Claim Missing Document
Check
Articles

Found 16 Documents
Search

Identifikasi Jalan Kampus Universitas Sriwijaya Berbasis Fully Convolutional Networks Caroline, Caroline; Yogta, Abeng; Thayeb, Rudyanto; Hermawati, Hermawati; Dwijayanti, Suci; Suprapto, Bhakti Yudho
JURNAL SURYA ENERGY Vol. 4 No. 1 2019
Publisher : UNIVERSITAS MUHAMMADIYAH PALEMBANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32502/jse.v4i1.2057

Abstract

Perkembangan mobil listrik sangat pesat seiring dengan semakin berkurangnya sumber energi fosil. Untuk mampu bergerak otomatis identifikasi dan deteksi jalan sangat diperlukan. Namun proses ini sulit dikarenakan jalan yang ada tidak memiliki garis sebagai acuan. Banyak metode yang telah digunakan salah satunya dengan menggunakan Fully Convolutional Networks (FCNs). Metode ini berhasil dalam melakukan identifikasi terhadap jalan yang ada pada kampus Universitas Sriwijaya. Berdasarkan hasil pengujian didapatkan nilai Intersection over Union (IoU) 90%. Sehingga, model yang dihasilkan oleh FCNs dapat digunakan untuk identifikasi jalan yang dilalui. Selain itu parameter lain yang diperhitungkan yaitu nilai akurasi 98,12% pada data latih dan 97,87% pada data uji. Sedangkan error yang dihasilkan sebesar 6 % pada data latih dan 7% pada data uji. Kata kunci: Fully Convolutional Networks (FCNs), Intersection over Union, Jalan kampus, Mobil ListrikABSTRACTThe development of electric cars is very rapid along with the decreasing source of fossil energy. To move automatically, the electric car is needs identification and detection of roads. But this process is difficult because the existing road does not have a line as a reference. Many methods have been used, one of them is using Fully Convolutional Networks (FCNs). This method is successful in identifying existing roads on the Sriwijaya University campus. Based on the results of testing, it obtained Intersection over Union (IoU) value of 90%. So, the model produced by FCNs can be used to identify the path traveled. In addition, other parameters taken into account are the accuracy value of 98.12% in the training data and 97.87% in the test data. While the resulting error of 6% in training data and 7% in test data.
Comparison of Control Methods PD, PI, and PID on Two Wheeled Self Balancing Robot Suprapto, Bhakti Yudho; Amri, Djulil; Dwijayanti, Suci
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 1: EECSI 2014
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1071.789 KB) | DOI: 10.11591/eecsi.v1.348

Abstract

A robot must employ a suitable control method to obtain a good stability. The Two-Wheeled Self Balancing Robot in this paper is designed using a MPU-6050 IMU sensor module and ATmega128 microcontroller as its controller board. This IMU sensor module is employed to measure any change in the robot’s tilt angle based on gyroscope and accelerometer readings contained in the module. The tilt angle readings are then utilized as the setpoint on the control methods, namely PD (Proportional Derivative), PI (Proportional Integral), or PID (Proportional Integral Derivative). Based on the conducted testing results, the PID controller is the best control strategy when compared to the PD and PI control. With parameters of Kp = 14, Ki = 0005 and Kd = 0.1, the robot is able to adjust the speed and direction of DC motor rotation to maintain upright positions on flat surfaces.
Desain Pengembangan Sistem Pembangkit Listrik Tenaga Gelombang Laut Berbasis Keseimbangan Gyroscope Agustina, Sri; Yusup, Muhammad; Dwijayanti, Suci; Otong, Muhammad; Suprapto, Bhakti Yudho
JURNAL SURYA ENERGY Vol 5 No. 2 2021
Publisher : UNIVERSITAS MUHAMMADIYAH PALEMBANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32502/jse.v5i2.3328

