Claim Missing Document
Check
Articles

Found 6 Documents
Search

Object Tracking Based on Camera Using Anfis and Fuzzy Classifier for RGB Color Iqbal Robiyana; Timbo Faritcan Parlaungan; Sarifudin; Suhendra, Muhamad Agung
TIME in Physics Vol. 1 No. 2 (2023): August
Publisher : Universitas Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11594/timeinphys.2023.v1i2p85-91

Abstract

Image processing technology has a wide range of applications, such as in the medical, military, surveillance, and robotics industries. Analyzing objects in images is crucial when it comes to image processing. This study focuses on image processing to track objects of red, green, and blue (RGB) colors through the utilization of a camera. There are two research schemes: image processing and data classification. The data classification method used is the fuzzy and adaptive neuro-fuzzy inference system (ANFIS). The methods of image subtracting and region properties are commonly utilized for image processing. Based on the classification data results, the fuzzy logic classification demonstrated a higher accuracy rate of 86% when compared to Anfis' 65%. This was observed when both classification models were tested using a random sample. The value of Anfis is small due to the limited size of the training data used. As a result, it is recommended to use a fuzzy classifier for object color tracking for good performance.
A Computational Study of Numerical Integration in Physics Applications Using Trapezoidal and Simpson's Methods Suhendra, Muhamad Agung; Assegaf, Sufiyah; Robiyana, Iqbal; Nurizati
TIME in Physics Vol. 2 No. 2 (2024): September
Publisher : Universitas Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11594/timeinphys.2024.v2i2p85-95

Abstract

This research conducts a comprehensive evaluation of the efficiency and accuracy of two widely-used numerical integration methods, the Trapezoidal Rule and Simpson's Rule, within the context of solving physics-related problems. The study focuses on four representative cases: the calculation of kinetic energy, the determination of electric field strength, the work done by an ideal gas, and the gravitational potential energy. The performance of these methods is analyzed through key metrics such as convergence behavior, error magnitude, and computational time. The findings reveal that Simpson's Rule consistently delivers higher accuracy compared to the Trapezoidal Rule, especially for functions exhibiting non-linear characteristics. This highlights Simpson's Rule as a preferred method for complex physical problems, while the Trapezoidal Rule remains effective for simpler cases requiring lower computational overhead.
Canonical Correlation Analysis and Its Extension for SSVEP-based BCI Detection: A Systematic Review Muhamad Agung Suhendra; Iqbal Robiyana; Tedi Sumardi; Ahmad Sofyan Sulaeman; Permono Adi Putro; Nurizati Nurizati; Usep Tatang Suryadi; Anderias Eko Wijaya; Sunanto Ajidarmo; Arief Budiman; M. Faizal Amri
Jurnal Penelitian Pendidikan IPA Vol 10 No 12 (2024): December
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v10i12.9844

Abstract

SSVEP-based Brain-Computer Interfaces (BCIs) utilize steady-state visual evoked potentials, which are brain responses triggered by visual stimuli flickering at specific frequencies. Users can focus on these stimuli, allowing the system to interpret their intent based on the brain's electrical activity. This technology has applications in communication for individuals with disabilities, gaming, and neuro-feedback, offering an ultimate means of interaction through thought alone. In this study, systematic literature review was conducted to identify analytical methods for SSVEP spellers with PRISMA method from the eligibility criteria. CCA and its extension become gold-standar method that give excellent performances for SSVEP recognition and signal classification. Some uniques features also found such as MsetCCA, FB-CCA, MF-CCA, TW-CCA, CP-CCA, IIS-CCA, TT-CCA and RLS-CCA. Therefore, we have various options for choosing the best method for recognizing SSVEP from EEG signals based BCI.
Analisis Pengukuran Taraf Intensitas Bunyi Pengeras Suara Masjid Menggunakan Aplikasi Sound Level Meter Nurizati, Nurizati; Sumardi, Tedi; Robiyana, Iqbal
Jurnal Riset Fisika Indonesia Vol 5 No 1 (2024): Desember 2024
Publisher : Jurusan Fisika, Universitas Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33019/jrfi.v5i1.5583

