Garuda - Garba Rujukan Digital

Design of Application On/Off Electronic Device with Markov Model Using Speech Recognition on Android Widyatmoko, Rochman; Purwantoro E. S. G, Sugeng; Syahbana S, Yoanda Alim
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 3, August 2018
Publisher : Universitas Muhammadiyah Malang

Electronic devices are supported by a switch that is used to turn the device on and off. Manually pressed switches with distances between remote switches to cause less efficiency in saving human time and manpower. This can be solved by building a system to control electronic devices automatically. The system uses human voice commands to turn on and off electronic devices. The command will be processed into text by the Google Voice Speech Recognition library. The Android app sends human commands that have been processed by Arduino Uno R3 microcontroller. Commands are obtained after the text and data in the database are processed using the Markov Model algorithm. Communication between Android smartphone and microcontroller will be designed through a WIFI network. This system is tested based on noise level with data accuracy level with noise 0-45 dB and obtained 65% result. Based on the test response time obtained that the noise level 0-45 dB obtained results of 5.41 seconds. Based on the test results from the scenario, it can be concluded that the lower the noise generated, the better the system will also respond to commands. From the test suitability get value X = 1, meaning that the system is suitability with error rate 0. In testing accuracy to view status function get value 0 with error level 0. Testing of Markov model algorithm yields the calculated 0.125 algorithms manually and code for each command

Perancangan dan Implementasi Website sebagai Media Survei Kualitas Video berdasarkan ITU-P.910 Yoanda Alim Syahbana
Annual Research Seminar (ARS) Vol 2, No 1 (2016)
Publisher : Annual Research Seminar (ARS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Pengukuran kualitas video adalah proses penting dalam menjaga kualitas layanan video. Proses ini bisa dilakukan dengan dua pendekatan. Pendekatan pertama dilakukan dengan menggunakan algoritma pengukur kualitas video secara objektif. Pendekatan ini unggul dalam kecepatan namun lemah dalam akurasi pengukuran. Pendekatan kedua dilakukan berdasarkan hasil survei kualitas video secara subjektif. Pendekatan ini lebih akurat dibandingkan dengan yang pertama namun membutuhkan banyak waktu dan tenaga. Untuk menanggulangi masalah waktu dan tenaga, penelitian ini fokus pada perancangan dan implementasi website sebagai media survei kualitas video. Sebagai panduan, penelitian menggunakan standar ITU-P.910. Website telah dirancang dan berhasil diimplementasikan. Website telah diuji untuk melakukan pengukuran lima sampel video dengan melibatkan 30 responden. Hasil pengujian dengan metode Black Box menunjukkan keberhasilan 100%. Sedangkan, hasil pengujian skala Likert menghasilkan 48.89% responden sangat setuju dalam enam pertanyaan terkait kualitas website. Website hasil penelitian ini diharapkan meningkatkan efektivitas pengukuran kualitas video secara subjektif dalam hal waktu dan tenaga.

Perancangan dan Implementasi Aplikasi Android Penentu Salient Area pada Video dengan Algoritma K-Medoids Yoanda Alim Syahbana
Annual Research Seminar (ARS) Vol 2, No 1 (2016)
Publisher : Annual Research Seminar (ARS)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Salient Area adalah area yang paling menarik dari sebuah tampilan video. Area ini melingkupi objek berwarna tertentu, objek bergerak, atau objek khusus seperti wajah. Salah satu cara untuk mendeteksi Salient Area adalah dengan melakukan survey dan mendata area mana yang paling menarik menurut responden. Penelitian ini fokus pada rancang bangun aplikasi Android sebagai media survey penentu Salient Area. Aplikasi telah digunakan oleh 20 responden yang menonton video dan menunjukkan Salient Area dengan menggerakkan jari. Aplikasi merekam pergerakan jari dalam bentuk koordinat pixel. Seluruh data responden kemudian di-cluster dengan algoritma K-Medoids untuk mendapatkan kesimpulan akhir. Hasil pengujian menunjukkan bahwa aplikasi dan algoritma K-Medoids telah berhasil menemukan 4 kluster Salient Area pada video pengujian berdasarkan Davies-Bouldin Index (DBI). Selain itu, aplikasi juga dinilai oleh 20 responden dengan hasil 65% setuju tentang kemudahan dan fungsionalitas aplikasi. Aplikasi hasil penelitian ini bermanfaat sebagai alat bantu pendeteksian salient area untuk penelitian lain terkait kualitas video.

