Publication Search

Communication is a fundamental human need for conveying information and ideas. However, individuals who are deaf and mute face difficulties in communicating with the broader community that does not understand sign language. This study aims to design and implement a real-time static sign language translator into speech using five flex sensors, an MPU6050 sensor, a Raspberry Pi Pico, an ADS1115 ADC module, and a DFPlayer Mini module as the audio output medium. Testing results show that the device successfully recognizes finger movements and hand orientation. The system is capable of playing audio output corresponding to recognized gestures, with the shortest latency recorded at 1.1 seconds and the longest at 2.8 seconds, achieving a detection accuracy rate of 75% based on 60 tests across 12 sign words. This device supports the translation of 12 simple sign words. The implementation demonstrates potential as an assistive communication tool, although further development is needed to improve accuracy, expand vocabulary, and conduct trials directly with deaf or mute users.

Power transformer theft, a pervasive issue disrupting critical infrastructure, necessitates the development of cost-effective and energy-autonomous security solutions. This paper presents the design and implementation of a detection-focused anti-theft framework that integrates a Raspberry Pi Zero W, camera module, and passive infrared (PIR) motion sensors powered by a solar system for continuous monitoring. The system is designed for remote, off-grid deployment, utilizing a headless Raspberry Pi powered by a 5V solar panel and power bank to ensure energy autonomy. Upon motion detection, captured images are processed on the edge device using OpenCV’s Haar Cascade classifier, optimized for upper-body detection to minimize false positives and verify human presence. Captured images are processed locally on the edge device using OpenCV’s Haar Cascade classifier to confirm human presence before an alert is sent to the mobile application, emphasizing real-time operation and low latency. Once an intrusion is confirmed, the images are saved locally and uploaded via the Secure File Transfer Protocol to a custom-developed Android application. The app provides a dedicated remote monitoring interface, enabling secure file transfer and system access, while providing users with immediate notifications and image management capabilities. The system emphasizes low power consumption, real-time operation, and low deployment cost. Tests over 200 triggered events under varied environmental conditions achieved 90% detection accuracy with an average latency of 4.5 s. Solar autonomy was maintained for approximately 24 h under normal operation. It is concluded that the integration of solar power, edge computing of images, and mobile monitoring provides a feasible, scalable, and financially viable framework for securing transformers, especially in resource-constrained environments.

Internet of Things (IoT)-based digital transformation has become a major catalyst in improving the efficiency of operational systems in various sectors, including the modern retail industry. One of the common logistics problems found in supermarket environments is the accumulation of unorganized shopping trolleys, which can hinder service flow and increase staff workload. This study presents a design of an IoT-based autonomous smart trolley system and automatic navigation to address these problems in a structured manner. The system design utilizes the integration of ESP32 and Arduino UNO microcontrollers, ultrasonic sensors for distance detection, line sensors for automatic path navigation, and Raspberry Pi modules for visual image processing in location tracking. The system is designed to be able to independently reposition the trolley to a predetermined parking station. Conceptual analysis shows that this system has significant potential in reducing operational costs, increasing labor efficiency, and strengthening customer service automation. Initial evaluation of technical and economic feasibility aspects strengthens the opportunity for widespread system implementation in the future. This design is the first step in developing a smart retail solution based on adaptive technology that is in line with the principles of Society 5.0. Furthermore, the development of this smart trolley system also considers user safety and comfort through additional features such as anti-collision sensors, an early warning system in the event of technical problems, and a manual control option as an alternative in emergency situations. The integration of Internet of Things-based technology also enables real-time monitoring and management systems through a web-based dashboard or mobile application, which can be accessed by supermarket management for operational analysis. Thus, this system not only addresses internal logistics needs but also contributes to improving the overall customer experience.

This final project presents the design and development of a digital microscope based on Raspberry Pi 4 integrated with Internet of Things (IoT) technology. The aim of this project is to create a digital microscope that allows real-time observation and data sharing over the internet, enhancing accessibility for researchers and students, especially in remote areas. The digital microscope utilizes a high-quality camera (Sony IMX307) for capturing images, which are processed by the Raspberry Pi 4 and displayed on a touchscreen LCD. This project not only facilitates remote learning and collaborative research but also aims to improve the efficiency of scientific observations. The methodology includes the design, assembly, and testing of the microscope, with a focus on functionality and user experience. The results indicate that the digital microscope successfully meets the objectives, providing an affordable and innovative solution for educational and research purposes. Further development and testing will enhance its capabilities, making it more suitable for diverse scientific applications.

