Garuda - Garba Rujukan Digital

Sistem Pengaturan Pencahayaan Ruangan Berbasis Android pada Rumah Pintar Putro, Muhamad Dwisnanto; Kambey, Feisy D.
JURNAL NASIONAL TEKNIK ELEKTRO Vol 5, No 3: November 2016
Publisher : Jurusan Teknik Elektro Universitas Andalas

Smart Home generally pay attention to energy efficiency can be maximized by using natural lighting during the day, the layout of the lighting, the use of electrical equipment that are energy efficient and use energy-saving lamps. lighting control system should normally only uses the principle on / off and impractical to operate, This system still has the disadvantage of effectiveness.Besides all the convenience factor and needs in lighting the room became an important influence on the health of human eyesight. The purpose of this research is to build an efficient lighting control system, practical, according to the needs and equipped with the optimization of the lighting control based on efficiency and standard of room lightning SNI 03-6197-2000. This system was designed practically controlled remotely using a smartphone android device. This research is helpful to people occupying the residence so that they can feel comfortable, efficient and practical to operate the lighting control system in smart home. In its design of this system consists of hardware design and software design hardware design consist of the design of sensors, actuators, controllers and remote control. While for design of the software consists of intelligent programming algorithms and programming mobile systems. In the design of intelligent programming using arduino IDE application while the mobile programming using the application APP INVENTOR 2. Disadvantages of this system is the method of determining the value parameter, the parameter value ranges are narrow and the fast response changes in light intensity makes this system is not stable.Keywords: Smart Home, Lighting the Room, AndroidÂ Abstrak - Rumah pintar pada umumnya memperhatikan efesiensi pemakaian energi yang dapat dimaksimalkan dengan memakai pencahayaan alami di siang hari, tata letak lampu penerangan yang tepat, pemakaian peralatan listrik yang hemat energi dan pemakaian lampu hemat energi. Sistem lampu pengaturan penerangan ruangan pada umunya hanya menggunakan prinsip on/offÂ dan tidak praktis untuk dioperasikan, Sistem ini masih memiliki kelemahan yaitu dalam hal efektifitas. Selain dari pada itu faktor kenyamanan dan kebutuhan dalam penerangan ruangan menjadi pengaruh penting untuk kesehatan penglihatan mata manusia. Adapun tujuan dari penelitian ini yaitu membangun sistem pengaturan pencahayaan yang efisien, praktis, sesuai kebutuhan dan dilengkapi dengan optimasi pengaturan pencahayan berdasarkan efesiensi dan standar penerangan ruangan SNI 03-6197-2000. Sistem ini pun dirancang praktis yang dikendalikan secara jarak jauh dengan menggunakan perangkat android smartphone. Penelitian ini bermanfaat bagi masyarakat penghuni rumah tinggal sehingga dapat merasa nyaman, efisien dan praktis untuk mengoperasikan sistem pengaturan pencahayaan pada rumah pintar. Pada perancangannya sistem ini terdiri atas perancangan perangkat keras dan perancangan perangkat lunak perancangan perangkat keras terdiri atas perancangan sensor, aktuator, pengendali dan pengendalian jarak jauh. Sedangkan untuk perancangan perangkat lunak terdiri atas algoritma pemograman cerdas sistem dan pemograman mobile. Pada perancangan pemograman cerdas menggunakan aplikasi Arduino IDE sedangkan pada pemograman mobile menggunakan aplikasi APP INVENTOR 2. Pada Aplikasi smartphone berbasis android menghasilkan pengendalian sistem pengaturan pencahayaan rungan yang dapat dikendalikan secara mode manual dan mode otomatis melalui media nirkabel bluetooth. Kekurangan dari sistem ini adalah dalam penentuan metode nilai parameter, dengan cakupan nilai parameter yang sempit dan respon perubahan intensitas cahaya yang cepat membuat sistem ini belum stabil.Kata Kunci : Rumah pintar, Pengaturan Pencahayaan Ruangan, Android

