Claim Missing Document
Check
Articles

RANCANG BANGUN MODEL PENGIDENTIFIKASI SUARA HURUF HIJAIYAH DENGAN METODE MEL FREQUENCY CEPSTRUM COEFFICIENT DAN CONVOLUTIONAL NEURAL NETWORK Robbani Punggawa Arcapada; Widyadi Setiawan; I Made Arsa Suyadnya
Jurnal SPEKTRUM Vol 8 No 4 (2021): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (711.068 KB) | DOI: 10.24843/SPEKTRUM.2021.v08.i04.p1

Abstract

Learning the Qur'an is a necessity for a Muslim, because the Qur'an acts as a guideand way of life. One thing that is learned in the Qur'an is how to pronounce Hijaiyah letters orMakharijul letters. In learning Makharijul Letters it takes an ustaz or accompanying teacher whois limited by distance and time. To overcome the limitations of distance and time, a learningapplication model is needed that can be accessed without the limitations of distance and thetime. This is studied aim to develop the Hijaiyah letter recognition model using the MelFrequency Cepstrum Coefficient (MFCC) and Convulational Neural Network (CNN) methods.Based validation results, the model built using the MFCC and CNN methods can identify theletters read with an accuracy of 49.1%. Then based of the test result with Confusion Matrix, thismodel have a precision value of 50%, recall is 53%, and F-Measure is 0.514.
Sistem Pengenalan Wajah Dengan Metode Face Features Ardiansiah Ardiansiah; Widyadi Setiawan; Linawati Linawati
Jurnal SPEKTRUM Vol 3 No 2 (2016): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (235.718 KB)

Abstract

Pengenalan citra wajah atau Face Recognition adalah salah satu teknologi biometric yang telah banyak diaplikasikan dalam sistem keamanan. Perhitungan model pengenalan wajah memiliki beberapa masalah, kesulitan muncul ketika wajah dipresentasikan dalam suatu pola berisi informasi unik yang membedakan dengan wajah lain. Dalam implementasinya, secara umum pengenalan citra wajah dilakukan menggunakan sebuah webcam untuk menangkap citra wajah seseorang kemudian citra wajah tersebut dibandingkan dengan citra wajah sebelumnya yang telah disimpan. Pengujian ini dibagi menjadi dua bagian, yang pertama pengujian similarity kecocokan wajah dan yang kedua perhitungan False Acceptance Rate (FAR) dan False Rejection Rate (FRR). Pengujian menggunakan perangkat lunak Luxand FaceSDK dengan 30 sampel. Setiap sampel diambil 10 citra wajah untuk kemudian diuji kecocokan wajah, ekspresi dan kontur wajah dari sampel. Sistem ini mampu mengenali wajah dengan tingkat akurasi terbaik sebesar FAR = 8% dan FRR = 7% dengan nilai ambang 90%. Dan nilai ambang terburuk 10% dengan FAR = 95% dan FRR = 0,7%.
KINERJA PROTOKOL NETWORK REDUNDANSI VRRP, HSRP DAN GLBP PADA LAYANAN VIDEO STREAMING I Putu Gede Krsna Yudha Dharma; Pande Ketut Sudiarta; Widyadi Setiawan
Jurnal SPEKTRUM Vol 8 No 2 (2021): Jurnal SPEKTRUM
Publisher : Program Studi Teknik Elektro UNUD

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (697.177 KB) | DOI: 10.24843/SPEKTRUM.2021.v08.i02.p17

