10 research outputs found
Studi Komparasi Simulasi Sistem Kendali PID Pada Matlab, GNU Octave, SciLab dan Spyder
Get PDFDalam penelitian ini perbandingan antara perangkat lunak MATLAB, GNU Octave, Scilab dan Spyder akan diamati. Proses yang menjadi obyek dalam penelitian ini adalah sistem kendali PID yang digunakan untuk mengendalikan plant yang berupa model motor DC. Fungsi alih dari motor DC merupakan model dari motor DC yang diturunkan dari hukum newton ke-2 dan hukum kirchoff tegangan. Simulasi dilakukan pada perangkat lunak menggunakan 2 cara yaitu kode program dan block programming. Jumlah baris kode program yang terpendek adalah MATLAB dengan 17 baris dan yang terpanjang adalah Spyder dengan 20 baris kode program. Untuk block programming hanya dapat dilakukan pada MATLAB dan Scilab karena perangkat lunak yang lain tidak memiliki fitur tersebut. Waktu eksekusi kode program diamati padan masing-masing perangkat lunak dan Spyder adalah yang tercepat dengan waktu 0.0682 detik. Hasil plot dari masing-masing perangkat lunak tidak banyak memiliki perbedaan. MATLAB adalah perangkat lunak yang terbaik dengan fiturnya namun diperlukan biaya lisensi dalam menggunakannya
Implementasi Integrasi Computer Vision dan Kendali PID untuk Robot Line Follower dengan Kendali Kecepatan Dinamis
No full textThis research aims to develop a dynamic speed control system for line follower robots by integrating computer vision technology and PID control. The main challenge in controlling line follower robots is maintaining stability and speed while navigating various types of turns and complex paths. This study proposes the use of computer vision to detect paths more accurately and responsively, and PID control to dynamically adjust the robot\u27s speed based on detected errors. The research methods involve simulating the e-puck robot in a Webots environment, developing algorithms for black line detection and error calculation, and designing the PID control system. The test results show that in Arena 1, the completion time with fixed base speed is 58.08 seconds, while with dynamic base speed it is 50.386 seconds, indicating a 13.3% reduction in completion time. In Arena 2, the completion time with fixed base speed is 71.584 seconds, while with dynamic base speed it is 66.624 seconds, indicating a 6.9% reduction in completion time. Thus, this control system is more effective in keeping the robot on the desired path, reducing deviations and improving path tracking accuracy.Penelitian ini bertujuan untuk mengembangkan sistem kendali kecepatan dinamis pada robot line follower dengan mengintegrasikan teknologi computer vision dan kendali PID. Dalam pengendalian robot line follower, tantangan utama adalah menjaga kestabilan dan kecepatan robot saat menghadapi berbagai jenis belokan dan jalur yang kompleks. Penelitian ini mengusulkan penggunaan computer vision untuk mendeteksi jalur dengan lebih akurat dan responsif, serta kendali PID untuk menyesuaikan kecepatan robot secara dinamis berdasarkan error yang terdeteksi. Metode penelitian melibatkan simulasi robot e-puck di lingkungan Webots, pembuatan algoritma deteksi jalur hitam dan perhitungan error, serta perancangan sistem kendali PID. Hasil pengujian menunjukkan bahwa pada Arena 1, waktu tempuh dengan base speed tetap adalah 58.08 detik, sedangkan dengan base speed dinamis adalah 50.386 detik, menunjukkan pengurangan waktu tempuh sebesar 13.3%. Pada Arena 2, waktu tempuh dengan base speed tetap adalah 71.584 detik, sementara dengan base speed dinamis adalah 66.624 detik, menunjukkan pengurangan waktu tempuh sebesar 6.9%. Dengan demikian, sistem kendali ini lebih efektif dalam menjaga robot tetap pada jalur yang diinginkan, mengurangi penyimpangan dan meningkatkan akurasi tracking jalur
SISTEM KENDALI FUZZY UNTUK ROBOT MOBILE: STUDI KASUS PELACAKAN OBJEK BERGERAK MENGGUNAKAN SIMULASI WEBOTS
Get PDFDalam era perkembangan teknologi robotika yang semakin maju, implementasi sistem kendali menjadi sangat penting dalam berbagai aplikasi, termasuk logistik, pengawasan, dan layanan kesehatan. Penelitian ini mengembangkan dan menguji sistem pengendalian robot menggunakan fuzzy logic untuk mendeteksi dan mengikuti objek bergerak berwarna biru dalam lingkungan dinamis. Penggunaan fuzzy logic dipilih karena kelebihannya dalam menangani ketidakpastian dan dinamika lingkungan yang kompleks dibandingkan dengan metode pengendalian tradisional seperti PID. Robot Khepera IV digunakan sebagai platform, dan simulasi dilakukan menggunakan software Webots. Sistem ini mengintegrasikan sensor kamera untuk pendeteksian objek dan sensor inframerah untuk penghindaran rintangan. Hasil percobaan menunjukkan bahwa sistem kendali fuzzy logic yang dikembangkan mampu mengikuti objek dengan baik, menunjukkan waktu rise time yang cepat bernilai 0,384 detik, dan tidak mengalami overshoot. Penelitian ini membuktikan bahwa fuzzy logic efektif dalam pengendalian robot untuk pelacakan objek berwarna, dengan hasil terbaik menunjukkan rata-rata error yang rendah yaitu -1,687 dan respon kendali yang responsif terhadap perubahan posisi objek