Algoritma Penyisipan Frame untuk Peningkatan Akurasi Metode Aligned Peak Signal-to-Noise Ratio dalam Pengukuran Kualitas Video Yoanda Alim Syahbana; Wecka Imam Yudhystira; Syefrida Yulina
Jurnal Komputer Terapan Vol. 1 No. 1 (2015): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Pengukuran kualitas video secara objektif mampu mengatasi kekurangan penilaian kualitas secara subjektif dalam hal waktu dan tenaga yang dibutuhkan. Pengukuran secara objektif ini menggunakan sinyal video, noise, dan parameter encoder untuk memperkirakan kualitas yang dirasakan penonton. Peak Signal-to-Noise Ratio (PSNR) merupakan salah satu metode pengukuran secara objektif yang cukup populer. Tetapi, metode PSNR yang konvensional memiliki ketidak-akurasian ketika mengukur video yang ditransmisikan melalui jaringan nirkabel dan mobile. Ini dikarenakan adanya paket hilang yang bisa menyebabkan hilangnya frame video. Pada tulisan ini dipaparkan rancangan sebuah algoritma penyisipan frame untuk meningkatkan akurasi metode PSNR. Percobaan telah dilakukan untuk menguji algoritma yang dirancang. Hasilnya percobaan menunjukkan PSNR dengan algoritma penyisipan frame mampu mencapai nilai PMCC sebesar 0.86. Dengan kata lain, akurasi PSNR konvensional telah mengalami peningkatan dengan adanya algoritma penyisipan frame.

Pengaruh Frame yang Hilang pada Kualitas Video Konten Head-and-Shoulder dalam Layanan VoD Yoanda Alim Syahbana; memen akbar
Jurnal Komputer Terapan Vol. 3 No. 2 (2017): Jurnal Komputer Terapan November 2017
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (389.455 KB)

Video konten Head-and-Shoulder memiliki karakteristik khas. Video konten ini ditampilkan berupa seorang yang sedang menginformasikan sesuatu dalam sorotan kamera yang menampilkan kepala, bahu, hingga ke bagian atas diagfarma. Contoh umum video konten ini dapat dilihat pada video pembaca berita, reportase, ataupun seorang pembawa acara. Pada penelitian ini, video konten Head-and-Shoulder yang diambil dari repositori CDVL dijadikan objek penelitian. Video ini akan diturunkan kualitasnya dengan menghilangkan beberapa frame video. Video ini kemudian dinilai dalam sebuah penilaian kualitas video secara subjektif berdasarkan ITU P.910. Penilaian ini melibatkan 47 responden sebagai penonton awam. Hasil penilaian kemudian dianalisa untuk melihat bagaimana pengaruh kualitas video pada video konten Head-and-Shoulder akibat dari penghilangan frame. Hasil penelitian menunjukkan bahwa video konten Head-and-Shoulder sangat baik dalam beradaptasi terhadap hilangnya frame video. 3 pola frame yang hilang dengan jumlah GOP yang berbeda menghasilkan nilai rata-rata MOS=2.89 dengan σMOS=0.05. Hasil penelitian ini dapat dimanfaatkan dalam pengaturan strategi pentransmisian video dalam layanan Video on Demand (VoD).