Abstract

Nowadays streaming video services have become the main need for internet users. Tokeep the streaming video service awake, an alternative path is needed to avoid network failure.In creating an alternative path, you can use first hop redundancy protocol (FHRP). In FHRPthere are three redundancy protocols including VRRP, HSRP and GLBP. The purpose of thisstudy is to find out better protocol performance, especially by using streaming video services.The method used is to simulate redundancy protocol using GNS-3 software with 3 scenariosthat run including normal network, down network and recovery network. As for testing eachscenario including testing routers with priority, route trace route, link transfer time and quality ofservice (QoS) video streaming. Based on the results of the study, it was obtained that GLBPprotocol has better performance with an average link transfer time of 1.51 seconds, delay of8.12 ms, packet loss of 0 % and throughput of 1,248 Mbps. This is because in GLBP protocolthere is a load balancing feature that can split the load equally and utilize resources moreeffectively from each router.
Perbandingan Peramalan Beban Listrik Jangka Pendek Menggunakan Support Vector Machine Dan Jaringan Syaraf Tiruan Perambatan Balik I Nyoman Setiawan; Widyadi Setiawan
Jurnal Teknologi Elektro Vol 12 No 2 (2013): (July - December) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (124.352 KB)

Abstract

Penelitian ini membahas pemakaian Jaringan Syaraf Tiruan (JST) Perambatan Balik dan Support Vector Machine (SVM) untuk peramalan kebutuhan beban listrik. Variabel yang dipakai dalam JST dan SVM adalah data beban listrik wilayah Bali. Hasil peramalan memiliki persentase kesalahan rata-rata absolut 5,71% untuk metode JST dan 3,53% untuk metode SVM. Metode JST mempunyai rata-rata eror minimal 0,35% dan maksimal 17,34%. Metode SVM mempunyai rata-rata eror minimal 0,16% dan maksimal 10,53%. Metode SVM memiliki keakuratan lebih baik dibandingkan dengan metode JST.
PENGUKURAN KECEPATAN KENDARAAN SECARA REALTIME BERBASIS ANDROID Rendi Gustina; Widyadi Setiawan; Ngurah Indra ER
Jurnal Teknologi Elektro Vol 15 No 1 (2016): (January - June) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (857.802 KB) | DOI: 10.24843/MITE.2016.v15i01p16

Abstract

Abstract— Intelligent transport systems in the android operating system is able to bring about change is very important in human life. Objectives and benefits in this thesis is to obtain an application program measuring the speed of vehicles in real time based on Android using the Frame Difference and Bounding Box wearingreference distance, the vehicle speed of 10 km / h, 20 km / h and 30 km / h and distance 6 meters. After getting the average speed of vehicles, will be calculated deviation measurements of vehicle speed and the actual results compared to the average. For the measurement of the speed of vehicles put on the vehicle speed measurement applications in realtime based on android gained an average of 20.572 km / h with a maximum deviation 0.572 km / h and an average of 29.688 km / h with minimal deviation 0.312 km / h. For the measurement of the speed of vehicles put on the analysis of vehicle speed measurement in digital video recording obtained by an average of 31.454 km / h with a maximum deviation 1,454 km / h and an average of 10.112 km / h with minimal deviation 0.112 km / h.
APLIKASI JARINGAN SYARAF TIRUAN PERAMBATAN BALIK PADA PENGENALAN ANGKA TULISAN TANGAN Widyadi Setiawan; Sri Andriani Asri
Jurnal Teknologi Elektro Vol 4 No 2 (2005): (July - December) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (40.72 KB)

Abstract

Pengenalan Angka terlihat sederhana bagi manusia, namun menjadi tugas yang sangat sulit bagi program komputer untuk menyelesaikannya. Pengenalan angka secara otomatis menjadi sangat vital pada berbagai aplikasi seperti aplikasi pengolahan check dan pengolahan dokumen keuangan lainnya pada bank. Pada penelitian ini, sistem yang dikembangkan melibatkan Jaringan Syaraf Tiruan Perambatan Balik (Neural Network Backpropagation). Jaringan dilatih memakai algoritma pelatihan terbimbing, dengan memasukkan sampel-sampel digit yang bervariasi yang dilakukan secara berulang-ulang. Hasil yang didapat berupa parameter unjuk-kerja optimal sistem pengenalan tulisan tangan angka sebesar 80,31 %.
Optimasi Penempatan Recloser untuk Meningkatkan Keandalan Menggunakan Metode Virus Evolutionary Genetic Algorithm (VEGA) Novadianto Yudha Irawan; Anak Agung Ngurah Amrita; Widyadi Setiawan
Jurnal Teknologi Elektro Vol 17 No 2 (2018): (May - Agustus) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (784.824 KB) | DOI: 10.24843/MITE.2018.v17i02.P03

