Garuda - Garba Rujukan Digital

PREDIKSI LAMA TINGGAL PASIEN RAWAT INAP DI RUMAH SAKIT PADA MASA PANDEMI COVID-19 MENGGUNAKAN METODE ENSEMBLE LEARNING DAN DECISSION TREE irmawati irmawati irmawati; Hermanto Hermanto; Eka Herdit Juningsih; Syaifur Rahmatullah; Faruq Aziz
Jurnal Informatika Kaputama (JIK) Vol 5, No 2 (2021): Volume 5, Nomor 2 Juli 2021
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.1234/jik.v5i2.565

Beban pada sistem perawatan kesehatan berasal dari insiden tertinggi, yakni COVID-19. Banyak langkah yang dilakukan untuk meningkatkan manajemen perawatan kesehatan yakni, mengurangi populasi pasien untuk disparitas kesehatan, serta adanya inisiatif peningkatan kualitas untuk fasilitas keperawatan. Oleh karena itu, pada penelitian ini membahas prediksi lama tinggal pasien rawat inap di rumah sakit pada masa pandemi COVID-19 dengan tujuan membuat model akurasi yang tepat untuk memprediksi lama tinggal pasien agar menigkatkan efisiensi manajemen perawatan kesehatan di rumah sakit. Penulis menggunakan model Decision Tree dan Ensemble Learning. pada Decision Tree dengan menggunakan kriteria Entropy dan Information Gain dengan variasi nilai 4, 8, 12, 16, 20 untuk melihat hasil performa akurasi, f1 score, dan AUC. Sedangkan ensemble learning menggunakan 4 variasi yaitu klasifikasi Random Forest, Gradient Boosting, AdaBoost, dan AdaBoost dengan Logistc Regressi. Hasil tertinggi dari penelitian ini untuk menentukan klasifikasi terkait lama rawat inap (stay) selama pandemi COVID-19 menggunakan teknik Ensemble Learning variasi Gradiant Boosting dengan akurasi 41%, f1 score 22% dan AUC 79%.

Prediksi nilai akademik peserta didik di masa pandemi covid-19 dengan regresi linier berganda Syaifur Rahmatullah; Eka Herdit Juningsih; Susan Rachmawati
JISAMAR (Journal of Information System, Applied, Management, Accounting and Research) Vol 7 No 1 (2023): JISAMAR : February 2023
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisamar.v7i1.1012

With the implementation of Learning From Home (BDR) learning patterns, there are several problems that exist, namely the decline in student achievement in learning outcomes, decreased interest in learning and the presence of students in online learning activities, and decreased participation of parents/guardians of students in paying attention to learning conditions and achievements of students at SDN Cengkareng Timur 01 Pagi. On the basis of all that research related to predicting the academic value of students will later be able to help the school to make permanent decisions on the problems that occur in the school environment. This study, using the multiple linear regression method, is effectively used to predict the final grades of students, so that by predicting school institutions can take preventive steps to boost student grades. The test results from 3 tools, namely Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Square Error (MSE) show that the prediction results are accurate enough to be used as a predictive model. Therefore, it is hoped that the prediction model will periodically test the prediction model every semester and applications that can be used directly without having to use a spreadsheet.

PREDIKSI LAMA TINGGAL PASIEN RAWAT INAP DI RUMAH SAKIT PADA MASA PANDEMI COVID-19 MENGGUNAKAN METODE ENSEMBLE LEARNING DAN DECISSION TREE Irmawati Irmawati; Hermanto Hermanto; Eka Herdit Juningsih; Syaifur Rahmatullah; Faruq Aziz
Jurnal Informatika Kaputama (JIK) Vol 5 No 2 (2021): Volume 5, Nomor 2, Juli 2021
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59697/jik.v5i2.276

Beban pada sistem perawatan kesehatan berasal dari insiden tertinggi, yakni COVID-19. Banyak langkah yang dilakukan untuk meningkatkan manajemen perawatan kesehatan yakni, mengurangi populasi pasien untuk disparitas kesehatan, serta adanya inisiatif peningkatan kualitas untuk fasilitas keperawatan. Oleh karena itu, pada penelitian ini membahas prediksi lama tinggal pasien rawat inap di rumah sakit pada masa pandemi COVID-19 dengan tujuan membuat model akurasi yang tepat untuk memprediksi lama tinggal pasien agar menigkatkan efisiensi manajemen perawatan kesehatan di rumah sakit. Penulis menggunakan model Decision Tree dan Ensemble Learning. pada Decision Tree dengan menggunakan kriteria Entropy dan Information Gain dengan variasi nilai 4, 8, 12, 16, 20 untuk melihat hasil performa akurasi, f1 score, dan AUC. Sedangkan ensemble learning menggunakan 4 variasi yaitu klasifikasi Random Forest, Gradient Boosting, AdaBoost, dan AdaBoost dengan Logistc Regressi. Hasil tertinggi dari penelitian ini untuk menentukan klasifikasi terkait lama rawat inap (stay) selama pandemi COVID-19 menggunakan teknik Ensemble Learning variasi Gradiant Boosting dengan akurasi 41%, f1 score 22% dan AUC 79%. Kata

Pelatihan Digital Security Dalam Keamanan Berorganisasi Bagi Jaringan Pemuda dan Remaja Masjid Indonesia Jakarta Achmad Rifai; Tyas Setiyorini; Syaifur Rahmatullah; Sita Anggraeni
PRAWARA Jurnal ABDIMAS Vol 3 No 1 (2024): PRAWARA JURNAL ABDIMAS
Publisher : CV. Manha Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63297/abdimas.v3i1.89

