Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Mechatronics, Electrical Power, and Vehicular Technology Jurnal INKOM CommIT (Communication & Information Technology) Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Teknologi dan Sistem Komputer
Vicky Zilvan, Vicky
LIPI
Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Diseases Classification for Tea Plant Using Concatenated Convolution Neural Network Krisnandi, Dikdik; Pardede, Hilman F.; Yuwana, R. Sandra; Zilvan, Vicky; Heryana, Ana; Fauziah, Fani; Rahadi, Vitria Puspitasari
CommIT (Communication and Information Technology) Journal Vol 13, No 2 (2019): CommIT Vol. 13 No. 2 Tahun 2019
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v13i2.5886

Abstract

Plant diseases can cause a significant decrease in tea crop production. Early disease detection can help to minimize the loss. For tea plants, experts can identify the diseases by visual inspection on the leaves. However, providing experts to deal with disease identification may be very costly. The machine learning technology can be implemented to provide automatic plant disease detection. Currently, deep learning is state-of-the-art for object identification in computer vision. In this study, the researchers propose the Convolutional Neural Network (CNN) for tea disease detections. The researchers focus on the implementation of concatenated CNN, namely GoogleNet, Xception, and Inception-ResNet-v2, for this task. About 4727 images of tea leaves are collected, comprising of three types of diseases that commonly occur in Indonesia and a healthy class. The experimental results confirm the effectiveness of concatenated CNN for tea disease detections. The accuracy of 89.64% is achieved.
Identifikasi Pembicara Menggunakan Algoritme VFI5 dengan MFCC sebagai Pengekstraksi Ciri Zilvan, Vicky; Muttaqien, Furqon Hensan
INKOM Journal Vol 5, No 1 (2011)
Publisher : Pusat Penelitian Informatika - LIPI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (401.592 KB) | DOI: 10.14203/j.inkom.97

Abstract

Voting Feature Instervals (VFI) 5 memiliki akurasi yang cukup tinggi dalam mengklasifikasikan data berbasis teks dan citra. Berdasarkan hal tersebut dikembangkanlah metode identifikasi pembicara menggunakan algoritme VFI5 dengan Mel Frequency Ceptrum Coefficients (MFCC) sebagai pengekstraksi ciri suara untuk melihat keakuratan algoritme VFI5 dalam mengklasifikasikan data berbasis suara. Jenis identifikasi pembicara pada penelitian ini bersifat tertutup dan bergantung pada text. Pada penelitian ini juga dilakukan percobaan menggunakan suara ber-noise untuk melihat kehandalan VFI5 dalam mengklasifikasikan suara ber-noise. Dari hasil pengujian didapatkan bahwa metode yang telah dikembangkan ini memiliki akurasi cukup tinggi dengan akurasi tertinggi sebesar 97% untuk data suara tanpa noise.  Selain itu juga diketahui bahwa jumlah data latih yang optimal untuk menghasilkan akurasi yang tinggi adalah 11. Sedangkan untuk suara bernoise dengan SNR sebesar 30 dB, akurasi tertinggi mencapai 81,5 % dan untuk suara bernoise dengan SNR sebesar 20 dB tingkat akurasi tertinggi mencapai 59 %.
Ekstraksi Objek pada Citra Radar FM-CW dengan Metode DBSCAN Zilvan, Vicky
INKOM Journal Vol 9, No 1 (2015)
Publisher : Pusat Penelitian Informatika - LIPI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (504.726 KB) | DOI: 10.14203/j.inkom.419

Abstract

Makalah ini membahas rancang bangun dan implementasi ekstraksi objek pada radar FM-CW untuk mengatasi permasalahan kualitas citra yang ditangkap oleh radar. Teknik clustering density based spatial clustering of applications with noise (DBSCAN) digunakan untuk mengekstraksi objek dari data input. Hasil dari penelitian ini adalah rancang bangun ekstrasi objek dengan nilai minPts sebesar 4 dan nilai eps sebesar 4 sebagai parameter input untuk DBSCAN. Hasil dari rancang bangun ekstraksi objek adalah titik-titik data hasil ekstraksi objek yang lebih sederhana yang mampu mengatasi permasalahan kualitas citra yang ditangkap oleh radar. Selain itu, titik-titik data yang dihasilkan juga memiliki kualitas data yang lebih baik karena teknik clustering DBSCAN memiliki kemampuan untuk memisahkan noise dari data input.
Automatic detection of crop diseases using gamma transformation for feature learning with a deep convolutional autoencoder Zilvan, Vicky; Ramdan, Ade; Supianto, Ahmad Afif; Heryana, Ana; Arisal, Andria; Yuliani, Asri Rizki; Krisnandi, Dikdik; Suryawati, Endang; Suryo Kusumo, Raden Budiarianto; Yuawana, Raden Sandra; Kadar, Jimmy Abdel; Pardede, Hilman F.
Jurnal Teknologi dan Sistem Komputer [IN PRESS] Volume 10, Issue 3, Year 2022 (July 2022)
Publisher : Department of Computer Engineering, Engineering Faculty, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jtsiskom.2022.14250

