Article Per Year (5 Year)
p-Index From 2021 - 2026
1.745
P-Index
This Author published in this journals
All Journal JOURNAL OF SCIENCE AND SOCIAL RESEARCH JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) Community Engagement and Emergence Journal (CEEJ) Jurnal Tekinkom (Teknik Informasi dan Komputer) Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer Jurnal Kolaborasi Sains dan Ilmu Terapan INOVTEK Polbeng - Seri Informatika
Mohammad Irfan Fahmi
Universitas Prima Indoensia, Medan
Aerospace Engineering Humanities Automotive Engineering Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Social Sciences

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Desain Prototype Smart Building Menggunakan Internet of Things dengan Protokol MQTT Evta Indra; Mohammad Irfan Fahmi; Daniel Ryan Hamonangan Sitompul; Stiven Hamonangan Sinurat; Andreas Situmorang; Ruben Ruben; Dennis Jusuf Ziegel
JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) Vol. 5 No. 1 (2022): Jutikomp Volume 5 Nomor 1 April 2022
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34012/jutikomp.v5i1.2595

Abstract

Energy saving is the most wanted thing to prevent overspending in carrying out daily activities in the building. One form of energy savings is implementing Smart Building technology to control Air conditioners (AC) dan lamps according to its need. Methods used in this research were started with the Architectural Design of the devices, Managing of the devices, and their Decommission. The result carried in this research is that the prototype made was running well on low-scale implementation. Buttons in the website functioned well, even though there are still many problems when implementing the project on a huge scale because this research still uses a freeware-based MQTT broker.
PENERAPAN METODE FORCASTING DALAM MENENTUKAN JUMLAH SISWA BARU MENGGUNAKAN ALGORITMA SIMPLE LINEAR REGRESSION Tajrin Tajrin; Mohammad Irfan Fahmi; Maikel Felix Ginting; Unika Nduru
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 6 No 1 (2023)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v6i1.880

Abstract

New student admission is a school activity to recruit new prospective students that occurs regularly every year even in the middle of the teaching year. Madrasah Tsanawiyah (MTs) Al-Ittihadiyah is a school under the auspices of the Ministry of Religion. Where every year the school always accepts a fairly large number of new students around 300 people. This results in the school always having difficulties in preparing infrastructure facilities such as classrooms and teachers because the increase in the number of new students increases every year. This will happen repeatedly in schools from year to year. So that it will be an accumulation of data every year to help transform data into data information into useful information. This large amount of data opens up opportunities to generate useful information for schools. In this study, researchers see an opportunity to create a new technology that answers the needs and problems that have occurred so far. In determining the number of new students at MTs. Al-Ittihadiyah Pkl. Masyhur researchers used 2 dataset scenarios where scenario 2 datasets used a simple linear regression algorithm. In pre-processing data that produces prediction performance, namely Y = 71.9538 + 0.709269X, in the dataset for forecasting estimates for the number of new students if the registrant is 374 students, it will produce a prediction of new students of 337 students.
ANALISIS SENTIMEN ULASAN APLIKASI MEDIA SOSIAL WHATSAPP MENGGUNAKAN METODE NAIVE BAYES CLASSIFIER Nova Rosalina Siahaan; Rosita Yolanda Tiffany; Shandy Roland Evansius Sinaga; Elsa Vio Nauli Br Naibaho; Mohammad Irfan Fahmi
JURNAL ILMIAH BETRIK Vol. 14 No. 02 AGUSTUS (2023): JURNAL ILMIAH BETRIK : Besemah Teknologi Informasi dan Komputer
Publisher : P3M Institut Teknologi Pagar Alam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36050/betrik.v14i02 AGUSTUS.104

