D4 Teknologi Rekayasa Robotika

Permanent URI for this collectionhttps://repository.polibatam.ac.id/handle/PL029/1765

Browse

Filters

2023 - 202437

Settings

Search Results

Now showing 1 - 10 of 37
  • Repository Politeknik Negeri Batam
    Item
    Pengembangan Application Programming Interface pada Database MongoDB menggunakan FastAPI
    (2024-08-16) wahyi, afdal; jamzuri, eko rudiawan
    Pengembangan aplikasi online dan seluler saat ini merupakan aspek penting dalam dunia perangkat lunak yang dinamis. Permintaan akan proses perizinan yang efisien, responsif, dan terhubung dengan layanan dan sumber daya lain semakin meningkat. Application Programming Interface (API) memainkan peran penting dalam memastikan interoperabilitas dan komunikasi yang efektif antara komponen perangkat lunak. Representational State Transfer API (RESTAPI) adalah jenis API yang banyak digunakan, menggunakan protokol HTTP untuk mentransfer data dalam format JSON atau XML. Inovasi terkini dalam pengembangan API adalah FastAPI, sebuah kerangka pemrograman web Python yang efisien dan kuat. Integrasi FastAPI dengan MongoDB, basis data NoSQL yang fleksibel, memberikan solusi efektif dalam pengembangan aplikasi modern. FastAPI memungkinkan pembuatan API dengan validasi data otomatis dan dokumentasi terintegrasi, sementara MongoDB mendukung penyimpanan data yang dapat berkembang dan mengatasi pertumbuhan skala horizontal. Hasil penelitian ini menunjukkan waktu respons menggunakan koneksi kabel LAN yang lebih rendah dengan rata-rata 33.4 ms dibandingkan jaringan WiFi dengan rata-rata 1674.9 ms, sehingga integrasi FastAPI dan MongoDB mampu menghasilkan aplikasi yang responsif, efisien, dan mampu menangani data yang terus berkembang pesat, menjadikannya solusi yang sesuai dengan kebutuhan aplikasi kontemporer.
  • Repository Politeknik Negeri Batam
    Item
    Implementasi Protokol Komunikasi Data Modbus TCP/IP pada Perangkat Kamera Cerdas Berbasis Raspberry Pi
    (Politeknik Negeri Batam, 2024-01-12) Aryani, Yeni; Jamzuri, Eko Rudiawan
    Protokol Modbus TCP/IP dirancang sebagai solusi bagi kompleksitas interaksi antara manusia dan mesin, serta meningkatnya kebutuhan akan keselamatan tinggi di lingkungan industri. Berfungsi sebagai jembatan data, protokol ini telah terbukti mendukung sistem Kesehatan dan Keselamatan Kerja industri. Dengan kecepatan transfer mencapai 0,01994 Mbps, latensi 2,01229 ms, dan integrasi Pemantauan Objek, protokol ini memberikan solusi komprehensif untuk meningkatkan kinerja dan keamanan di berbagai sektor industri. Penggunaan Protokol Modbus TCP/IP mampu meningkatkan keselamatan pekerja, meminimalisir risiko kecelakaan, dan mengoptimalkan produktivitas, menjadikannya inovasi penting dalam mencapai standar keselamatan tinggi dan efisiensi di lingkungan industri.
  • Repository Politeknik Negeri Batam
    Item
    Finger Recognition Detection System Using Mediapipe as Communication Solution for People with Disabilities
    (Atlantis Press, 2024-12-25) M.WAHYU ELFANDER M.WAHYU ELFANDER; Wijaya, Ryan Satria
    Sign language is a language used by people with disabilities, especially the deaf and mute to communicate. The problem is, not everyone can understand sign language. This study aims to create a system that can translate sign language. The system can also produce sound with the text to voice method. The system is built using Mediapipe to detect fingers that form sign language. The system performs classification by combining 2 machine learning models with the Artificial Neural Network (ANN) method. The first model is used to classify letters A-Z and the second model is used to classify movement patterns in letters J and Z. The accuracy of the first model is 94% and the accuracy of the second model is 95%. The model will also be evaluated using the confusion matrix technique to find recall, f1-score, and precision of 25 letters or classes.
  • Repository Politeknik Negeri Batam
    Item
    Depth Realsense Camera-Based Human Detection Using Yolov5
    (2024-07-15) Putri Suside Simanjuntak, Wati; Wibisana, Anugerah
