Claim Missing Document
Check
Articles

Found 18 Documents
Search

The Performance of EEG-P300 Classification using Backpropagation Neural Networks Arjon Turnip; Demi Soetraprawata
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 4, No 2 (2013)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.mev.2013.v4.81-88

Abstract

Electroencephalogram (EEG) recordings signal provide an important function of brain-computer communication, but the accuracy of their classification is very limited in unforeseeable signal variations relating to artifacts. In this paper, we propose a classification method entailing time-series EEG-P300 signals using backpropagation neural networks to predict the qualitative properties of a subject’s mental tasks by extracting useful information from the highly multivariate non-invasive recordings of brain activity. To test the improvement in the EEG-P300 classification performance (i.e., classification accuracy and transfer rate) with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis (BLDA). Finally, the result of the experiment showed that the average of the classification accuracy was 97% and the maximum improvement of the average transfer rate is 42.4%, indicating the considerable potential of the using of EEG-P300 for the continuous classification of mental tasks.
Failure assessment in lithium-ion battery packs in electric vehicles using the failure modes and effects analysis (FMEA) approach Rizky Cahya Kirana; Nicco Avinta Purwanto; Nadana Ayzah Azis; Endra Joelianto; Sigit Puji Santosa; Bentang Arief Budiman; Le Hoa Nguyen; Arjon Turnip
Journal of Mechatronics, Electrical Power, and Vehicular Technology Vol 14, No 1 (2023)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.mev.2023.v14.94-104

Abstract

The use of batteries in electric cars comes with inherent risks. As the crucial component of these vehicles, batteries must possess a highly dependable safety system to ensure the safety of users. To establish such a reliable safety system, a comprehensive analysis of potential battery failures is carried out. This research examines various failure modes and their effects, investigates the causes behind them, and quantifies the associated risks. The failure modes and effect analysis (FMEA) method is employed to classify these failures based on priority numbers. By studying 28 accident reports involving electric vehicles, data is collected to identify potential failure modes and evaluate their risks. The results obtained from the FMEA assessment are used to propose safety measures, considering the importance of the potential failure modes as indicated by their risk priority number (RPN). The design incorporates safeguards against mechanical stress, external short circuits, and thermal runaway incidents. The findings of this study enhance our understanding of electric vehicle (EV) battery safety and offer valuable insights to EV manufacturers, regulators, and policymakers, aiding them in the development of safer and more reliable electric vehicles.
Prototype of Portable Heart Monitoring System using BITalino SITOMPUL, ERWIN; SUHARTOMO, ANTONIUS; DARMAWAN, FARHAN; SYAFEI, NENDI SUHENDI; TURNIP, ARJON
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 11, No 1: Published January 2023
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v11i1.31

Abstract

ABSTRAKJantung adalah organ vital yang menuntut perhatian khusus, terutama untuk orang dengan resiko serangan jantung. Bagi orang kategori ini, diperlukan detektor detak jantung yang bekerja secara kontinu dan real-time yang dapat mendeteksi adanya gangguan jantung secara dini. Pada penelitian ini, penulis mengajukan prototipe sistem monitoring jantung portable (PSMJP) dengan menggunakan modul bio-signal BITalino. Hasil pengukuran diproses pada perangkat komputer yang terhubung dengan BITalino melalui transmisi Bluetooth. Suatu program pemroses sinyal dirancang dengan menggunakan Algorithma Hamilton. Tingkat keberhasilan deteksi pada pengujian terhadap sampel EKG mentah dan pengukuran EKG mentah adalah 100%. PSMJP diujikan kepada 15 naracoba untuk kondisi duduk dan kondisi berjalan. PSMJP berfungsi baik pada 29 dari 30 pengukuran, dimana sinyal elektrik dari jantung terbukti dapat diproses dan memberikan hasil akhir berupa fitur-fitur gelombang detak jantung dan laju detak jantung.Kata kunci: denyut jantung, algoritma Hamilton, BITalino, EKG ABSTRACTThe heart is a vital organ that requires special attention, especially for people with heart attack risk. For people of this category, a heart rate detector that works continuously and in real-time is needed so that heart problems can be detected. In this study, the authors proposed a prototype of a portable heart monitoring system (PPHMS) using the BITalino bio-signal module. The measurement results are processed on a computer device connected to BITalino via Bluetooth transmission. A signal processing program was designed using Hamilton Algorithm. The detection success rate on testing for a raw ECG sample and raw ECG measurement was 100 %. PPHMS was tested on 15 subjects for sitting conditions and walking conditions. PPHMS works well in 29 of the 30 measurements, where electrical signals from the heart are proven to be successfully processed. The final results in the form of heart wave features and heart rate can be provided.Keywords: heart rate, Hamilton Algorithm, BITalino, ECG
An IoT-Enabled Smart System Utilizing Linear Regression for Sheep Growth and Health Monitoring Efendi, Syahril; Sihombing, Poltak; Mawengkang, Herman; Turnip, Arjon; Weber, Gerhard Wilhelm
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.901

