Garuda - Garba Rujukan Digital

Pendeteksian Lokasi Sumber Noise (Partial Discharge) secara Tiga Dimensi menggunakan Antenna Array IBRAHIM, NUR
Jurnal Elkomika Vol 3, No 2 (2015): Jurnal Elkomika
Publisher : Jurnal Elkomika

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

Abstrak Pada penelitian ini akan dilakukan simulasi teknik pendeteksian lokasi sumber noise berupa partial discharge (PD) pada peralatan tegangan tinggi, dengan menggunakan susunan antena yang terdiri dari empat buah antena monopole sebagai sensor untuk mendeteksi gelombang elektromagnetik (EM) yang dipancarkan dari partial discharge (PD). Algoritma yang digunakan mengacu kepada time difference of arrival (TDOA) dari sinyal yang diterima antar antena (dengan menjadikan salah satu antena sebagai antena referensi). Metode yang digunakan untuk menentukan TDOA adalah metode Akaike Information Criterion, metode Energy Criterion, metode Gabor Centroid, metode threshold detection, metode peak detection, dan metode cross-correlation. Sistem pendeteksian lokasi sumber noise ini menggunakan konfigurasi susunan antena membentuk Y. Jarak antar antena diatur sejauh 2 meter dan 4 meter. Berdasarkan hasil pengamatan dan analisis, konfigurasi susunan antena membentuk Y memiliki tingkat akurasi 97.67%. Metode yang paling akurat untuk menentukan TDOA adalah metode cross-correlation. Kata kunci: PD, TDOA, susunan antena. Abstract This paper presents a simulation of locating noise source (Partial Discharge) on high-voltage apparatuses, by using antenna array that consisted of four monopole antennas as sensor to record the electromagnetic waves (EM) emitted from Partial Discharge (PD). The detection algorithm is based on the time difference of arrival (TDOA) of the signals received between antennas (by using one of four antennas as reference antenna). The methods to determine TDOAs are Akaike Information Criterion method, Energy Criterion method, Gabor Centroid method, threshold detection method, peak detection method, and/or cross-correlation method. These system use Y-shaped array configuration. The adjusted distance between antennas are 2 meter and 4 meter. From the observation and analysis results, Y-shaped array antenna configuration has accuracy 97.76%. The best method to get TDOA is the cross-correlation method. Keywords: PD, TDOA, antenna array.

Compressive Sensing Audio Watermarking dengan Metode LWT dan QIM SAFITRI, IRMA; IBRAHIM, NUR; YOGASWARA, HERLAMBANG
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 6, No 3 (2018): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v6i3.405

ABSTRAKPenelitian ini mengembangkan teknik Compressive Sensing (CS) untuk audio watermarking dengan metode Lifting Wavelet Transform (LWT) dan Quantization Index Modulation (QIM). LWT adalah salah satu teknik mendekomposisi sinyal menjadi 2 sub-band, yaitu sub-band low dan high. QIM adalah suatu metode yang efisien secara komputasi atau perhitungan watermarking dengan menggunakan informasi tambahan. Audio watermarking dilakukan menggunakan file audio dengan format *.wav berdurasi 10 detik dan menggunakan 4 genre musik, yaitu pop, classic, rock, dan metal. Watermark yang disisipkan berupa citra hitam putih dengan format *.bmp yang masing-masing berukuran 32x32 dan 64x64 pixel. Pengujian dilakukan dengan mengukur nilai SNR, ODG, BER, dan PSNR. Audio yang telah disisipkan watermark, diuji ketahanannya dengan diberikan 7 macam serangan berupa LPF, BPF, HPF, MP3 compression, noise, dan echo. Penelitian ini memiliki hasil optimal dengan nilai SNR 85,32 dB, ODG -8,34x10-11, BER 0, dan PSNR ?.Kata kunci: Audio watermarking, QIM, LWT, Compressive Sensing. ABSTRACTThis research developed Compressive Sensing (CS) technique for audio watermarking using Wavelet Transform (LWT) and Quantization Index Modulation (QIM) methods. LWT is one technique to decompose the signal into 2 sub-bands, namely sub-band low and high. QIM is a computationally efficient method or watermarking calculation using additional information. Audio watermarking was done using audio files with *.wav format duration of 10 seconds and used 4 genres of music, namely pop, classic, rock, and metal. Watermark was inserted in the form of black and white image with *.bmp format each measuring 32x32 and 64x64 pixels. The test was done by measuring the value of SNR, ODG, BER, and PSNR. Audio that had been inserted watermark was tested its durability with given 7 kinds of attacks such as LPF, BPF, HPF, MP3 Compression, Noise, and Echo. This research had optimal result with SNR value of 85.32 dB, ODG value of -8.34x10-11, BER value of 0, and PSNR value of ?.Keywords: Audio watermarking, QIM, LWT, Compressive Sensing.

