cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arsyad Ramadhan Darlis
Contact Email
arsyad@itenas.ac.id
Phone
-
Journal Mail Official
jte.itenas@itenas.ac.id
Editorial Address
-
Location
Kota bandung,
Jawa barat
INDONESIA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika
Published by Institut Teknologi Nasional Bandung
ISSN : 23388323     EISSN : 24599638     DOI : -
Core Subject : Engineering,
Electrical & Electronics Engineering Engineering
Jurnal ELKOMIKA diterbitkan 3 (tiga) kali dalam satu tahun pada bulan Januari, Mei dan September. Jurnal ini berisi tulisan yang diangkat dari hasil penelitian dan kajian analisis di bidang ilmu pengetahuan dan teknologi, khususnya pada Teknik Energi Elektrik, Teknik Telekomunikasi, dan Teknik Elektronika.
Arjuna Subject : -
Articles 22 Documents
 1   2   3 
Search results for , issue "Vol 12, No 4: Published October 2024" : 22 Documents clear
Analisis Pengaruh Teknik Coakan Dua Langkah terhadap Penurunan Torka Cogging terhadap Pergeseran Poros pada Mesin Magnet Permanen CORREIA, LUCIO ALFREDO; NUR, TAJUDDIN; PANDJAITAN, LANNY; HERLINA, HERLINA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.1007

Abstract

ABSTRAKTorsi cogging adalah torsi yang terjadi akibat interaksi antara gaya tangensial di ujung magnet dengan material alur stator, yang menahan gerakan rotor pada generator magnet permanen. Torsi ini harus diminimalkan dalam aplikasi turbin angin karena dapat menghambat pergerakan awal generator. Penelitian ini bertujuan untuk menganalisis pengaruh metode tertentu dalam mengurangi torsi cogging dan pergeseran poros. Metode yang digunakan melibatkan penerapan coakan dua tingkat pada ujung magnet rotor dengan tiga konstruksi magnet rotor yang berbeda, sementara kondisi inti stator tetap identik. Analisis numerik menggunakan FEMM 4.2 menunjukkan pengurangan torsi cogging yang signifikan sebesar 99,70% dan pengurangan pergeseran poros sebesar 60% secara vertikal dan 51% secara horizontal.Kata kunci: coakan dua tingkat, generator magnet permanen, gaya magnet tangensial, torka cogging, pergeseran poros ABSTRACTCogging torque is the torque resulting from the interaction between tangential forces at the magnet's edge and the stator slot material, which opposes the rotor's motion in a permanent magnet generator. This torque must be minimized in wind turbine applications as it can hinder the generator's initial movement. This study aims to analyze the effect of a specific method on reducing cogging torque and shaft shifting. The method involves applying a two-step notch at the rotor magnet's edge with three different rotor magnet constructions, while keeping the stator core conditions identical. Numerical analysis using FEMM 4.2 achieved a significant cogging torque reduction of 99.70% and reduced shaft displacement by 60% vertically and 51% horizontally.Keywords: Two-step notch, permanent magnet generator, tangential magnetic force, shaft shifting
Identifikasi Penyakit Katarak berdasarkan Citra Fundus menggunakan Siamese Convolutional Neural Network RAHMADWATI, RAHMADWATI; IMRAN, AZZAM ZAHFRAN; ASWIN, MUHAMMAD; FERDIANA, KHAIRUNISA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.838