Abstract

The global livestock industry faces significant pressures from climate change, land constraints, and rising consumer demand, necessitating greater efficiency and sustainability in production. To address these challenges, there is a critical need for accessible, data-driven tools; however, accessible and individualized tools for monitoring the growth and health of livestock like sheep remain underdeveloped, limiting farmers' ability to transition from reactive to proactive management. This study developed and validated an Internet of Things (IoT) smart system for monitoring sheep using an Arduino and ESP32 platform equipped with a DHT22 sensor for temperature and humidity and a load cell for weight. Weekly weight data from 15 sheep were collected over a six-month period. Simple linear regression was then applied to model the individual growth trajectory of each animal. The IoT system was successfully implemented and deployed in a farm setting. The primary finding was that individualized linear regression models provided a highly accurate method for tracking sheep growth, with R² values consistently exceeding 99% for most animals. The system effectively delivered real-time reports on growth trajectories and health-relevant environmental conditions (e.g., temperature and humidity) to a smartphone interface, confirming its practical utility. The primary implication of this research is a validated framework for practical and interpretable precision livestock farming. The system empowers farmers to shift from reactive to proactive management by using individualized growth curves as baselines for early problem detection. This dual-function system enhances productivity through precise growth tracking while supporting animal welfare via environmental monitoring, offering a valuable tool for modern, sustainable sheep farming.
Acute effects of methadone on neural oscillations: an EEG study of theta, alpha, beta power, and frontal alpha asymmetry in opioid rehabilitation patients Nadiya, Ulfah; Simbolon, Artha Ivonita; Kusumandari, Dwi Esti; Rahmawati, Annida; Amri, M Faizal; Wibowo, Jony Winaryo; Danasasmita, Febrianti Santiardi; Sobana, Siti Aminah; Iskandar, Shelly; Turnip, Arjon
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 7 No. 2 (2025): May
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/ijeeemi.v7i2.64

Abstract

Methadone is a synthetic opioid that commonly employed in opioid substitution therapy (OST) to reduce withdrawal symptoms and suppress cravings in individuals with opioid use disorder. While its pharmacological effects are well-documented, the neurophysiological changes it induces especially during acute administration remain underexplored. This study aims to address that gap by investigating methadone-induced alterations in brain oscillatory activity through electroencephalography (EEG). Specifically, it examines changes in theta (4–8 Hz), alpha (8–12 Hz), and beta (12–30 Hz) frequency bands, along with frontal alpha asymmetry (FAA) for F4-F3 and F8-F7, a biomarker associated with emotional and cognitive processing. EEG data were collected from patients enrolled in opioid rehabilitation programs both prior to and one hour following oral methadone intake. The results revealed a significant global decrease in theta power, notably within the frontal, temporal, and occipital cortices. This reduction may reflect changes in executive functioning, emotional regulation, and increased sedation. In contrast, alpha power showed a marked increase, particularly in the central, parietal, and occipital regions, suggesting reduced sensory processing and heightened sedation or attentional disengagement. Meanwhile, beta power was consistently reduced across cortical regions, pointing toward decreased cortical arousal and cognitive alertness. FAA analysis revealed high variability among participants, indicating that methadone's influence on emotional valence and approach-avoidance behavior may differ significantly across individuals. These findings underscore methadone’s sedative and stabilizing effects on neural activity and support its clinical role in managing opioid dependence. Further research into inter-individual differences in EEG responses may inform more personalized and effective OST protocols.
ECG-BASED ARRHYTHMIA DETECTION USING THE NARROW NEURAL NETWORK CLASSIFIER Chandra, Angelia Ayu; Sunnia, Cecilia; Wijaya, Kenrick Alvaro; Dharma, Abdi; Turnip, Arjon; Turnip, Mardi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 2 (2025): JITK Issue November 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i2.7121

