Garuda - Garba Rujukan Digital

Klasterisasi Tingkat Masa Studi Tepat Waktu Mahasiswa Menggunakan Algoritma K-Medoids Firzada, Fahmi; Yunus, Yuhandri
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jsisfotek.v3i3.146

The period of study on time is one of the parameters of a student's success in completing college to obtain a bachelor's degree. A student is said to have completed his studies on time if he is able to complete his studies less than or equal to the predetermined time. Academic Provides facilities to find out the estimated time of student graduation. By providing information on which students are included in the cluster, they can complete their studies on time and which students do not complete their studies on time. In this study, the data processed were data from students who had graduated in the previous year. Then the data is processed using rapidminer software. This study applies the K-Medoids algorithm in clustering. The result of testing this method is to determine the student clusters who can complete the study period on time and the student clusters who cannot complete the study period on time. This research is expected to contribute to the campus in evaluating the tendency of students to complete their studies on time or not. The results of the evaluation of performance can produce information for study programs, lecturers and students in making policies.

The Conjugate Gradient Backpropagation Algorithm in Predicting Inmate Rates in Pematangsiantar City Based on Gender Darma, Surya; Robiansyah, Wendi; Firzada, Fahmi; Irawan, Eka; Saputra, Widodo
IJISTECH (International Journal of Information System and Technology) Vol 8, No 2 (2024): The August edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i2.353

The increase in the number of inmates in Indonesia, particularly in Pematangsiantar City, is a significant social issue. In this context, it is important to predict inmate levels based on demographic factors, including gender. One promising approach is the use of Artificial Neural Networks (ANN) with the Backpropagation Conjugate Gradient (BPCG) algorithm. ANN is a computational model that mimics the way the human brain processes information and has been used in various applications, including crime prediction. The BPCG algorithm is a variant of the backpropagation algorithm that efficiently accelerates the convergence of ANN training. This study aims to implement ANN with the BPCG algorithm to predict inmate levels in Pematangsiantar City based on gender and to evaluate the performance of this model in the context of available crime data. MATLAB (version 7.13 R2011b) was used as a tool, employing five model architectures (7-3-1, 7-5-1, 7-11-1, 7-12-1, and 7-15-1) to test data for estimation/prediction. The best model, 7-12-1, achieved 100% accuracy with 16 iterations in less than 1 second and an MSE of 0.1477446359. With 100% accuracy, this model will be used to predict the number of inmates in Pematangsiantar City by gender in 2023. This study can make a significant contribution to the fields of criminology and data analysis and serve as a reference for future research on the use of artificial intelligence in legal and criminal contexts.

The Conjugate Gradient Backpropagation Algorithm in Predicting Inmate Rates in Pematangsiantar City Based on Gender Darma, Surya; Robiansyah, Wendi; Firzada, Fahmi; Irawan, Eka; Saputra, Widodo
IJISTECH (International Journal of Information System and Technology) Vol 8, No 2 (2024): The August edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i2.353

The increase in the number of inmates in Indonesia, particularly in Pematangsiantar City, is a significant social issue. In this context, it is important to predict inmate levels based on demographic factors, including gender. One promising approach is the use of Artificial Neural Networks (ANN) with the Backpropagation Conjugate Gradient (BPCG) algorithm. ANN is a computational model that mimics the way the human brain processes information and has been used in various applications, including crime prediction. The BPCG algorithm is a variant of the backpropagation algorithm that efficiently accelerates the convergence of ANN training. This study aims to implement ANN with the BPCG algorithm to predict inmate levels in Pematangsiantar City based on gender and to evaluate the performance of this model in the context of available crime data. MATLAB (version 7.13 R2011b) was used as a tool, employing five model architectures (7-3-1, 7-5-1, 7-11-1, 7-12-1, and 7-15-1) to test data for estimation/prediction. The best model, 7-12-1, achieved 100% accuracy with 16 iterations in less than 1 second and an MSE of 0.1477446359. With 100% accuracy, this model will be used to predict the number of inmates in Pematangsiantar City by gender in 2023. This study can make a significant contribution to the fields of criminology and data analysis and serve as a reference for future research on the use of artificial intelligence in legal and criminal contexts.