This study aims to develop an intuitive and efficient smart home control system by utilizing hand tracking and speech recognition technologies. These technologies employ the OpenCV, Mediapipe, PyAudio, and Speech Recognition libraries to recognize hand gestures and voice commands in real-time. The system is developed using a Raspberry Pi connected to a webcam and microphone as input devices, and a relay to control electronic appliances. The results show a high accuracy rate at optimal light intensity for hand tracking and a specific distance for speech recognition. This system is implemented in an IoT environment to control devices such as lights and door locks. The research is expected to contribute to the development of smarter and more user-friendly smart homes.

Sea water pollution is an increasingly urgent global issue, caused by various factors such as industrial waste, household waste, and ship activities. One of the solutions needed to overcome this pollution is the development of a detection system that is able to monitor polluting substances quickly, accurately, and efficiently. This research aims to design and build a microcontroller-based seawater pollution detection system, which can identify various pollution parameters in real-time. This research uses the Research and Development (R&D) method to develop a system consisting of several main components, including a pH sensor, turbidity sensor, Arduino Uno, GPS module, Raspberry Pi 4, USB camera, LiPo battery, and step-down converter. Each component is tested individually before being integrated into the overall system. The results of testing in a real environment show that the system is able to detect seawater pollution parameters with high accuracy. However, there are some errors in data collection, especially in the camera sensor with a percentage error of 32%, turbidity sensor 20%, and pH sensor 24%. Further improvements and developments were made based on the evaluation results to enhance system performance. The resulting system is considered accurate, reliable and easy to use, making an important contribution to efforts to protect seawater quality and mitigate the negative impacts of pollution on the environment and human health.

The storage space for CO2 gas cylinders is inside the ship's accommodation, so there is a risk of danger if a leak occurs because the ship's accommodation has poor air circulation. This research is devoted to removing dangerous gases from the room. This research designs and modifies a tool that can detect CO2 levels and can provide a danger signal to the surroundings. This modification uses a Raspberry Pi Pico W microcontroller. This research method uses system design, a series of tools with wiring design and uses 2 test plans, namely: testing static and dynamic testing.  Testing the precision of the sensor by reading the CO2 leak detector using a CO2 measuring instrument obtained an average error value of 3.5%. The error value is still categorized as a safe difference value and the prototype works according to the expected function. Testing the function of the tool results in values ​​for the MQ-135 buzzer and exhaust fan sensors which will turn on if the CO2 level is above 600 ppm in accordance with the safe threshold for CO2 levels in the air which has been set in the program. Telegram request bot testing can work well as expected. Testing the Telegram Receive bot can work well as expected. However, for testing Telegram bots, requests and receives are influenced by the internet network.

Research on weather elements is very necessary for the benefit and welfare of mankind, the observed weather elements will become material for predicting the weather in the future. This data is also used to prevent the risk of adverse impacts caused by the weather itself. To measure the weather with this automatic system, a tool called AWS is needed. The AWS design requires a Rasberry Pi. By using this Rasberry Pi we can monitor weather changes originating from BMKG via the web in the form of an Analog Gauge.

The Dental Unit consists of a patient chair, lights, machines and equipment or other equipment accessories needed during surgery to directly examine the inside of the teeth. Doctors usually use a curved mirror to be able to see the inside of the patient's teeth. This will be quite troublesome for doctors because they will not be free to check the condition of the patient's teeth. So in this research, we intend to design a tool that can be used to examine patients' teeth using a camera equipped with a wireless connection on a PC so that the results of the doctor's examination can be seen on the monitor screen. Measurement point 1 (TP1) of the PLN network with an average of 221.68 and an error value of 0.76%. Measurement point 2 (TP2) Rasberry power supply with an average of 4.61 and an error value of 8%. Measurement point 3 (TP3) keyboard with an average of 4.73 and an error value of 7%. Measurement point 4 (TP4) dental camera with an average of 4.53 and an error value of 9.3%. Measurement point 5 (TP5) rasberry fan cooler with an average of 5.05 and an error value of 1%. In testing the function of the camera module in the dental unit, the author will present images taken when testing the function of the device, when the camera is inserted into the patient's mouth and produces good images. measurements performed by researchers on monitor resources      

