Article Per Year (5 Year)
p-Index From 2021 - 2026
1.944
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Jurnal Buana Informatika TELKOMNIKA (Telecommunication Computing Electronics and Control) Bulletin of Electrical Engineering and Informatics Bulletin of Electrical Engineering and Informatics Jurnal Teknologi Informasi dan Ilmu Komputer JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Bulletin of Electrical Engineering and Informatics Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Syntax Literate: Jurnal Ilmiah Indonesia MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Jurnal Rekayasa elektrika Jurnal Pengabdian Rekayasa dan Wirausaha
Fitri Arnia
Syiah Kuala University
Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Law, Crime, Criminology & Criminal Justice Social Sciences Other

Published : 30 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 30 Documents
Search

 1   2   3 
Simulasi Pelacakan Titik Daya Maksimum Modul Surya dengan Metode Grey Wolf Optimization Rizki Faulianur; Ira Devi Sara; Fitri Arnia
Jurnal Rekayasa Elektrika Vol 14, No 1 (2018)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v14i1.8973

Abstract

The photovoltaic module has a nonlinear current and voltage characteristic curve where there is a maximum power point to be tracked to avoid wasted energy. Some methods for tracking the maximum power points have been developed such as perturb and observe (P O), Incremental Conductance (IC), and Hill Climbing (HC). However, those methods were not so accurate to find the maximum power point and they were also slow to respond the changes in solar radiation and temperature. To overcome the shortcomings of the method, a new optimization approach was developed. This method is called Gray Wolf Optimization (GWO). It work based on the wolf behavior in capturing the prey. In this study, it will be determined to what extent the GWO method can track the maximum working point of solar modules that undergo changes in radiation and working temperature quickly and accurately. This research was conducted by simulation using Matlab/Simulink by comparing the extract of power GWO method with its power characteristics. The results obtained by the GWO method trace maximum power with an average accuracy rate of 99.14 % with time less than 0.1 second. From this data, it can be concluded that the GWO method successfully responds well and accurately to changes in radiation and temperature.
Cross-Spectral Cross-Distance Face Recognition via CNN with Image Augmentation Techniques Rahmatika, Nisa Adilla; Arnia, Fitri; Oktiana, Maulisa
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 5 (2024): October 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i5.5929

Abstract

Facial recognition is a critical biometric identification method in modern security systems, yet it faces significant challenges under varying lighting conditions, particularly when dealing with near-infrared (NIR) images, which exhibit reduced illumination compared to visible light (VIS) images. This study aims to evaluate the performance of Convolutional Neural Networks (CNNs) in addressing the Cross-Spectral Cross-Distance (CSCD) challenge, which involves face identification across different spectra (NIR and VIS) and varying distances. Three CNN models—VGG16, ResNet50, and EfficientNetB0—were assessed using a dataset comprising 800 facial images from 100 individuals, captured at four different distances (1m, 60m, 100m, and 150m) and across two wavelengths (NIR and VIS). The Multi-task Cascaded Convolutional Networks (MTCNN) algorithm was employed for face detection, followed by image preprocessing steps including resizing to 224x224 pixels, normalization, and homomorphic filtering. Two distinct data augmentation strategies were applied: one utilizing 10 different augmentation techniques and the other with 4 techniques, trained with a batch size of 32 over 100 epochs. Among the tested models, VGG16 demonstrated superior performance, achieving 100% accuracy in both training and validation phases, with a training loss of 0.55 and a validation loss of 0.612. These findings underscore the robustness of VGG16 in effectively adapting to the CSCD setting and managing variations in both lighting and distance.
CNN Performance Improvement for Classifying Stunted Facial Images Using Early Stopping Approach Yunidar, Yunidar; Yusni, Y; Nasaruddin, N; Arnia, Fitri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 1 (2025): February 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i1.6068

Abstract

Stunting, a condition characterised by short stature, is a growth disorder caused by chronic malnutrition, which often begins in the womb. Children affected by stunting usually show different physical and cognitive characteristics compared to their peers. Research shows that these physical differences can also be observed in facial features. Because faces provide important information and are commonly studied in digital image processing, in this study, we will compare the facial image classification performance of stunted children versus normal children using various Convolutional Neural Network (CNN) architectures. The evaluated architectures include MobileNetV2, InceptionV3, VGG19, ResNet18, EfficientNetB0, and AlexNet. To improve the learning process, augmentation techniques with Haar cascade and Gaussian filters were applied so that the data set increased from 1,000 to 6,000 images. After adding the dataset, training is carried out with an early stop approach to minimise overfitting. The main aim of this research is to identify the CNN model that is most effective in differentiating facial images of stunted children from normal children. The results show that the EfficientNetB0 architecture outperforms other models, achieving 100% accuracy. Early stopping has been shown to improve training efficiency and help prevent overfitting.
Pemanfaatan Alat Ukur Status Gizi Otomatis Berbasis Mikrokontroler di Posyandu Meulati Gampong Blang Krueng Kecamatan Baitussalam, Aceh Besar Yunidar, Yunidar; Arnia, Fitri; Melinda, Melinda; Away, Yuwaldi; Fathurrahman, Fathurrahman
Jurnal Pengabdian Rekayasa dan Wirausaha Vol 1, No 1 (2024)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jprw.v1i1.36528

