Garuda - Garba Rujukan Digital

Speed and Accuracy Comparison of Person Detection Using Pretrained CenterNet and Yolov3 Friendly; Harizahayu; Sembiring, Zakaria
International Journal of Research in Vocational Studies (IJRVOCAS) Vol. 3 No. 4 (2024): IJRVOCAS - Special Issues - International Conference on Science, Technology and
Publisher : Yayasan Ghalih Pelopor Pendidikan (Ghalih Foundation)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53893/ijrvocas.v3i4.17

Implementations of object detection by using common devices for general purpose application is not widely used for speed and prone to errors. Most of research in speed detection using known method such as Centernet, Yolov3, Fast-RNN has variant result since the computer used are different. This experiment try to conduct experiments for person detection with Centernet and Yolov3 method using commonly used computer only using CPU. Based on the experiments, Yolov3 can give a much better precision for person detection by 98.42% of mAP point while Centernet only 97%. In terms of processing speed, Centernet can give much better speed where it can detect a person in average 370ms better than Yolov3 with average of 1050 ms or 1 second.

Predictive Modeling of Preeclampsia Risk Using Random Forest Algorithm within a Machine Learning Framework Harizahayu; Friendly; Purwo Seputro , Bintarto; Benar; Hermanto, Koko
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 4 (2024): Articles Research October 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i4.4779

Preeclampsia is a serious pregnancy complication characterized by high blood pressure, potentially leading to organ damage, making early risk prediction crucial to reducing maternal morbidity and mortality. This study aims to develop a preeclampsia risk prediction model using medical and clinical data from 80 patients at Rumah Bersalin Sadan. The data include demographic profiles, blood pressure, weight, maternal age, preeclampsia history, body mass index, number of previous pregnancies, as well as genetic and environmental factors. The dependent variable is the risk of preeclampsia, either as a binary outcome (yes/no) or as a continuous risk score. The predictive model was built using multivariate linear regression and the Random Forest algorithm. The results showed that the Random Forest model achieved an accuracy of 65.22%, with an F-statistic of 7.345 and a very small p-value (1.908e-06), indicating that the model effectively explains data variability. However, the low Kappa value suggests room for improvement through feature refinement, hyperparameter tuning, or exploring other algorithms. Although these findings suggest that Random Forest is a promising method, further evaluation and model optimization are needed to enhance predictive performance and determine whether this method is the most suitable for the dataset used.

Perancangan Teknologi Multimedia Pada Mitra Komunitas Generasi Baru Indonesia Komisariat Politeknik Negeri Medan Supriadi Chan, Andi; Friendly; Bastanta Tarigan, Andre; Daniel Sinaga, Jose; Dwi Ilham, Muhammad; Karerina Kristanti Sianturi, Yessi
Jurnal Pengabdian Masyarakat IPTEK Vol. 5 No. 1 (2025): Edisi Januari 2025
Publisher : STMIK Triguna Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53513/abdi.v5i1.10569

Teknologi pada masa sekarang sudah menjadi salah satu aspek yang harus ada dalam setiap kehidupan umat manusia. Hal ini karena keberadaannya yang memberi kemudahan dalam semua aktivitas termasuk dalam hal pembelajaran. Dalam kegiatan Pengabdian ini, dilakukan dengan Komunitas Generasi Baru Indonesia (GENBI) komisariat Politeknik Negeri Medan. Divisi Pendidikan dan Kebudayaan sebagai mitra bertujuan untuk menerapkan teknologi multimedia sebagai media belajar pada pengenalan serta perawatan mata uang rupiah dan pengenalan komunitas Genbi komisariat Politeknik Negeri Medan berupa video edukasi, video company profile serta permainan edukasi. Divisi pendidikan dan kebudayaan GenBI komisariat Politeknik Negeri medan memiliki potensi dalam mendukung perkembangan media sosialisasi materi pengenalan dan perawatan rupiah dengan teknologi multimedia. Metode Pelaksanaan mencakup sosialisasi hasil, penerapan teknologi dan pendampingan.

