Article Per Year (5 Year)
p-Index From 2021 - 2026
1.513
P-Index
This Author published in this journals
All Journal POSITRON JOIV : International Journal on Informatics Visualization Indonesian Journal of Physics (IJP) Journal of Engineering and Technological Sciences
Evita, Maria
Unknown Affiliation
Aerospace Engineering Astronomy Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Earth & Planetary Sciences Electrical & Electronics Engineering Energy Engineering Physics

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Application of Unmanned Aerial Vehicles for Micro-Small and Medium Enterprises Agricultural in West Java Sawita, I Kadek Agus Sara; Evita, Maria; Kane, Hansel; Rausyanfikr, Fadhil; Djamal, Mitra
POSITRON Vol 12, No 2 (2022): Vol. 12 No. 2 Edition
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam, Univetsitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (565.014 KB) | DOI: 10.26418/positron.v12i2.54176

Abstract

Agricultural Micro-Small and Medium Enterprises (MSMEs) play a vital role in maintaining national food security. In terms of sources of economic growth, the agricultural sector is the largest contributor to West Java's economic growth in the first quarter of 2021. The agricultural business sector contributed as much as 0.94%, greater than its contribution in the fourth quarter of 2020 which amounted to 0.39%. MSMEs still have external and internal constraints, especially in terms of financing, product marketing, and lack of access to information. These constraints often hinder MSMEs in developing their business and expanding their market share. From various cases of marketing agricultural MSME products in West Java, it is necessary to implement technology to market agricultural commodities. One of them is a map application, which is useful in providing the location of agricultural MSMEs and how to reach that location from the customer's current location. So that sellers/farmers and buyers can do direct transactions. Therefore, map applications using Unmanned Aerial Vehicles (UAV) can be used as the alternative technology to solve that problem. While, this research only focuses on generating the map. UAV - DJI Phantom 4 Pro has been used in this research to take images at each location of the sample locations. To control the UAV automatically for each mission, it used Pix4D capture flight plans. The data were processed by Agisoft Metashape Professional software. The location of image data collection was carried out in various areas: a building, an open space area and a real small and medium agriculture enterprises location. Two-dimensional maps and 3D maps of these areas have been successfully created. The average RMS error is 0.17 (2.88 pixels) indicating under 1% of the average error.
Application of YOLOv5s Algorithm for Real-Time Object Detection in Mobile Robot for Volcano Monitoring System Evita, Maria
Indonesian Journal of Physics Vol 35 No 1 (2024): vol 35 no 1 2024
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2024.35.1.2

Abstract

Indonesia, a country with 172 volcanoes and second after Japan for the most eruption events, should monitor and predict the volcano eruption to prevent the effect of this natural disaster. Therefore, we have developed a 4-wheeled mobile robot equipped with monitoring sensors and a Logitech camera for this purpose. The robot should have the ability to detect objects in this extreme environment to avoid collision while moving and monitoring the volcano’s physical parameters. It has been designed a deep machine learning of YOLOv5s algorithm for two objects mostly found at volcanoes such as trees and stones. After the training steps (object identification; dataset downloading (Google Chrome Extension and Open Images v6); image labeling (LabeImg); augmentation process (blur and rotation)) had been carried out, the images of the object then trained in three model variation which resulted in: mAP_0.5 = 51.9%, mAP_0.5:0.95 = 28.6%, 58% of precision and 50% recall with 12 minutes and 33 seconds of training time for the first model (batch=16 and epochs=100); mAP_0.5 = 59.7%, mAP_0.5:0.95 = 36.3%, 74% of precision and 54% recall with 36 minutes and 4 seconds of training time for the second model (batch=16 and epochs=300); mAP_0.5 = 59.9%, mAP_0.5:0.95 = 37.6%, 80% of precision and 55% recall with one hour and 25 seconds of training time for the last one (batch=16 and epochs=500) as the best model of these variations. Furthermore, these results were displayed for all test images for the best model.
Analysis of Temperature Sensors in a Volcanic Detection System Muid, Abdul; Sawita, I Kadek Agus Sara; Appriyana, Nazira; Albab, Alfi Nur; Tarigan, Darell Timothy; Kamal, Muhammad; Evita, Maria; Suprijadi, Suprijadi; Djamal, Mitra
Indonesian Journal of Physics Vol 36 No 1 (2025): Vol 36 No 1 2025
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2025.36.1.1

