Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computing and Informatics Research Bulletin of Artificial Intelligence Bulletin of Information System Research
Solikhun Solikhun
STIKOM Tunas Bangsa, Pematangsiantar
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Pengujian Jaringan Saraf Tiruan Dalam Mendiagnosa Gangguan Jiwa Menggunakan Algoritma Backpropogation Levenberg-Marquardt Solikhun Solikhun; Sundari Putri Lestari
Journal of Information System Research (JOSH) Vol 4 No 3 (2023): April 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v4i3.3285

Abstract

Mental disorders are mental health issues that make it hard to meet one's own or other people's needs. A person's life may be affected by changes in behavior brought on by this condition. To conquer this issue, a backpropagation calculation has been created to help with distinguishing mental problems. This calculation utilizes information got from mental tests to distinguish early indications of mental problems in an individual. With this calculation, psychological wellness experts can settle on additional quick and precise symptomatic choices. The Levenberg-Marquadt method and the backpropogation algorithm were used in this study to diagnose mental disorders. The aim of this study is to make it easier to diagnose mental disorders by analyzing a patient using the 24 attributes of the questions. After the diagnosis is made, the results will show up, and the Levenberg-Marquardt Backpropagation Algorithm will be used to test a person to see if they have bipolar disorder, OCD, or any other disorder. Researchers will have a difficult time determining the patient's mental illness if this diagnosis is not carried out. The aftereffects of this study are as demonstrative inquiries for mental issues that have been given. The Levenberg Marquadt method backpropagation algorithm is the bridge to accuracy, supporting this study's success. MSE is 24-10-1, with training performance equal to 0.000014246 and testing performance equal to 0.0000146. The diagnosis that comes out of it is more accurate the less error there is.
Optimasi Prediksi Penyakit Asma Menggunakan Improved LightGBM Berbasis Bayesian Optimization dengan Hybird SMOTE-ENN dan SHAP Feature Selection Tiara Dwi Lestari Purba; Solikhun Solikhun
Bulletin of Information System Research Vol 4 No 2 (2026): April 2026
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/bios.v4i2.283

Abstract

Asthma is one of the most prevalent chronic respiratory diseases worldwide, affecting more than 300 million people, and its early prediction is essential for timely clinical intervention. A major obstacle in data-driven asthma prediction is the severe class imbalance of large-scale clinical datasets, which biases conventional classifiers toward the majority (non-asthma) class. This study proposes an Improved LightGBM that integrates three components: Hybrid SMOTE-ENN to correct class imbalance and remove noisy boundary samples, SHAP-based feature selection to retain the most informative attributes, and Bayesian Optimization for hyperparameter tuning. A Kaggle-derived asthma dataset (409,216 SMOTE-balanced training records and 59,672 test records over 23 encoded clinical features) was used. Hybrid SMOTE-ENN reduced a 40,000-sample working set to 8,322 cleaned, balanced instances; SHAP selected 13 of 23 features; and Bayesian Optimization produced the optimal configuration (best cross-validation accuracy 92.20%). On the balanced hold-out test set the proposed Improved LightGBM achieved an accuracy of 93.87%, precision of 0.9447, recall of 0.9359, F1-score of 0.9403, and ROC-AUC of 0.9839, clearly surpassing the LightGBM Bayesian-Optimization baseline reported in the main reference (78% accuracy, ROC-AUC 0.975). Evaluation on the original imbalanced test distribution (accuracy 72.83%, ROC-AUC 0.6392) transparently reflects the difficulty of severely imbalanced real-world clinical data. The results show that combining Hybrid SMOTE-ENN, SHAP feature selection, and Bayesian Optimization yields a more accurate, interpretable, and discriminative asthma-prediction model
Optimasi Seleksi Fitur Adaptive Particle Swarm Optimization Untuk Klasifikasi Penyakit Jantung Dengan Ensemble Learning Bagas Adi Nata; Solikhun Solikhun
Journal of Computing and Informatics Research Vol 5 No 3 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/comforch.v5i2.2630