Abstract

Indonesia sebagai negara maritim yang luas memiliki potensi sumber energi terbarukan yang berasal dari laut. Dengan memanfaatkan gelombang laut sebagai energi, pembangkit listrik tenaga gelombang laut (PLTGL) dapat menghasilkan tegangan listrik yang cukup untuk memberikan suplai ke peralatan listrik. Selama ini gelombang merupakan permasalahan karena sangat tergantung pada besar kecilnya angin sehingga mempengaruhi tenaga listrik yang dihasilkan. Oleh karena itu pada penelitian ini dikembangkan Sistem Pembangkit Listrik Tenaga Gelombang Laut yang berbasis keseimbangan gyroscope. Pada artikel ini fokus pembahasan pada pengaruh gerakan rotasi gimbal terhadap power take off (PTO) generator. Pergerakan dari flywheel yang berputar akan memberikan momentum kepada gimbal untuk dapat berotasi. Berdasarkan simulasi numerik interaksi antara gimbal dan PTO generator akan menghasilkan tegangan listrik. Hasil yang didapatkan dari percobaan akan mendukung analisa teoritis dan simulasi, serta sebagai acuan untuk membuat desain PLTGL yang memiliki pengendali berkinerja tinggi.
Pengaruh tegangan pada pengolahan synthetic oily wastewater dengan metode electro-adsorption menggunakan karbon aktif dan elektroda aluminium Lia Cundari; Bazlina D. Afrah; Suci Dwijayanti; Luthfiyah A. Sayyidah; Althaf Taufiqurrahman; Aldi Ramadhani; Alvina Suryadinata
Jurnal Teknik Kimia Vol 27 No 1 (2021): Jurnal Teknik Kimia
Publisher : Chemical Engineering Department, Faculty of Engineering, Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36706/jtk.v27i1.8

Abstract

Larutan berminyak yang dihasilkan pengilangan 0,4-1,6 kali jumlah produksi minyak, dengan kadar minyak dan chemical oxygen demand (COD) masing-masing 100-300 mg/L dan 850-1020 mg/L. Komponen minyak dalam limbah dapat menghambat ekosistem perairan, mulai dari pertumbuhannya, fisiologi, dan reproduksi. Elektro-adsorpsi merupakan teknologi pemisahan hybrid untuk pemurnian dan desalinasi air dengan mengkombinasikan metode elektrolisis dan adsorpsi. Penelitian ini bertujuan untuk mengkarakterisasi karbon aktif sebelum dan sesudah proses elektro-adsorpsi dan untuk mengetahui pengaruh tegangan pada pengolahan larutan berminyak ditinjau dari nilai COD dan konsentrasi minyak-lemak. Karakteristik karbon aktif dilihat melalui scanning electron microscope (SEM) dan fourier transform infra red (FTIR). Elektro-adsorpsi dilakukan menggunakan adsorben karbon aktif komersial dan elektroda aluminium, dengan memvariasikan tegangan (0, 5, 10, 15 V) dan waktu (5, 10, 15, 20, 25 menit). Larutan berminyak sintetik dibuat dengan mencampurkan 1 g biosolar (B30) dengan 1 liter air Sungai Musi. Hasil penelitian menunjukkan bahwa metode elektro-adsorpsi efektif digunakan pada pengolahan larutan berminyak sintetik. Hasil analisa SEM karbon aktif sebelum dan sesudah proses elektrolisis adsorpsi menunjukkan distribusi pori-pori tidak beraturan dan banyak pengotor di sekitar pori-pori karbon aktif. Diamater pori-pori rata-rata setelah proses elektrolisis adsorpsi sebesar 2,54 μm dari 2,58 μm. Hasil Analisa FTIR karbon aktif setelah proses menunjukkan terbentuknya puncak gelombang yang menandakan adanya gugus fungsi yang menjadi karakteristik dari biosolar yang teradsorpsi ke dalam karbon aktif. Penurunan kadar COD dan konsentrasi minyak-lemak paling tinggi masing-masing 40,21% pada 5 V selama 5 menit dan 95,25% pada 15 V selama 10 menit.
PENGENALAN SIDIK JARI MENGGUNAKAN JARINGAN SYARAF TIRUAN BERBASIS SCALED CONJUGATE GRADIENT Suci Dwijayanti; Puspa Kurniasari
Jurnal Mikrotiga Vol 1, No 2 (2014)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (265.266 KB)

