Garuda - Garba Rujukan Digital

Improvement of FPS and Efficiency of Parameters Mask R-CNN with MobileNetV3 Small for Cardboard Detection Tri Vicika, Vikha; Indra, Jamaludin; Faisal, Sutan; Hikmayanti, Hanny
Digital Zone: Jurnal Teknologi Informasi dan Komunikasi Vol. 16 No. 1 (2025): Digital Zone: Jurnal Teknologi Informasi dan Komunikasi
Publisher : Publisher: Fakultas Ilmu Komputer, Institution: Universitas Lancang Kuning

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31849/digitalzone.v16i1.26349

Inventory management in warehouses often experiences discrepancies in recording the number of cardboard boxes due to errors during the manual recording process. To overcome this problem, a cardboard detection method was developed using the Default Mask R-CNN model and a modified model using MobileNetV3 Small. The training data was obtained from a collection of cardboard photos which then went through an annotation stage. In the cReonfiguration stage, various anchor scales were applied to determine the bounding box parameters, while the training process used Stochastic Gradient Descent (SGD). The default model is trained with the initial Mask R-CNN settings, while the custom model modifies the backbone and Feature Pyramid Network (FPN) adjustments. The test results show that the custom model has higher efficiency with a parameter count of 20,857,704 and an average FPS of 10.92. However, the accuracy level of the custom model is lower than that of the default model

Implementasi Algoritma Support Vector Machine (SVM) dan Random Forest Untuk Klasifikasi Penyakit Hipertensi Berdasarkan Data Kesehatan Azhaar, Siti Alia; Mudzakir, Tohirin Al; Novita, Hilda Yulia; Faisal, Sutan
JURIKOM (Jurnal Riset Komputer) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8744

One of the most common non-communicable diseases causing death in Indonesia is hypertension. At one community health center, the prevalence of hypertension is quite high. Based on examination results, more than 1,000 patients are diagnosed with hypertension each year. The issue faced at this health center is the lack of structured data classification for hypertensive and normal patients. The objective of this study is to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in creating a hypertension classification model based on health examination data from the Anggadita Health Center. Data from 2,500 patients was collected and preprocessed, including handling missing values, removing duplicate data, transforming data using label encoding, and dividing the data into training and testing sets. The SVM method applied a Radial Basis Function (RBF) kernel, while the RF consisted of 100 decision trees. Evaluation was conducted using a confusion matrix to calculate accuracy, precision, recall, and F1-score. The results showed that the SVM method achieved an accuracy of 93%, precision of 0.96 (Normal) and 0.90 (Hypertension), and F1-scores of 0.94 and 0.92. Meanwhile, the RF model showed superior performance with an accuracy of 96%, precision of 0.97 (Normal) and 0.95 (Hypertension), and F1-scores of 0.97 and 0.95, respectively. Thus, the Random Forest algorithm performs better in classifying hypertension data and can be implemented as a tool to assist healthcare institutions in managing patient data.

IMPROVING HEART DISEASE PREDICTION ACCURACY USING PRINCIPAL COMPONENT ANALYSIS (PCA) IN MACHINE LEARNING ALGORITHMS Jayidan, Zirji; Siregar, Amril Mutoi; Faisal, Sutan; Hikmayanti, Hanny
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 3 (2024): JUTIF Volume 5, Number 3, June 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.3.2047

This study aims to improve the accuracy of heart disease prediction using Principal Component Analysis (PCA) for feature extraction and various machine learning algorithms. The dataset consists of 334 rows with 49 attributes, 5 classes and 31 target diagnoses. The five algorithms used were K-nearest neighbors (KNN), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Decision Tree (DT). Results show that algorithms using PCA achieve high accuracy, especially RF, LR, and DT with accuracy up to 1.00. This research highlights the potential of PCA-based machine learning models in early diagnosis of heart disease.

Penerapan Metode Regresi Logistik Untuk Memprediksi Peristiwa Biner Pasien Pasca Operasi Kanker Payudara Sujana, Sylvia; Juwita, Ayu Ratna; Rahmat, Rahmat; Faisal, Sutan
Journal of Information System Research (JOSH) Vol 5 No 4 (2024): Juli 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i4.5521

Breast cancer is the second leading cause of death in women worldwide. To overcome this growing problem, this study designed a model that can predict breast cancer by utilizing datasets and then processed using the Logistic Regression Prediction method. This method is appropriate for predicting the data used because of its ability to handle dependent variables that are categorical and provide outups in the form of probabilities. This study uses a dataset of 306 samples with 4 attributes. Data used Research steps include data collection, preprocessing, modeling with logistic regression and evaluating results using matrices such as confusion matrix, MAE, MSE, and R-Square. The results showed a prediction accuracy of 86%, with an MSE value of 0.137 and R-Square of 0.309. This study shows the effectiveness of logistic regression in predicting the survival of patients after breast cancer surgery. However, by applying different algorithms, this study can select the best set of significant attributes to increase the prediction accuracy value in postoperative breast cancer patients.

Implementasi Algoritma Support Vector Machine (SVM) dan Random Forest Untuk Klasifikasi Penyakit Hipertensi Berdasarkan Data Kesehatan Azhaar, Siti Alia; Mudzakir, Tohirin Al; Novita, Hilda Yulia; Faisal, Sutan
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8744

One of the most common non-communicable diseases causing death in Indonesia is hypertension. At one community health center, the prevalence of hypertension is quite high. Based on examination results, more than 1,000 patients are diagnosed with hypertension each year. The issue faced at this health center is the lack of structured data classification for hypertensive and normal patients. The objective of this study is to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in creating a hypertension classification model based on health examination data from the Anggadita Health Center. Data from 2,500 patients was collected and preprocessed, including handling missing values, removing duplicate data, transforming data using label encoding, and dividing the data into training and testing sets. The SVM method applied a Radial Basis Function (RBF) kernel, while the RF consisted of 100 decision trees. Evaluation was conducted using a confusion matrix to calculate accuracy, precision, recall, and F1-score. The results showed that the SVM method achieved an accuracy of 93%, precision of 0.96 (Normal) and 0.90 (Hypertension), and F1-scores of 0.94 and 0.92. Meanwhile, the RF model showed superior performance with an accuracy of 96%, precision of 0.97 (Normal) and 0.95 (Hypertension), and F1-scores of 0.97 and 0.95, respectively. Thus, the Random Forest algorithm performs better in classifying hypertension data and can be implemented as a tool to assist healthcare institutions in managing patient data.

Title

Found 25 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 25 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 25 Documents
Search