Abstract

ABSTRAKKatarak merupakan penyakit yang dipengaruhi oleh faktor-faktor tertentu seperti usia, aktivitas dan penderita penyakit genetik seperti diabetes, hipertensi, asam urat serta riwayat keluarga katarak. Diagnosis penyakit katarak ini dapat dipengaruhi oleh faktor subyektif seperti pengalaman dan keahlian dokter. Untuk mengatasi hal tersebut dan menurunkan tingkat subyektivitas diperlukan pendekatan yang akurat dan konsisten yaitu sistem identifikasi penyakit katarak terbantukan komputer. Penelitian ini bertujuan sebagai deteksi dini katarak. Metode SCNN digunakan untuk mengidentifikasi citra fundus mata katarak. Fine tuning parameter SCNN memberikan performa yang baik pada proses pelatihan dan pengujian yaitu 100 epoch, optimizer : RMS Prop dan loss function Binary Crossentropy. Performansi yang diberikan yaitu akurasi 91,25%, kepresisian 91%.Kata kunci: penyakit katarak, siamese convolutional neural network, citra fundus. ABSTRACTThe cataract is a disease that influenced by certain factors such as age, activity and people with genetic disease such as diabetes, hypertension, uric acid and family history of cataract. The diagnosis of cataracts based on opthamologist experience and expertise which signifies a level of a diagnostic subjectivities. In order to overcome that problem and reduce the level of subjectivity, the need for an accurate and consistent computer aided identification for cataract disease is inevitable. This research aims to as an early detection of cataracts. The SCNN is applied for identify the cataract disease based on eye fundus image. Fine tuning SCNN parameters which provide good performances in the training and testing process with 100 epochs, RMSProp optimizer, Binary Crossentropy Loss function.This system gives promising result with the accuracy 91,25% , precision level is 91%.Keywords: cataract disease, siamese convolutional neural network, fundus images
Influences of Environmental Factors of a Hybrid Photovoltaic and Thermoelectric Generation System WALUYO, WALUYO; DARLIS, ARSYAD RAMADHAN; HADIATNA, FEBRIAN; ABIMANYU, AHMAD
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.1038

Abstract

ABSTRAKSaat ini, pemanfaatan sumber energi terbarukan menjadi salah satu pilihan dalam menjawab tantangan krisis energi. Sistem pembangkit listrik fotovoltaiktermoelektrik hibrida yang menggabungkan keunggulan konversi energi cahaya dan panas dari matahari perlu dikaji kinerjanya. Penelitian ini membahas peningkatan efisiensi pembangkit listrik tenaga surya hybrid panel-termoelektrik dan hubungannya dengan pengaruh faktor lingkungan. Akuisisi data berdasarkan analisis komputasi menganalisis statistik multivariat, seperti regresi, korelasi, boxplot, dan principal component analysis (PCA). Hasil penelitian menunjukkan daya masukan MPPT lebih tinggi dibandingkan daya keluaran, dengan efisiensi tipikal sebesar 99,66%. Peningkatan suhu udara membuat tegangan sedikit menurun, dan daya yang dihasilkan meningkat cukup besar seiring dengan naiknya suhu udara. Peda penelitian terlihat bahwa radiasi ultraviolet (UV) meningkat secara signifikan seiring dengan peningkatan suhu lingkungan.Kata kunci: efisiensi, faktor lingkungan, fotovoltaik, analisis statistik, termoelektrik ABSTRACTRecently, using renewable energy sources is one option in answering the challenge of the energy crisis. The hybrid photovoltaic-thermoelectric power generation system is a solution that combines the advantages of converting both light and heat energy from the sun, which needs to be studied. This study discussed the increase in efficiency in a hybrid solar panel-thermoelectric power generation and its relationship to the influence of environmental factors. The data acquisition is based on the computational analyses of multivariate statistics, such as regressions, correlations, boxplots and principal component analysis. It showed the input power of the MPPT was higher than the output power, with a typical efficiency of 99.66%. The rising air temperature decreased the voltages and generated power considerably, increasing as the air temperature rose. Finally, the ultraviolet (UV) radiation increased significantly as the ambient temperature rose.Keywords: efficiency, environmental factor, photovoltaic, statistical analysis, thermoelectric
Penerapan Contour Detection dengan Pengontrol PID pada Robot Line Follower TANUJAYA, MIGUEL; PATRICK, RAFAEL; SEBASTIAN, HANS; WAHAB, FAISAL
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.923