Abstract

Abstrak—Sidik jari merupakan sistem biometrik yang paling banyak digunakan untuk keamanan. Salah satu metode yang sangat baik untuk mengenali sidik jari adalah menggunakan jaringan syaraf tiruan. Penelitian ini membahas tentang pengenalan sidik jari dengan menggunakan algoritma variasi backpropagation, scaled conjugate gradient. Proses pengenalan sidik jari meliputi image acquisition, image pre-processing, feature extraction dan image recognition. Pada proses pre-processing dan feature extraction menggunakan algoritma fast fourier transform untuk memperbaiki kualitas sidik jari yang akan digunakan sebagai input pada proses pengenalan. Proses enrollment menggunakan fingerprint reader. Dari hasil pelatihan, dari 9 sampel sidik jari ada 2 sidik jari yang memiliki error lebih dari 0.05, sedangkan dari data pengujian diperoleh 91% data secara keseluruhan mampu dikenali dengan menggunakan backpropagation berbasis scaled conjugate gradient.Kata kunci: Jaringan Syaraf Tiruan, Backpropagation, Scaled Conjugate Gradient, Sidik Jari.Abstract-A fingerprint biometric system is the most widely system used for security. One of the best method to recognize fingerprints is using neural network. This paper describes the fingerprint recognition using scaled conjugate gradient, a variation backpropagation algorithm. The fingerprint recognition procesess include image acquisition, image pre-processing, feature extraction and image recognition. In the pre-processing and feature extraction, Fast Fourier Transform algorithm is used to improve the quality of prints that will be used as input in the recognition process. Enrollment process use the fingerprint reader. From the training results obtained that there are 2 fingerprints have errors more than 0.05 from 9 samples, while test data obtained 91 % of the whole data that could be identified by using backpropagation based on scaled conjugate gradient.Keywords. Neural Network, Backpropagation, Scaled Conjugate Gradient, Fingerprint
Road and Vehicles Detection System Using HSV Color Space for Autonomous Vehicle Aulia Ghaida; Hera Hikmarika; Suci Dwijayanti; Bhakti Yudho Suprapto
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 6, No 1 (2020): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v16i1.16949

Abstract

Nowadays, an autonomous vehicle is one of the fastest-growing technologies. In its movements, the autonomous vehicle requires a good navigation system to run on the specified lane. One sensor that is often used in navigation systems is the camera. However, this camera is constrained by the process and its reading, especially to detect roads that are suitable for the vehicle's position. Thus, this research was conducted to detect the road and distance of nearby objects using the HSV color space method. From the test results, this research succeeded in detecting roads with an accuracy of 78.012 %, and an accuracy of 80% for the safe/unsafe area detection. The results also showed that the method achieved an accuracy of 80% and 74.76%for object detection and object distance detection, respectively. The results of this research implied that the HSV method wasquite good with fairly high accuracy to detect roads and vehicles.
The Detection System of Helipad for Unmanned Aerial Vehicle Landing Using YOLO Algorithm Bhakti Yudho Suprapto; A. Wahyudin; Hera Hikmarika; Suci Dwijayanti
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol 7, No 2 (2021): August
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v7i2.20684

Abstract

The challenge with using the Unmanned Aerial Vehicle (UAV) is when the UAV makes a landing. This problem can be overcome by developing a landing vision through helipad detection. This helipad detection can make it easier for UAVs to land accurately and precisely by detecting the helipad using a camera. Furthermore, image processing technology is used on the image produced by the camera. You Only Look Once (YOLO) is an image processing algorithm developed to detect objects in real-time, and it is the result of the development of one of the Convolutional Neural Network (CNN) algorithm methods. Therefore, in this study the YOLO method was used to detect a helipad in real-time. The models used in the YOLO algorithm were Mean-Shift and Tiny YOLO VOC. The Tiny YOLO VOC model performed better than the Mean-Shift method in detecting helipads. The test results obtained a confidence value of 91.1%, and the system processing speed reached 35 frames per second (fps) in bright conditions and 37 fps in dark conditions at an altitude of up to 20 meters.
MULTI OBJECTIVE FUNCTION TO TEST PARTICLE SWARM OPTIMIZATION AND R3 CYCLIC PERFORMANCE Suci Dwijayanti
Jurnal Rekayasa Sriwijaya Vol 22, No 1 (2013): Jurnal Rekayasa Sriwijaya Edisi Maret 2013
Publisher : Jurnal Rekayasa Sriwijaya

