Claim Missing Document
Check
Articles

Found 10 Documents
Search

Novel of MEMS Resonant Gyroscope using DETF as Sensing Structure Uvi Desi Fatmawati; Fan Shang Chun; Zhanshe Guo
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 1: EECSI 2014
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1156.619 KB) | DOI: 10.11591/eecsi.v1.412

Abstract

Nowadays MEMS product is widely used in all fields such as industry, automation, aerospace, marine, etc. With advances fabrication and lowering cost, MEMS product is very useful and its simple design enabling the user use it easily. This research introduced a new design of MEMS resonant gyroscope using DETF as sensing structure. The decoupled DETF has been designed to be able to produce the natural frequency of 80 KHz, while the whole gyroscope structures generate natural frequency of 3511,8 Hz. Above condition is done to avoid force miss detection in sense mode and drive mode, which has become the biggest problem in gyroscope design. The result showed that the new design of MEMS Resonant Gyroscope is feasible.
Perbandingan Metode SVM-Segmentasi Untuk Mendeteksi Kutu Beras Dalam Citra Beras Uvi Desi Fatmawati; Wahyu Hidayat; Dananjaya Ariateja; Iqbal Ahmad Dahlan
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 9 No 1 (2022): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v9i1.1479

Abstract

Support Vector Machine (SVM) is a classification method that works by finding the hyperplane with the largest margin. Saturation Value (SV) is a digital image color model consisting of two elements, namely Saturation and Value. SV is taken from HSV, then only two elements are used. Segmentation is the process of separating an image that will be detected with a background image. Rice weevils are small pests that damage the quality of rice in rice storage. The quality and nutrition of rice will be reduced because of that bug. In this study, two methods have been used to detect the rice weevil that placed on a rice in an image. In the first method, feature extraction of the rice weevil texture is taken from RGB images and feature extraction of the SV brightness values ​​is taken from converting RGB images to HSV images. These two parameters are used as the SVM data training. In the second method, SV value in the HSV color model is used to separate between the rice weevil as the object detected and a rice as the background. The results showed that the first method provides an accuracy rate of 78.95% while the second method is 84.78%. Keywords—SVM, HSV, Segmentation, Rice Weevils, Accuracy
Sistem Deteksi Senjata Otomatis Menggunakan Deep Learning Berbasis CCTV Cerdas Iqbal Ahmad Dahlan; Dananjaya Ariateja; Muhammad Abditya Arghanie; Muhammad Azka Versantariqh; Muhammad David; Uvi Desi Fatmawati
Jurnal Sistem Cerdas Vol. 4 No. 2 (2021)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v4i2.172

Abstract

Nowadays, security and safety are big concerns in this modern and cyberwar era. Many countries invest some safety infrastructure to ensure their inhabitants for keeping their lives safely. Indonesia is the country with many problems because of urbanization and other challenges. This problem should be solved with smart city solution and it must be able to face the challenge of ensuring the safety and improving the quality of life regarding network centric warfare era. This problem also should be tackled with CCTV analytics with the ability to implement an automatic weapon detection system. It also can provide the early detection of potentially violent situations that is of paramount importance for citizens security. This paper is using deep Learning techniques based on Convolutional Neural Networks (CNN) can be trained to detect this type of object with YOLOv4 model and it proposes to implement CCTV analytics as a platform to process real-time data for monitoring weapon detection into knowledge displayed in a dashboard with accuracy 0.89, precision 0.82, recall 0.96 dan F1 Score 0.90 result on weapon detection with a real time speed of processing with NVIDIA 2080 Ti around of 35 FPS. It will send an early warning notification if the system detects the weapon detection such as a knife, gun etc.
Oksimeter Militer Pemantau Stres Prajurit TNI Berbasis Internet of Military Things Dananjaya Ariateja; Iqbal Ahmad Dahlan; Uvi Desi Fatmawati
Jurnal Sistem Cerdas Vol. 5 No. 1 (2022)
Publisher : APIC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37396/jsc.v5i1.174