Abstract

ABSTRAKSebuah robot line follower harus mampu mendeteksi garis dan bergerak mengikuti garis tersebut. Warna garis dan lantai yang tidak begitu kontras satu sama lain cukup sulit untuk dibedakan. Salah satu sensor yang dapat digunakan pada kasus tersebut adalah kamera. Dengan memanfaatkan pengolahan citra, robot dapat mengenali garis yang perlu diikuti. Untuk menghasilkan sistem line following yang konsisten dan rendah error, digunakan pengontrol PID yang bertujuan untuk menjaga posisi robot agar tetap pada lintasan yang diinginkan. Robot yang digunakan dalam penelitian ini adalah robot dengan empat roda mecanum. Perangkat keras yang digunakan meliputi kamera sebagai sensor utama, mikrokontroler Raspberry Pi 4 sebagai pusat pengolahan data dan pengendalian gerak motor. Hasil penelitian menunjukkan bahwa sistem line following yang dirancang memiliki rata-rata error posisi adalah 13,507%.Kata kunci: line follower, pengolahan citra, contour detection, PID, mecanum ABSTRACTA line-following robot must be able to detect a line and move along it. Lines and floors with low contrast are challenging to distinguish. One sensor that can be used in this case is a camera. By utilizing image processing, the robot can recognize the line it needs to follow. To produce a consistent and low-error linefollowing system, a PID controller is employed to keep the robot on the desired path. The robot used in this study is a four-wheeled mecanum robot. The hardware includes a camera as the primary sensor and a Raspberry Pi 4 microcontroller for data processing and motor control. The research results show that the designed line-following system has an average position error of 13.507%.Keywords: line follower, image processing, contour detection, PID, mecanum
Response Speed Analysis of Interactive Voicebot Receptionist UDZRI, MUHAMMAD HAFIDZ; YAKIN, NIZAR AINUL; HASNAH, FIDA YUZIDA; DARLIS, DENNY; REZAMELA, ERDIANSYAH; FITRI, IFTITA; FAUZI A, FARIS NUR; SUNARYA, UNANG
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.983

Abstract

ABSTRAKPusat Penelitian Teh dan Kina (PPTK) Gambung menghadapi tantangan dalam memberikan informasi cepat kepada pengunjung. Untuk mengatasinya, dikembangkan voicebot interaktif berbasis teknologi Python Speech Recognition dan Pyttsx3, yang menggunakan metode speech-to-text dan text-to-speech. Pengujian dilakukan dengan variasi kondisi internet, intensitas kebisingan, perbedaan aksen, dan analisis keluaran suara. Hasil menunjukkan akurasi hingga 90% dengan rata-rata kecepatan tanggap 1,94 detik pada koneksi internet stabil dan suara yang jelas. Di lingkungan bising dengan kekuatan suara tinggi (105 dB), voicebot tetap mampu menanggapi. Voicebot ini juga menunjukkan akurasi yang sama (90%) untuk penutur asli dan non-asli bahasa Inggris. Solusi ini berpotensi meningkatkan aksesibilitas informasi di PPTK Gambung, meskipun kinerjanya dipengaruhi oleh kestabilan internet dan kondisi lingkungan.Kata kunci: voicebot, voice-to-text, text-to-speech, pyttsx3, speech recognition ABSTRACTThe Gambung Tea and Cinchona Research Center (PPTK) faces challenges in providing timely information to visitors. To address this, an interactive voicebot based on Python Speech Recognition technology and Pyttsx3 was developed, utilizing speech-to-text and text-to-speech methods. Tests were conducted with variations in internet conditions, noise intensity, accent differences, and voice output analysis. Results show accuracy of up to 90% with an average response speed of 1,94 seconds on a stable internet connection and clear voice. In noisy environments with high voice strength (105 dB), the voicebot was still able to respond. The voicebot also showed similar accuracy (90%) for native and nonnative English speakers. This solution has the potential to improve information accessibility at PPTK Gambung, although its performance is affected by internet stability and environmental conditions.Keywords: voicebot, voice-to-text, text-to-speech, pyttsx3, speech recognition
Estimasi SOC Saat Discharging pada Baterai VRLA Berbasis Elman Backpropagation YANARATRI, DIAH SEPTI; SUTEDJO, SUTEDJO; FIRMANSYAH, ACHMAD DICKY; IRIANTO, IRIANTO; RAKHMAWATI, RENNY; ADILA, AHMAD FIRYAL
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.862

