Claim Missing Document
Check
Articles

Found 3 Documents
Search

Prototype smart integrated fire detection based on deep learning YOLO v8 and IoT (internet of things) to improve early fire detection Firdaus, Muhammad Azka; Dahlan, Iqbal Ahmad; Rimbawa, H A Danang; Versantariqh, Muhammad Azka; Prakosa, Setya Widyawan
International Journal of Applied Mathematics, Sciences, and Technology for National Defense Vol 2, No 2 (2024): International Journal of Applied Mathematics, Sciences, and Technology for Natio
Publisher : FoundAE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/app.sci.def.v2i2.437

Abstract

The high incidence of fires in Indonesia in 2018-2023 is 5,336 fire incidents have caused many deaths and enormous material losses. This system is designed to identify early signs of fire through object detection and sensor technology, which is integrated with the Blynk IoT platform for real-time sensor monitoring and Telegram for instant notifications to users. The waterfall prototype method was designed through observation, system design, program code creation, tool testing, and tool implementation. This research uses Deep Learning YOLOv8 technology and IoT using ESP 32 as a microcontroller. Based on the training datasets, it produces precision=0.95872; recall=0.91; mAP50=0.97; mAP50-95 =0.66. The system uses the integration of a multisensor KY-026 flame sensor, DHT 22 temperature and humidity sensor, and MQ-2 sensors can detect CO, LPG, and smoke gas. All these multisensors can be monitored on Blynk IoT and Telegrambot in real time.
Unmanned aerial vehicle classification and detection system based on deep learning, internet of military things, and PID control system Lesmana, Azka Versantariqh; Dahlan, Iqbal Ahmad; Tjahjadi, Hendrana; Prakosa, Setya Widyawan; Firdaus, Muhammad Azka
International Journal of Applied Mathematics, Sciences, and Technology for National Defense Vol 2, No 3 (2024): International Journal of Applied Mathematics, Sciences, and Technology for Natio
Publisher : FoundAE

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/app.sci.def..v2i3.439

Abstract

Indonesia is an archipelagic country situated between two continents and two oceans. With numerous islands, it is rich in natural resources but faces various military and non-military threats. One significant threat to maritime nations like Indonesia is from the air, which includes direct attacks from manned and unmanned aircraft and using aerial vehicles for intelligence and surveillance. The primary weapon system is crucial for national defense against such threats. Therefore, developing defense equipment in Indonesia must align with technological advancements to ensure quick and efficient operation. This research focuses on creating a classification and reconnaissance system for flying vehicles to enhance air defense capabilities. In the surveillance system, two servos are used for yaw and pitch axes, controlled by a Proportional, Integrative, and Derivative (PID) system. This PID control significantly improves servo movement both dynamically and statically. The system sends notifications via Telegram for monitoring, with an average FPS of 9.6. Flask is used for the website interface, averaging 6.8 FPS, and MIT App Inventor is used for the smartphone interface, averaging 7.6 FPS. This flying vehicle classification and reconnaissance system enhances Indonesia's air defense, utilizing YOLOv8 for classification, PID control for servo movements, and integrated notifications and interfaces for both web and smartphones.
Defect Rate Prediction in Manufacturing Process Using K-Nearest Neighbor Algorithm David, Muhammad; Firdaus, Muhammad Azka
International Journal of Informatics, Economics, Management and Science Vol 3 No 2 (2024): IJIEMS (August 2024)
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/ijiems.v3i2.1599

Abstract

The efficiency and effectiveness in the manufacturing industry are significantly impacted by artificial intelligence technology. An important application involves the improvement of product quality, which is measurable through the defects occurring during the production process. This research is aimed at predicting defects in the manufacturing process using the K-Nearest Neighbor (KNN) algorithm with various distance measurement methods, namely Euclidean, Minkowski, and Manhattan distances. The research methodology is composed of four stages: dataset collection, data preprocessing, modeling, and evaluation. The focus of this research is on the optimal K value and the conditions that yield the highest accuracy, considering various scenarios of training and test data splitting ratios and different random state values. The test results indicate that the Minkowski distance method, with a data division ratio of 80% for training data, 20% for test data, and a random state value of 32, provides the best performance, with an optimal K value of 10 and an accuracy of 86.41%.