Keamanan data pada surat elektronik atau email menjadi elemen krusial dalam konteks organisasi pada era digital saat ini. Meskipun email memainkan peran sentral dalam komunikasi organisasi, namun juga menjadi celah potensial bagi tindakan kejahatan siber yang tidak bertanggung jawab. Jaringan Pemuda dan Remaja Masjid Indonesia (JPRMI) Jakarta, yang aktif dalam berbagai kegiatan dan mengelola beragam informasi organisasi, mengakui pentingnya aspek keamanan digital, khususnya dalam konteks email. Dalam upaya pengabdian masyarakat, metode pelatihan dan diskusi digunakan untuk mengeksplorasi tantangan keamanan email yang dihadapi oleh organisasi, dengan fokus pada ancaman-ancaman seperti spamming, scamming, malware, dan spoofing. Keberadaan ancaman-ancaman tersebut menekankan perlunya pemahaman yang mendalam dan penerapan tindakan preventif guna melindungi data organisasi dari serangan siber. Tujuan utama pengabdian kepada masyarakat ini adalah memberikan panduan praktis kepada JPRMI, memungkinkan mereka untuk mengatasi tantangan keamanan email dengan pemahaman yang lebih mendalam terhadap risiko yang ada. Selain itu, pengabdian ini bertujuan meningkatkan kemampuan JPRMI dalam menerapkan langkah-langkah keamanan yang tepat dan melindungi data organisasi melalui email di era digital yang semakin kompleks. Dengan demikian, hasil dari pengabdian ini diharapkan dapat memberikan kontribusi signifikan dalam memperkuat lapisan keamanan digital organisasi, menciptakan lingkungan yang lebih aman dan terpercaya di dunia maya.

Pelatihan Teknologi AI Menggunakan Bing Microsoft Dan Vidnoz AI Bagi Karang Taruna Kelurahan Ragunan Sita Anggraeni; Syaifur Rahmatullah; Tyas Setiyorini; Achmad Rifai
AMMA : Jurnal Pengabdian Masyarakat Vol. 3 No. 4 : Mei (2024): AMMA : Jurnal Pengabdian Masyarakat
Publisher : CV. Multi Kreasi Media

Show Abstract | Download Original | Original Source | Check in Google Scholar

In the Era of Society 5.0, young people have different styles of interacting, socialising, and/or absorbing knowledge. Coupled with the fact that most of today's students are from the digital generation who are accustomed to speed and convenience in other aspects of life, students expect the same speed and convenience when it comes to learning. Bing AI is an integral part of the Bing search engine platform developed by Microsoft. Built with Artificial Intelligence (AI) technology, Bing AI aims to improve users' online search experience by providing more relevant and personalised results. As video content continues to dominate the digital world, creating engaging and high-quality videos is a top priority for the younger generation in content creation. Producing videos quickly while entertaining audiences is important to stay ahead of the curve. Vidnoz is a versatile and free AI Video Generator for easy video creation, this is done through the use of Artificial Intelligence and intelligent automation. Karang Taruna Kelurahan Ragunan has many positive activities and actively spreads content on social media such as Instagram but does not yet have knowledge in the use of AI technology using Bing AI from Microsoft and the use of Vidnoz in each content. The Karang Taruna Kelurahan Ragunan administrators need insight in the form of training in the application of AI technology in the distribution of content to be shared on social media and need technical steps in the application of the use of AI technology using Bing AI from Microsoft and the use of Vidnoz. With the training in this community service, it is hoped that Karang Taruna Kelurahan Ragunan can understand the knowledge of the use of AI technology using Bing AI from Microsoft and the use of Vidnoz in every content to be shared on social media owned by Karang Taruna Kelurahan Ragunan and practice and be creative in technical steps in the application of the use of AI technology using Bing AI from Microsoft and the use of Vidnoz in every content to be shared on social media owned by Karang Taruna Kelurahan Ragunan.

Machine Learning-Based Classification of Family Planning Participant Status Using Random Forest and the CRISP-DM Framework Irmawati Irmawati; Syaifur Rahmatullah; Mohammad Syamsul Azis
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6498

The Family Planning (FP) program requires accurate information to support evidence-based decision-making and improve the quality of reproductive health services. Classification of FP participant status can assist health authorities in identifying participant patterns and monitoring program implementation. Previous research using the Support Vector Machine (SVM) algorithm on the same dataset achieved an accuracy of 56.20%, indicating that improvements in classification performance are still required. This study proposes the Random Forest algorithm within the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework to classify FP participant status. The dataset consists of 1,402 FP participant records obtained from SATPEL PPKB, Cilebar District, Karawang Regency. Data preprocessing included data transformation, One Hot Encoding for categorical predictor variables, Label Encoding for the target variable, and Hold-Out Validation with an 80:20 train-test split using stratified sampling. The predictor variables were registration month, wife's birth year, wife's age, and contraceptive method, while the target variable was FP participant status (New, Change Method, and Repeat). Model performance was evaluated using accuracy, precision, recall, F1-score, confusion matrix, classification report, and feature importance analysis. The Random Forest model achieved an accuracy of 59.43%, with weighted precision, recall, and F1-score of 59.00%. However, the macro-average precision, recall, and F1-score were 45.00%, 44.00%, and 44.00%, respectively, indicating performance differences across classes caused by class imbalance. The model achieved the highest F1-score for the New class (0.63), followed by the Repeat class (0.59), whereas the Change Method class obtained the lowest F1-score (0.11). Feature importance analysis identified wife's birth year and wife's age as the most influential predictor variables. Compared with the previous SVM-based model, Random Forest provided a modest improvement in accuracy and enhanced model interpretability through feature importance analysis. Nevertheless, the low macro-average performance indicates that further research should investigate class-balancing techniques and hyperparameter optimization to improve classification performance, particularly for minority classes.

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