Abstract

ABSTRAKPenurunan performa baterai terjadi akibat siklus pengisian dan pengosongan berulang yang melebihi batas, mempercepat degradasi. Penelitian ini bertujuan untuk meningkatkan akurasi estimasi State of Charge (SOC) baterai menggunakan Artificial Neural Network (ANN) dengan algoritma Elman Backpropagation. Metode digunakan karena menambahkan lapisan context neuron yang mampu menangkap pola dinamis pada data baterai. Pengujian dilakukan dengan membandingkan hasil estimasi SOC dari metode ini dengan metode Coulomb Counting. SOC baterai diestimasi dari 100% hingga 60%, dan hasil menunjukkan bahwa meskipun Coulomb Counting awalnya memberikan SOC lebih tinggi, estimasi dari kedua metode menjadi lebih mirip seiring waktu. Error estimasi berkisar antara 0,1% hingga 14,7%. Algoritma Elman Backpropagation terbukti mampu memberikan estimasi SOC yang lebih akurat, namun masih memerlukan kalibrasi lebih lanjut untuk meningkatkan presisi.Kata kunci: Artificial Neural Network, Baterai, Coulumb Counting, Elman Backpropagation, State of Charge. ABSTRACTThe decline in battery performance occurs due to repeated charge and discharge cycles that exceed limits, accelerating degradation. This study aimed to improve the accuracy of State of Charge (SOC) estimation using an Artificial Neural Network (ANN) with the Elman Backpropagation algorithm. The method used was unique in adding a context neuron layer capable of capturing dynamic patterns in battery data. Testing was conducted by comparing SOC estimates from this method with the Coulomb Counting method. The battery's SOC was estimated from 100% to 60%, and the results showed that although Coulomb Counting initially provided higher SOC estimates, the estimates from both methods became more similar over time. Estimation errors ranged from 0.1% to 14.7%. The Elman Backpropagation algorithm proved to provide more accurate SOC estimates, although further calibration is needed to improve precision.Keywords: Artificial Neural Network, Battery, Coulumb Counting, Elman Backpropagation, State of Charge.
Kelayakan Finansial Pembangunan Pembangkit Listrik Tenaga Hybrid Di Sanggar Kota Batu, Jawa Timur MULJANTO, WIDODO PUDJI; WIYOGA, BELDA ROSALIE PUTRI; WARTANA, I MADE; SULISTIAWATI, IRRINE BUDI
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.1063

