Article Per Year (5 Year)
p-Index From 2021 - 2026
1.452
P-Index
This Author published in this journals
All Journal Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika Jurnal Teknologi dan Sistem Komputer Indonesian Journal of Artificial Intelligence and Data Mining JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Teknologi Terpadu JTIULM (Jurnal Teknologi Informasi Universitas Lambung Mangkurat) Tematik : Jurnal Teknologi Informasi Komunikasi JITEL (Jurnal Ilmiah Telekomunikasi, Elektronika, dan Listrik Tenaga)
Martin Clinton Tosima Manullang
Institut Teknologi Sumatera
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Automatic Gate for Body Temperature Check and Masks Wearing Compliance Using an Embedded System and Deep Learning Rahman Indra Kesuma; Rivaldo Fernandes; Martin Clinton Tosima Manullang
Khazanah Informatika Vol. 8 No. 1 April 2022
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v8i1.15205

Abstract

A new coronavirus variant known as n-Cov has emerged with a fast transmission rate. The World Health Organization (WHO) has declared the related disease or COVID-19 as a global pandemic that requires special handling. Many parties have shown efforts to reduce virus transmission by implementing health protocols and adapting a new normal lifestyle. Implementation of the health protocol creates new problems, especially in the health check at the main entrance. The officers in charge of measuring body temperature are at risk of getting infected by COVID. Such a measurement is prone to errors. This study proposed a solution to build an automatic gate system that worked based on the new normal health protocol. The system utilizes the MLX90614 contactless temperature sensor to probe body temperature. It applies deep learning implementing the Convolutional Neural Network (CNN) algorithm with the MobileNetV2 architecture as a determinant of the conditions of wearing face masks. The system is equipped with an IoT-based remote controller to control the gate. Experimental results prove that the system works well. Temperature measurement takes a response time of 20 seconds for each user with 99% accuracy for the sensor and masks classification model.
Pengembangan Pedal Efek Gitar Elektrik Menggunakan Arduino Martin Clinton Tosima Manullang; R. Rizal Isnanto; Eko Didik Widianto
Jurnal Teknologi dan Sistem Komputer Volume 3, Nomor 1, Tahun 2015 (Januari 2015)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (709.119 KB)

Abstract

The guitar has become common entertainment show at the moment. Devices Arduino controller board is present as a central processing for a variety of processing requirements, one of which is processing the sound. So the goal is achieved from this study was to test the Arduino as a controller device that is used in the effect processing. This study uses the waterfall method of development. Steps being taken begins with identifying needs and then proceed with the process of designing both the hardware and software. Then proceed with the testing design. In the testing phase used 3 kinds of testing, those are hardware testing, test using the software, and testing using respondents. The test results showed that the Arduino can be used as a controller of guitar sound processing with two inputs and outputs. It was also found that the true bypass pedal interface can change the path of the guitar input to be routed directly to the output. Other interfaces available on the system is also functioning as it should and can set values that affect the processing of voice. Based on the test results with the respondents, producing a sound that is quite good, has a full feature, and quite easy to operate.
Implementasi Penghitung Laju Respirasi pada Sistem Polisomnografi menggunakan Mikrofon dan Arduino Nano Martin Clinton Tosima Manullang; Nova Resfita
Jurnal Teknologi Terpadu Vol. 7 No. 1: Juli, 2021
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v7i1.295

Abstract

Sleep apnea is a severe sleep disorder leading to severe threats such as heart attacks, strokes, diabetes, kidney failure, hypertension, etc. Not only is the diagnosis of sleep apnea a challenging measure, but it also requires a high cost of equipment, the limitations of available tools, and becomes a complicated diagnosis operated personally at home. Using the microphone embedded in the Arduino Nano, a system to measure the respiratory rate develops as a minor part of the sleep apnea diagnostic system using polysomnography. A filtering system is attached to eliminate noise and environmental consequences around the observation site. This prototype evaluates by comparing the output value with the manual calculation of the respiratory rate. Of the trials executed, the achieved system accuracy in counting the respiratory rate is above 93%, meaning that this prototype system is ideal as a method of measuring the respiratory rate.
Implementation of AD8232 ECG Signal Classification Using Peak Detection Method For Determining RST Point Martin Clinton Tosima Manullang; Jonathan Simanjuntak; Ahmad Luky Ramdani
Indonesian Journal of Artificial Intelligence and Data Mining Vol 2, No 2 (2019): September 2019
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (611.711 KB) | DOI: 10.24014/ijaidm.v2i2.7593

