Claim Missing Document
Check
Articles

Found 20 Documents
Search

Prediksi Jumlah Produksi Kelapa Sawit di Indonesia Menggunakan Algoritma Backpropagation Safii, M.; Alfina, Ommi
Majalah Ilmiah METHODA Vol. 14 No. 2 (2024): Majalah Ilmiah METHODA
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methoda.Vol14No2.pp166-174

Abstract

Indonesia is a country that has advantages in the agricultural sector which has the largest plantation and agricultural areas in ASEAN, one of which is oil palm plantations. Indonesia is one of the largest crude palm oil (CPO) business players in the world. More and more palm oil mills and oil palm land are being converted to oil palm cultivation, because oil palm plantations are more beneficial for farmers and palm oil processors. Palm oil plantations are still trying in several ways to maintain stable market demand, one of which is by increasing palm oil production, because palm oil is the main source of other product derivatives. Palm oil production fluctuates every month, but the ups and downs are caused by many factors, namely climate, rainfall, soil fertility, selling prices, and others. Reduced production has a direct impact on the income of farmers and workers in the sector, which in turn can cause economic instability. Actions are needed to ensure the continuity of this industry, one of which is by making predictions. One prediction technique is the Backpropagation artificial neural network. The prediction model can provide very accurate estimates of palm oil production at the provincial level. By analyzing historical data, this research can identify patterns that can help predict future palm oil production. The urgency lies in the strategic role of palm oil in the Indonesian economy.
Klasifikasi Pola Konsumsi Energi Rumah Tangga Menggunakan Algoritma Machine Learning untuk Mendukung Implementasi Smart City Alfina, Ommi; M. Safii
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No2.pp300-306

Abstract

Population growth in urban areas drives a significant increase in household energy consumption. This condition poses a major challenge for the implementation of the smart city concept, particularly in achieving energy efficiency and sustainability. This study aims to classify household energy consumption patterns based on household power consumption data to support intelligent decision-making in urban energy management. The research method includes data preprocessing, data cleaning, and aggregation of daily energy consumption by utilizing key attributes such as Global Active Power, Voltage, Global Intensity, and three sub-metering variables. Consumption pattern categories are formed using the tertile method into three classes: Low, Medium, and High. Several machine learning algorithms are applied to build the classification model, including Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, and Gradient Boosting. The test results show that the Random Forest model with hyperparameter adjustments produces the best performance with an accuracy value of 0.98 and an F1-macro value of 0.98, surpassing other models. These findings indicate that the ensemble learning approach is able to capture the complexity of household energy consumption patterns more effectively than conventional linear models. The contribution of this research lies in the development of a machine learning-based predictive model to support adaptive energy consumption monitoring and control systems in smart city implementations.
PELATIHAN PEMBUATAN IKLAN PEMASARAN PRODUK PROMOSI MENGGUNAKAN APLIKASI VOICE MAKER PENGISI AUDIOTEXT TO SPEECH (TTS) DI SMK BM BUDI AGUNG MEDAN Siregar, Elida Tuti; Alfina, Ommi; Ambarita, Wisesa Panca Praja Damanik
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 3 No 1 (2023): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methabdi.Vol3No1.pp54-58

Abstract

Product promotion is an activity of introducing products, persuading, reminding and influencing the public so that potential buyers want to buy the goods and services offered. Advertising in the form of communication that has the intention of conveying information about the products offered with global marketing communications and e-marketing using a combination of graphics, animation and sound. This training is aimed at students at private schools in the city of Medan, SMK Budi Agung Class XII, majoring in marketing, in the form of multimedia practicum training using Macromedia Flash, making product advertisement animations and advertising voiceovers using the Voice maker Free Text to Speech (TTS) application. This training is a higher education tridharma each semester carrying out community service as a routine each semester.
PELATIHAN PENGINPUTAN DATA SECARA OTOMATIS DI MICROSOFT EXCEL MENGGUNAKAN DATA FORM DAN MACRO VBA (BASIC FOR APLICATION) DI SMA IT UNGGUL AL-MUNADI MEDAN Siregar, Elida Tuti; Alfina, Ommi; Puspita, Dahlia; Safii, M.
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 3 No 2 (2023): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methabdi.Vol3No2.pp150-154