Abstract

Electrocardiograms (ECG) are important for detecting arrhythmias. Conventional models such as CNN and LSTM are accurate but require large amounts of computation, making them difficult to use on wearable devices and for real-time monitoring. This study evaluates the Narrow Neural Network Classifier (NNNC) as a lightweight and efficient alternative. The dataset consists of 21 subjects with 881 ECG samples, categorized based on walking, sitting, and running activities, and processed through bandpass filtering, normalization, and P-QRS- T wave segmentation. The data is divided into training (70%), validation (15%), and test (15%) sets. The NNNC has 11 convolutional layers, a ReLU activation function, a Softmax output, and 120,000 parameters. The model was trained using the Adam optimizer, a batch size of 32, and a learning rate of 0.001 for 100 epochs and compared with SVM, CNN, and LSTM using accuracy, precision, recall, F1-score, and ROC-AUC. The results show that NNNC achieves an accuracy of 98.9%, a precision of 99.2%, a recall of 99.2%, and an F1-score of 99.2%, higher than SVM and comparable to CNN/LSTM, with lower computational consumption. The model is capable of reliably detecting early arrhythmias. These findings support the potential of NNNC for ECG-based automatic diagnostic systems, including real-time implementation on wearable devices, although further research is needed for large-scale validation
Analysis of brain activity to methamphetamine stimulus using electroencephalography technology with Naive Bayes algorithm Putri, Suci Rahmalia; Hasibuan, Amanda Khalishah; Sinaga, Cindy Ananda; Manullang, Ernest Natanael; Turnip, Arjon; Dharma, Abdi; Turnip, Mardi
Bulletin of Electrical Engineering and Informatics Vol 15, No 2: April 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i2.10385

Abstract

The increasing use of methamphetamine among young generations has led to significant alterations in brain function, affecting both behavior and mental health. However, scientific understanding of the neural activity changes induced by methamphetamine remains limited. This study aims to analyze brainwave patterns using electroencephalography (EEG) and classify addiction response levels through the Naive Bayes algorithm. The experimental procedure involved presenting each subject with visual stimuli related to methamphetamine while recording their brain activity using EEG for three minutes. The extracted EEG features were then analyzed with the Naive Bayes classifier. The results demonstrated a classification accuracy of 97.9%. The proposed method successfully categorized brain activity patterns into five levels of response: non-addicted, mildly addicted, moderately active, addicted, and highly addicted. These findings indicate that the Naive Bayes algorithm is effective in distinguishing subtle variations in brainwave patterns associated with different levels of methamphetamine addiction response.
Analysis of arrhythmia detection and classification using electrocardiogram signals with decision tree algorithm Marpaung, Putri Juniarti; Anggreni Matondang, Nia; Margaretta Siregar, Rince; Ester Novelia Siahaan, Angelica; Dharma, Abdi; Turnip, Arjon; Turnip, Mardi
Bulletin of Electrical Engineering and Informatics Vol 15, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i3.10317

Abstract

Heart disease remains the primary cause of death globally, with arrhythmia diagnosis often limited by restricted access to medical personnel and the complexity of electrocardiogram (ECG) interpretation. Accurate arrhythmia classification is essential to prevent cardiovascular complications. The proposed method successfully categorized classify ECG signals into five categories: normal, abnormal, potentially arrhythmia, moderate arrhythmia risk, and highly potentially arrhythmia. Data were collected from 30 subjects under three activity scenarios: sitting, walking, and running. The proposed model achieved an accuracy of 99.4%, demonstrating strong potential for real-time monitoring applications. Performance evaluation was conducted using accuracy, precision, recall, and F1-score for each class. Although the dataset size remains relatively small, the findings highlight the effectiveness of decision tree as an efficient and interpretable classification method. Future research will involve validation using large-scale public databases like the arrhythmia database at MIT-BIH and comparisons with advanced methods including convolutional neural network (CNN), transformer-based models, and explainable artificial intelligent (XAI) frameworks.