Abstract

The medical world, especially those related to diseases and management of the heart uses ECG as a measurement tool. ECG has important points determined based on predetermined characteristics. The point is PQRST, where three of them are used as research objects in this paper. AD8232 is used as a research medium where the RST points must be determined in the AD8232 plot results by first determining the R points based on the highest peak. The results obtained were satisfactory wherein from 10 ECG graphic samples, 9 of them obtained RST point measurements which tended to be similar to conventional ECG measurements using millimeter paper as plotting media. Accuracy values reaching more than 90% indicate the reliability of the implementation results.
PURWARUPA PENYIRAMAN OTOMATIS DENGAN ARSITEKTUR MQTT DAN LOGIKA FUZZY SUGENO UNTUK MENINGKATKAN KEEFEKTIFAN MANAJEMEN PENYIRAMAN TANAMAN (STUDI KASUS : ITERA) Muhamad Arwin Wijaya; Raidah Hanifah; Martin Clinton Tosima Manullang
Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM) Vol. 5 No. 2 (2020)
Publisher : Fakultas Teknik Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/jtiulm.v5i2.55

Abstract

ITERA merupakan kampus dengan slogan smart, friendly and forest campus. Kampus hijau (forest campus) dapat diwujudkan dengan melakukan penyiraman secara rutin pada tanaman. Ketika penyiraman tanaman tersebut tidak mencukupi maka tanaman akan layu dan mati, namun air yang berlebihan juga menyebabkan tanaman tidak dapat tumbuh karena terjadi pembusukan pada akar tanaman. Sistem penyiraman otomatis yang dapat memantau kondisi lingkungan tanaman dengan menggunakan protokol MQTT dapat dirancang sebagai sistem yang dapat memantau kondisi lingkungan tanaman secara jarak jauh dan waktu nyata. Sistem ini dibuat menggunakan sensor DHT11 yang berfungsi untuk membaca suhu dan juga sensor YL-69 yang berfungsi untuk membaca kelembaban tanah. DHT11 membaca suhu dengan nilai antara 0 – 50 C dengan rata-rata nilai error 2.22 %. Semakin tinggi nilai output sensor suhu maka suhu akan semakin panas, apabila nilai output sensor suhu semakin rendah maka suhu akan semakin dingin. Untuk sensor YL-69 dapat membaca nilai dari kelembaban tanah yang memiliki rentang antara 0 – 1023 dengan rata-rata nilai error 11.09%. Semakin tinggi nilai output sensor kelem- bapan tanah maka kondisi tanah akan semakin kering, apabila nilai output sensor kelembaban tanah semakin rendah maka kondisi tanah semakin lembap. Sensor tersebut dikirim menuju server oleh mikrokontroler ESP32s. Pengiriman data menggunakan modul Wi-Fi ke server Node-RED. Data dari hasil pembacaan sensor diolah dengan metode fuzzy logic Sugeno untuk mendapatkan keluaran jenis penyiraman memiliki nilai rata-rata error 0.573728 %, semua data pada server ditampilkan pada web server dashboard Node-RED dalam bentuk teks, grafik dan juga kondisi waktu nyata.
Pendeteksian Pelanggaran Pada Penyebrangan Jalan Menggunakan Single-Shot Detector Pada ESP32 Novaldi, Fahri; Amrulloh, Iqbal; Wisesa, I Wayan Wiprayoga; Manullang, Martin Clinton Tosima
TEMATIK Vol 9 No 2 (2022): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2022
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v9i2.997