Abstract

Kutampi Diesel Power Plant that supplies the Lembongan Island electrical system has a reliability value index that has not met the standard with SAIDI 95.85 hours / customer / year and SAIFI 76 times / customer / year while the WCS standard for SAIDI is 2.5 hours / customer / year and SAIFI is 3 times / customers / year. Reliability value can be improved one of them by adding recloser. The addition of the recloser should pay attention to the area of frequent interference, the percentage of load and impedance of the electricity system. The VEGA method was used to determine the optimal recloser location by minimizing the SAIDI and SAIFI values. The result of the optimization method using VEGA shows optimal recloser location in the group 5 with the highest fitness 8,8396 with SAIDI 0,0070 hour / customer / year and SAIFI 0,0061 times / customer / year with program running time ± 3,6 minutes. These values indicate the VEGA method is more accurate than the fuzzy and genetic algorithm combination method but requires a longer running time.
OPTIMASI REAKTIF POWER DISPATCH MENGGUNAKAN REAL-CODED GENETIC ALGORITHM (RGA) Widyadi Setiawan; Satriya Utama
Jurnal Teknologi Elektro Vol 10 No 1 (2011): (January - June) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (74.733 KB)

Abstract

Pada penelitian ini metode real-coded genetic algorithm (RGA) dipakai sebagai salah satu teknik untuk mendapatkan solusi permasalahan optimal reactive power dispatch (ORPD). Metode RGA dibedakan dengan GA standar pada pemakaian kode real (real-coded) pada kromosomnya. Sistem IEEE 14-bus, IEEE 30-bus dan sistem Jawa-Bali dipakai sebagai sistem uji untuk memperlihatkan perbedaan antara metode GA standar dengan metode RGA. Pada sistem IEEE 14-bus, unjuk kerja metode GA memberikan rugi-rugi saluran total 13,3477 MW, sedangkan metode RGA memberikan rugi-rugi saluran total 13,1959 MW. Pada sistem IEEE 30-bus, unjuk kerja metode GA memberikan rugi-rugi saluran total 17,4866 MW, sedangkan metode RGA memberikan rugi-rugi saluran total 17,4403 MW MW. Pada sistem Jawa-Bali, unjuk kerja metode GA memberikan rugi-rugi saluran total 130,445 MW, sedangkan metode RGA memberikan rugi-rugi saluran total 126,4791 MW. Hasil penelitian memperlihatkan metode RGA memberikan solusi lebih efisien dibandingkan metode GA standar pada permasalahan ORPD.
ANALISIS PENYEIMBANGAN BEBAN PADA TRANSFORMATOR DISTRIBUSI MENGGUNAKAN METODE FUZZY I Putu Weda Suryawan; Anak Agung Ngurah Amrita; Widyadi Setiawan
Jurnal Teknologi Elektro Vol 17 No 1 (2018): (Januari - April) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (125.88 KB) | DOI: 10.24843/MITE.2018.v17i01.P19

Abstract

Load Balancing is basically provide the load on the transformer is in accordance with its capacity. Load Balancing is done on a transformer KA 0223 which supported by Bunisari Feeder and powered by the GI Pesanggaran. A transformer is located on Kubu Anyar Street Legian Kuta with the installed capacity of 200 kVA. The Transformer brand used is Starlite. The number of customers in a transformer KA 0223 as much as 173 customers. Measurement of load current is done at peak load that is at night. The data of measurement result then processed using Fuzzy method to get balanced result, the percentage of unbalance of load according to ANSI / IEEE Std 446-1987 is 5% and to know the point of customer that must be added or subtracted. The data used in 2015 are in January and June, 2016 in January and June, in 2017 in January. Measurement results in the year 2017 January 1st semester percentage of load unbalance before using the Fuzzy method of 13.5%. After using the Fuzzy method, the percentage of load unbalance is much better than before at 2.5%. The measurement result of 2015 in 2sd semester is said to be balanced, because the percentage of load unbalance is equal to 5%. After using Fuzzy method, the percentage of load unbalance is much better than before that is equal to 2.2%. This proves that the program can work when the system is either balanced or not.
Analisa Horizontal Handover Terhadap Qos Layanan Streaming Multimedia E-Learning Pada Jaringan WLAN 802.11 I M.O. Widyantara; Bagus D. Cahyono; Widyadi Setiawan
Jurnal Teknologi Elektro Vol 14 No 1 (2015): (January - June) Majalah Ilmiah Teknologi Elektro
Publisher : Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (211.652 KB) | DOI: 10.24843/MITE.2015.v14i01p08