Abstract

Volcanoes are geological phenomena that can cause significant disasters to human life and the environment, such as eruptions, pyroclastic flows, and lahars. Therefore, early warning systems for volcanoes are crucial to reduce disaster risks and provide sufficient time for evacuation. Monitoring surface temperature and the surrounding air around volcanoes is one of the key parameters in detecting volcanic activity. Temperature increases often serve as an early indication of magmatic activity beneath the surface. This study proposes an early warning system for volcanoes based on temperature sensors integrated with fuzzy logic to monitor volcanic activity in real-time. The system consists of a wireless temperature sensor network based on the Internet of Things (IoT) connected to an IoT platform for data monitoring and analysis. The SHT31D, SHT2X, BME280 and DHT11 sensors are used to measure the ambient temperature, and the temperature data is processed using fuzzy logic methods to detect changes in volcanic activity. The system was tested in both simulation and field environments using sensor node devices consisting of several temperature sensors controlled by a microcontroller. The fuzzy logic algorithm built using 256 rules is able to classify new data from sensor nodes into one of the categories of volcano vulnerability levels, namely “Normal”, “Caution”, “Warning”, or “Evacuate”. This system has the potential to serve as a real-time temperature monitoring tool for volcanoes, supporting disaster mitigation and volcanic activity risk management.
Object Distance Detection System with Ultrasonic Sensor on Mobile Robot Ramdhani, Adrian Pandjie; Ramadan, Hafiz Arshad; Permatasari, Indah; Abi Hanafi, Aliif Fahrur; Sara Sawita, I Kadek Agus; Evita, Maria; Djamal, Mitra
Indonesian Journal of Physics Vol 36 No 1 (2025): Vol 36 No 1 2025
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2025.36.1.2

Abstract

Indonesia is home to 76 active volcanoes, one of them being Mount Tangkuban Perahu. To ensure that a robot that can move around to collect data does not get stopped in its tracks, HC-SR04 ultrasonic sensors are used to detect obstacles within 100 cm. The sensors were first characterized by measuring distances between 10 and 100 cm with an increment of 10 cm. They were then tested in a laboratory environment with differing conditions. Finally, they were tested on Mount Tangkuban Perahu. Characterization shows that, within 100 cm, one of the two sensors had good linearity, while the other showed larger error values. This difference in performance carried onto the laboratory scale test and the field test.
Seismic Frequency Analysis of Mount Tangkuban Parahu Using IoT-Based MPU6050 Sensor System Almazari, Abar; Faradyba, Anggi; Akbar, Reyhan Nugraha; Sawita, Agus Sara; Evita, Maria; Djamal, Mitra
Indonesian Journal of Physics Vol 36 No 1 (2025): Vol 36 No 1 2025
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2025.36.1.3

Abstract

Indonesia is located at the convergence of three major tectonic plates—the Eurasian Plate, the Indo-Australian Plate, and the Pacific Plate—and lies within the Pacific Ring of Fire, making the country highly prone to seismic activity. Thus, seismic activity is one of the physical parameters used to define the status of a volcano. Consequently, the availability of affordable and accessible early earthquake detection systems is crucial to minimizing infrastructure damage and human casualties. One proposed solution involves the use of the MPU6050 sensor, which is capable of detecting ground acceleration. This sensor has been integrated and installed on a mobile robot for volcano monitoring, which was developed in previous research. In this study, the Fast Fourier Transform (FFT) is employed to convert ground acceleration data into ground frequency, which can then be used to assess seismic activity. Additionally, an ESP32 microcontroller is utilized to collect and process sensor data, which is automatically transmitted via a broker, allowing frequency data and seismic status to be visualized on a dashboard. This research aims to compare acceleration data collected in a laboratory setting (ITB campus) and in the field (Mount Tangkuban Parahu), measure ground vibration frequency at Mount Tangkuban Parahu, and determine the seismic activity status based on the ground vibration frequency at Mount Tangkuban Parahu.
Determining the Hydrogen Sulfide Concentration at Tangkuban Perahu Mount Using TGS-2602 Sensor Putra, Adiyasa Pratama; Alam Purnama, Atra Ardiyanto; Prihatini, Jihan; Adrian, Kristofer; Sawita, I Kadek Agus Sara; Evita, Maria; Djamal, Mitra
Indonesian Journal of Physics Vol 36 No 1 (2025): Vol 36 No 1 2025
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2025.36.1.4

Abstract

Indonesia is a country with numerous volcanoes which are a great hazard to people living in surrounding areas. As a result, eruption predictions and pre-emptive warnings are extremely important. In mount Tangkuban Perahu in particular, hydrogen sulfide is abundantly produced. By detecting hydrogen sulfide levels, volcanic activities in Tangkuban Perahu can be predicted and early warnings can be released to alert the people in the area. To obtain a reading of the concentration of hydrogen sulfide we use the TGS 2602 gas sensor equipped with Arduino to process the readings and ESP-32S to connect the system to IOT. This sensor system is equipped on a mobile robot which had been developed in previous research. Through field experiments, we have determined that our system has successfully obtained the readings of hydrogen sulfide in various parts of the day. Our readings showed that mount Tangkuban Perahu is safe and stable throughout the day with none of the average hydrogen sulfide reading in the morning, afternoon, and evening exceeding 0.3 ppm.
Design of Object Detection System for Tangkuban Parahu Volcano Monitoring Application Evita, Maria; Mustikawati, Sekar Tanjung; Srigutomo, Wahyu; Meilano, Irwan; Djamal, Mitra
Journal of Engineering and Technological Sciences Vol. 56 No. 5 (2024)
Publisher : Directorate for Research and Community Services, Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/j.eng.technol.sci.2024.56.5.3

