Claim Missing Document
Check
Articles

Pengenalan Alfabet SIBI Menggunakan Convolutional Neural Network sebagai Media Pembelajaran Bagi Masyarakat Umum Fadhilah, Zahrah; Marpaung, Noveri Lysbetti
Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 2 (2023)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v8i2.5221

Abstract

SIBI is one of the Sign Languages used in Indonesia and has been widely used in the community, especially the school (SLB). Communication limitations of the deaf and speech community cause limited communication with the general public, especially many general public who do not know Sign Language or SIBI. For this reason, this research was conducted in order to become a learning media for the general public in recognizing the SIBI alphabet so that it can support communication with the deaf and speech community. This research was conducted to become a medium that can be used as a learning medium in the introduction of the SIBI alphabet. The method used in this research is CNN. CNN is used because it is a deep learning method that has the most significant results in image recognition. The data used is 2,600 images which are divided into 80% training data and 20% validation data. Training was done ten times by comparing the parameters that produce the best accuracy. The parameters used are batch size and epoch. From ten trials, the best accuracy is obtained using batch size 8 and epoch 50. The best accuracy produced is 85% training accuracy and 87% validation accuracy.
Deep Learning untuk Identifikasi Daun Tanaman Obat Menggunakan Transfer Learning MobileNetV2 Hendri Butar-Butar, Rio Juan; Marpaung, Noveri Lysbetti
Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 2 (2023)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v8i2.5217

Abstract

Medicinal plants are plants used as alternative medicines for healing or preventing various diseases due to their active substances. The utilization of medicinal plants in Indonesia has been widespread among the community since ancient times and is a heritage passed down from ancestors. Medicinal plants have leaf structures that are almost similar between one plant and another, which can lead to confusion for some people and require precision in identifying the leaves of medicinal plants. Incorrect identification can have negative consequences for the users. In recent years, deep learning has been used to identify objects because of its ability to interpret images. This study used a transfer learning method to identify medicinal plants. Transfer learning utilizes a pre-trained model to learn and perform new tasks, making it suitable for smaller datasets. The pre-trained model used in this study is MobileNetV2. MobileNetV2 has a lightweight architecture and high accuracy. Fine-tuning techniques were applied in this study to improve the model's performance. Several experiments were conducted with parameters such as epochs and fine-tuning layers to obtain the best results. The research yielded a training accuracy of 97%, validation accuracy of 96%, and testing accuracy of 93%.
Klasifikasi Jamur Berdasarkan Genus Dengan Menggunakan Metode CNN Rahmadhani, Ummi Sri; Marpaung, Noveri Lysbetti
Jurnal Informatika: Jurnal Pengembangan IT Vol 8, No 2 (2023)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v8i2.5229

Abstract

Mushrooms are plants that do not have true roots and leaves. There are many types of mushrooms that have been identified worldwide, with various shapes, sizes, and colors. Mushrooms have many benefits in the fields of economy, health, and others. One of the benefits of mushrooms is as a food source in Indonesia, but not all types can be consumed. To identify mushroom species, the concepts of Genus and species can be used. The concept of Genus is considered easier because it groups mushroom types based on similar morphological characteristics. Therefore, a model is needed to classify mushrooms based on consumable and toxic genera. The method used in this research is Convolution Neural Network (CNN) due to its good predictive results in image recognition. The model in the research utilizes three convolution layers, three MaxPooling layers, and two dropout layers. The use of dropout aims to reduce overfitting in the model. The research uses a dataset of 1200 images with a training and testing data ratio of 70:30, resulting in 840 training data and 360 testing data. The best accuracy achieved by this model is 89% for training and 82% for validation. Therefore, it can be concluded that the model is able to classify mushrooms based on Genus using the CNN method
Desain Dan Implementasi Inverter Satu Fasa Berbasis Teknologi Mikrokontroler Arduino Uno Suwitno, Suwitno; Aziz, M.; Ali, Nurhalim Dani; Rosma, Iswadi Hasyim; Firdaus, Firdaus; Marpaung, Noveri Lysbetti
JET (Journal of Electrical Technology) Vol 10, No 3 (2025): Edisi Oktober
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v10i3.13158