Abstract

Automatic data input using Microsoft Excel as a number processor or application for automatically processing data such as numerical values, mathematical formulas and making financial reports hone students' skills in knowledge of the use of computer technology, which is a basic need nowadays to operate a computer, a skill that students must master in the future world of work. because computer operating skills are really needed by companies, especially the Microsoft Excel application to process technology-based company data in determining decision makers in a company. This training will produce graduates who can operate computers and input data automatically. This activity provides skills and knowledge to students at SMA IT Unggul Al Munadi Medan using Microsoft Excel to process and input data automatically with Visual Basic forms and macros (VBA)
Klasifikasi Pola Konsumsi Energi Rumah Tangga Menggunakan Algoritma Machine Learning untuk Mendukung Implementasi Smart City Alfina, Ommi; M. Safii
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

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

Abstract

Population growth in urban areas drives a significant increase in household energy consumption. This condition poses a major challenge for the implementation of the smart city concept, particularly in achieving energy efficiency and sustainability. This study aims to classify household energy consumption patterns based on household power consumption data to support intelligent decision-making in urban energy management. The research method includes data preprocessing, data cleaning, and aggregation of daily energy consumption by utilizing key attributes such as Global Active Power, Voltage, Global Intensity, and three sub-metering variables. Consumption pattern categories are formed using the tertile method into three classes: Low, Medium, and High. Several machine learning algorithms are applied to build the classification model, including Logistic Regression, K-Nearest Neighbors (KNN), Random Forest, and Gradient Boosting. The test results show that the Random Forest model with hyperparameter adjustments produces the best performance with an accuracy value of 0.98 and an F1-macro value of 0.98, surpassing other models. These findings indicate that the ensemble learning approach is able to capture the complexity of household energy consumption patterns more effectively than conventional linear models. The contribution of this research lies in the development of a machine learning-based predictive model to support adaptive energy consumption monitoring and control systems in smart city implementations.
Pelatihan Mengenal dan Mengoptimalkan Prompt GPT untuk Pembelajaran Digital di SMK PAB 8 Sampali Alfina, Ommi; Syahputri, Nita; Lahilote, Abqoriy Hisan; Rustam, Muhammad Taufiq; Safii, M.
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 5 No 1 (2025): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

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

Abstract

The training program titled "Introduction and Optimization of GPT Prompts for Digital Learning at SMK PAB 8 Sampali" was conducted as an effort to enhance digital literacy and technological skills among teachers and students. In the era of Education 4.0, artificial intelligence (AI) technology, particularly Generative Pre-trained Transformer (GPT), holds great potential to support teaching and learning processes, including generating exam questions, summarizing materials, and planning lessons. This training aimed to provide basic understanding of GPT concepts and practical skills in crafting effective prompts for various educational purposes. The implementation method employed hands-on practice and real-life case studies within the SMK environment. The results showed an improvement in teachers' and students' abilities to utilize AI technologies, as well as increased awareness of the importance of ethical and creative use of technology in digital education. Through this training, SMK PAB 8 Sampali is expected to become a pioneer in the application of AI in vocational secondary schools in Medan.
Penerapan Internet of Things (IoT) Dasar dalam Sistem Monitoring Lingkungan Sekolah Serta Smart Classroom di SMK PAB 8 Sampali Medan Alfina, Ommi; Syahputri, Nita; Ananda Pratama; Muhammad Taufiq Rustam; M. Safii; Jamaluddin, Jamaluddin
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 5 No 2 (2025): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methabdi.Vol5No2.pp259-265