Pengamanan Pesan pada Steganografi Citra dengan Teknik Penyisipan Spread Spectrum SAIDAH, SOFIA; IBRAHIM, NUR; WIDIANTO, MOCHAMMAD HALDI
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 7, No 3 (2019): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v7i3.544

ABSTRAKPada studi ini, dilakukan penggabungan metode - metode untuk memperkuat dan meningkatkan sisi keamanan proses pertukaran informasi atau pesan digital. Metode yang digunakan diantaranya adalah metode kriptografi dan metode steganografi. Implementasi pada sistem yang dibangun dilakukan dengan menyandikan pesan pada penerapan metode steganografi citra dalam menyembunyikan pesan tersandi yang dihasilkan ke dalam sebuah citra warna (RGB) dalam domain Discrete Cosine Transform dengan teknik penyisipan Spread Spectrum. Hasil penelitian menunjukan bahwa kualitas dari stego image sangat mirip dengan cover citra yang digunakan, berdasarkan perolehan nilai performansi objektif PSNR diatas 30 db dan subjektif MOS di atas nilai 4.Kata kunci: Steganografi, Discrete Cosine Transform, Spread Spectrum, PSNR, SNR ABSTRACTIn this study, a combination of methods was used to strengthen and enhance the security side of the process of exchanging information or digital messages. The methods used include cryptographic methods and steganography methods. The implementation of the system built is done by encoding the message on the application of the image steganography method in hiding the encrypted message generated into a color image (RGB) in the Discrete Cosine Transform domain with the Spread Spectrum insertion technique. The results of the study show that the quality of the stego image is very similar to the cover image used, based on the acquisition of an objective performance value of PSNR above 30 db and subjective MOS above a value of 4.Keywords: Steganografi, Discrete Cosine Transform, Spread Spectrum, PSNR, SNR

Pendeteksian Lokasi Sumber Noise (Partial Discharge) secara Tiga Dimensi menggunakan Antenna Array IBRAHIM, NUR
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 3, No 2 (2015): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v3i2.106

ABSTRAKPada penelitian ini akan dilakukan simulasi teknik pendeteksian lokasi sumber noise berupa partial discharge (PD) pada peralatan tegangan tinggi, dengan menggunakan susunan antena yang terdiri dari empat buah antena monopole sebagai sensor untuk mendeteksi gelombang elektromagnetik (EM) yang dipancarkan dari partial discharge (PD). Algoritma yang digunakan mengacu kepada time difference of arrival (TDOA) dari sinyal yang diterima antar antena (dengan menjadikan salah satu antena sebagai antena referensi). Metode yang digunakan untuk menentukan TDOA adalah metode Akaike Information Criterion, metode Energy Criterion, metode Gabor Centroid, metode threshold detection, metode peak detection, dan metode cross-correlation. Sistem pendeteksian lokasi sumber noise ini menggunakan konfigurasi susunan antena membentuk Y. Jarak antar antena diatur sejauh 2 meter dan 4 meter. Berdasarkan hasil pengamatan dan analisis, konfigurasi susunan antena membentuk Y memiliki tingkat akurasi 97.67%. Metode yang paling akurat untuk menentukan TDOA adalah metode cross-correlation.Kata kunci: PD, TDOA, susunan antena.ABSTRACTThis paper presents a simulation of locating noise source (Partial Discharge) on high-voltage apparatuses, by using antenna array that consisted of four monopole antennas as sensor to record the electromagnetic waves (EM) emitted from Partial Discharge (PD). The detection algorithm is based on the time difference of arrival (TDOA) of the signals received between antennas (by using one of four antennas as reference antenna). The methods to determine TDOAs are Akaike Information Criterion method, Energy Criterion method, Gabor Centroid method, threshold detection method, peak detection method, and/or cross-correlation method. These system use Y-shaped array configuration. The adjusted distance between antennas are 2 meter and 4 meter. From the observation and analysis results, Y-shaped array antenna configuration has accuracy 97.76%. The best method to get TDOA is the cross-correlation method.Keywords: PD, TDOA, antenna array.

