Article Per Year (5 Year)
p-Index From 2021 - 2026
0.947
P-Index
This Author published in this journals
All Journal Jurnal Mantik Journal of Intelligent Decision Support System (IDSS) Jurnal Pengabdian Kepada Masyarakat dan Desa (PASSA) The Journal of Information Technology, Computer Science, and Electrical Engineering
Junaidi Junaidi
Politeknik Negeri Medan
Agriculture, Biological Sciences & Forestry Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Languange, Linguistic, Communication & Media

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Implementation of multi-hop lora network for centralized remote display of running text message based on IoT Morlan Pardede; Elferida Hutajulu; Regina Sirait; Junaidi Junaidi; Arnold Pakpahan
Jurnal Mantik Vol. 7 No. 2 (2023): Agustus: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v7i2.4117

Abstract

Running text is a promotional and information billboard made by LED. It can be programmed by using a computer to display text, images, and animations. Running text makes people interested to read some message because a color of the lights and animation. For wide location such as campuses, airports and many more place, several running texts are needed. It’s difficult to change some message manually one by one. It will spend energy and time. To solve the problem, this research was conducted to create a system to display of messages on three running texts centrally using a multihop LoRa wireless network. Each running text board consists of four P10 panel boards, an ESP 32 as a microcontroller, and a LoRa SX1276 as a sender and receiver. Message setting is done from a computer connected to the Gateway or from an android phone via Telegram bot. The results are LoRa power 10 dBm, distance between nodes can be reached 110 m. The amount of round-trip time (RTT) for point to point is 103 ms and for two hops of 1221 ms. The length of the message that can be sent 256 characters with the character patterns available in the DMD 32 library. This system is very suitable to support areas where internet is not available. The signal emitted by LoRa is Line of sight for achieve maximum coverage. The antenna between the nodes must be installed facing without obstruction
PKM Pelatihan Simulasi Listrik Menggunakan Proteus di SMK Markus 2 Medan Sumatera Utara Henry Toruan; Junaidi; Morlan Pardede; Elferida Hutajulu; Regina Sirait
Jurnal Pengabdian Kepada Masyarakat dan Desa Volume 3, Nomor 2, Januari 2026
Publisher : Politeknik Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51510/passa.v3i2.2807

Abstract

Latar belakang permasalahan SMK Markus 2 Medan yang ditemukan adalah kurang tertariknya para siswa mempelajari kelistrikan karena kurangnya kemampuan guru membuat simulasi rangkaian elektronika serta keterbatasan jumlah infokus. Tujuan kegiatan tim pengabdian Politeknik Negeri Medan di SMK Markus 2 Medan untuk mentransfer pengetahuan menggunakan Proteus membuat simulasi rangkaian elektronika agar para guru dan siswa memiliki pengetahuan dalam membuat simulasi rangkaian dan menambah infokus di sekolah. Pelaksanaan pelatihan dilaksanakan selama 2 hari di SMK Markus 2 dengan menggunakan 20 buah perangkat komputer dengan peserta sebanyak 20 orang terdiri dari guru dan perwakilan siswa dari kelas Teknik Instalasi Tenaga Listrik dan kelas Audio Video di SMK Markus 2 Medan Sumatera Utara. Pada hari pertama, tim pengabdian pada masyarakat menyebarkan kuisioner pada peserta sebelum pelatihan dimulai serta menjelaskan dan membimbing peserta mengoperasikan software Proteus untuk membuat simulasi meliputi pengenalan Proteus, pemahaman fungsi dan menu serta pembuatan simulasi dasar. Pada hari kedua tim membuat simulasi lanjut yang meliputi materi rangkaian listrik kendaraan sepeda motor dan rangkaian lampu berjalan serta menyebarkan kuisioner yang isinya sama dengan yang disebarkan hari pertama pada peserta.  Dari hasil kuisioner yang disebarkan dapat dilihat bahwa para peserta mengalami peningkatan dalam katagori baik dalam pengenalan software simulasi proteus dari 0% menjadi 100%, pemahaman lembar kerja proteus untuk simulasi listrik dari 0% menjadi 60%, penggunaan proteus untuk simulasi listrik 0% menjadi 50%. Partisipasi mitra SMK Markus 2 Medan dalam pelaksanaan kegiatan pelatihan ini sangat antusias dengan mendirikan plang, mempersiapkan ruang praktek komputer sebagai tempat kegiatan pelatihan ini serta berperan aktif sebagai peserta. Setelah selesai kegiatan tim pengabdian menyerahkan proyektor sebagai tanda mata menambah proyektor yang ada dalam menunjang pembelajaran di sekolah. 
Design And Development of a Vehicle Security System Using Vibration Sensors and GPS Based on Arduino Gunawan; Achmad Yani; Junaidi; Zumhari; E Hutajulu; R Sirait
Journal of Information Technology, computer science and Electrical Engineering Vol. 1 No. 3 (2024): October 2024
Publisher : Yayasan Sinergi Multidimensi Kreatif