Sistem Pengaturan Pencahayaan Ruangan Berbasis Android pada Rumah Pintar Muhamad Dwisnanto Putro; Feisy D. Kambey
JURNAL NASIONAL TEKNIK ELEKTRO Vol 5 No 3: November 2016
Publisher : Jurusan Teknik Elektro Universitas Andalas

Smart Home generally pay attention to energy efficiency can be maximized by using natural lighting during the day, the layout of the lighting, the use of electrical equipment that are energy efficient and use energy-saving lamps. lighting control system should normally only uses the principle on / off and impractical to operate, This system still has the disadvantage of effectiveness.Besides all the convenience factor and needs in lighting the room became an important influence on the health of human eyesight. The purpose of this research is to build an efficient lighting control system, practical, according to the needs and equipped with the optimization of the lighting control based on efficiency and standard of room lightning SNI 03-6197-2000. This system was designed practically controlled remotely using a smartphone android device. This research is helpful to people occupying the residence so that they can feel comfortable, efficient and practical to operate the lighting control system in smart home. In its design of this system consists of hardware design and software design hardware design consist of the design of sensors, actuators, controllers and remote control. While for design of the software consists of intelligent programming algorithms and programming mobile systems. In the design of intelligent programming using arduino IDE application while the mobile programming using the application APP INVENTOR 2. Disadvantages of this system is the method of determining the value parameter, the parameter value ranges are narrow and the fast response changes in light intensity makes this system is not stable.Keywords: Smart Home, Lighting the Room, Android Abstrak - Rumah pintar pada umumnya memperhatikan efesiensi pemakaian energi yang dapat dimaksimalkan dengan memakai pencahayaan alami di siang hari, tata letak lampu penerangan yang tepat, pemakaian peralatan listrik yang hemat energi dan pemakaian lampu hemat energi. Sistem lampu pengaturan penerangan ruangan pada umunya hanya menggunakan prinsip on/off dan tidak praktis untuk dioperasikan, Sistem ini masih memiliki kelemahan yaitu dalam hal efektifitas. Selain dari pada itu faktor kenyamanan dan kebutuhan dalam penerangan ruangan menjadi pengaruh penting untuk kesehatan penglihatan mata manusia. Adapun tujuan dari penelitian ini yaitu membangun sistem pengaturan pencahayaan yang efisien, praktis, sesuai kebutuhan dan dilengkapi dengan optimasi pengaturan pencahayan berdasarkan efesiensi dan standar penerangan ruangan SNI 03-6197-2000. Sistem ini pun dirancang praktis yang dikendalikan secara jarak jauh dengan menggunakan perangkat android smartphone. Penelitian ini bermanfaat bagi masyarakat penghuni rumah tinggal sehingga dapat merasa nyaman, efisien dan praktis untuk mengoperasikan sistem pengaturan pencahayaan pada rumah pintar. Pada perancangannya sistem ini terdiri atas perancangan perangkat keras dan perancangan perangkat lunak perancangan perangkat keras terdiri atas perancangan sensor, aktuator, pengendali dan pengendalian jarak jauh. Sedangkan untuk perancangan perangkat lunak terdiri atas algoritma pemograman cerdas sistem dan pemograman mobile. Pada perancangan pemograman cerdas menggunakan aplikasi Arduino IDE sedangkan pada pemograman mobile menggunakan aplikasi APP INVENTOR 2. Pada Aplikasi smartphone berbasis android menghasilkan pengendalian sistem pengaturan pencahayaan rungan yang dapat dikendalikan secara mode manual dan mode otomatis melalui media nirkabel bluetooth. Kekurangan dari sistem ini adalah dalam penentuan metode nilai parameter, dengan cakupan nilai parameter yang sempit dan respon perubahan intensitas cahaya yang cepat membuat sistem ini belum stabil.Kata Kunci : Rumah pintar, Pengaturan Pencahayaan Ruangan, Android