Abstract

ABSTRAKIndonesia masih bergantung pada energi fosil untuk sumber pembangkit listrik. Mengingat, bahan bakar fosil terbatas, upaya melakukan peralihan ke energi terbarukan dan ramah lingkungan semakin digiatkan. Studi kasus penelitian dilakukan di Sanggar Latar di Batu dengan melakukan analisa kelayakan pembangunan Pembangkit Listrik Tenaga Phikohidro dan Pembangkit Lisrik Tenaga Surya. Analisa yang digunakan untuk melihat layak dan tidaknya proyek dengan menghitung selisih kas masuk dan keluar (NPV), tingkat pengembalian yang diharapkan dari proyek (IRR), serta total manfaat yang diperoleh beserta pengeluaran biaya yang dilakukan. Menggunakan asumsi investasi selama 25 tahun dan suku bunga 6 %, diperoleh besar selisih kas sebesar Rp 86.158.036,-, Tingkat pengembalian (IRR) 47%, dengan total manfaat sebesar (BCR) 4,10. Waktu yang dibutuhkan untuk pengembalian investasi selama 2,33 tahun artinya pembangunan pembangkit listrik tenaga hybrid dapat direalisasikan.Kata kunci: analisis investasi, kelayakan proyek, pembangkit listrik tenaga hibrid ABSTRACTIndonesia still relies on fossil energy as a power plant. Knowing that fossil fuels are limited, the efforts of new and environmentally friendly energy resources are being intensified. A case study conducted at Sanggar Latar in Batu, using the analysis of the feasability of establishing both a biomass power plant (PLTPh) and a solar power plant (PLST). The analysis that is used to the project on worthy or not with calculating differences of cash in and out (NPV), the level of returning that is hoped from the project (IRR), and the total of benefits received with the expenses that is done. Using investment assumption for 25 years and interest rate 6%, a large differences was obtained with Rp 86.158.036,-, cash, level of return (IRR) 47%, and the benefit total (BCR) 4,10. Time needed for the investment return is 2,33 years that is the development of hybrid power plant can be realized.Keywords: investment analysis, project feasibility, hybrid power plant
Komunikasi Cahaya Tampak untuk Model Sistem Pintu Otomatis Berbasis Internet of Things NATALI, YUS; R. F, NURWAN; NURHAYATI, ADE; RIZKY, M.; A, M. NABIL; M, MOSES; ROIHAN, M.; S, ALVA NURVINA; DORAND, PIETRA; SUYATNO, SUYATNO
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.938

Abstract

ABSTRAKKomunikasi cahaya tampak (Visible Light Communication) merupakan solusi untuk komunikasi berkecepatan tinggi pada sistem berbasis Internet of Things. Model pintu otomatis berbasis IoT menggunakan komunikasi cahaya tampak berhasil dibuat untuk keamanan rumah. Komunikasi tersebut dengan panjang gelombang 650 nm berwarna merah diujicobakan untuk jarak 20 cm. Penerima fotodioda mengaktifkan motor servo untuk membuka pintu dengan maksimal sudut rotasi 120 derajat. Ada enam macam kondisi pintu terbuka yang ditampilkan di LCD dan dikirimkan melalui internet ke website. Secara keseluruhan sistem berjalan dengan baik. Komunikasi cahaya tampak juga diujicobakan sebagai sinyal pembawa dengan mendeteksi tegangan yang dikirimkan oleh laser di fotodioda. Berdasarkan ujicoba didapatkan data yang dikirimkan dapat diterima dengan baik, walaupun perubahan tegangan turun sampai dengan 1.5% di fotodioda.Kata kunci: komunikasi cahaya tampak (Visible Light Communication), Internet of Things, pintu otomatis, keamanan, sinyal pembawa ABSTRACTVisible Light Communication (VLC) is a solution for high-speed communication that can be utilized for Internet of Things (IoT) systems. An automatic door model based on IoT using VLC has been successfully assembled for user security at home. This communication, with a wavelength of 650 nm in red light, was tested for 20 cm. The photodiode receiver activates the servo motor to open the door with a maximum rotation angle of 120 degrees. The open door process consists of 6 different conditions displayed on the LCD and transmitted via the internet to the website. In a comprehensive evaluation, the system operates optimally. In addition, VLC was also tested as a carrier signal to examine the voltage sent by the laser. Based on the experiment, the data sent can still be received well, even though there is a voltage change up to 1.5% at the photodiode receiver.Keywords: Visible Light Communications (VLC), Internet of Things, automatic door, security, carrier signal
Studi Pengaruh Biomassa Bahan Bakar Jumputan Padat (BBJP) pada Proses Co-firing di PLTU ADE ARTA, MOCHAMAD ZAINUDIN; WIDAYAT, WIDAYAT; MUCHAMMAD, MUCHAMMAD
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.995