PENERAPAN KINEMATIKA TERBALIK PADA ROBOT LENGAN LIMA SENDI (5 DOF) DENGAN CITRA DIGITAL
Get PDFPerkembangan teknologi yang semakin maju memberi dampak pada sistem kendali robot, salah satunya ialah robot lengan. Sistem kendali yang sering digunakan pada lengan robot adalah kinematika terbalik dan kinematika maju. Penelitian ini membahas penerapan kinematika terbalik pada robot lengan dengan lima derajat kebebasan (5 DOF) yang diintegrasikan dengan teknologi citra digital untuk meningkatkan presisi dan efisiensi operasional. Deteksi objek dan warna dilakukan melalui pemrosesan citra yang digunakan sebagai masukan untuk algoritma kinematika terbalik. Dengan metode tersebut didapatkan keluaran berupa derajat untuk masing-masing aktuator. Berdasarkan hasil pengujian yang dilakukan kombinasi kinematika terbalik dan citra digital masih memiliki error yang cukup besar, seperti pada sumbu x dengan error tertingginya pada 4.11, sumbu y dengan error tertingginya 13 dan sumbu z dengan error 26.74. Meskipun nilai error masih cukup besar tetapi metode ini berhasil mengendalikan robot lengan 5-DOF
Advanced multimodal emotion recognition for Javanese language using deep learning
Get PDFThis research develops a robust emotion recognition system for the Javanese language using multimodal audio and video datasets, addressing the limited advancements in emotion recognition specific to this language. Three models were explored to enhance emotional feature extraction: the SpectrogramImage Model (Model 1), which converts audio inputs into spectrogram images and integrates them with facial images for emotion labeling; the Convolutional-MFCC Model (Model 2), which leverages convolutional techniques for image processing and Mel-frequency cepstral coefficients for audio; and the Multimodal Feature-Extraction Model (Model 3), which independently processes video and audio features before integrating them for emotion recognition. Comparative analysis shows that the Multimodal Feature-Extraction Model achieves the highest accuracy of 93%, surpassing the Convolutional-MFCC Model at 85% and the Spectrogram-Image Model at 71%. These findings demonstrate that effective multimodal integration, mainly through separate feature extraction, significantly enhances emotion recognition accuracy. This research improves communication systems and offers deeper insights into Javanese emotional expressions, with potential applications in human-computer interaction, healthcare, and cultural studies. Additionally, it contributes to the advancement of sophisticated emotion recognition technologies
PERBANDINGAN KONTROL LOGIKA FUZZY DAN PID PADA ROBOT E-PUCK WALL FOLLOWING MENGGUNAKAN WEBOTS
Get PDFPenelitian ini mengeksplorasi penerapan Fuzzy Logic Control (FLC) pada robot E-Puck untuk tugas mengikuti dinding atau wall following menggunakan simulasi Webots. serta membandingkan efisiensi antara sistem FLC dan Proportional-Integral-Derivative (PID). Robot E-Puck dilengkapi dengan sensor proximity inframerah untuk mendeteksi dan mempertahankan jarak yang stabil dari dinding. Logika Fuzzy dipilih karena kemampuannya dalam menangani ketidakpastian dan membuat keputusan adaptif dalam lingkungan yang dinamis. Proses kontrol FLC meliputi fuzzifikasi data sensor, inferensi menggunakan aturan IF-THEN, dan defuzzifikasi untuk menghasilkan sinyal kontrol crisp yang mengatur motor robot. Hasil pengujian menunjukkan bahwa FLC menghasilkan gerakan yang lebih stabil dibandingkan dengan kontrol PID, dengan nilai error rata-rata sebesar -3.32 untuk FLC dibandingkan dengan -13.39 untuk PID. Namun kontrol FLC memiliki nilai waktu puncak 3.71 detik sedangkan PID memiliki nilai waktu puncak 2.24 yang berarti kontrol PID lebih responsif dibandingkan dengan kontrol FLC. Secara keseluruhan, FLC lebih efektif dalam mengontrol gerakan robot dalam tugas wall following, sedangkan kontrol PID lebih efektif dalam mendapatkan respons yang lebih cepat
Development of Javanese speech emotion database (Java-SED)
No full textJavanese is one of the most widely spoken regional languages in Indonesia, alongside other regional languages. Emotions can be recognized in a variety of ways, including facial expression, behavior, and speech. The recognition of emotions through speech is a straightforward process, but the outcomes are quite significant. Currently, there is no database for identifying emotions in Javanese speech. This paper aims to describe the creation of a Javanese emotional speech database. Actors from the Kamasetra UNY community who are accustomed to performing in dramatic roles participated in the recording. The location where recordings are made is free of interference and noise. The actors of Kamasetra have simulated six types of emotions, including happy, sad, fear, angry, neutral, and surprised. The cast consists of ten people between the ages of 20 and 30, including five men and five women. Both humans (30 Javanese-speaking verifiers ranging in age from 17 to 50) and a machine learning system (30 Javanese-speaking verifiers with ages between 17 and 50) verify the database that has been created. The verification results indicate that the database can be used for Javanese emotion recognition. The developed database is offered as open-source and is freely available to the research community at this link https://beais-uny.id/dataset