Abstract

Penelitian ini membahas desain dan implementasi inverter satu fasa berbasis mikrokontroler Arduino dengan teknik modulasi gelombang persegi. Sistem inverter dirancang untuk mengonversi sumber tegangan DC menjadi tegangan AC satu fasa dengan frekuensi 50 Hz. Arduino digunakan sebagai pembangkit sinyal kendali, sedangkan IC IR2110 berfungsi sebagai driver untuk menghubungkan sinyal logika mikro kontroler dengan piranti switching MOSFET pada rangkaian inverter. Untuk meningkatkan kualitas tegangan keluaran, diterapkan rangkaian filter kapasitor pada sisi sekunder transformator guna mereduksi komponen harmonisa yang dihasilkan oleh modulasi gelombang persegi. Pengujian dilakukan dengan variasi beban resistif berupa lampu pijar 15 W, 25 W, dan 40 W untuk mengevaluasi kestabilan tegangan dan bentuk gelombang keluaran inverter. Hasil pengujian menunjukkan bahwa setelah pemasangan kapasitor filter, bentuk gelombang keluaran inverter mendekati sinusoidal dengan tingkat distorsi yang lebih rendah. Tegangan keluaran terukur tanpa beban sebesar 219,8 V dengan frekuensi 50 Hz, sesuai dengan standar system listrik AC. Meskipun terjadi penurunan tegangan saat beban 40W 3,1% seiring peningkatan beban, inverter tetap mampu mempertahankan kinerja yang stabil tanpa distorsi gelombang yang signifikan. Hasil penelitian ini menunjukkan bahwa inverter satu fasa berbasis Arduino dengan modulasi gelombang persegi dan penambahan filter kapasitor dapat digunakan secara efektif untuk aplikasi daya rendah.
Internet Network Monitoring in Oil Palm Irrigation Using MQTT Based on QoS Parameters Edy Ervianto; Noveri Lysbetti Marpaung; Karin Dwi Purnomo; Khoirul Azmi; Sakti Hutabarat; Rahyul Amri; Linna Oktaviana Sari; Ika Mayla Sari
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 2 (2026): Juni 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.2.2026.245-260

Abstract

Oil palm plantations require continuous and reliable monitoring to ensure efficient irrigation, yet many farmers still depend on manual watering methods that are time-consuming and inconsistent. To address this issue, this study develops an Internet of Things (IoT)-based irrigation monitoring system using the MQTT communication protocol to support real-time data delivery and automated control. The system integrates ESP32 microcontrollers, soil moisture and environmental sensors, HiveMQ Cloud as the MQTT broker, and Telegram Bot notifications. The research was conducted on a 27 m × 70 m oil palm plantation consisting of 24 trees. System testing was performed over seven days with two irrigation sessions daily, during which sensor data transmission and notification timestamps were recorded. QoS parameters including throughput, packet loss, delay, and jitter were analyzed using Wireshark. The results show that sensor data and irrigation notifications were consistently delivered within 3–5 seconds, demonstrating stable real-time communication. QoS evaluation indicates 0% packet loss, an average delay of 180 ms, and an average jitter of 0.17 ms, with an overall QoS index of 3.02, classified as “Satisfied.” These findings confirm that MQTT provides reliable communication performance in plantation environments and effectively supports automated irrigation monitoring for improving agricultural efficiency.
Pencegahan Kegagalan Produksi Ikan Bilis Asam Masyarakat Nelayan Akibat Musim Hujan Di Desa Bunsur Apit Kabupaten Siak Rahyul Amri; Noveri Lysbetti Marpaung; Edy Ervianto; Nurhalim Nurhalim
BATOBO: Jurnal Pengabdian Kepada Masyarakat Vol 1 No 1: BATOBO: Juni 2023
Publisher : Jurusan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31258/batobo.1.1.36-48