Robot Pintar Pengukur Kepuasan Konsumen pada Pusat Perbelanjaan Muhamad Dwisnanto Putro; Jane Litouw
Jurnal Teknologi dan Sistem Komputer Volume 6, Issue 1, Year 2018 (January 2018)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

The shopping center generally uses the questionnaire instrument in measuring the level of customer satisfaction services. Processing and presentation of conventional questionnaire data tend to be long and less effective. The problem will be solved by using smart robots to measure consumer satisfaction at shopping centers. This robot has a digital questionnaire module located on the robot's chest and the facial module that is used as a robot expression when the consumer chooses to be satisfied or not with the shopping center service. The digital robot questionnaire module is able to accommodate, store and process customer satisfaction data in statistics. Robotic expression when receiving a choice of consumer satisfaction in the form of happy or disappointed facial expressions combined with a voice expression in the form of thanks to customers who have visited.

Robot Pintar Penyambut Costumer pada Pusat Perbelanjaan Kota Manado Muhamad Dwisnanto Putro; Jane Litouw
Jurnal Rekayasa Elektrika Vol 13, No 1 (2017)
Publisher : Universitas Syiah Kuala

Aspects of robotics technology have now been able to explore and reach the entertainment, education, and health. Making robots with privileges and special expertise is closely related to the needs of the modern world that requires a device with a high capacity are useful to help the work of man. On the other hand, advanced technology is useful to complete the work that could not and did not want to do by men as a greeter job. Greeter costumer jobs is a very tedious job. So it is necessary in the field of robotics technology that is smart robot greeter customers that replace the role of humans to improve the quality of waiters, efficiency, and economical savings at shopping centers in the city of Manado. The smart robot is designed to greet the customer by giving the greeting on the customer entrance and exit shopping center. The robot system is powered with less use of multiple technologies including ultrasonic distance and PIR sensors to detect humans, servo and DC motor as an actuator of the robot, and use voice module so that the robot can speak. The robot system is also equipped with a remote control using the Android smartphone so the smart robot can perform monitoring, operation, and control over long distances. The test results describe the action of robots have been able to make the detection of costumer and activities greeting the customer with the analysis of determining the value of the parameter distance between ultrasonic sensors use trigonometry comparative analysis.

Robot Pintar Penyambut Costumer pada Pusat Perbelanjaan Kota Manado Muhamad Dwisnanto Putro; Jane Litouw
Jurnal Rekayasa Elektrika Vol 13, No 1 (2017)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v13i1.5901

Aspects of robotics technology have now been able to explore and reach the entertainment, education, and health. Making robots with privileges and special expertise is closely related to the needs of the modern world that requires a device with a high capacity are useful to help the work of man. On the other hand, advanced technology is useful to complete the work that could not and did not want to do by men as a greeter job. Greeter costumer jobs is a very tedious job. So it is necessary in the field of robotics technology that is smart robot greeter customers that replace the role of humans to improve the quality of waiters, efficiency, and economical savings at shopping centers in the city of Manado. The smart robot is designed to greet the customer by giving the greeting on the customer entrance and exit shopping center. The robot system is powered with less use of multiple technologies including ultrasonic distance and PIR sensors to detect humans, servo and DC motor as an actuator of the robot, and use voice module so that the robot can speak. The robot system is also equipped with a remote control using the Android smartphone so the smart robot can perform monitoring, operation, and control over long distances. The test results describe the action of robots have been able to make the detection of costumer and activities greeting the customer with the analysis of determining the value of the parameter distance between ultrasonic sensors use trigonometry comparative analysis.