Design of Application On/Off Electronic Device with Markov Model Using Speech Recognition on Android Rochman Widyatmoko; Sugeng Purwantoro E. S. G; Yoanda Alim Syahbana S
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 3, No 3, August 2018
Publisher : Universitas Muhammadiyah Malang

Electronic devices are supported by a switch that is used to turn the device on and off. Manually pressed switches with distances between remote switches to cause less efficiency in saving human time and manpower. This can be solved by building a system to control electronic devices automatically. The system uses human voice commands to turn on and off electronic devices. The command will be processed into text by the Google Voice Speech Recognition library. The Android app sends human commands that have been processed by Arduino Uno R3 microcontroller. Commands are obtained after the text and data in the database are processed using the Markov Model algorithm. Communication between Android smartphone and microcontroller will be designed through a WIFI network. This system is tested based on noise level with data accuracy level with noise 0-45 dB and obtained 65% result. Based on the test response time obtained that the noise level 0-45 dB obtained results of 5.41 seconds. Based on the test results from the scenario, it can be concluded that the lower the noise generated, the better the system will also respond to commands. From the test suitability get value X = 1, meaning that the system is suitability with error rate 0. In testing accuracy to view status function get value 0 with error level 0. Testing of Markov model algorithm yields the calculated 0.125 algorithms manually and code for each command

Detection of Congested Traffic Flow during Road Construction using Improved Background Subtraction with Two Levels RoI Definition Yoanda Alim Syahbana; Yasunari Yokota
International ABEC 2021: Proceeding International Applied Business and Engineering Conference 2021
Publisher : International ABEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1135.416 KB)

This study is aimed to detect traffic congestion that may occur during roadblocks of road construction. We improved the background subtraction method by considering Region of Interest (RoI) in the video frame to detect the congestion. The proposed method has experimented with video test material that shows traffic condition in the road construction site. The performance of the proposed method is evaluated using Confusion Matrix by comparing the result of the experiment with ground truth obtained visually. As a benchmarking process, the performance is also compared with the conventional background subtraction method. The result shows that the proposed method can achieve an accuracy of 83.2% for video from the first camera and 82.3% for video from the second camera. In comparison, the conventional background subtraction method only achieves 49.8% for video from the first camera and 0% for video from the second camera. Based on this evaluation, the proposed method can support implementation of efficient traffic control using adaptive traffic light that is equipped with camera.

Object Detection And Monitor System For Building Security Based On Internet Of Things (IoT) Using Illumination Invariant Face Recognition Ivan Chatisa; Yoanda Alim Syahbana; Agus Urip Ari Wibowo
International ABEC Vol. 2 (2022): Proceeding International Applied Business and Engineering Conference 2022
Publisher : International ABEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (688.688 KB)

Theft, burglary and intrusion are criminal acts that often occur in the environment when there are opportunity or negligence made by the owner and security officers. Many studies have been carried out to improve environmental security by applying cameras as a surveillance medium. However, the camera is still not optimal at detecting objects if the environment is in poor lighting conditions (dark). Therefore, in this study, a monitoring and object detection system was built by applying the Illumination Invariant model. Illumination Invariant model that is used to improve the appearance of object images from light and shadow reflections. In this study, the detection process and objects are carried out using human facial features captured by the camera. The camera used is a Logitec C270 Webcam HD 720p via the USB port on the Raspberry Pi. Raspberry Pi processes human face image data and sends the results of data processing to a MySQL database using the HTTP Protocol. The process of sending data is done with the concept of API (Application Programming Interface) using Python Flask. In this study, all tests were carried out on the system using black box testing techniques with the results of the functional requirements being successfully executed 100%. In this study, testing the object detection feature based on different lighting conditions. The test was carried out 15 times by comparing the original image and the results of the implementation of the Illumination Invariant model. Based on the test results by applying the illumination of the Invariant model, the quality of object detection accuracy is 86.7%.