Alih Fungsi Kolam Tanah Menjadi Kolam Beton Pada Budidaya Ikan Lele di Kelompok Tani Wakaf Mandiri harizahayu, Harizahayu; Friendly; Ferdinand R. Tampubolon
Jurnal Ilmiah Madiya (Masyarakat Mandiri Berkarya) Vol. 2 No. 1 (2021): Edisi Mei 2021
Publisher : Politeknik Negeri Medan

Air juga menjadi faktor yang utama dalam pembudidayaan ikan air tawar, dengan sistem konvensional/tradisional dibutuhkan tidak kurang dari 2000 liter air untuk budidaya ikan air tawar yang harus diganti sekurangnya setiap 3 bulan agar air kolam tidak bau dan berwarna, sedangkan dengan terbatasnya ketersediaan air di hampir sebagian besar wilayah Medan Selayang tepatnya di jalan Abdul Hakim, Medan Selayang membuat warga kesulitan air untuk membudidayakan ikan dalam kolam air tawar. Pengembangan melalui percobaan konstruksi kolam beton sederhana diharapkan akan menghemat ruang dimana setiap 1 lahan akan mampu dibudidayakan ikan lebih dari 2000 ekor lele dengan penggunaan air dimana setiap 0,5 air mampu dibudidayakan 2000-3000 ekor ikan lele melalui sistem airasi. Rumusan masalah dalam penelitian ini adalah: 1) Bagaimana membuat desain dan konstruksi kolam ikan air tawar dilahan pekarangan yang sempit namun padat menampung ikan lebih banyak 2) Bagaimana membuat sistem kolam ikan air tawar yang dapat menghemat penggunaan air 3) Seberapa luas pengematan lahan dan volume air yang dapat dihemat pada kolam ikan air tawar.

Predictive Modeling of Preeclampsia Risk Using Random Forest Algorithm within a Machine Learning Framework Harizahayu; Friendly; Purwo Seputro , Bintarto; Benar; Hermanto, Koko
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 4 (2024): Articles Research October 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i4.4779

Preeclampsia is a serious pregnancy complication characterized by high blood pressure, potentially leading to organ damage, making early risk prediction crucial to reducing maternal morbidity and mortality. This study aims to develop a preeclampsia risk prediction model using medical and clinical data from 80 patients at Rumah Bersalin Sadan. The data include demographic profiles, blood pressure, weight, maternal age, preeclampsia history, body mass index, number of previous pregnancies, as well as genetic and environmental factors. The dependent variable is the risk of preeclampsia, either as a binary outcome (yes/no) or as a continuous risk score. The predictive model was built using multivariate linear regression and the Random Forest algorithm. The results showed that the Random Forest model achieved an accuracy of 65.22%, with an F-statistic of 7.345 and a very small p-value (1.908e-06), indicating that the model effectively explains data variability. However, the low Kappa value suggests room for improvement through feature refinement, hyperparameter tuning, or exploring other algorithms. Although these findings suggest that Random Forest is a promising method, further evaluation and model optimization are needed to enhance predictive performance and determine whether this method is the most suitable for the dataset used.

Analysis of Regression and Neural Network Models in Predicting Patient Visit Volume Harizahahyu; Friendly; Fathoni, Muhammad; Lase, Yuyun Yusnida; Prayudani, Santi; Harfita, Nur Laily
International Journal of Science and Society Vol 7 No 4 (2025): International Journal of Science and Society (IJSOC)
Publisher : GoAcademica Research & Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54783/ijsoc.v7i4.1561

Predicting patient visit volume plays a crucial role in supporting decision-making and resource allocation in healthcare services. This study aims to compare the performance of Multiple Linear Regression and an Artificial Neural Network (ANN) in forecasting patient visits at a dental clinic, using daily patient visit data and predictor variables such as holidays and promotional activities. Multiple regression was used to capture the linear relationship between the predictor and response variables, while ANN was applied to explore potential non-linear relationships. The results indicate that multiple regression outperformed the ANN, demonstrated by lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) values, and provided clearer interpretability, making it more beneficial for healthcare practitioners, particularly in the context of a limited dataset. In contrast, the ANN tended to produce overestimates and was less responsive to short-term variations. Therefore, multiple regression can still be considered a reliable, efficient, and interpretable prediction method for clinical data with a moderate sample size, while future research is recommended to use larger datasets and test other machine learning algorithms to improve the accuracy and generalizability of the results.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search