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

Abstract

Particle Swarm Optimization (PSO)and R3 cyclic are the simple optimizer algorithm. In this paper, these algorithms will be compared to find out which one is better and more robust. The criteria will be based on the iteration numbers, NoFe and number of success in finding the optimal solution. The tested functions are the multi objective function with surface aberration. We use traditional stopping criteria with stopping distance 0.001. From the result, in term of the iteration number and number of function to be evaluated, R3 cyclic is better than PSO. The less number of iteration and NoFE will not burden the computation time and cost. But the result that is obtained by R3 cyclic is not always the global optima, sometimes it trapped in the local optima. So in term of accuracy, PSO is better than R3 cyclic. At the end, the term of goodness, effectiveness and better will depend on the term that wants to be reached, if it is the accuracy, the best choice is PSO but if the goal is the cost of computation, R3 cyclic is a better choice. Keywords: Particle Swarm Optimization, R3 cyclic, Optimizer
Comparison of Control Methods PD, PI, and PID on Two Wheeled Self Balancing Robot Bhakti Yudho Suprapto; Djulil Amri; Suci Dwijayanti
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 1: EECSI 2014
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1071.789 KB) | DOI: 10.11591/eecsi.v1.348

Abstract

A robot must employ a suitable control method to obtain a good stability. The Two-Wheeled Self Balancing Robot in this paper is designed using a MPU-6050 IMU sensor module and ATmega128 microcontroller as its controller board. This IMU sensor module is employed to measure any change in the robot’s tilt angle based on gyroscope and accelerometer readings contained in the module. The tilt angle readings are then utilized as the setpoint on the control methods, namely PD (Proportional Derivative), PI (Proportional Integral), or PID (Proportional Integral Derivative). Based on the conducted testing results, the PID controller is the best control strategy when compared to the PD and PI control. With parameters of Kp = 14, Ki = 0005 and Kd = 0.1, the robot is able to adjust the speed and direction of DC motor rotation to maintain upright positions on flat surfaces.
Speaker Identification Using a Convolutional Neural Network Suci Dwijayanti; Alvio Yunita Putri; Bhakti Yudho Suprapto
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 1 (2022): Februari 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (459.255 KB) | DOI: 10.29207/resti.v6i1.3795

Abstract

Speech, a mode of communication between humans and machines, has various applications, including biometric systems for identifying people have access to secure systems. Feature extraction is an important factor in speech recognition with high accuracy. Therefore, we implemented a spectrogram, which is a pictorial representation of speech in terms of raw features, to identify speakers. These features were inputted into a convolutional neural network (CNN), and a CNN-visual geometry group (CNN-VGG) architecture was used to recognize the speakers. We used 780 primary data from 78 speakers, and each speaker uttered a number in Bahasa Indonesia. The proposed architecture, CNN-VGG-f, has a learning rate of 0.001, batch size of 256, and epoch of 100. The results indicate that this architecture can generate a suitable model for speaker identification. A spectrogram was used to determine the best features for identifying the speakers. The proposed method exhibited an accuracy of 98.78%, which is significantly higher than the accuracies of the method involving Mel-frequency cepstral coefficients (MFCCs; 34.62%) and the combination of MFCCs and deltas (26.92%). Overall, CNN-VGG-f with the spectrogram can identify 77 speakers from the samples, validating the usefulness of the combination of spectrograms and CNN in speech recognition applications.