Abstract

In carrying out their duties, TNI soldiers often experience pressure and threats that attack both physically and psychologically. This can trigger stress. Uncontrolled stress will cause disease disorders such as arrhythmias and hypoxemia. We offer a solution by building an Internet of Military Things (IoMT) based military oximeter for soldier stress monitoring. The proposed tool is real-time and portable, can monitor heart rate (BPM) and blood oxygen saturation (SpO2) when soldiers are on duty in conflict areas. This military oximeter is equipped with notifications and alarms that are integrated with applications installed on smartphones, so commanders can monitor the condition of their soldiers directly and view their health history. Based on the test results, obtained an accuracy of 99.7% and 99.88% for measuring heart rate and oxygen saturation in the blood. This military oximeter can be used as a medical aid to monitor the health condition of soldiers while on duty.
Instrumentasi Pemantauan Perairan Berbasis Telemetri Pada Prototipe Unmanned Surface Vehicle (USV) Dananjaya Ariateja; Uvi Desi Fatmawati; Iqbal Ahmad Dahlan
JTEV (Jurnal Teknik Elektro dan Vokasional) Vol 7, No 2 (2021): JTEV (Jurnal Teknik Elektro dan Vokasional)
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (563.147 KB) | DOI: 10.24036/jtev.v7i2.113096

Abstract

Technological advances, especially in the field of remote control, both automatic and non-automatic, are very rapid. This can be seen from the technological capabilities that can work on the land, air, and water. Indonesia as one of the largest archipelagic countries in the world that have borders such as land, air, and vast seas must have this technology to anticipate the potential for problems that endanger citizens and the state. So far, Indonesia has reached this technology, for example, drone technology as a border monitoring mission through the air and aerial photography purposes. Ground robots are used to defuse remote-controlled bombs. To complete this, the researchers conducted research related to a remotely controlled prototype of an unmanned water vehicle. The research conducted discusses the manufacture of prototypes of unmanned surface vehicles and control stations that can communicate with each other. This prototype is controlled by the Arduino Nano microcontroller module, while the main control system uses a desktop-based application that is run via a laptop. Based on the test results, sending sensor data to Arduino and to the control station via the RF-module media went well. The transmission distance of transmitting sensor data and navigation control reaches approximately 250 meters, while the transmission distance of IP camera images reaches approximately 9 meters.
Penerapan Metode HSV-TCA Untuk Mendeteksi Kutu Beras (Sitophylus Oryzae L) Secara Real-Time Uvi Desi Fatmawati; Wibby Aldryani Astusi Praditasari; Ria Aprilliyani
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 11, No 2 (2023)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v11i2.56039

Abstract

Metode HSV-TCA adalah sebuah penggabungan antara metode Tresholding dalam ruang warna HSV yang disempurnakan dengan metode deteksi Contour Area. Dalam penelitian ini, metode tresholding digunakan untuk memisahkan antara objek yang berupa kutu beras jenis Sitophilus Oryzae L dengan background-nya yaitu beras. Prinsip Region Of Interest (ROI) digunakan untuk meminimalisir kesalahan dalam pendeteksian dari kamera webcam dikarenakan ukuran beras dan kutu yang relatif kecil. Nilai treshold dan contour area (jenis contour dan lebar contour area) dapat dijadikan input dalam penggambaran ROI sehingga dapat dilakukan pengambilan gambar dalam bentuk tertentu seraca real-time. Percobaan pada dua kualitas beras telah dilakukan. Beberapa library OpenCV digunakan dan berfungsi dengan baik. Hasil penelitian ini menunjukkan bahwa metode ini bisa memisahkan antara objek kutu beras jenis Sitophilus Oryzae L dengan background-nya yaitu beras dimana keduanya sama-sama berukuran kecil, sekaligus mendeteksi kutu beras jenis Sitophilus Oryzae L secara real-time.
Smart Rice Box - The Prototype of Organic Rice Storage Anti-Rice Weevil for Food Security during Pandemic Fatmawati, Uvi Desi; Pratami, Mentari Putri; Hidayat, Wahyu; Kurdianto, Kurdianto
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 7 No. 1 (2023)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v7i1.604