Abstract

Pengabdian kepada mayarakat ini dilaksanakan di Desa Bunsur Kecamatan Sungai Apit Kabupaten Siak Propinsi Riau dengan khalayak sasarannya masyarakat nelayan desa tersebut. Sektor pertanian dan nelayan merupakan profesi yang sangat dominan sebagai sumber kehidupan di desa ini. Berdasarkan informasi kepala desa, desa ini terkenal sebagai penghasil ikan Bilis Asam. Berdasarkan hasil survei harga jual ikan ini di Pasar Panam Kota Pekanbaru berkisar Rp. 125 ribu per kg. Harga ini menunjukkan nilai keekonomian yang tinggi dan sangat menjanjikan bagi kehidupan masyarakat nelayan di Desa Bunsur ini. Dari informasi para nelayan, pada musim hujan semua hasil tangkapan ikan ini tidak dapat dijual bahkan dibuang begitu saja karena membusuk akhibat tidak bisa dikeringkan karena tidak ada cahaya matahari. Keadaan ini dapat diatasi dengan membuat sebuah tempat pengeringan khusus dengan teknik rekayasa cahaya lampu dalam sebuah ruangan yang dirancang sedemikian rupa. Ruangan ini akan dapat menyelamatkan gagal produksi ikan Bilis Asam masyarakat nelayan di Desa Bunsur dengan demikian kehidupan mayarakat nelayan dapat lebih stabil di setiap musim, baik musim hujan maupun musim panas. Pengeringan ikan yang akan dirancang adalah tipe pengeringan mekanis dengan rekayasa cahaya lampu. Pengeringan ikan ini akan dibuat transparan yang dikelilingi akrilik bening dan tembus cahaya. Penjemuran tembus cahaya ini bertujuan agar di musim panas masyarakat juga tetap menggunakan penjemuran ini.  Penjemuran ini akan dipasang sensor sehingga pada saat hujan atau panas pengeringan tetap berfungsi dengan baik dan otomatis. Sistem ini dirancang agar nelayan tidak perlu kuatir ikannya terkena hujan atau tidak kena panas karena sudah beroperasi secara otomatis
Perancangan Aplikasi Pengelolaan Properti Berbasis Website Cut Muthia Ramadhani; Noveri Lysbetti Marpaung; Sakti Hutabarat; Rahyul Amri; Edy Ervianto; Nurhalim; Suwitno
CSRID (Computer Science Research and Its Development Journal) Vol. 18 No. 1 (2026): Februari 2026
Publisher : LPPM Universitas Potensi Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22303/csrid-.18.1.2026.32-45

Abstract

This study discusses the development of a web-based property management system designed to meet the needs of two types of users: administrators and tenants. The system was developed using the Research and Development (R&D) method with the Rational Unified Process (RUP) approach and implements the Model-View-Controller (MVC) architectural pattern. The application was built using the Laravel framework and MySQL database. It consists of two main interfaces: an administrator interface that includes a landing page, login page, and dashboard, and a tenant interface that is designed to be user-friendly. The features available in the administrator interface include property management, tenant data management, financial management, complaint handling, and user account management, all aimed at improving operational efficiency. System testing was conducted using SonarQube to evaluate code quality, PageSpeed Insights to assess application performance, and the User Experience Questionnaire (UEQ) to measure user experience. The test results indicate that the application meets various important quality aspects, including functional suitability, reliability, maintainability, performance efficiency, portability, compatibility, security, and usability. Despite the system’s many advantages, several areas for improvement remain. Suggested enhancements include integration with WhatsApp for better communication, a notification system to keep users updated, the addition of diverse payment options, and optimization of the user interface for a more responsive and attractive design. Therefore, the developed application is expected to improve the efficiency of property management and enhance user satisfaction, particularly for administrators managing property units, tenant data, finances, complaints, and user accounts.  
Perancangan Pembangkit Listrik Tenaga Surya (PLTS) Untuk Supply Aerator pada Kolam Ikan dengan Sistem Bioflok Suwitno Suwitno1; Muhammad Nasir Harahap; Nurhalim Dani Ali; Iswadi Hasyim Rosma; Fri Murdiya; Firdaus Firdaus; Noveri Lysbetti Marpaung
JET (Journal of Electrical Technology) Vol 10, No 2 (2025): Edisi Juni
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v10i2.12215

Abstract

Penelitian ini membahas perancangan Pembangkit Listrik Tenaga Surya (PLTS) untuk kolam ikan dengan sistem bioflok di Kampung Pangan Madani. Terdapat lima kolam ikan lele berkapasitas 1.000 ekor/kolam dan satu kolam ikan gurame dengan 250 ekor/kolam, yang memerlukan konsumsi energi listrik sebesar 6,6 kWh per hari. Analisis dilakukan menggunakan simulasi perangkat lunak PVSyst pada tiga topologi sistem PLTS, yakni On-grid, Off-grid, dan Hybrid. Hasil simulasi menunjukkan bahwa PLTS On-grid dengan 4 panel 250 Wp menghasilkan 1.325 kWh/tahun dan dinyatakan layak secara ekonomi dengan nilai COE Rp.1.404,00, NPV Rp.561.442 dalam 11 tahun, Shadow Price 1,01 per 1% perubahan, PI sebesar 1,49 dan DPP 11,97 tahun. Sementara itu, PLTS Off-grid dengan 10 panel 250 Wp dan 8 baterai 180 Ah menghasilkan 3.084 kWh/tahun, namun dinyatakan tidak layak dengan nilai COE Rp.2.951,84, NPV Rp.-86.075,46, PI 0,99 dan DPP 21 tahun. Pada analisa ekonomi dengan Shadow Price PLTS Off-Grid dengan NPV pada tahun ke-21 di peroleh hasil 0,94 per 1% perubahan. Adapun PLTS Hybrid dengan 5 panel 250 Wp dan 1 baterai menghasilkan 1.558 kWh/tahun dan dinyatakan layak dengan nilai COE Rp.1.799,50, NPV Rp.1.370.980 dalam 13 tahun,Shadow Price 0,99 per 1 % perubahan, PI 1,35,dan DPP 13,95 tahun. Penelitian ini menunjukkan bahwa sistem PLTS On-grid dan Hybrid lebih layak diterapkan untuk memenuhi kebutuhan energi listrik kolam ikan berbasis bioflok
Desain Dan Implementasi Inverter Satu Fasa Berbasis Teknologi Mikrokontroler Arduino Uno Suwitno Suwitno; M. Aziz; Nurhalim Dani Ali; Iswadi Hasyim Rosma; Firdaus Firdaus; Noveri Lysbetti Marpaung
JET (Journal of Electrical Technology) Vol 10, No 3 (2025): Edisi Oktober
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/jet.v10i3.13158