Abstract

ABSTRAKUntuk mereduksi emisi Gas Rumah Kaca (GRK), Pemerintah Indonesia mengajukan kebijakan untuk mengaplikasikan teknologi berbasis Energi Terbarukan (EBT) di PT PLN (Persero) dengan menerapkan co-firing di PLTU batubara. Untuk mengevaluasi karakteristik co-firing biomassa BBJP dilakukan pengujian dengan metode direct co-firing dan uji laboratorium untuk mendapatkan komposisi biomassa BBJP melalui Analisis Proksimat dan Analisis Ultimate. Hasil pengujian menunjukkan bahwa Gross Caloric Value (as received) dan Hardgrove Grindability Index (as received) biomassa BBJP 2646 Kcal/kg dan 20. Hasil uji arus pulverizer, pulverizer outlet temperature, AFR pulverizer mengalami peningkatan seiring kenaikan persentase biomassa BBJP dan sebaliknya untuk coal flow mengalami penurunan. Hasil uji Specific Fuel Consumption (SFC) co-firing biomassa BBJP 5% sebesar 0,58 dan NPHR 2.687 kcal/kWh.Kata kunci: co-firing, SFC, biomassa, pulverizer, Hardgrove Grindability Index ABSTRACTTo reduce greenhouse gas (GHG) emissions, the Government of Indonesia has proposed a policy to apply Renewable Energy-based technology (EBT) at PT PLN (Persero) by implementing co-firing in coal-fired power plants. To evaluate the co-firing characteristics of BBJP biomass, tests were conducted using the direct co-firing method and laboratory tests to obtain the composition of BBJP biomass through Proximate Analysis and Ultimate Analysis. The test results showed that the Gross Caloric Value (as received) and Hardgrove Grindability Index (as received) of BBJP biomass were 2,646 Kcal/kg and 20. The test results of pulverizer flow, pulverizer outlet temperature, AFR pulverizer increased as the percentage of BBJP biomass increased and vice versa for coal flow decreased. Specific Fuel Consumption (SFC) test results of co-firing 5% BBJP biomass amounted to 0.58 and NPHR of 2,687 kcal/kWh.Keywords: co-firing, SFC, biomass, pulverizer, Hardgrove Grindability Index
Optimasi Teknologi WAV2Vec 2.0 menggunakan Spectral Masking untuk meningkatkan Kualitas Transkripsi Teks Video bagi Tuna Rungu NOERCHOLIS, ACHMAD; DWIANDINI, TITANIA; MUKTI, FRANSISKA SISILIA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.877

Abstract

ABSTRAKTeknologi Automatic Speech Recognition (ASR) telah berkembang pesat sebagai alat untuk meningkatkan aksesibilitas informasi bagi penyandang tuna rungu, terutama melalui video. WAV2Vec 2.0, salah satu teknologi ASR unggulan, efektif dalam transkripsi teks, namun kinerjanya menurun saat menghadapi noise. Penelitian ini bertujuan mengoptimalkan WAV2Vec 2.0 dengan menerapkan Spectral Masking untuk mengurangi noise tanpa mengorbankan kejelasan sinyal utama. Evaluasi dilakukan pada tiga jenis video: podcast, video dengan background noise, dan video dengan background music. Hasil menunjukkan penurunan Word Error Rate (WER) yang signifikan, sebesar 78.06% pada podcast dan 53.85% pada video dengan background noise. Hasil penelitian menunjukkan bahwa Spectral Masking efektif dalam meningkatkan akurasi transkripsi, menawarkan solusi inovatif untuk aksesibilitas tuna rungu dalam kondisi audio yang kompleks.Kata kunci: noise reduction, spectral masking, tuna rungu, WAV2Vec 2.0 ABSTRACTAutomatic Speech Recognition (ASR) technology has rapidly evolved as a tool to enhance information accessibility for the hearing impaired, particularly through video content. WAV2Vec 2.0, a leading ASR technology, is effective in text transcription, but its performance degrades in the presence of noise. This study aims to optimize WAV2Vec 2.0 by applying Spectral Masking to reduce noise without compromising the clarity of the main signal. The evaluation was conducted on three types of videos: podcasts, videos with background noise, and videos with background music. The results show a significant reduction in Word Error Rate (WER), with a 78.06% decrease in podcasts and a 53.85% decrease in videos with background noise. These findings demonstrate that Spectral Masking effectively enhances transcription accuracy, offering an innovative solution for improving accessibility for the hearing impaired in complex audio conditions.Keywords: noise reduction, spectral masking, tuna rungu, WAV2Vec 2.0