    Penelitian ini mengembangkan sistem deteksi manusia berbasis kamera depth Intel RealSense D455 menggunakan algoritma YOLOv5n. Sistem ini dirancang untuk mengatasi tantangan deteksi objek dalam berbagai kondisi lingkungan dan pencahayaan, serta untuk aplikasi real-time dengan keterbatasan perangkat keras. Hasil pengujian menunjukkan bahwa sistem ini memiliki akurasi tinggi dalam mendeteksi jarak dan sudut pada siang hari, dengan tingkat kesalahan gabungan sekitar 2.439%. Namun, kinerja sistem menurun pada malam hari dengan tingkat kesalahan gabungan mencapai sekitar 10.042%, menunjukkan kerentanan terhadap perubahan pencahayaan rendah. Evaluasi menggunakan metrik mean Average Precision (mAP) menunjukkan model mencapai nilai mAP sebesar 0.99 pada threshold IoU 0.5 dan nilai rata-rata mAP sebesar 0.9 pada berbagai threshold dari 0.5 hingga 0.95, menandakan akurasi tinggi dalam deteksi dan klasifikasi objek. Integrasi informasi kedalaman dari kamera RealSense dan kemampuan deteksi real-time dari YOLOv5n menunjukkan efektivitas yang baik dalam deteksi manusia. Namun, diperlukan peningkatan lebih lanjut untuk meningkatkan kinerja dalam kondisi pencahayaan rendah. Secara keseluruhan, sistem yang dikembangkan menunjukkan potensi signifikan dalam aplikasi deteksi manusia terutama dalam kondisi pencahayaan terang namun memerlukan penyesuaian lebih lanjut untuk konsistensi deteksi dalam berbagai kondisi pencahayaan.
  • Repository Politeknik Negeri Batam
    Item
    Comparative Study of Deep Learning Algorithms Between YOLOv5, YOLOv7 and YOLOv8 As Fast and Robust Outdoor Object Detection Solutions
    (Journal of Applied Electrical Engineering, 2024-06-01) Santonius; Wijaya Ryan Satria S.Tr.T., M.Tr.T.
    object detection is one of the most popular applications among young people, especially among millennials and generation Z. The use of object detection has become widespread in various aspects of daily life, such as face recognition, traffic management, and autonomous vehicles. The use of object detection has expanded in various aspects of daily life, such as face recognition, traffic management, and autonomous vehicles. To perform object detection, large and complex datasets are required. Therefore, this research addresses what object detection algorithms are suitable for object detection. In this research, i will compare the performance of several algorithms that are popular among young people, such as YOLOv5, YOLOv7, and YOLOv8 models. By conducting several Experiment Results such as Detection Results, Distance Traveled Experiment Results, Confusion Matrix, and Experiment Results on Validation Dataset, I aim to provide insight into the advantages and disadvantages of these algorithms. This comparison will help young researchers choose the most suitable algorithm for their object detection task.
  • Repository Politeknik Negeri Batam
    Item
    Development of Graphical User Interface for Drones Vehicles in Warehouse Inventory Management System
    (2023-12-21) Hidayat Fatahillah; Kannedi Ajie Rizki; Farkhani M.Zotie; Risi Faiz Albar; Nakul Fitriyanti; Nakul Fitriyanti
    This research introduces an innovative approach to enhance warehouse inventory management through unmanned aircraft technology. The study focuses on the development and testing of user-friendly graphical user interfaces (GUI) for the Unmanned Aircraft (UAV) Control Page and the Inventory Data Processing Page. The Unmanned Aircraft Control Page testing validated successful Unmanned Aircraft connections, Micro Air Vehicle Link to Robot Operating System (MAVROS) system activations, and data monitoring of Unmanned Aircraft status. Efficiency comparisons revealed significantly shorter flight preparation times with the GUI compared to conventional methods. Testing on the Inventory Data Processing Page ensured seamless functionality of data tables, database connections, and data export features. The results provide a robust assessment of interface reliability and quality. Statistical analysis confirmed the GUI's consistent superiority in reducing flight preparation times. These findings underscore the GUI's potential to enhance operational efficiency in UAVs dedicated to inventory tasks.
  • Repository Politeknik Negeri Batam
    Item
    Implementasi Protokol Komunikasi Data Modbus TCP/IP pada Perangkat Kamera Cerdas Berbasis Raspberry Pi
    (Politeknik Negeri Batam, 2024-01-12) Aryani, Yeni;
    Protokol Modbus TCP/IP dirancang sebagai solusi bagi kompleksitas interaksi antara manusia dan mesin, serta meningkatnya kebutuhan akan keselamatan tinggi di lingkungan industri. Berfungsi sebagai jembatan data, protokol ini telah terbukti mendukung sistem Kesehatan dan Keselamatan Kerja industri. Dengan kecepatan transfer mencapai 0,01994 Mbps, latensi 2,01229 ms, dan integrasi Pemantauan Objek, protokol ini memberikan solusi komprehensif untuk meningkatkan kinerja dan keamanan di berbagai sektor industri. Penggunaan Protokol Modbus TCP/IP mampu meningkatkan keselamatan pekerja, meminimalisir risiko kecelakaan, dan mengoptimalkan produktivitas, menjadikannya inovasi penting dalam mencapai standar keselamatan tinggi dan efisiensi di lingkungan industri.