Abstract

Penelitian ini membahas desain dan implementasi inverter satu fasa berbasis mikrokontroler Arduino dengan teknik modulasi gelombang persegi. Sistem inverter dirancang untuk mengonversi sumber tegangan DC menjadi tegangan AC satu fasa dengan frekuensi 50 Hz. Arduino digunakan sebagai pembangkit sinyal kendali, sedangkan IC IR2110 berfungsi sebagai driver untuk menghubungkan sinyal logika mikro kontroler dengan piranti switching MOSFET pada rangkaian inverter. Untuk meningkatkan kualitas tegangan keluaran, diterapkan rangkaian filter kapasitor pada sisi sekunder transformator guna mereduksi komponen harmonisa yang dihasilkan oleh modulasi gelombang persegi. Pengujian dilakukan dengan variasi beban resistif berupa lampu pijar 15 W, 25 W, dan 40 W untuk mengevaluasi kestabilan tegangan dan bentuk gelombang keluaran inverter. Hasil pengujian menunjukkan bahwa setelah pemasangan kapasitor filter, bentuk gelombang keluaran inverter mendekati sinusoidal dengan tingkat distorsi yang lebih rendah. Tegangan keluaran terukur tanpa beban sebesar 219,8 V dengan frekuensi 50 Hz, sesuai dengan standar system listrik AC. Meskipun terjadi penurunan tegangan saat beban 40W 3,1% seiring peningkatan beban, inverter tetap mampu mempertahankan kinerja yang stabil tanpa distorsi gelombang yang signifikan. Hasil penelitian ini menunjukkan bahwa inverter satu fasa berbasis Arduino dengan modulasi gelombang persegi dan penambahan filter kapasitor dapat digunakan secara efektif untuk aplikasi daya rendah.
NETWORK APPLICATION IN OIL PALM SEEDLING WATERING MONITORING SYSTEM USING ESP32 Anang Arif Hibaturrahman; Noveri Lysbetti Marpaung; Sakti Hutabarat; Edy Ervianto; Yogie Rinaldy Ginting; Nurhalim; Rahyul Amri
SOSIOEDUKASI Vol 15 No 2 (2026): SOSIOEDUKASI : JURNAL ILMIAH ILMU PENDIDIKAN DAN SOSIAL
Publisher : Fakultas Keguruan Dan Ilmu Pendidikan Universaitas PGRI Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36526/sosioedukasi.v15i2.8369