Suara manusia memiliki banyak sekali karakteristik. Ada yang memiliki suara berat, suara yang lembut, suara yang tinggi, suara yang rendah dan lain sebagainya. Manusia dapat mengenali karakteristik suara tersebut dan mengerti hal-hal yang diucapkan. Berbagai inovasi telah dikeluarkan untuk merancang suatu kecerdasan buatan untuk mengerti arti ucapan yang diberikan oleh manusia. Hal ini menjadi ketertarikan bagi penulis untuk merancang sistem pengenalan suara. Rancangan yang dibuat penulis adalah membuat sistem pengenalan suara yang berbasis Google Speech API pada Smartphone Android untuk dapat mengendalikan sepeda motor dengan menggunakan teknologi Bluetooth HC-05 pada Raspberry Pi. Penelitian ini menggunakan 3 tahap pengujian. Pengujian pertama merupakan pengujian untuk mengetahui jarak ideal antara bibir dengan microphone pada Smartphone Android saat memberikan perintah kepada sepeda motor. Pengujian kedua dilakukan untuk mengetahui jarak ideal untuk berkomunikasi antara Smartphone Android dengan Raspberry Pi, dan pengujian ketiga adalah untuk merancang sistem keamanan tambahan dengan menggunakan sidik jari pada Smartphone Android. Hasil yang didapatkan pada pengujian pertama adalah persentase keberhasilan tertinggi berada pada jarak 5cm dengan nilai sebesar 99.17% dan tingkat terendah pada jarak 30cm antara bibir dengan microphone dengan nilai sebesar 78.33%. Pengujian kedua didapatkan hasil bahwa jarak maksimal untuk melakukan komunikasi antara Smartphone Android dengan modul Bluetooth HC-05 pada Raspberry Pi adalah sebesar 20m, lebih dari itu perangkat tidak dapat berkomunikasi. Pengujian ketiga didapatkan hasil bahwa selain sidik jari yang terdaftar maka user tidak dapat menggunakan aplikasi yang telah dirancang karena aplikasi akan melakukan looping secara terprogram.

Pelacakan objek merupakan suatu proses untuk menentukan dan mengikuti posisi dari sebuah objek bergerak yang diinginkan menggunakan kamera secara realtime. Ada berbagai macam algoritma dalam pembuatan sistem pelacakan objek, salah satunya adalah algoritma correlation tracker pada pustaka DLIB. Sistem pelacakan objek ini menggunakan Raspberrry Pi 4 yang berisi program python untuk pelacakan objek. Pi Camera digunakan sebagai input gambar video realtime. Hasil penggunaan algoritma correlation tracker yang ada pada pustaka DLIB, yaitu proses pelacakan objek dapat berjalan dengan baik. Terdapat 5 objek yang dilacak dan hasilnya kotak pelacakan selalu berada di sekitar objek, baik saat objek bergerak ke kiri, ke kanan, maju dan mundur. Apabila objek bergerak maju dan mundur, skala pada kotak pelacakan dapat berubah mengikuti ukuran objek. Performa pada Raspberry Pi dapat dilihat dari framerate video sebesar 10,5 fps.

Security aspects is needed in various fields of life today. Safety is becoming a concern for everyone. One of the important concerns is the security of the room. The indoor security system uses Raspberry Pi and RFID based Firebase Cloud Messaging and Motion Detection Camera, is a room security system that includes expensive equipment, so this device is designed for protection or robbery and also provides assistance in advance. . The security system in this room consists of several parts, namely Raspberry Pi as a brain system, selenoid door lock as an electric lock on the door, RFID system and CCTV camera as a detector of the amount of human movement, PIR sensor as a detector of human temperature, alarm as an indicator of intruders which transfers rooms, and database applications as user storage databases for security recorders