Abstract

Analisis sentimen adalah proses menggunakan teknik dan metode komputasional untuk memahami dan mengevaluasi opini, sikap, atau emosi yang terkandung dalam teks atau data lainnya. Masalah utama dalam aplikasi media sosial whatsapp ini pada saat mengupload foto atau video story resolusi tidak jernih dan pecah . Masalah lain muncul pesan error atau terhenti, biasanya bertuliskan WhatsApp telah berhenti, atau mungkin pesan error lainnya. Hal semacam ini tentu mengganggu para pengguna karena pasti akan terbatas dalam aktivitas yang dilakukan . Untuk memberikan pengalaman yang baik bagi pengguna whatsapp, penting bagi pengembang aplikasi untuk memahami perasaan dan harapan pengguna. Penelitian ini bertujuan untuk menganalisis sentimen ulasan aplikasi WhatsApp menggunakan metode Naive Bayes Classifier. Hasil penelitian menunjukkan bahwa metode Naive Bayes Classifier efektif dalam menganalisis sentimen ulasan aplikasi media sosial WhatsApp. Pada Pelabelan, untuk mengklasisfikasi ulasan – ulasan dari suatu produk ke dalam kategori Positif, Negatif, dan Netral. Pada penelitian ini, tim peneliti telah melakukan pelabelan kedalam dataset. Pelabelan pada dataset ini dapat berupa : Rating <3 (lebih kecil dari angka-3) adalah sentimen Negatif, ==3 (sama dengan dari angka-3) adalah sentimen Netral, dan >3 (lebih besar dari angka -3) adalah Positif. Dan disertai penambahan kolom yaitu ‘Label’ yang berisi Sentimen Positif, Negatif, dan Netral.
ANALISIS PENILAIAN KINERJA DOSEN MENGGUNAKAN METODE ADAPTIVE NEURON-FUZZY INFERENCE SYSTEM (ANFIS) Rut Ronauli Hutagaol; Aida Elda Afriza; Mohammad Irfan Fahmi
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1331

Abstract

This research examines the performance of lecturers at Universitas Prima Indonesia using the Adaptive Neuro-Fuzzy Inference System (ANFIS) method to evaluate and enhance teaching quality. The research employs a quantitative approach, collecting data through observations, literature reviews, and questionnaires distributed to 100 students from the Faculty of Science and Technology. Four input variables used are pedagogical competence, professional competence, personal competence, and social competence. The collected data is analyzed using Matlab with ANFIS, which combines the capabilities of artificial neural networks and fuzzy logic to produce accurate predictions. The analysis results show that the ANFIS method is effective in measuring lecturer performance, with high validation results and low error rates. The ANFIS simulation indicates that the majority of lecturers fall into the "Quite Satisfied" category based on student assessments. This study is expected to make a significant contribution to improving the teaching quality of lecturers at Universitas Prima Indonesia through more accurate and technology-based performance evaluations.
PENERAPAN METODE ANT COLONY OPTIMIZATION (ACO) DALAM MENENTUKAN JALUR ALTERNATIF SOLUSI KEMACETAN KOTA MEDAN William William; Rizky Syahputra Sitompul; Adilman Reliance Hia; Roy F. Hasudungan Malau; Saut Parsaoran Tamba; Mohammad Irfan Fahmi
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 1 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i1.1221

Abstract

This research aims to analyze and implement the Ant Colony Optimization (ACO) method in determining alternative routes to reduce traffic congestion in Medan City. Against the background of significant congestion problems during rush hours, this research collects traffic data through surveys and observations to serve as input for the ACO algorithm. This method is inspired by the natural behavior of ants in searching for food, where ants collectively find the shortest route based on pheromone trails. Tests were carried out with variations in ACO parameters such as pheromone evaporation rate, number of ants, and iterations to analyze the effectiveness of alternative paths. The research results show that the application of this method can help reduce the burden on the road network and is proven to be able to reduce travel time by 37.5%, where the time needed from 40 minutes can be reduced to 25 minutes. The results of this research can contribute to the development of an intelligent transportation system that is adaptive to changes in traffic conditions and the needs of road users in the city of Medan.
Analisis kepuasan Pengguna Terhadap Produk Alat Kesehatan Dengan Menggunakan Metode Naive Bayes Classifier Besante Singh; Berwyn Hulbert Tanadi; Mohammad Irfan Fahmi
Jurnal Kolaborasi Sains dan Ilmu Terapan Vol. 4 No. 2 (2026): Jurnal Kolaborasi Sains dan Ilmu Terapan
Publisher : Utiliti Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69688/juksit.v4i2.137