A Lightweight Drowning Person Detection Using Deep Learning Algorithm Ni Made Shavitri Mustikayani; Dayen Manoppo; Marsel Marhaen Wungow; Wahyuni Fithratul Zalmi; Muhamad Dwisnanto Putro
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9841

Visual obstructions and fatigue often hinder human surveillance in preventing drowning incidents. Manual surveillance methods are susceptible to visual obstructions, distractions from crowds, and fatigue. To address these issues, this study proposes an automated real-time drowning detection system that utilizes state-of-the-art deep learning techniques. We use the YOLOv12-Nano architecture, selected for its balance between detection accuracy and computational efficiency. This model was trained and evaluated on the SelfMade dataset, which covers various water conditions and poses indicating swimmers in distress. In testing, YOLOv12-Nano achieved a mAP@50 of 0.984 and a mAP@50-95 of 0.732, with 2.52 million parameters and a computational requirement of 6 GFLOPs. These results demonstrate that YOLOv12-Nano-based automatic detection provides reliable, resource-efficient real-time monitoring, is suitable for implementation on real-world application, and can support human surveillance and accelerate emergency responses to reduce fatal drowning accidents.

Detection of Vehicle License Plates Using YOLO11: Deteksi Tanda Nomor Kendaraan Bermotor menggunakan Algoritma YOLO11 Samuel Meinus Untu; Salvius P. Lengkong; Muhamad Dwisnanto Putro
Jurnal Teknik Elektro dan Komputer Vol. 15 No. 2 (2026): Jurnal Teknik Elektro dan Komputer
Publisher : Universitas Sam Ratulangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35793/jtek.v15i2.63538

Abstract — An automatic vehicle license plate detection and recognition system was developed by integrating the YOLO11n algorithm with EasyOCR. The objective is to build a computer vision-based system capable of accurately detecting license plate positions and recognizing alphanumeric characters under real-world campus conditions at Sam Ratulangi University. The detection model achieved high performance with 97% precision, 98.4% recall, 97.7% F1-score, and 99% mAP@0.5. Character recognition using EasyOCR demonstrated near-zero Character Error Rate (CER) and Word Error Rate (WER) across most test images. Video testing with a three-hour duration recorded 1,757 successfully detected vehicles out of 2,866, resulting in a 61.3% detection accuracy. These results indicate that the integration of YOLO11n and EasyOCR provides an efficient, accurate, and adaptive solution for Automatic License Plate Recognition (ALPR) systems under varying lighting and plate orientation conditions. Key words — YOLO11n; EasyOCR; object detection; character recognition; Automatic License Plate Recognition (ALPR) Abstrak — Sistem deteksi dan pengenalan tanda nomor kendaraan bermotor otomatis dikembangkan dengan mengintegrasikan algoritma YOLO11n dan EasyOCR. Tujuannya adalah membangun sistem berbasis visi komputer yang mampu mendeteksi posisi plat nomor serta membaca karakter alfanumeriknya secara akurat pada kondisi nyata di lingkungan kampus Universitas Sam Ratulangi. Hasil pengujian menunjukkan performa deteksi tinggi dengan nilai precision sebesar 97%, recall 98,4%, F1-score 97,7%, dan mAP@0.5 99%. Proses pengenalan karakter melalui EasyOCR menunjukkan tingkat kesalahan rendah dengan nilai CER dan WER mendekati 0 pada sebagian besar citra uji. Pengujian video berdurasi tiga jam menunjukkan sistem mampu mendeteksi 1.757 dari total 2.866 kendaraan dengan tingkat keberhasilan 61,3%. Hasil tersebut membuktikan bahwa integrasi YOLO11n dan EasyOCR efektif diterapkan untuk sistem Automatic License Plate Recognition (ALPR) yang efisien, akurat, dan adaptif terhadap variasi pencahayaan serta orientasi plat nomor di lapangan. Kata kunci — YOLO11n; EasyOCR; deteksi objek; pengenalan karakter; Automatic License Plate Recognition (ALPR)