  • Repository Politeknik Negeri Batam
    Item
    Implementasi Algoritma SSD MobileDets untuk Mendeteksi Aktivitas Operator Memasuki Area Hazard di Sekitar Mesin
    (2024-01-15) Fikri, Abdillah; Jamzuri, Eko Rudiawan
    Abstract— Safety laser scanners are the main sensors proposed to protect work accidents in the industrial sector. However, they are expensive and limited to a 2D scanning area. Therefore, in this final project, research is carried out related to low-cost sensors using monocular cameras and Edge TPU as an alternative security laser scanner. The system can inform safety warnings using green, yellow, and red indicator lights, and use warning sounds using a buzzer in dangerous conditions. I captured the safe area using a monocular camera and processed the MobileDets SSD deep learning object detection image. To be able to detect objects, the person data that has been collected will be carried out a model training process, the model training process is carried out in order to produce a model that is ready for use. During the training process, the model obtained an mAP value of 0.217% on the validation data, and obtained an mAP value of 0.274% on the test data. Next, the object detector was run on Edge TPU, a USB device to accelerate the deep learning process. The resulting object detector model can detect objects in the form of people with an average accuracy of 73,81%. The object detector will recognize people and mark them with a bounding box. From the resulting bounding box, the object coordinates are then calculated to analyze people entering the safe area. When a person is detected entering a safe area, the system will provide a warning with the resulting indicator light. In addition, this system can generate security signals using USB Input/Output that can be integrated with machine or robot controllers
  • Repository Politeknik Negeri Batam
    Item
    Minimize UAV Landing Error by Development of Precision Landing System Based on Object Detection
    (2023-12-21) Rizki Kanedi, Ajie; Nakul, Fitriyanti
    Unmanned Aerial Vehicle (UAV) or commonly known as drones have undergone various kinds of technological developments, so that they are widely utilized in any field, in this paper focuses on developing a precision landing system for drones when completed in an RFID tag mission in a warehouse, utilizing technologies such as Pixhawk, Raspberry Pi, Intel Realsense T265 for navigation, and a webcam to help detect objects for precision landing of drones. The system of precision landing combines or communicates from Intel Realsense T265 and Vision Camera, which detects a marker where the drone is landing, then Pixhawk receives the command. The addition of this object detection-based precision landing system is to minimize the drone landing error if it only utilizes Intel RealSense T265, thus the development of this precision landing system minimizes the error from the drone when landing, so that the drone still lands in a safe area or predetermined place.
  • Repository Politeknik Negeri Batam
    Item
    Altitude Optimization Based on TF Mini Plus LiDAR as a Guided System for Autonomous Drones in Inventory Management
    (2023-12-21) Farkhani, M Zotie; Risi, Faiz Albar; Kanedi, Ajie Rizki; Hidayat, Fatahillah; Nakul, Fitriyanti; Nakul, Fitriyanti
    This research is an in-depth look at optimizing drone operations by integrating LiDAR sensors for more advanced altitude control, with a particular focus on inventory management. This study evaluates the performance of drones using three main sensors: Benewake TFmini Plus LiDAR, IMU Intel Realsense Tracking Camera, and Pixhawk Barometer. Autonomous drone missions included 5-meter and 10-meter forward flights, as well as obstacle recognition scenarios. Measurement datasets from 50 cm to 500 cm at 50 cm intervals were used as the basis for comparison of sensor accuracy and consistency. The experimental results illustrate the drone's dynamic response to LiDAR under various flight conditions, highlighting its adaptability and precision. This research makes a significant contribution to the understanding of the effectiveness of LiDAR sensors in height measurement, particularly in the context of inventory management in complex indoor environments. The findings stimulate further discussion on the potential development of autonomous drone technology for inventory management in the future.