Abstract

Tingginya jumlah kendaraan bermotor dan pertumbuhannya di kota-kota besar, serta tingginya angka pelanggaran membuat identifikasi pelanggaran terhadap pengendara kendaraan bermotor menjadi sulit, terutama dalam hal pengendara yang berhenti di marka persimpangan jalan (zebra cross). Pemanfaatan teknologi computer vision diharapkan dapat membantu mengidentifikasi pelanggaran dengan mengenali objek berupa kendaraan bermotor yang terdapat pada area visual yang tertangkap kamera. Sistem menggunakan metode pendeteksi single-shot detector dari model yang dilatih dan diimplementasikan pada perangkat keras ESP32. Sistem yang dikembangkan tidak hanya berupa perangkat keras tetapi juga perangkat lunak antarmuka yang dapat digunakan untuk mengkonfigurasi dan menentukan region yang diinginkan. Dua macam pengujian dilakukan, empat pengujian dalam skenario real time dan 20 pengujian secara offline menggunakan dataset Pedestrian Traffic Light. Seluruh keadaan pada skenario real-time dapat dideteksi dengan tepat. Sementara itu, eksperimen offline menggunakan dataset dari Dataset Pedestrian Traffic Light menghasilkan akurasi 96,78%.
Adapting remote photoplethysmography for Indonesian subjects: an examination of diverse rPPG techniques Aprini, Istighfariza; Manullang, Martin Clinton Tosima
JITEL (Jurnal Ilmiah Telekomunikasi, Elektronika, dan Listrik Tenaga) Vol. 3 No. 3: September 2023
Publisher : Jurusan Teknik Elektro, Politeknik Negeri Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35313/jitel.v3.i3.2023.165-180

Abstract

Vital sign measurements are essential in intensive care patients, such as in the ICU or emergency department, and also for newborns or prenatal babies. The duty nurse usually monitors these vital signs by manually writing down the patient's condition on a large piece of paper in front of the patient's room. The lack of nurses can hinder the process of monitoring patient vital signs. However, since the COVID-19 pandemic, people have limited contact with their surroundings, making measuring vital signs with contact uncomfortable and unhygienic. The typical non-contact method for measuring heart rate is the remote photoplethysmography (rPPG) technique. In this study, we proposed to assess the performance of various rPPG algorithms on the Indonesian subjects dataset. The algorithms used are CHROM, GREEN, ICA, LGI, PBV, PCA, and POS on 70 pieces of data. Based on the test results with three types of evaluation metrics, namely MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and Bland Altman, it is found that the measurement results with the best performance POS algorithm with a low prediction error rate with the resulting MAE value of 2.59 and RMSE of 4.65.
Comparative Analysis of CNN, Transformers, and Traditional ML for Classifying Online Gambling Spam Comments in Indonesian Manullang, Martin Clinton Tosima; Rakhman, Arkham Zahri; Tantriawan, Hartanto; Setiawan, Andika
Journal of Applied Informatics and Computing Vol. 9 No. 3 (2025): June 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i3.9468

Abstract

The rise of user-generated content on social media and live-streaming platforms has intensified the spread of spam, particularly online gambling (Judi Online) promotions, which remain prevalent in Indonesian comment sections. This study investigates the effectiveness of various machine learning (ML) and deep learning (DL) approaches in classifying such spam content in Bahasa Indonesia. We compare five models: Support Vector Machine (SVM), Random Forest (RF), a CNN-based model, IndoBERT, and a custom lightweight transformer model named Wordformer. While IndoBERT achieves the highest performance across all metrics, it comes with high computational demands. Wordformer, in contrast, delivers a strong balance between accuracy and efficiency, outperforming traditional models while being significantly more lightweight than IndoBERT. Wordformer achieved 0.9975 accuracy and macro F1-score, surpassing SVM (0.9578) and Random Forest (0.9729), while maintaining a significantly smaller model size and fewer multiply-add operations. An extensive ablation study further explores the architectural and training design choices that influence Wordformer’s performance. The findings suggest that lightweight transformer models can offer practical, scalable solutions for spam detection in low-resource language settings without the need for large pretrained backbones.
From Speech to Summary: A Pipeline-Based Evaluation of Whisper and Transformer Models for Indonesian Dialogue Summarization Manullang, Martin Clinton Tosima; Yulita, Winda; Kartagama, Fathan Andi; Putra, A. Edwin Krisandika
Journal of Applied Informatics and Computing Vol. 10 No. 1 (2026): February 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i1.11826