Abstract

The need for organic rice among the people continues to increase in line with the declining level of public health due to the COVID-19 pandemic. Consuming organic rice is one way to maintain body immunity, but organic rice is susceptible to attack by Sitophilus Oryzae L, a type of rice weevil which is the main pest in postharvest commodities. Proper storage of rice is one way to address food security during a pandemic. In this study, a prototype of an anti-rice weevil (Sytophilus Oryzae L) organic rice storage was made using a Raspberry Pi controller and several additional sensors such as a camera sensor and temperature and humidity sensors. UV Hydroponic Lamp and LED Grow Light are used to reduce the growth rate of rice bugs during storage. The results showed that the whole system was running well and the rice bugs on rice were drastically reduced within 36 hours and 18 minutes of storage.
Perbandingan Efektivitas Cairan Pendingin pada Liquid Cooling System dengan Website Simscale untuk Mengurangi Biaya Produksi dan Operasional Andrea Songklanaita; Anry Christiano Tambunan; Muhammad Rey Renoult; Fitra Rizki Aleva; Prasasti Alamsyah; Putra Ramanda; Uvi Desi Fatmawati
Mars : Jurnal Teknik Mesin, Industri, Elektro Dan Ilmu Komputer Vol. 2 No. 4 (2024): Agustus : Mars : Jurnal Teknik Mesin, Industri, Elektro Dan Ilmu Komputer
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/mars.v2i4.265

Abstract

The rapid development of technology demands solutions to optimise heat management for electronic components. Through this study, the researchers evaluated the effectiveness of various types of coolants in a liquid cooling system for electrical equipment, especially CPUs. Using design simulations conducted through SolidWorks software, this research aims to optimise the flow rate and selection of coolant type to achieve maximum thermal efficiency and reduce production and operational costs. The simulation results show that water is the most efficient coolant with significant temperature reduction compared to Ethylene Glycol (EG), Propylene Glycol (PG), and silicone oil. Water shows a temperature drop of 11.76°C, while EG and PG show a temperature drop of 8.82°C and 7.35°C respectively and silicone oil shows a temperature drop of 4.9°C. It can be seen from the simulation that water shows the most effective temperature reduction compared to EG, PG, and Silicone Oil.
Desain Simulasi Interface Pistol G2 COMBAT Kal. 9 mm dengan Simulator Pimp My Gun Wibby Aldryani Astuti Praditasari; Dananjaya Ariateja; Uvi Desi Fatmawati; Herwin Melyanus Hutapea; Tjahjadi Tjahjadi; Agus Sunardi; Muhammad David; Angelita Friskilla; Pandhu Dewanata
Jurnal Otomasi Kontrol dan Instrumentasi Vol 15 No 2 (2023): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2023.15.2.3

Abstract

The development of firearms has been included as an introduction and use at the University of Defense. However, using firearms that are not used freely is a barrier for students to understand the ins and outs of firearms better. Therefore, in this research, firearms are replaced with interface simulation design. One firearm that needs to be designed for interface simulation is the G2 Combat pistol. The reason for using the G2 Combat pistol in making an interface simulation design is because the Indonesian armed forces have widely used it. The interface simulation design uses Pimp My Gun software. The method of designing the G2 Combat pistol interface simulation uses the waterfall method. The waterfall method is considered easy and systematic. After the interface simulation design is carried out, the results are compared with the original item or image, photo, and others. Assessment of the G2 Combat pistol interface simulation design with the original pistol by comparing and finding the level of similarity. The assessment results are 87.61% at imgonline.com and 86.14% at blue2digital.com. With two assessment results close to 100%, the G2 Combat pistol interface simulation design is successful. However, there still needs to be improvements so that the interface simulation design is even better in the future.
Machine learning-based approach for evaluating physical fitness through motion detection Rais, M. Fazil; Chadafa Zulti Noorta; M. Ilham AlFatrah; H.A Danang Rimbawa; Fatmawati, Uvi Desi
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.406

Abstract

Physical fitness assessment is crucial for evaluating an individual's physical performance and endurance. However, traditional methods often rely on manual observation, which can lead to subjectivity and inconsistent results. This study proposes a machine learning-based approach for physical fitness evaluation through motion detection using pose estimation and exercise classification models. A quantitative method was employed to train and evaluate models for four exercise types: push-ups, sit-ups, pull-ups, and chinning. Each model was trained separately and assessed using accuracy, precision, recall, and F1-score metrics, achieving accuracies of 97.50% for push-ups, 97.67% for sit-ups, 97.00% for pull-ups, and 98.50% for chinning. The maximum error margin compared to manual counting was 2.48%. System-generated outputs were validated against manual observations using standard evaluation matrices. These findings indicate that machine learning can offer a reliable, consistent, and automated solution for physical fitness assessment, with the potential to enhance training programs, support remote fitness monitoring, and reduce human error in performance evaluation.