Early Detection and Tracking of Distant Incoming Traffic using Improved Detection on Road Vanishing Point Reference for Adaptive Traffic Light Signaling Yoanda Alim Syahbana; Yokota Yasunari
International ABEC Vol. 2 (2022): Proceeding International Applied Business and Engineering Conference 2022
Publisher : International ABEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (938.846 KB)

Real-time monitoring is essential and influences the decision-making process of adaptive traffic light systems. During temporary road closures, only one side of the lane can be accessed, increasing the need to recognize and track oncoming vehicles. Therefore, it is crucial to detect oncoming vehicles that are far away as early as possible, as waiting for an oncoming vehicle near a traffic light may delay the signal, leading to sudden braking or an accident. The purpose of this study was to improve traffic detection and tracking, even when the traffic is still far from the traffic lights. Vanishing point as detection reference is estimated, and Region of Interest (RoI) is calculated. An evaluation is performed based on how quickly the proposed method detects oncoming traffic compared to the R-CNN method. The results show that the proposed method requires an average of 17.75 frames to detect the target vehicle, while R-CNN requires an average of 63.36 frames to detect the target vehicle. The results show that the accuracy of the proposed method depends on the number of pixel orientations when estimating the vanishing point and how accurately the RoI is defined. Therefore, the proposed method reliably supports the safety and reliability of adaptive traffic light systems.

IMPLEMENTASI SCL UNTUK MENAMBAH KOMPETENSI SISWA SMK DALAM MEMONITOR PROYEK IOT MELALUI PLATFORM BLYNK Yoanda Alim Syahbana; Sugeng Purwantoro E.S.G.S; Memen Akbar; Wenda Novayani; Mardhiah Fadhli
Jurnal Pengabdian Masyarakat Multidisiplin Vol 6 No 3 (2023): Juni
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/jpm.v6i3.3192

SMK Taruna Persada Dumai merupakan salah satu SMK yang mengikuti program SMK Pusat Keunggulan. Program ini fokus pada pengembangan kompetensi keahlian tertentu untuk siswa SMK. Pengembangan kompetensi diprioritaskan pada kompetensi yang selaras dengan dunia usaha, dunia industri, dan dunia kerja. Berdasarkan evaluasi kegiatan PkM tahun sebelumnya, pihak SMK Taruna Persada Dumai meminta untuk melanjutkan kegiatan dengan fokus penambahan kompetensi siswanya. Kompetensi yang akan diajarkan dalam PkM PSTRK tahun 2022 adalah pengenalan bidang IoT yang saat ini sedang berkembang. PSTRK melaksanakan implementasi Student Centered Learning (SCL) untuk menambah kompetensi siswa SMK dalam memonitor proyek IoT melalui platform Blynk. PkM telah dilaksanakan pada 6 September 2022 dari jam 9.00 pagi sampai dengan jam 14.00 siang. Kegiatan ini diikuti oleh 20 siswa-siswi Jurusan Teknik Komputer Jaringan, SMKS Taruna Persada Kota Dumai. Modul SCL yang diberikan terdiri dari 5 bagian. Bagian pertama fokus pada model pembelajaran small group discussion dalam pengenalan prosesor, aktuator, dan sensor. Kemudian, bagian kedua siswa-siswi melakukan simulasi rangkaian LED dan ESP32 menggunakan simulator wokwi.com. Bagian ketiga dilanjutkan dengan model case study rangkaian LED dan NodeMCU 8266. Antusiasme dan semangat siswa dalam melakukan pembelajaran mandiri membuat bagian ketiga ini memakan waktu yang lama. Sehingga, bagian keempat berupa role-play kontrol lampu warna-warni berupa kontrol LED melalui Blynk dan bagian kelima berupa model discovery learning pembacaan data sensor DHT11 tidak sempat dikerjakan. Sebagai solusi, tim PkM meninggalkan dua set modul pembelajaran untuk bisa dikerjakan siswa-siswi di lain waktu secara mandiri. Di akhir pembelajaran, umpan balik dari siswa-siswi dikumpulkan dan hasilnya menunjukkan kepuasan mereka terhadap materi yang diberikan, cara penyajiannya, kualitas modul, dan kesesuaian materi. Siswa-siswi juga berharap kembali diikutkan pada program PkM lainnya dengan materi yang berbeda.

Title

Found 19 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 19 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 19 Documents
Search