Abstract

The rapid increase in online meetings has produced massive amounts of undocumented spoken content, creating a practical need for automatic summarization. For Indonesian, this task is hindered by a dual-faceted resource scarcity and a lack of foundational benchmarks for pipeline components. This paper addresses this gap by creating a new synthetic conversational dataset for Indonesian and conducting two systematic, discrete benchmarks to identify the optimal components for an end-to-end pipeline. First, we evaluated six Whisper ASR model variants (from tiny to turbo) and found a clear, non-obvious winner: the turbo (distil-large-v2) model was not only the most accurate (7.97% WER) but also one of the fastest (1.25s inference), breaking the expected cost-accuracy trade-off. Second, we benchmarked 13 zero-shot summarization models on gold-standard transcripts, which revealed a critical divergence between lexical and semantic performance. Indonesian-specific models excelled at lexical overlap (ROUGE-1: 17.09 for cahya/t5-base...), while the multilingual google/long-t5-tglobal-base model was the clear semantic winner (BERTScore F1: 67.09).
Analisis perbandingan Region of Interest untuk pengukuran frekuensi denyut nadi secara non-kontak menggunakan algoritma POS pada citra wajah Ardoni Yeriko Rifana Gultom; Martin Clinton Tosima Manullang
JITEL (Jurnal Ilmiah Telekomunikasi, Elektronika, dan Listrik Tenaga) Vol. 6 No. 2: July 2026
Publisher : Jurusan Teknik Elektro, Politeknik Negeri Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35313/jitel.v6.i2.2026.113-128

Abstract

Pengukuran frekuensi denyut nadi (FDN) merupakan indikator penting dalam pemantauan kesehatan kardiovaskular. Metode konvensional berbasis kontak, seperti pulse oximeter, memiliki keterbatasan dalam hal kenyamanan dan potensi risiko infeksi. Teknologi remote photoplethysmography (rPPG) berbasis citra wajah menawarkan pendekatan non-kontak yang lebih aman dan praktis, namun performanya sangat dipengaruhi oleh pemilihan Region of Interest (ROI). Meskipun algoritma Plane Orthogonal to Skin (POS) terbukti efektif dalam ekstraksi sinyal rPPG, belum ada studi yang secara khusus membandingkan performa berbagai ROI dengan algoritma ini. Penelitian ini mengevaluasi tujuh ROI (dahi, pipi kanan, pipi kiri, hidung, mulut, nasion, dan dagu) untuk menentukan ROI terbaik dalam estimasi FDN menggunakan algoritma POS. Dengan menggukanan dataset PURE sinyal RGB dari masing-masing ROI diproses dengan POS dan bandpass filter, lalu dianalisis menggunakan metode peak detection. Hasil menunjukkan bahwa ROI hidung memberikan estimasi FDN paling akurat dengan MAE 6,86 dan RMSE 11,71, serta performa yang stabil dalam berbagai kondisi gerakan. Sistem berbasis Flask yang dikembangkan mampu melakukan estimasi secara real-time dengan latensi rendah sekitar 2 detik, lebih cepat dibandingkan pulse oximeter yang membutuhkan waktu 4-7 detik. Selain itu, akurasi sistem sangat mendekati hasil pengukuran oximeter, sehingga menunjukkan potensinya untuk digunakan dalam pemantauan kesehatan non-kontak secara efisien dan andal.
Co-Authors Amrulloh, Iqbal Andika Setiawan, Andika Aprini, Istighfariza Ardoni Yeriko Rifana Gultom Eko Didik Widianto Hartanto Tantriawan I Wayan Wiprayoga Wisesa Jonathan Simanjuntak Kartagama, Fathan Andi Muhamad Arwin Wijaya Nova Resfita Novaldi, Fahri Putra, A. Edwin Krisandika R Rizal Isnanto Rahman Indra Kesuma Raidah Hanifah Rakhman, Arkham Zahri Ramdani, Ahmad Luky Rivaldo Fernandes Yulita, Winda