Pengklasifikasian Grade Telur Ayam Negeri menggunakan Klasifikasi K-Nearest Neighbor berbasis Android IBRAHIM, NUR; BACHERAMSYAH, TASYA FIKRIYAH; HIDAYAT, BAMBANG; DARANA, SJAFRIL
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 6, No 2 (2018): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v6i2.288

ABSTRAKTelur ayam negeri yang dibeli oleh masyarakat Indonesia di toko swalayan, pasar, ataupun di peternakan memiliki grade yang berbeda-beda. Pada penelitian sebelumnya, telah dilakukan pembuatan sistem pengklasifikasian telur ayam dengan berbasis Windows, namun belum dapat digunakan secara praktis oleh masyarakat. Penelitian ini dilakukan agar masyarakat dapat menggunakannya di lapangan dalam mengklasifikasikan grade telur ayam negeri, dimana pengklasifikasian grade pada telur ayam negeri ini menggunakan klasifikasi KNearest Neighbor (K-NN) yang berbasis android. Berdasarkan hasil pengujian, sistem ini dapat mengklasifikasikan grade telur ayam negeri dengan tingkat akurasi sebesar 80% (dibandingkan menggunakan Haugh Unit Micrometer) menggunakan parameter layer 4 (grayscale), metode penghitungan jarak cosine, dan nilai k=1 dimana jumlah tetangga yang dibandingkan pada algoritma K-NN adalah 1.Kata kunci: K-NN, telur ayam negeri, android.ABSTRACTChicken eggs purchased by Indonesian people in supermarkets, markets, or farms have different grades. In the previous research, the classification system of chicken eggs has been done in the windows platform, but it cannot be used practically by the people. This research was made so the people can use it on the field to classify chicken eggs grade, using the classification of K-Nearest Neighbor (K-NN) based on android. Based on testing results of this system, can classify eggs grade chicken with an accuracy of 80% (compared with Haugh Unit Micrometer) using layer 4 (grayscale), cosine distance method, and value of k=1 which is the total of compared neighborhood in K-NN algorithm is 1.Keywords: K-NN, chicken egg, android.

IMAGE WATERMARKING PADA CITRA MEDIS MENGGUNAKAN COMPRESSIVE SENSING BERBASIS STATIONARY WAVELET TRANSFORM HAFIZHANA, YASQI; SAFITRI, IRMA; NOVAMIZANTI, LEDYA; IBRAHIM, NUR
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 8, No 1 (2020): ELKOMIKA
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v8i1.43