Abstract

Penelitian ini bertujuan untuk memahami sampai di mana pengguna merasa puas dengan produk alat kesehatan yang digunakan, dengan menerapkan metode Naïve Bayes Classifier. Kepuasan pengguna adalah acuan penting dalam menilai kualitas produk dan layanan, terutama di bidang alat kesehatan yang berdampak langsung pada keselamatan dan kenyamanan pengguna. Penelitian ini mengadopsi pendekatan kuantitatif dengan metode analitis deskriptif, serta menerapkan teknik data mining dalam proses mengklasifikasikan data. Data didapat dengan cara memberikan kuesioner pada 100 orang responden. Kuesioner menggunakan skala Likert yang mencakup tujuh faktor utama, yaitu kemudahan dalam menggunakan produk, akurasi alat, kualitas barang, desain dan tampilan, ketahanan produk, harga, serta pelayanan perusahaan. Selain itu, ada satu faktor lain yang dinilai, yaitu tingkat kepuasan pengguna. Data yang dikumpulkan selanjutnya diuji terlebih dahulu mengenai kevalidan dan keandalannya sebelum dianalisis dengan metode Naïve Bayes. Penelitian menunjukkan bahwasanya sebagian besar orang yang diwawancara merasa puas, dengan tingkat kemungkinan sebesar 0,82, sementara hanya sebagian kecil yang merasa tidak puas, yaitu sebesar 0,18. Pengujian model dengan menggunakan RapidMiner menunjukkan akurasi sebesar 92%, yang menandakan bahwasanya metode Naïve Bayes sangat efektif dalam mengkategorikan tingkatan kepuasan pengguna. Dari hasil tersebut, terlihat bahwasanya metode Naïve Bayes Classifier cocok dan berhasil digunakan untuk mengevaluasi tingkat kepuasan pengguna terhadap produk alat kesehatan. Hasil penelitian ini diharapkan bisa dipakai oleh perusahaan untuk mengevaluasi kualitas produk dan layanan mereka, serta bisa menjadi acuan bagi kajian mendatang.
Implementasi K-Nearest Neighbor Untuk Prediksi Karakteristik Penghuni Citraland Gama City Agustian Gunawan; Mohammad Irfan Fahmi
Community Engagement and Emergence Journal (CEEJ) Vol. 7 No. 2 (2026): Community Engagement & Emergence Journal (CEEJ)
Publisher : Yayasan Riset dan Pengembangan Intelektual

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/ceej.v7i2.11839

Abstract

Pengelolaan data penghuni di Citraland Gama City masih menghadapi berbagai permasalahan, seperti belum optimalnya pemanfaatan data penghuni, proses analisis yang masih dilakukan secara manual, tingginya risiko kesalahan dalam pengelompokan data, serta belum adanya sistem yang mampu memprediksi karakteristik penghuni secara otomatis. Kondisi ini menyebabkan pihak pengelola kesulitan mengidentifikasi pola dan karakteristik penghuni secara akurat sehingga pengambilan keputusan terkait penyediaan fasilitas dan pelayanan menjadi kurang efektif. Selain itu, belum diterapkannya metode klasifikasi berbasis data mining, seperti K-Nearest Neighbor (KNN), membuat proses pengolahan data menjadi kurang efisien di tengah meningkatnya jumlah penghuni. Oleh karena itu, diperlukan penerapan metode KNN untuk membantu proses prediksi dan klasifikasi karakteristik penghuni secara lebih cepat, sistematis, dan akurat sehingga dapat mendukung pengelolaan kawasan perumahan yang lebih optimal. Penelitian ini menggunakan metode K-Nearest Neighbor (KNN) untuk memprediksi karakteristik penghuni Citraland Gama City berdasarkan data usia, pekerjaan, pendapatan, jumlah anggota keluarga, dan tipe hunian. Tahapan penelitian meliputi pengumpulan data, preprocessing, implementasi KNN, serta pengujian akurasi. Analisis dilakukan melalui perhitungan jarak Euclidean Distance, penentuan nilai K, dan evaluasi hasil prediksi untuk mengetahui tingkat ketepatan metode dalam mengklasifikasikan karakteristik penghuni. Berdasarkan hasil penelitian, implementasi metode K-Nearest Neighbor (KNN) untuk prediksi karakteristik penghuni Citraland Gama City Kota Medan terbukti mampu membantu proses klasifikasi data penghuni secara lebih cepat dan sistematis. Metode KNN dapat mengelompokkan karakteristik penghuni berdasarkan variabel usia, pekerjaan, tingkat pendapatan, jumlah anggota keluarga, dan tipe hunian. Hasil pengujian menunjukkan bahwa metode KNN menghasilkan tingkat akurasi sebesar 79%, sehingga metode ini cukup baik digunakan untuk memprediksi karakteristik penghuni.
Analysis of Differences Between AI and Human Texts Using the Natural Language Processing Method Dinda Cahyana; VitoReyLukito Sijabat; Mohammad Irfan Fahmi
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/3wqgd409