Abstract

This research aims to design and implement an Internet of Things (IoT) based monitoring and control system for watering and fertilizing oil palm seedlings using the ESP32 microcontroller. The system was developed to overcome the weaknesses of manual watering methods which still rely on estimated soil conditions so that they are less efficient and risk inhibiting seedling growth. The system utilizes a soil moisture sensor to detect soil moisture and a DHT22 sensor to monitor temperature and air humidity in real-time. The data from the sensor readings is sent through the internet network and displayed on the Telegram application as a medium for remote monitoring and control. The system was tested for 14 days under morning and evening watering conditions with Quality of Service (QoS) analysis using throughput, delay, packet loss, and jitter parameters. The results of the study show that the system successfully works automatically and is able to monitor the environmental conditions of the seedlings in real-time. The average value of the QoS index in morning watering was 2.46 with a quality percentage of 61.50%, while afternoon watering was 2.39 with a quality percentage of 59.75%, both of which are in the medium category. The packet loss parameter shows excellent performance with packet loss close to zero, while delay and jitter are in the good to good category. However, the throughput parameters are still relatively low, so it is necessary to improve network quality for system optimization. Overall, the system is designed to support the monitoring and control process of watering oil palm seedlings automatically with a fairly stable data communication quality.
Co-Authors Abu Yazid Raisal Afrianti, Dedeh Kurnia Aielsa Naomi Athaya Akbar Hanafi Siregar Ali, Nurhalim Dani Alwi, Rangga Aminuyati Amirul Latief Azzmi Amzah, Ridho Al Anang Arif Hibaturrahman Andhi, Rahmat Rizal Anhar Anhar Anhar Antonius Rajagukguk Antonius Rajagukguk, Antonius Athaya, Aielsa Naomi Ayunda Widia Kusuma Aziz, M. Azwir Rezari Celfin Cut Muthia Ramadhani Dani Ali, Nurhalim Dedy Nurahmadin Demiza, Khosfikra Desty, Hygiana Prima Dian Yayan Sukma, Dian Yayan Dwi Nur Indah Sari, Dwi Nur Indah Edy Ervianto Eka Novvala Dewi Eko Marjan Elfrida Nova Sartika Elirza Halena Elizabeth, Ivena Era Yohana Oktaviani Silalahi Esther Joan Ruthmika Sianturi Fadhilah, Zahrah Fadli Julianto Erga Fahmi, Ziddan Fakhriyah, Salsabila Febrizal Ujang Feranita Feranita Ferdian, Fhinta Syahila Feri Candra Fiki Sanora Firdaus Firdaus Firdaus Firdaus Fitria Sari Fri Murdiya, Fri Ginting, Yogie Rinaldy Gultom, Marlina Octa Venita Guspi Candra Hadiwandra, T Yudi Harahap, Muhammad Nasir Hassan, Rohana Hendri Butar-Butar, Rio Juan Henti Nuraini Napitupulu Hutabalian, Raja Hizkia Hygiana Prima Desty Ibrahim, Sajid Ika Mayla Sari Illahi, Hayatul Izzi, Mambaul Jesslin Halim Karin Dwi Purnomo Kelvin Rainey Salim Khoirul Azmi Linna Oktaviana Sari Lutfia, Anisa M. Aziz Mahindra, Syaputra Dwi Mar Qosim Marbun, Andreas Marsaulina Marpaung Maulana, Farhan Muhammad Ilham Muhammad Nasir Harahap Muhammad, Satyo Mulia Sakti Rambe, Mulia Sakti Ningsi, Rani Fitri Arya Nofri Afandi Noviana, Eka Rani Nuraini, Dwi Nur Indah Sari Nurhalim Nurhalim Dani Ali Nurhalim Nurhalim Nurhalim Nurhalim, Nurhalim nursaldila, nursaldila Nurul Laili Nurul Whusto Octavia, Bunga Okpi Pranata Reskha Okta Rivaldi Padang, Junelka Lisendra Pasaribu, Dewi Fitri Novita Pratama, Muhammad Yogi Purnomo, Karin Dwi Putri, Katya Blinda R., Antonius Rahmadhani, Ummi Sri Rahyul Amri Rajagukguk, Jelita Mianarta Ramadhan, Ashry Ramadhan, Riyan Putra Ramadhan, Roza Syahputra Raudah, Aulia Reski Lasari Ridho Al Amzah Rio Juan Hendri Butar Butar Rio Juan Hendri Butar-Butar Rizka Dwi Saputri Rosiki, Muhammad Habib Rosma, Iswadi Hasyim Sakti Hutabarat Sakti Hutabarat Sakti Hutabarat Salhazan Nasution Saputra, Muhammad Hakim Saputri, Rizka Dwi Septiyandi Kurniawan Settian Dwi Cahaya Siagian , Ruben Cornelius Siahaan, Chandro Nainggolan Sihombing, Taruli Devi Siregar, Albert Timbul Siregar, Vivi Devina Siti Zubaidah Sofinanda Sari Solly Aryza Surya Sahri Ramadhan Suwitno Suwitno Suwitno, Suwitno Suwitno Suwitno1 Suwitno1, Suwitno Ummi Sri Rahmadhani Vadri, Yasminne R.A.S Valendino, Muhammad Wakhidah Rohayati Wijaya, Puri Yasminne R.A.S Vadri Yoga Pratama Yohanes, Edwin Yudha Hadi Martha Zahrah Fadhilah