ABSTRAK Watermarking pada citra medis dilakukan untuk melindungi hak kepemilikan dan keaslian sebuah citra medis. Proses embedding dan extraction dirancang menggunakan metode Stationary Wavelet Transform (SWT) dan Statistical Mean Manipulation (SMM) untuk mengubah citra host menjadi sinyal sparse kemudian memasuki proses watermarking. Citra watermark dioptimasi dengan menggunakan metode Compressive Sensing (CS). Hasil akhir dari penelitian ini menunjukkan simulasi Image Watermarking dengan Bit Error Rate (BER) mendekati nilai nol dan PSNR lebih besar dari 40 dB, tanpa diberikan serangan. Penerapan Compressive Sensing menyebabkan nilai PSNR meningkat hingga 3,5 dB dan embedding capacity menjadi empat kali lipat lebih baik. Kata Kunci: Image watermarking, Telemedicine, Stationary Wavelet Transform, Statistical Mean Manipulation, Compressive Sensing. ABSTRACT Watermarking in medical images is carried out to protect ownership rights and authenticity of a medical image. The embedding and extraction process was designed using Stationary wavelet transform (SWT) and Statistical Mean Manipulation (SMM) methods to convert the host image into a sparse signal and then enter the watermarking process. The watermark image is optimized using the Compressive Sensing (CS) method. The final result of this final project shows the simulation of Image Watermarking with the Bit Error Rate (BER) approaching zero and PSNR greater than 40 dB, without being given an attack. The application of the Compressive Sensing pursuit will cause the PSNR increase up to 3.5 dB and embedding capacity four times better. Keywords: Image watermarking, Telemedicine, Stationary Wavelet Transform, Statistical Mean Manipulation, Compressive Sensing.

TEA LEAVES GMB SERIES CLASIFFICATION USING CONVOLUTIONAL NEURAL NETWORK Rizal, Syamsul; Pratiwi, Nor Kumalasari Caecar; Ibrahim, Nur; Vidya, Hurianti; Saidah, Sofia; Fu'adah, R Yunendah Nur
JESCE (JOURNAL OF ELECTRICAL AND SYSTEM CONTROL ENGINEERING) Vol 3, No 2 (2020): Journal Of Electrical And System Control Engineering Februari
Publisher : Universitas Medan Area

This study classifies GMB series tea leaves by using a convolutional neural network as a classification system. GMB series tea are the superior tea seeds in Indonesia. Gambung series, namely: GMB 1 to GMB 11, are planting material seeds that have been recommended by the Ministry of Agriculture. The potential of these tea series yield of 4,000 - 5,800 kg / ha of dried tea. The morphological similarity level of GMB 1 to GMB 11 is very high, because many elders from the clones are from the same crossing parents. During this time, the process of identifying GMB clones 1 through GMB 11 is done manually using the visual eye of an experts at PPTK Gambung. These experts are limited to be able to identify each tea series. This process is susceptible to errors in the reading of clone types, and is very dependent on the presence of the experts. If an error occurs in the process of identifying the type of clone, it will interfere with the nursery process. Errors in the selection of recommended clones will harm the process of a long period of time, because the economic age of tea plants can reach until 50 years. The potential loss of production due to misuse of plant material can reach 1,200 kg / ha per year. Against the background of these problems, it is very necessary to have a system to identify the GMB series clone. Continuous studies has been conducted to build an automation system for the identification and classification of GMB series tea clones. The system is designed using the Convolutional Neural Network (CNN) method. The results obtained from this system output in the form of accuracy with a value of 85%.

KLASIFIKASI DAUN TEH GAMBUNG VARIETAS ASSAMICA MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR LENET-5 Abdul Hafiz Suherman; Nur Ibrahim; Heri Syahrian; Vitria Puspitasari Rahadi; Muhammad Khais Prayoga
JOURNAL OF ELECTRICAL AND SYSTEM CONTROL ENGINEERING Vol 4, No 2 (2021): Journal of Electrical And System Control Engineering
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jesce.v4i2.4136

Indonesia merupakan salah satu pengolahan produk teh gambung terbesar. Produk teh gambung dihasilkan dengan jenis teh yang berbeda. Namun, kualitas system pengolahan produk mengalami penurunan dikarenakan pekebun sulit membedakan jenis daun teh produksi dengan daun teh unggul dan masih menggunakan prosedur pengolahan daun secara manual. Diketahui, daun teh gambung memiliki 11 klon jenis. Daun teh GMB (1-11) merupakan klon unggul jenis teh dari jenis assamica maupun jenis sinensis dari hasil riset Pusat Penelitian Teh dan Kina (PPTK). Oleh karena itu, diperlukan teknologi pengenalan jenis daun teh sebagai peningkatan kualitas produk. Penelitian ini membuat metode klasifikasi, yaitu dengan menggunakan metode Convolutional Neural Network (CNN) sebagai algoritma klasifikasi. Proses klasifikasi data citra daun akan diuji dengan kelas sebanyak 11 jenis daun klon dan jumlah dataset diaugmentasi sebesar 4400 data. Arsitektur LeNet-5 akan digunakan pada pengujian model klasifikasi. Proses klasifikasi memperoleh hasil terbaik dengan nilai akurasi sebesar 94.55% dengan parameter optimizer Adam dan learning rate yang digunakan sebesar 0.001.