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61306/jitcse.v1i3.152

Abstract

Incidents of theft and theft of motor vehicles have recently become more and more prevalent. This is suspected by the increase in the number of motorized vehicles every year. The most stolen or stolen types of motor vehicles are two-wheeled vehicles or motorcycles. So the researcher in this case conducted research in the form of designing motor vehicle safety using brittle sensors and GPS (Global Positioning System). The vibration sensor is functional to detect theft by forcibly moving the vehicle. Meanwhile, GPS functions to detect the location of the presence of the motor vehicle so that it can be monitored by the owner of the vehicle. This research focuses on measuring the accuracy and optimization of vibration sensors and GPS so that outputs in the form of simple patents and prototypes of motor vehicle safety devices can be obtained.
Artificial Intelligence-Based Driver Drowsiness Alarm System for Real-Time Monitoring Gunawan; Achmad Yani; Heri Trisna Frianto; Junaidi
Journal of Information Technology, computer science and Electrical Engineering Vol. 3 No. 1 (2026): February-May 2026
Publisher : Yayasan Sinergi Multidimensi Kreatif

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

Abstract

This research aims to design and build a drowsy driver detection alarm that uses Android-based artificial intelligence. Drowsy drivers are one of the factors that cause serious and potentially fatal traffic accidents. Therefore, it is necessary to develop a system that can detect the signs of drowsy drivers and provide timely warnings to prevent accidents. In this study, we implemented artificial intelligence technology to detect signs of drowsy drivers based on data analysis such as eye movements, head position, and driver activity. The system uses sensors and cameras on Android devices to monitor and analyze driver behavior in real-time. The designed system will alert the driver if signs of drowsiness are detected. The alert can be in the form of sound, vibration, or visual display on the Android device's screen. In addition, the system can also record and report drowsy driver detection data to related parties, such as vehicle owners or traffic control centers. The software development method used in this study is the software development lifecycle model (SDLC) with the stages of needs analysis, design, implementation, testing, and maintenance. We also used machine learning techniques to train sleepy driver detection models based on the data collected. The result of this study is a drowsy driver detection alarm system that can be integrated with Android devices. These systems can help prevent traffic accidents caused by drowsy drivers by providing timely and effective alerts.This research aims to design and build a drowsy driver detection alarm that uses Android-based artificial intelligence. Drowsy drivers are one of the factors that cause serious and potentially fatal traffic accidents. Therefore, it is necessary to develop a system that can detect the signs of drowsy drivers and provide timely warnings to prevent accidents. In this study, we implemented artificial intelligence technology to detect signs of drowsy drivers based on data analysis such as eye movements, head position, and driver activity. The system uses sensors and cameras on Android devices to monitor and analyze driver behavior in real-time. The designed system will alert the driver if signs of drowsiness are detected. The alert can be in the form of sound, vibration, or visual display on the Android device's screen. In addition, the system can also record and report drowsy driver detection data to related parties, such as vehicle owners or traffic control centers. The software development method used in this study is the software development lifecycle model (SDLC) with the stages of needs analysis, design, implementation, testing, and maintenance. We also used machine learning techniques to train sleepy driver detection models based on the data collected. The result of this study is a drowsy driver detection alarm system that can be integrated with Android devices. These systems can help prevent traffic accidents caused by drowsy drivers by providing timely and effective alerts.
Computational intelligence for solar photovoltaic power plant monitoring and fault diagnosis: a machine learning approach Regina Sirait; Arnold Pakpahan; Junaidi Junaidi; Reynaldo Pakpahan; Aprima A Matondang
Journal of Intelligent Decision Support System (IDSS) Vol 9 No 2 (2026): June: Intelligent Decision Support System (IDSS)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/idss.v9i2.369

Abstract

Solar photovoltaic (PV) power plants are increasingly deployed in tropical regions such as Indonesia, yet their performance is often degraded by undetected faults including partial shading, dust accumulation, and module mismatch. This study presents a computational intelligence framework for real-time monitoring and fault diagnosis of grid-connected PV systems from a computer science perspective. The framework consists of three main components: (1) a data acquisition module that simulates 12 months of PV system operation (25 kWp capacity) using meteorological data from Medan, Indonesia, generating 8,760 hourly samples of voltage, current, power, irradiance, and temperature; (2) a machine learning-based fault classifier using Random Forest (RF) and Support Vector Machine (SVM) algorithms to distinguish between four fault types (normal operation, partial shading, dust accumulation, and module mismatch) and one healthy state; and (3) a web-based dashboard built with PHP and MySQL for real-time visualization and alerting. Experimental results show that the Random Forest classifier achieves 97.3% accuracy, 95.8% precision, and 96.2% recall, outperforming SVM (91.6% accuracy). The algorithm detects faults within 1.8 seconds of occurrence, enabling rapid operator response. The proposed system is implemented as an open-source prototype and can be deployed on low-cost hardware (Raspberry Pi 4) with an average response time of 1.8 seconds. The framework is validated using tropical climate data from Medan, Indonesia, addressing a gap in existing PV fault diagnosis research. This research contributes a practical, software-based fault diagnosis tool for PV system operators in tropical environments
Co-Authors Achmad Yani Arnold Pakpahan Arnold Pakpahan E Hutajulu Gunawan Gunawan Henry Toruan - Heri Trisna Frianto Hutajulu, Elferida Morlan Pardede - R Sirait Regina Sirait - Reynaldo Pakpahan Zumhari