Abstract

Precision agriculture is a management strategy for sustaining and increasing the production of agricultural commodities. One of its implementations is for crop disease detection. Currently, deep learning methods have become widespread methods for the automatic detection of crop diseases. Most deep learning methods showed better performance when using an original image in raw form as inputs. However, the original image of crop diseases may appear similar between one disease to another.  Therefore, the deep learning methods may misclassify the data. To deal with these, we propose the gamma transformation with a deep convolutional autoencoder to extract good features from the original image data. We use the output of the gamma transformation with a deep convolutional autoencoder as inputs to a classifier for the automatic detection of crop diseases. Our experiments show that the average accuracies of our method improve the performance of crop disease detection compared to only using raw data as inputs.
Robust remaining useful life prediction of lithium-ion battery with convolutional denoising autoencoder Yuliani, Asri Rizki; Pardede, Hilman Ferdinandus; Ramdan, Ade; Zilvan, Vicky; Yuwana, Raden Sandra; Amri, M Faizal; Kusumo, R. Budiarianto Suryo; Pramanik, Subrata
Journal of Mechatronics, Electrical Power, and Vehicular Technology Vol 15, No 1 (2024)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55981/j.mev.2024.905

Abstract

Using lithium-ion (Li-ion) batteries exceeding their useful lifetime may be dangerous for users, and hence, developing an accurate prediction system for batteries that remain useful for life is necessary. Many deep learning models, such as gated recurrent units and long short-term memory (LSTM), have been proposed for that purpose and have shown good results. However, their performance when dealing with noisy data degrades significantly. This may hamper their implementations for the real world since battery data are prone to noise. In this paper, we develop a robust prediction model in a noisy environment for predicting the remaining useful life (RUL) of Li-ion batteries. We propose a denoising autoencoder (DAE) utilized to remove noise from the data. The DAE is built with convolutional layers instead of traditional feed-forward networks here. We combine DAE with LSTM as the predictor. The proposed framework is evaluated using artificially corrupted battery data provided by National Aeronautics and Space Administration (NASA). The results reveal that our proposed method improves robustness when data contain various types of noise. A comparative study using the traditional approach has also been conducted. Our evaluation shows that convolutional layers are more effective than the traditional approach and that the original composition of the DAE was built using traditional feed-forward networks. DAE with convolutional layers has the best average performance with MSE of 0.61 and is the most consistent model.
Peningkatan Performa Pengelompokan Siswa Berdasarkan Aktivitas Belajar pada Media Pembelajaran Digital Menggunakan Metode Adaptive Moving Self-Organizing Maps Prasetyo, Onky; Supianto, Ahmad Afif; Anam, Syaiful; Pardede, Hilman Ferdinandus; Zilvan, Vicky; Kusumo, R. Budiarianto Suryo
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 9 No 1: Februari 2022
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2022915579

Abstract

Digitalisasi proses pembelajaran memungkinkan untuk dihasilkannya rekaman terhadap setiap aktivitas siswa selama belajar. Rekaman yang dihasilkan tersebut dapat digunakan untuk mengelompokkan siswa berdasarkan pola dari proses belajar yang dilakukan. Hasil pengelompokkan yang peroleh dapat digunakan untuk melakukan penyesuaian komponen pembelajaran ataupun metode pembelajaran bagi siswa. Salah satu metode pengelompokan yang sering digunakan adalah Self-Organizing Maps (SOM), SOM merupakan metode jaringan syaraf tiruan dengan tujuan untuk mempertahankan topologi data ketika data input multidimensi diubah menjadi data output dengan dimensi yang lebih rendah. Neuron SOM pada dimensi input diperbaharui sepanjang proses pelatihan, sedangkan neuron pada dimensi output tidak mendapatkan pembaruan sama sekali, hal ini menyebabkan struktur neuron yang digunakan pada tahapan inisialisasi akan tetap sama hingga akhir proses pengelompokan. Pada penelitian ini menggunakan metode Adaptive Moving Self-Organizing Maps (AMSOM) yang menggunakan struktur neuron lebih fleksibel, dengan dimungkinkannya terjadi perpindahan, penambahan dan penghapusan dari neuron menggunakan data 12 assignments dari media pembelajaran MONSAKUN. Hasil penelitian menunjukkan terdapat perbedaan yang signifikan secara statistik antara nilai quantization error dan nilai topographic error dari algoritme AMSOM dengan algoritme SOM. Metode AMSOM menghasilkan rata-rata nilai quantization error 27 kali lebih kecil dan rata-rata nilai topographic error 54 kali lebih kecil dibandingkan dengan metode SOM.AbstractThe digitization of the learning process makes it possible to produce recordings of each student's activity during learning. The resulting record can be used to group students based on the pattern of the learning process. The grouping results can be used to make adjustments to the learning components or learning methods for students. One of the most frequently used clustering methods is Self-Organizing Maps (SOM), SOM is a neural network method to maintain data topology when multidimensional input data is converted into output data with lower dimensions. The SOM neurons in the input dimension are updated throughout the training process, while the neurons in the output dimension do not get updated at all, this causes the neuron structure used in the initialization stage to remain the same until the end of the grouping process. In this study, the Adaptive Moving Self-Organizing Maps (AMSOM) method uses a more flexible neuron structure, allowing for the transfer, addition and deletion of neurons using 12 assignments of data from MONSAKUN learning media. The results showed that there was a statistically significant difference between the quantization error and the topographic error of the AMSOM algorithm and the SOM algorithm. The AMSOM method produces an average quantization error 27 times smaller and an average topographic error 54 times smaller than the SOM method.
Co-Authors Ade Ramdan Ahmad Afif Supianto Amri, M Faizal Andria Arisal, Andria Fani Fauziah, Fani Furqon Hensan Muttaqien Heryana, Ana Kadar, Jimmy Abdel Krisnandi, Dikdik Kusumo, R. Budiarianto Suryo Pardede, Hilman F. Pardede, Hilman Ferdinandus Pramanik, Subrata Prasetyo, Onky Suryawati, Endang Suryo Kusumo, Raden Budiarianto Syaiful Anam Vitria Puspitasari Rahadi Yuawana, Raden Sandra Yuliani, Asri Rizki Yuwana, R. Sandra Yuwana, Raden Sandra