Abstract

In this globalization era, the state of the user who no longer occupies in a single place, but always moving, it is necessary to continuity of communication that will cause a handover. This paper intends to analyze the effect of 802.11 WLAN horizontal handover to the QoS of streaming e-learning. Methods of data collection process using the Cisco 3500 series access point that supports handover with existing network systems, ad-hoc network and type of hard handover. The results of the data analysis showed that the handover process is able to improve the QoS by gradually restored gradually, to get back to normal QoS
Co-Authors A.A Ngurah Amrita Alfian Hadianto Antonius Ibi Weking Ardiansiah Ardiansiah Axel Adamma Diwanda Azra Ariel Azmir Bagus D. Cahyono Desi Ramayanti Dewa Gede Satria Bayu Putra Dewa Made Wiharta Dewa Ngakan Made Barel Dove Gandaria, Aaron Gerry Ian Duman Care Khrisne Dyana Arjana, I Gd. E. Duta Nugraha, I Putu Gede Sastra Utara Gede Sukadarmika Hilmy Jawas I Dewa Gde Bayu Wiranatha I Dewa Gede Aditya Pemayun I Dewa Gede Angga Prastika I G. A. K. Diafari Djuni Hartawan I Gede Dyana Arjana I Gede Dyana Arjana, I Gede I Gede Wiyoga Putra I Gusti Agung Adhi Waskita I Gusti Agung Komang Diafari Djuni Hartawan I Gusti Made Andi Dipayana I Ketut Ariek Astana Adi I Made Arsa Suyadnya I Made Martina Edi Putra I Made Oka Widyantara I N Satya Kumara I Nyoman Budiastra I Nyoman Setiawan I Putu E. Duta Nugraha I Putu Gede Krsna Yudha Dharma I Putu Hardy Sarjana I Putu Weda Suryawan I Wayan Darma Satika Ida Ayu Putu Intania Paramitha1 Ida Bagus A. Swamardika Issabelle M. Merry Jaime Luis da Costa Kevin Philip Komang Oka Saputra Komang Rio Adi Prasetya Limbong, Patrick Andreas Linawati Linawati M. Merry, Issabelle Made R. D. Prabawa Maharta Pemayun, A.A Gd. Maria Gusti Agung Ayu Permata Michael Angelo Vincensio Simon Muhamad Sony Pratama Ngurah Indra ER Ni Kadek Diah Parwati Ni Made Ary Esta Dewi Wirastuti Ni Putu Dina Rahmawati Ni Wayan Ernawati Novadianto Yudha Irawan Nyoman Putra Sastra Oktafiana Susanti, Baiq Dwinda Padwita Darma, I Made Angga Pande Ketut Sudiarta, Pande Ketut Patrick Andreas Limbong Pawana, I Wayan Adi Juliawan Permata Sari, Indah Ayu Philip, Kevin R. D. Prabawa, Made Rendi Gustina Riawanto Tambun Robbani Punggawa Arcapada Rukmi Sari Hartati Satriya Utama Sri Andriani Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri Sri Andriati Asri, Sri Andriati Sri Dianing Asri Sungkono, Gilberth Tjok Gede Indra Partha Vina Yuliani, Ni Putu Willy Sucipto Willy Susanto