Page 2 of 3 | Total Record : 22

 1   2   3 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 13, No 4: Published November 2025 Vol 13, No 3: Published July 2025 Vol 13, No 2: Published April 2025 Vol 13, No 1: Published January 2025 Vol 12, No 4: Published October 2024 Vol 12, No 3: Published July 2024 Vol 12, No 2: Published April 2024 Vol 12, No 1: Published January 2024 Vol 11, No 4 (2023): ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektr Vol 11, No 4: Published October 2023 Vol 11, No 3: Published July 2023 Vol 11, No 2: Published April 2023 Vol 11, No 1: Published January 2023 Vol 10, No 4: Published October 2022 Vol 10, No 3: Published July 2022 Vol 10, No 2: Published April 2022 Vol 10, No 1: Published January 2022 Vol 9, No 4: Published October 2021 Vol 9, No 3: Published July 2021 Vol 9, No 2: Published April 2021 Vol 9, No 1: Published January 2021 Vol 8, No 3: Published September 2020 Vol 8, No 2: Published May 2020 Vol 8, No 2 (2020): ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektro Vol 8, No 1: Published January 2020 Vol 8, No 1 (2020): ELKOMIKA Vol 7, No 3: Published September 2019 Vol 7, No 3 (2019): ELKOMIKA Vol 7, No 2: Published May 2019 Vol 7, No 2 (2019): ELKOMIKA Vol 7, No 1 (2019): ELKOMIKA Vol 7, No 1: Published January 2019 Vol 6, No 3 (2018): ELKOMIKA Vol 6, No 3: Published September 2018 Vol 6, No 3 (2018): ELKOMIKA Vol 6, No 2 (2018): ELKOMIKA Vol 6, No 2: Published May 2018 Vol 6, No 1 (2018): ELKOMIKA Vol 6, No 1: Published January 2018 Vol 5, No 2 (2017): ELKOMIKA Vol 5, No 2: Published July - December 2017 Vol 5, No 1: Published January - June 2017 Vol 5, No 1 (2017): ELKOMIKA Vol 4, No 2: Published July - December 2016 Vol 4, No 2 (2016): ELKOMIKA Vol 4, No 1 (2016): ELKOMIKA Vol 4, No 1 (2016): Jurnal Elkomika Vol 4, No 1: Published January - June 2016 Vol 3, No 2 (2015): Jurnal Elkomika Vol 3, No 2: Published July - December 2015 Vol 3, No 2 (2015): ELKOMIKA Vol 3, No 1 (2015): ELKOMIKA Vol 3, No 1 (2015): Jurnal Elkomika Vol 3, No 1: Published January - June 2015 Vol 2, No 2 (2014): ELKOMIKA Vol 2, No 2: Published July - December 2014 Vol 2, No 2 (2014): Jurnal Elkomika Vol 2, No 1 (2014): ELKOMIKA Vol 2, No 1 (2014): Jurnal Elkomika Vol 2, No 1: Published January - June 2014 Vol 1, No 2: Published July - December 2013 Vol 1, No 2 (2013): Jurnal Elkomika Vol 1, No 2 (2013): ELKOMIKA Vol 1, No 1 (2013): ELKOMIKA Vol 1, No 1: Published January - June 2013 Vol 1, No 1 (2013): Jurnal Elkomika More Issue