Studi Perbandingan Model Lightweight YOLOv12 untuk Deteksi Objek Bawah Air Secara Real-Time Hebron Prasetya; Revin R. Balo; Tasya Tumbal; Alwin M. Sambul; Muhamad Dwisnanto Putro
Jurnal Telematika Vol. 20 No. 2 (2025)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v20i2.799

Metode deep learning dalam computer vision berperan penting dalam pelokalan objek menggunakan sensor berbasis kamera dengan Convolutional Neural Networks sebagai pendekatan utama dalam deteksi objek. Namun, banyak model yang ada memiliki biaya komputasi yang tinggi akibat arsitektur yang dalam dan operasi yang kompleks sehingga membatasi penerapannya untuk kebutuhan waktu nyata pada perangkat berbiaya rendah dan dengan sumber daya terbatas. Arsitektur YOLOv12 menawarkan beberapa varian ringan yang dirancang untuk meningkatkan efisiensi komputasi. Penelitian ini mengevaluasi keseimbangan antara efisiensi dan kinerja deteksi dengan membandingkan berbagai varian model berdasarkan jumlah parameter, operasi floating-point, dan kecepatan inferensi, serta mengukur akurasi menggunakan mean average precision. Hasil evaluasi ini digunakan untuk menilai kesesuaian model yang ringan dalam penerapan waktu nyata pada lingkungan dengan sumber daya terbatas, seperti pemantauan dan konservasi bawah air. Hasil eksperimen pada dataset real-world underwater object detection menunjukkan bahwa YOLOv12-nano memiliki akurasi 5,7% lebih rendah dibandingkan YOLOv12-medium, namun hanya membutuhkan 2,57 juta parameter dan 6,5 GFLOPs, jauh lebih kecil dibandingkan YOLOv12-medium yang memiliki 20,1 juta parameter dan 67,8 GFLOPs. Selain itu, YOLOv12-small membutuhkan 9,26 juta parameter dan 21,5 GFLOPs sehingga berada di antara varian nano dan medium dari sisi kompleksitas, dengan akurasi yang tetap kompetitif. Pada proses inferensi, YOLOv12-nano mencapai kecepatan 16,48 FPS pada CPU Intel(R) Core (TM) i5-12450HX generasi ke-12. Sebagai perbandingan, YOLOv12-small berjalan pada 6,28 FPS, sedangkan YOLOv12-medium mencapai 2,36 FPS. Hasil ini menunjukkan bahwa YOLOv12-nano merupakan varian yang paling sesuai untuk penerapan waktu nyata pada platform berbasis CPU.

DOLPHIN DETECTION USING AN ENHANCED LIGHTWEIGHT YOLO ARCHITECTURE Febriyanti Ludja; Robby Moody Lintong; Florensce Sumarauw; Alwin M. Sambul; Steven R. Sentinuwo; Muhamad Dwisnanto Putro
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 3 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i3.9169

Dolphin detection plays an important role in marine ecosystem monitoring, species conservation, and behavioral analysis. However, visual identification in underwater environments faces challenges such as light refraction, water turbidity, and dynamic sea conditions. This study proposes a deep learning-based dolphin detection approach by modifying the YOLOv8 architecture to produce a lightweight yet accurate model. The modifications include reducing the number of channels in the backbone and neck, as well as simplifying the SPPF block, thereby reducing the model parameters from 3.01 million to 1.83 million and the computational complexity from 8.2 GFLOPs to 7.2 GFLOPs. A specialized dolphin dataset consisting of 5,493 labeled images, collected from underwater and surface conditions, was developed to train and evaluate the model. Experimental results show that the proposed model achieves 67.1% mAP@50 and 45.8% mAP@50–95, outperforming YOLOv8-Nano and other lightweight YOLO variants. Additionally, the model demonstrates better runtime efficiency, with a latency of 49.2 ms and 20.38 FPS, making it suitable for real-time implementation on resource-constrained devices. Overall, this research presents a more efficient and accurate dolphin detection solution, while also providing a specialized dataset that can support further research in the field of computer vision-based marine conservation.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search