Algoritma Bayesian Regulation untuk Prediksi Kemiskinan Sebagai Evaluasi Awal Mendukung Kebijakan Ekonomi Hijau Firzada, Fahmi; Darma, Surya
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6011

This study aims to utilize the Bayesian Regulation algorithm to predict poverty in Simalungun, Pematangsiantar, Asahan, Batu Bara, and Tebing Tinggi, as an initial step to evaluate the Green Economy policy. Poverty remains a serious issue, particularly in Pematangsiantar and Simalungun, where social inequality and limited access to basic services are prevalent. High poverty rates and limited resources present significant challenges to improving community welfare. The Green Economy policy could be a potential solution to reduce the negative environmental impact of development and enhance community well-being. This research uses secondary time-series poverty data from 2012 to 2023, obtained from the Central Bureau of Statistics of North Sumatra, based on the basic needs approach. The applied Machine Learning algorithm is Bayesian Regulation, used to predict poverty levels in these areas based on five architectural models (10-5-1, 10-10-1, 10-15-1, 10-20-1, and 10-25-1). The 10-25-1 model was selected as the best model due to its smallest MSE (error), 0.00218055780, compared to the other four models. This study aims to provide insights into the development of poverty in these regions and offer an initial evaluation of the effectiveness of the Green Economy policy. It is also expected to propose more effective policy recommendations for reducing poverty and supporting environmental sustainability, particularly in Pematangsiantar and Simalungun.

Pemanfaatan Algoritma Levenberg-Marquardt untuk Analisis Prediksi Persentase Penduduk yang Melakukan Pengobatan Sendiri Darma, Surya; Firzada, Fahmi
Journal of Computer System and Informatics (JoSYC) Vol 6 No 1 (2024): November 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v6i1.6153

Self-medication is a practice in which individuals use drugs or administer treatments without a doctor's prescription or medical supervision. This phenomenon has become a significant health issue in Indonesia, particularly in the city of Pematangsiantar and Simalungun Regency, where many residents tend to self-medicate without receiving adequate medical consultation. Therefore, the aim of this study is to analyze the predicted percentage of health independence development among residents who self-medicate in Pematangsiantar and Simalungun Regency using the Levenberg-Marquardt algorithm. The research data consists of time-series data on the percentage of residents self-medicating in Pematangsiantar and Simalungun Regency from 2018 to 2023, obtained from the Central Statistics Agency of North Sumatra. The analysis was conducted using five architecture models: 4-5-1, 4-10-1, 4-15-1, 4-20-1, and 4-25-1. The results show that the Levenberg-Marquardt algorithm with the 4-15-1 architecture model provided the best performance, with the lowest Mean Squared Error (MSE) value of 0.0268691174 compared to the other architecture models. This study is expected to assist local governments by providing information on the development of the percentage of residents who self-medicate in Pematangsiantar and Simalungun Regency, enabling them to formulate the best policies for improving public health in the region in the future. This research also contributes to the development of artificial intelligence-based health prediction methods, particularly for analyzing the percentage of self-medicating residents in complex and dynamic regional contexts.

Optimization of the K-Means Method and Davies-Bouldin Index (DBI) Technique in Mapping Spotify's Most Popular Songs Based on Mood Septiani, Rizky; Lubis, Muhammad Ridwan; Firzada, Fahmi
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 3 (2025): Articles Research July 2025
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v7i3.6655

Spotify is a leading music streaming platform that offers a wide variety of songs with audio characteristics capable of influencing listeners' moods. This study aims to optimize the K-Means method to cluster popular songs based on users’ moods, with the support of the Davies-Bouldin Index (DBI) technique to determine the optimal number of clusters. The dataset was obtained from Kaggle, utilizing audio features such as danceability, valence, energy, and others as the basis for clustering. The results show that the implementation of K-Means optimized with DBI produces more accurate clustering, as indicated by lower DBI values. This approach has the potential to enhance mood-based music recommendation systems, enriching the user experience.

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