TEA LEAVES GMB SERIES CLASIFFICATION USING CONVOLUTIONAL NEURAL NETWORK Syamsul Rizal; Nor Kumalasari Caecar Pratiwi; Nur Ibrahim; Hurianti Vidya; Sofia Saidah; R Yunendah Nur Fu'adah
JOURNAL OF ELECTRICAL AND SYSTEM CONTROL ENGINEERING Vol 3, No 2 (2020): Journal Of Electrical And System Control Engineering Februari
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jesce.v3i2.3320

This study classifies GMB series tea leaves by using a convolutional neural network as a classification system. GMB series tea are the superior tea seeds in Indonesia. Gambung series, namely: GMB 1 to GMB 11, are planting material seeds that have been recommended by the Ministry of Agriculture. The potential of these tea series yield of 4,000 - 5,800 kg / ha of dried tea. The morphological similarity level of GMB 1 to GMB 11 is very high, because many elders from the clones are from the same crossing parents. During this time, the process of identifying GMB clones 1 through GMB 11 is done manually using the visual eye of an experts at PPTK Gambung. These experts are limited to be able to identify each tea series. This process is susceptible to errors in the reading of clone types, and is very dependent on the presence of the experts. If an error occurs in the process of identifying the type of clone, it will interfere with the nursery process. Errors in the selection of recommended clones will harm the process of a long period of time, because the economic age of tea plants can reach until 50 years. The potential loss of production due to misuse of plant material can reach 1,200 kg / ha per year. Against the background of these problems, it is very necessary to have a system to identify the GMB series clone. Continuous studies has been conducted to build an automation system for the identification and classification of GMB series tea clones. The system is designed using the Convolutional Neural Network (CNN) method. The results obtained from this system output in the form of accuracy with a value of 85%.

Identifikasi Kematangan Daun Teh Berbasis Fitur Warna Hue Saturation Intensity (HSI) dan Hue Saturation Value (HSV)(Identification Maturity Tea Leaves Based on Color Feature Hue Saturation Intensity (HSI) and Hue Saturation Value (HSV)) Rahma Nur Auliasari; Ledya Novamizanti; Nur Ibrahim
JUITA : Jurnal Informatika JUITA Vol. 8 Nomor 2, November 2020
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Indonesia merupakan negara penghasil komoditi perkebunan teh terbesar di dunia. Sampai saat ini, penentuan tingkat kematangan daun teh hanya menggunakan sistem gilir petik, dimana suatu blok tanam telah ditentukan kapan akan dipanen. Perancangan sistem identifikasi kematangan daun teh membuat daun teh dengan tingkat kematangan tertentu terlihat lebih jelas. Pada penelitian ini, telah dirancang sistem identifikasi kematangan daun teh. Citra diambil di setiap blok dimana blok tersebut memiliki umur petik yang berbeda yakni blok yang sedang dipanen (matang), blok yang dalam waktu dekat akan dipanen (setengah matang), dan blok yang belum untuk dipanen (belum matang). Ekstraksi fitur menggunakan Hue Saturation Intensity (HSI) dan Hue Saturation Value (HSV), serta metode klasifikasi K-Nearest Neighbor (K-NN). Akurasi pada fitur warna HSI 100% dan HSV 83.33% dengan waktu komputasi masing-masing 28.4 mili detik dan 27.3 mili detik.

Title

Found 54 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 54 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 54 Documents
Search