Abstract

The development of Internet of Things (IoT) technology has opened up significant opportunities for improving the efficiency and effectiveness of learning systems as well as school environmental management. This community service activity aims to provide basic IoT training and implement an environmental monitoring system and smart classroom at SMK PAB 8 Sampali Medan. The implementation method includes three main stages: (1) socialization of basic IoT concepts and their application in the educational field, (2) practical training for creating simple IoT devices based on temperature, humidity, and light sensors, and (3) implementation of a school environmental monitoring system integrated with a web-based platform and a real-time dashboard. In addition, participants were also introduced to the concept of a smart classroom, where classroom conditions can be monitored and controlled automatically through the developed IoT system. The results of the activity showed an 85% increase in participants' understanding of basic IoT concepts and their ability to independently design environmental monitoring system prototypes. This program has had a positive impact on enhancing digital literacy, technical skills, and school readiness for IoT-based educational digital transformation.
Penilaian Otomatis di SMK TI Budi Agung dengan Certainty Factor Alfina, Ommi
TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 5 No 1 (2025): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/tamika.Vol5No1.pp27-34

Abstract

The assessment system at SMK TI Budiagung still relies on conventional methods but has gradually shifted towards AI-based automated assessment. This study aims to analyze the effectiveness of an automated assessment system using the Certainty Factor method in evaluating students objectively and accurately. The research methodology includes interviews with educators and an analysis of the implemented system. The findings indicate that automated assessment enhances efficiency in grading objective answers but faces challenges in evaluating subjective aspects such as creativity and problem-solving skills. Furthermore, the application of the Certainty Factor method allows the system to provide assessments based on calculated certainty levels from available data. The main challenge is ensuring valid and weighted data for more accurate evaluation results. With further development and integration into the learning system, automated assessment is expected to improve academic evaluation quality at SMK TI Budiagung.
Perancangan Aplikasi E-Rekrutmen dan Penempatan Karyawan Menggunakan Metode PSI pada PT. Mutiara Inti Persada Utomo, Tedi; Alfina, Ommi
TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 5 No 2 (2025): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/tamika.Vol5No2.pp149-158

Abstract

PT. Mutiara Inti Persada is a company operating in the field of labor distribution services with the vision of providing and managing human resources professionally. However, employee recruitment and placement processes that are still carried out manually are often inefficient, lack objectivity, and face challenges in matching applicant profiles with the needs of partner companies. To overcome this problem, this research aims to design a web-based e-recruitment and employee placement application using the Preference Selection Index (PSI) method. The PSI method is applied to provide an objective assessment of applicants based on predetermined criteria, such as work experience, education and skills. The system developed is also equipped with an employee placement feature designed to optimally match applicant profiles with the needs of partner companies. This research uses data collection methods through observation, interviews and documentation to understand company needs, as well as a system development method using the Waterfall model. The research results show that the designed application is able to increase the efficiency of the recruitment process, reduce bias in applicant assessment, and ensure more appropriate employee placement.
Pengembangan Aplikasi Penjualan Kopi dengan Metode FIFO pada CV. Mandiri Kopi Berbasis Android Ramadhania, Dwindah; Alfina, Ommi
TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 5 No 2 (2025): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/tamika.Vol5No2.pp236-243

Abstract

CV. Mandiri Kopi is a coffee company with a variety of product variants. The company faces a challenge in accurately managing its inventory, particularly ensuring that incoming and outgoing products comply with their expiration dates and arrival dates. This can potentially lead to losses if older products are not promptly sold. To address this issue, this study aims to develop an Android-based coffee sales application that implements the FIFO method in inventory management. The application's main features include recording sales transactions, managing inventory using the FIFO method, recording sales reports, and notification of products approaching expiration. Test results show that the application can help the company manage product inventory more efficiently, reduce the risk of stockpiling, and make it easier for admins to monitor sales reports. Thus, the Android-based coffee sales application using the FIFO method can improve the effectiveness and accuracy of inventory management at CV. Mandiri Kopi.