Abstract

Artificial Intelligence has become increasingly proficient in generating text that mimics human writing, yet existing detection tools remain limited in accuracy and adaptability. Previous studies indicate that systems like Turnitin and GPTZero often perform below 80% accuracy and struggle with paraphrased or advanced AI-generated content. This study addresses that gap by analyzing linguistic differences between AI-generated and human-written texts using Natural Language Processing. A dataset of 487,235 texts (305,797 human-written and 181,438 AI-generated) was processed using TF-IDF vectorization and classified with the Multinomial Naive Bayes algorithm. The model achieved 99.35% accuracy and an F1-score of 0.9948, with balanced performance in detecting both text types. Results show that while AI-generated texts are structurally consistent, they often lack the emotional depth and cultural nuance found in human writing. These findings suggest NLP methods are highly effective in distinguishing between the two, and have practical implications for developing more reliable detection systems to ensure textual authenticity in education, journalism, and digital media monitoring.
BIG DATA ANALYSIS OF RAINFALL USING APACHE SPARK: A CASE STUDY OF INDONESIA Arnold Paulinus Partogi Sinaga; Jhon Nobel Helsingki Turnip; Mohammad Irfan Fahmi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 9 No. 4 (2026): August 2026 (1)
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i4.7078

Abstract

Rainfall is one of the most important climatological parameters that plays a significant role in supporting agriculture, water resource management, and hydrometeorological disaster mitigation in Indonesia. As the volume of meteorological data continues to increase, technologies capable of processing large-scale data efficiently are required. This study aims to analyze rainfall patterns in Indonesia using a Big Data approach by utilizing Apache Spark as the primary data processing framework. The data used in this research consist of daily rainfall data from 34 provinces in Indonesia obtained from the Meteorology, Climatology, and Geophysics Agency (BMKG) in CSV format. This research employs a descriptive quantitative method consisting of data ingestion, data cleaning, data transformation, and descriptive statistical analysis using Apache Spark with PySpark. The analysis was conducted to obtain information regarding the number of valid records, average rainfall, maximum rainfall, and minimum rainfall values for each province. The results indicate that Apache Spark is capable of processing rainfall data in a structured, efficient, and automated manner. Based on the analysis, West Sumatra Province recorded the highest average rainfall at 16.01 mm/day, while Central Sulawesi Province recorded the lowest average rainfall at 0.30 mm/day. In addition, the highest maximum rainfall was observed in Bengkulu Province at 186.4 mm. The use of Spark DataFrame and aggregation functions such as count(), avg(), max(), and min() proved effective in supporting data processing and analysis activities. The findings demonstrate that Apache Spark can serve as an effective solution for large-scale climatological data processing and provide valuable information to support decision-making in agriculture, water resource management, and disaster mitigation in Indonesia.
Co-Authors Adilman Reliance Hia Agustian Gunawan Aida Elda Afriza Andreas Situmorang Arnold Paulinus Partogi Sinaga Berwyn Hulbert Tanadi Besante Singh Daniel Ryan Hamonangan Sitompul Dennis Jusuf Ziegel Dinda Cahyana Elsa Vio Nauli Br Naibaho Evta Indra Jhon Nobel Helsingki Turnip Maikel Felix Ginting Nova Rosalina Siahaan Rizky Syahputra Sitompul Rosita Yolanda Tiffany Roy F. Hasudungan Malau Ruben Ruben Rut Ronauli Hutagaol Saut Parsaoran Tamba Shandy Roland Evansius Sinaga Stiven Hamonangan Sinurat Tajrin Tajrin Unika Nduru VitoReyLukito Sijabat William William