Abstract

Indonesia has 127 active volcanoes, which have to be monitored continuously in normal, eruption, or after-eruption conditions, to minimize the effects of disaster. Therefore, we have developed a four-wheeled mobile robot for both exploration and monitoring of volcanoes. To finish its mission on uneven terrain full of obstacles, the robot should be able to detect and avoid these obstacles. Therefore, real-time object detection was designed using the YOLOv5s deep learning algorithm, which was implemented on a Raspberry Pi3 for the front camera of the robot. Before it was tested on a real volcano, the model of the algorithm was trained to be able to detect obstacles. The dataset was trained with three variations of epochs (100, 300, and 500) in sixteen batches of YOLOv5s. The last variant yielded the best results, at 63.4% mAP_0.5 and 40.4% mAP_0.5:0.95, with almost zero loss. This model was then implemented on a Raspberry Pi3 to detect trees and rocks captured by camera on Tangkuban Parahu Volcano. Most of the trees and rocks were successfully detected, with 90.9% recall, 79.9% precision, and 91.5% accuracy. Furthermore, the detection error was low, as indicated by low FP and FN numbers.
The The Analyse of Barton Pendulum for Application of Resonance Experiment for Senior High School Student ALBAB, ALFI NUR; Evita, Maria; Aminah, Nina Siti; Irvianto, Berlian Oka
Indonesian Journal of Physics Vol 36 No 1 (2025): Vol 36 No 1 2025
Publisher : Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itb.ijp.2025.36.1.5

Abstract

While pendulums have been around for thousands of years and have even been successfully incorporated into high school curricula, they are still minimally used in Physics experiments on resonance materials. In this study, we designed the Barton Pendulum as a simple laboratory kit operated by teachers and easily observed by students. The pendulum system consists of a series of objects and a small ball connected and suspended with a carbolic string. The small ball here is none other than the trigger that makes all objects oscillate. As an observation material, the length of the string for each object is made different (40 cm, 29.8 cm, 20 cm, 9.5 cm, 6.7 cm). The period of each object in the system is observed using a stopwatch so that the oscillation frequency of each object is known. The object that resonates with the ball is the object that has the same length as the length of the hanging string of the ball, which means that this object has the same natural frequency as the frequency of the ball. The phase difference between the object and the trigger is also observed. The phase difference is equal to rad for objects with a string length equal to the length of the trigger string, and the phase difference is equal to π rad for objects with a string length longer than the length of the trigger.
Determining Forest Fire Position from UAV Photogrammetry using Color Filtration Algorithm Muid, Abdul; Evita, Maria; Aminah, Nina; Budiman, Maman; Djamal, Mitra
JOIV : International Journal on Informatics Visualization Vol 6, No 4 (2022)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.6.4.956

Abstract

Forest fires frequently happen worldwide, especially in the dry season. A forest fire early warning system (EWS) is needed to prevent this disaster. The main part of EWS is the hotspot detection system. On the other side, Unmanned Aerial Vehicle (UAV) technology offers an alternative solution to detect the hotspot for poor satellite image processing accuracy. Remote sensing techniques with UAV working drones are progressively challenging. Drones can provide results in 2D and 3D images with high resolution and real-time. Therefore, in this research, we have used a photogrammetry application from the number of images collected by a UAV with an optimum flight plan for the mission to determine the location of the forest fire. This paper describes remote sensing experiments using drones to detect land fires. The experiment was carried out using a quadcopter drone of the DJI Phantom 4 Pro. The photos are processed using Agisoft Metashape Professional image processing software and become a 2D image. These images captured a fire simulation in a known location. After a high resolution (GSD – Ground Sampling Distance – 0.87cm/px) orthophoto had been generated, a color filtration algorithm detected a hotspot to detect a fire at the exact location. The results are almost zero deviation of longitude and latitude from the real location with 1.44 m2 and 1.06 m2 fire area from 2 experiments. This algorithm program has TPR and FPR are 0,78 and 0, respectively. Further research can develop an EWS with a combination of UAV and Wireless Sensor Networks.
Co-Authors Abdul Muid Abi Hanafi, Aliif Fahrur Adrian, Kristofer Akbar, Reyhan Nugraha Alam Purnama, Atra Ardiyanto Albab, Alfi Nur Almazari, Abar Aminah, Nina Siti Appriyana, Nazira Faradyba, Anggi Indah Permatasari Irvianto, Berlian Oka irwan meilano Kane, Hansel Maman Budiman Mitra Djamal Muhammad Kamal Mustikawati, Sekar Tanjung Nina Aminah, Nina Prihatini, Jihan Putra, Adiyasa Pratama Ramadan, Hafiz Arshad Ramdhani, Adrian Pandjie Rausyanfikr, Fadhil Sara Sawita, I Kadek Agus Sawita, Agus Sara Sawita, I Kadek Agus Sara Suprijadi Suprijadi Tarigan, Darell Timothy Wahyu Srigutomo