Abstract

Noise pollution can come from various sources around us, such as loudspeakers. In Indonesia, where the majority of the population is Muslim, many mosques use loudspeakers to broadcast the adhan, or call to prayer. Recently, the use of mosque loudspeakers has sparked debate, as some people are concerned that the noise may disrupt their comfort and potentially affect their health. This study aims to assess whether the noise level of the adhan from these loudspeakers is within safe limits or exceeds the threshold that could harm human health. The research involved measuring the sound intensity of the adhan using a sound level meter app. Measurements were taken at two locations: within the mosque courtyard and at a distance of 100 meters from the mosque. The study examined six mosques in Bekasi City, with two mosques located in residential areas, two in office areas, and two in school areas. The results indicate that the highest noise levels were recorded in the mosque courtyards, with levels decreasing as the distance from the mosque increased. Among the six mosques, the highest noise level recorded was 84.5 dB in the mosque courtyard, which is below the threshold set by the Ministry of Manpower Regulation No. 5 of 2018, meaning it is still considered safe for human health
EEG-Based Emotion Classification in Response to Humorous, Sad, and Fearful Video Stimuli Using LSTM Networks: A Comparative Study with Classical Machine Learning Models Muhamad Agung Suhendra; Tedi Sumardi; Iqbal Robiyana; Nurizati Nurizati
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.v7i2.100

Abstract

Emotion recognition based on EEG signals is a critical area within affective computing, with applications in mental health monitoring, human-computer interaction, and neuroadaptive systems. However, accurately classifying emotional states from inherently non-stationary and noisy EEG data remains a major challenge. This study explores the classification of three discrete emotions, Humorous, Sad, and Fearful, elicited through video stimuli, using EEG recordings from six participants acquired via a 19-channel Mitsar amplifier at a 500 Hz sampling rate. Preprocessing steps included bandpass filtering (1–40 Hz), epoch segmentation, and multi-domain feature extraction encompassing statistical measures, spectral features, differential entropy, Hjorth parameters, and hemispheric asymmetry indicators. Data augmentation was applied to balance class distributions, particularly for the underrepresented fear category. The resulting features were normalized and structured to support temporal deep learning and classical machine learning models. The classification performance of Long Short-Term Memory (LSTM) networks was evaluated alongside Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Random Forest (RF) classifiers. While LSTM demonstrated competency in capturing temporal dependencies, especially in fear recognition, SVM achieved the highest overall accuracy, 94.12%, outperforming LSTM at 85.16%, RF at 90.00%, and k-NN at 78.01%. These results suggest that when robust and discriminative features are employed, traditional models like SVM can surpass deep learning methods, particularly in small-scale EEG datasets with limited temporal complexity. This study underscores the importance of aligning model architecture with feature representation and contributes a comparative evaluation framework for EEG-based emotion recognition systems.
Penerapan Simulasi AI Sistem Drone Ganda untuk Optimasi Lintasan pada Pemantauan Perkebunan Sumardi, Tedi; Suhendra, M. Agung; Robiyana, Iqbal; Wijaya, Anderias Eko
Jurnal Teknologi Informasi dan Komunikasi Vol 18 No 1 (2025): April
Publisher : STMIK Subang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47561/jtik.v18i1.286

Abstract

Drone-based monitoring systems have emerged as an effective solution to improve the efficiency of large-scale agricultural land surveillance, particularly in oil palm plantations. This study proposes an artificial intelligence (AI)-based simulation using dual drones to map optimal and distributed flight paths. The simulation considers the random wind effect on trajectory accuracy using a grid-based waypoint approach across the plantation area. The results show that both drones successfully completed the land inspection mission with an average wind-induced deviation of ±0.14 meters, indicating system stability under dynamic environmental conditions. Drone 1 covered a total distance of 9244.10 meters, while Drone 2 covered 10602.47 meters. A 3D trajectory visualization illustrates that the path deviations remained controlled. This research provides a foundation for developing more adaptive and efficient autonomous drone systems in the context of smart farming.