Abstract

Heart disease classification using machine learning requires relevant features and predictive models capable of consistently generalizing clinical patterns. Previous studies on the Heart Failure Prediction dataset demonstrated that K-Nearest Neighbor (KNN) optimized with Particle Swarm Optimization (PSO) achieved an accuracy of 89.09% and an Area Under the Curve (AUC) of 0.935. However, the use of a fixed inertia weight and reliance on a single learner may limit the balance between exploration and exploitation, thereby reducing model robustness. This study proposes a feature selection approach based on Adaptive Particle Swarm Optimization (APSO), in which the inertia weight is gradually decreased from 0.90 to approximately 0.42 over 30 iterations. The optimal feature subset is subsequently utilized in a soft voting ensemble learning model. The dataset consists of 918 records, 11 predictive features, and one target class (HeartDisease). Experimental results indicate that the proposed APSO-based ensemble model achieved an accuracy of 89.71%, an F1-score of 0.8986, and an AUC of 0.9466. The confusion matrix yielded 90 true negatives, 12 false positives, 9 false negatives, and 93 true positives on 204 testing instances. Compared with the baseline KNN-PSO model, the proposed method improved classification accuracy by 0.62 percentage points and increased the AUC by 0.0116, while maintaining a disease-class recall of 91.18%. These findings demonstrate that combining adaptive search dynamics with heterogeneous ensemble learning enhances the discriminative capability of heart disease classification, although further validation using identical data partitioning strategies and external datasets is still required
Improved Genetic Algorithm with Adaptive Operators and Elitism for Random Forest Feature Selection in Heart Disease Classification Rahma Dhea Safitri; Solikhun Solikhun; Timbo Faritcan P. Siallagan
Journal of Information System Research (JOSH) Vol 7 No 4 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i4.10372

Abstract

Heart disease is one of the leading causes of mortality worldwide, and accurate prediction models are essential to support early diagnosis. However, conventional Random Forest classifiers generally utilize all available features, although not all features contribute equally to classification performance, resulting in unnecessary model complexity. This study proposes an Improved Genetic Algorithm (IGA) that extends the conventional Genetic Algorithm through elitism, adaptive crossover, and adaptive mutation operators to optimize feature selection for Random Forest-based heart disease classification. The proposed method was evaluated using the Cardiovascular Disease Dataset from Kaggle, which consisting of 1,000 records and 14 variables, where 12 predictor features were used for model development. The experimental procedure included data preprocessing, train-test splitting, class imbalance handling using SMOTE on the training set, feature normalization, Random Forest modeling, feature selection using the proposed IGA, and model evaluation. The proposed IGA selected six important features slope, chestpain, restingBP, restingelectro, oldpeak, and gender. The optimized Random Forest model achieved an accuracy of 99.50%, precision of 99.15%, recall of 100.00%, F1-score of 99.57%, and AUC-ROC of 99.90%. These findings indicate that feature selection can simplify the model without compromising classification performance, making the Random Forest + IGA approach a viable alternative for developing more efficient heart disease prediction models.
Klasifikasi Penyakit Ginjal Kronis pada Data Tidak Seimbang Menggunakan K-Nearest Neighbor Berbasis Seleksi Fitur Mutual Information dan GridSearchCV Mirza Afif Pradivta; Solikhun Solikhun; Timbo Faritcan P Siallagan
Bulletin of Artificial Intelligence Vol 5 No 1 (2026): April 2026
Publisher : Graha Mitra Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62866/buai.v5i1.227

Abstract

Chronic Kidney Disease (CKD) is a progressive disease characterized by a gradual decline in kidney function and requires early detection to reduce the risk of severe complications. Machine learning has been widely applied to support CKD classification based on clinical attributes; however, medical datasets often contain missing values, a combination of numerical and categorical features, and class imbalance. This study aims to evaluate the performance of the K-Nearest Neighbor (KNN) algorithm for CKD classification using Mutual Information feature selection and GridSearchCV. The dataset consisted of 400 samples, including 250 CKD cases and 150 non-CKD cases. The proposed methodology included data cleaning, missing value imputation, categorical feature encoding, numerical feature normalization using MinMaxScaler, feature selection using SelectKBest with Mutual Information, and hyperparameter tuning using GridSearchCV. Model performance was evaluated using hold-out testing and 10-fold cross-validation. The hold-out evaluation showed that the KNN model with GridSearchCV achieved 100.00% accuracy, precision, recall, F1-score, and AUC on the test set. To ensure that this result was not dependent on a single train-test split, additional evaluation was conducted using 10-fold cross-validation. The cross-validation results yielded an average accuracy of 99.25% for the KNN model with GridSearchCV, indicating consistent performance across different data partitions. Meanwhile, the KNN model with Mutual Information feature selection and GridSearchCV achieved 98.75% accuracy, 100.00% recall, and a 99.01% F1-score, demonstrating competitive performance while using a more compact feature subset. The findings indicate that the application of GridSearchCV improved the performance of the KNN model on the dataset used, while Mutual Information contributed to selecting relevant features, enabling the model to maintain strong classification performance with a reduced number of features
Co-Authors Bagas Adi Nata Mirza Afif Pradivta Rahma Dhea Safitri Sundari Putri Lestari Tiara Dwi Lestari Purba Timbo Faritcan P Siallagan Timbo Faritcan P. Siallagan