarray data

    by Ni Kadek Emik Sapitri, Umu Sa'ADah, Nur Shofianah

    Scientists have used microarray data to identify healthy people and patients with various types of cancer, including ovarian cancer. Ovarian cancer is the most dangerous of all types of cancer that attacks the female reproductive organ. The right combination of methods is needed to identify ovarian cancer from microarray data because that type of data is high-dimensional and imbalanced. This research aims to propose two hybrid methods which are a combination of infinite feature selection (IFS) as features selector with classification and regression tree (CART) as a classifier. IFS can work with two separate scenarios, namely supervised infinite feature selection (SIFS) and unsupervised infinite feature selection (UIFS). This research also compares the performance of the two hybrid methods proposed (SIFS-CART and UIFS-CART) with CART without IFS. The data used is OVA_ovary that has 10937 columns and 1545 rows. The results shows that SIFS-CART achieves maximum performance using 1000 features and UIFS-CART 5000 features. CART without IFS uses all 10935 features. The balanced accuracy results show SIFS-CART can outperform CART without IFS and UIFS-CART. Using less features to get highest balanced accuracy results, SIFS is more effective in performing feature selection on the OVA_ovary dataset compared to UIFS.

  • Open Access

    Feature Selection Risk Factors Cervical Cancer Using Hybrid Methods Random Forest and FOX-Inspired Optimization Algorithm

    by Afidatul Masbakhah, Umu Sa'ADah, Mohamad Muslikh

    Cervical cancer is one of the number four causes of death among women worldwide, with about 604,000 new cases and 324,000 deaths each year. Human Papillomavirus infection is one of the main factors in almost 99% of cervical cancer cases. In addition to HPV, other risk factors such as smoking, long-term use of oral contraceptives, and weak immunity also play an important role. Along with the development of technology and in an effort to detect cervical cancer early, machine learning algorithms have been widely used to analyze the risk of cervical cancer, one of which is Random Forest (RF). One of the main challenges in early detection of cervical cancer is the large amount of irrelevant and redundant data, which can reduce the accuracy of predictions, making feature selection imperative. SI is able to combine new algorithms to improve performance in feature selection. One of the SI-based optimization algorithms is the FOX-Inspired Optimization Algorithm. The results of research that has been carried out using the RF-FOX hybrid method, the Num of pregnancies feature has proven to be the most influential factor in detecting the risk of cervical cancer in patients. In addition, other features such as First sexual intercourse, Number of sexual partners, age, and Hormonal Contraceptives also occupy the top five most influential features. Therefore, the hybrid RF-FOX method allows the performance of the model to be more optimized, thus helping in the identification of patients at risk of cervical cancer more precisely.


  • Open Access

    VALUE AT RISK ESTIMATION FOR STOCK PORTFOLIO USING THE ARCHIMEDEAN COPULA APPROACH

    by Mohammad Dicky Saifullah, Umu Sa'ADah, Kwardiniya Andawaningtyas, Endang Wahyu Handamari

    Investment is one of the many ways to achieve future profits. One form of investment that is widely made is stocks. The return obtained in investing in stocks is potentially higher than other investment alternatives, but the risks borne are amplified, so it is necessary to analyze these risks that may occur. In this study, the Archimedean copula method is used to estimate the Value at Risk on shares of PT Bank Rakyat Indonesia Tbk (BBRI) and PT Telekomunikasi Indonesia Tbk (TLKM) for the period September 1, 2021, to August 31, 2023. The stock data is used to determine the Archimedean copula model and calculate the estimated value of Value at Risk (VaR) on the stock return portfolio using the Archimedean copula approach. The Archimedean copula models used are the Clayton copula model, Gumbel copula, and Frank copula. Of the three Archimedean copula models, the best model was selected by looking at the largest Maximum Likelihood Estimation (MLE) value. In this study, the log-likelihood value of Clayton copula is 7.958, Gumbel copula is 6.663, and Frank copula is 8.398. Therefore, Frank copula is the best Archimedean copula model with the largest log-likelihood value of 8.398 for the said data. Then the VaR estimation is done with the Frank copula model. The Value at Risk estimation results based on the Frank copula model show maximum loss rates of -0.0277 at the 90% confidence level, -0.0363 at the 95% confidence level, and -0.0516 at the 99% confidence level.


  • Open Access

    Knowledge Discovery from Confusion Matrix of Pruned CART in Imbalanced Microarray Data Ovarian Cancer Classification

    by Ni Kadek Emik Sapitri, Umu Sa’aDah, Nur Shofianah

    Purpose: The results of microarray data analysis is important in cancer diagnosis, especially in early stages asymptomatic cancers like ovarian cancer. One of the challenges in analyzing microarray data is the problem of imbalanced data. Unfortunately, research that carries out cancer classification from microarray data often ignores this challenge, so that it doesn’t use appropriate evaluation metrics. It makes the results biased towards the majority class. This study uses a popular evaluation metric “accuracy” and an evaluation metric that is suitable for imbalanced data “balanced accuracy (BA)” to gain information from the confusion matrix regarding accuracy and BA values in case of ovarian cancer classification.Methods: This study use Classification and Regression Tree (CART) as the classifier. CART optimized by pruning. CART optimal is determined from the results of CART complexity analysis and confusion matrix.Results: The confusion matrix and CART interpretations in this research show that CART with low complexity is still able to predict majority class respondents well. However, when none of the data in the minority class was classified correctly, the accuracy value was still quite high, namely 86.97% and 88.03% respectively at the training and testing stages, while the BA value at both stages was only 50%.Novelty: It is very important to ensure that the evaluation metrics used match the characteristics of the data being processed. This research illustrate the difference between accuracy and BA. It concluded that that classification of an imbalanced dataset without doing resampling can use BA as evaluation metric, because based on the results, BA is more fairly to both classes.