Alat Peringatan Pelanggaran Physical Distancing Berbasis Raspberry Pi sebagai Upaya Preventif Penyebaran Covid-19 pada Era New Normal
Get PDFThe Covid-19 pandemic that hit Indonesia forced the Indonesian population to be ready with a new normal order. With this condition, it is hoped that the community can implement changes to the new order of life by implementing health protocols. But nowadays, people often violate health protocols, physical distancing, which is one form of prevention in the new normal era. The innovation of a Raspberry Pi-based tool designed to produce warnings for physical distancing violations is expected to minimize violations. The camera installed on the system will help detect the distance between two or more people and will give a warning to immediately carry out physical distancing if the measured distance is less than 1 meter. The purpose of writing this research is to design a system and concept of "Preventive Efforts for the Spread of Covid-19 Through a Raspberry Pi-Based Distance Monitoring System". The method of writing this article uses the concept of a literature study involving several studies and scientific findings in the form of secondary data from research results that have been published in scientific journals. From the results of the tests that have been carried out, it is known that the tool has succeeded in detecting physical distancing violations between two or more people. After the tool can detect a violation, the tool emits a warning sound to inform the violation that has occurred. From the result, it can be concluded that this system proposed can run well as expected
Advanced Multimodal Emotion Recognition for Javanese Language Using Deep Learning
Get PDFThis research develops a robust emotion recognition system for the Javanese language using multimodal audio and video datasets, addressing the limited advancements in emotion recognition specific to this language. Three models were explored to enhance emotional feature extraction: the SpectrogramImage Model (Model 1), which converts audio inputs into spectrogram images and integrates them with facial images for emotion labeling; the Convolutional-MFCC Model (Model 2), which leverages convolutional techniques for image processing and Mel-frequency cepstral coefficients for audio; and the Multimodal Feature-Extraction Model (Model 3), which independently processes video and audio features before integrating them for emotion recognition. Comparative analysis shows that the Multimodal Feature-Extraction Model achieves the highest accuracy of 93%, surpassing the Convolutional-MFCC Model at 85% and the Spectrogram-Image Model at 71%. These findings demonstrate that effective multimodal integration, mainly through separate feature extraction, significantly enhances emotion recognition accuracy. This research improves communication systems and offers deeper insights into Javanese emotional expressions, with potential applications in human-computer interaction, healthcare, and cultural studies. Additionally, it contributes to the advancement of sophisticated emotion recognition technologies
Development of Javanese Speech Emotion Database (Java-SED)
Get PDFJavanese is one of the most widely spoken regional languages in Indonesia, alongside other regional languages. Emotions can be recognized in a variety of ways, including facial expression, behavior, and speech. The recognition of emotions through speech is a straightforward process, but the outcomes are quite significant. Currently, there is no database for identifying emotions in Javanese speech. This paper aims to describe the creation of a Javanese emotional speech database. Actors from the Kamasetra UNY community who are accustomed to performing in dramatic roles participated in the recording. The location where recordings are made is free of interference and noise. The actors of Kamasetra have simulated six types of emotions, including happy, sad, fear, angry, neutral, and surprised. The cast consists of ten people between the ages of 20 and 30, including five men and five women. Both humans (30 Javanese-speaking verifiers ranging in age from 17 to 50) and a machine learning system (30 Javanese-speaking verifiers with ages between 17 and 50) verify the database that has been created. The verification results indicate that the database can be used for Javanese emotion recognition. The developed database is offered as open-source and is freely available to the research community at this link https://beais-uny.id/dataset