Abstract

Posyandu merupakan salah satu program pemerintah Indonesia sebagai fasilitas layanan kesehatan masyarakat yang dikelola oleh masyarakat. Posyandu Balita dilaksanakan secara rutin untuk memantau perkembangan pertumbuhan pada balita dengan mengukur tinggi badan, berat badan dan lingkar kepala. Selama ini alat ukur yang digunakan oleh petugas kesehatan di posyandu merupakan alat ukur yang konvensional, dan penentuan status gizi anak masih dilakukan secara manual oleh petugas posyandu yang telah mahir mengkonversi nilai ukur yang diperoleh kedalam rumus skor-z. Hal ini tentu memakan waktu dan kurang efektif sehingga dari hasil penelitian mahasiswa prodi Teknik Elektro telah berhasil merancang alat ukur status gizi otomatis berbasis mikrokontroler dan telah diuji nilai presisi dan keakuratannya. Melalui program pengabdian kepada masyarakat kami akan mensosialisasikan alat ukur otomatis ini pada posyandu Meulati Gampong Blang Krueng, Kecamatan Baitussalam Kabupaten Aceh Besar. Tujuan dari kegiatan ini untuk meningkatkan mutu pelayanan posyandu sehingga dapat berjalan lebih efektif den efisien. Alat ukur ini terdiri dari modul status gizi berdasarkan nilai skor-z dilengakapi dengan LCD sebagai tampilan keluaran dan sensor ultrasonik yang berfungsi sebagai pengukur tinggi badan dan sensor load cell untuk mengukur berat badan. Hasil yang diperoleh dari kegiatan melalui survey kepuasan yang dibagikan ternyata semua orang tua dan wali balita setuju kegiatan pengabdian yang telah dilakukan sangat bermanfaat terutama bagi Masyarakat Blang Krueng.
Image Data Acquisition and Classification of Vannamei Shrimp Cultivation Results Based on Deep Learning Melinda, Melinda; Muthiah, Zharifah; Arnia, Fitri; Elizar, Elizar; Irhmasyah, Muhammad
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 3 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i3.3850

Abstract

This research aimed to employ deep learning techniques to address the classification of Litopenaeus vannamei cultivation results in land ponds and tarpaulin ponds. Despite their similar appearance, distinguishable differences exist in various aspects such as color, shape, size, and market price between the two cultivation methods, often leading to consumer confusion and potential exploitation by irresponsible sellers. To mitigate this challenge, the research proposed a classification method utilizing two Convolutional Neural Network (CNN) architectures: Visual Geometry Group-16 (VGG-16) and Residual Network-50 (ResNet-50), renowned for their success in various image recognition applications. The dataset comprised 2,080 images per class of vannamei shrimp from both types of ponds. Augmentation techniques enhanced the dataset’s diversity and sample size, reinforcing the model’s ability to discern shrimp morphology variations. Experiments were conducted with learning rates of 0.001 and 0.0001 on the Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (ADAM) optimizers to evaluate their effectiveness in model training. The VGG-16 and ResNet-50 models were trained with a learning rate parameter of 0.0001, leveraging the flexibility and reasonable control provided by the SGD optimizer. Lower learning rate values were chosen to prevent overfitting and enhance training stability. The model evaluation demonstrated promising results, with both architectures achieving 100% accuracy in classifying vannamei shrimp from soil ponds and tarpaulin ponds. Furthermore, experimental findings highlight the superiority of using SGD with a learning rate of 0.0001 over 0.001 on both architectures, underscoring the significant impact of optimizer and learning rate selection on model training effectiveness in image classification tasks.
Klasifikasi Otomatis Motif Tekstil Menggunakan Support Vector Machine Multi Kelas Ramadhani, Ramadhani; Arnia, Fitri; Muharar, Rusdha
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 1: Februari 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

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

Abstract

Tekstur merupakan pola atau motif tertentu yang tersusun secara berulang-ulang pada citra. Tekstur mudah dikenali/dikelompokkan oleh manusia, tetapi sulit bagi mesin. Klasifikasi tekstur secara otomatis berguna dan dibutuhkan pada banyak bidang seperti industri tekstil, pendaratan pesawat otomatis, fotografi dan seni. Pada industri tekstil, klasifikasi tekstur otomatis dapat meningkatkan efisiensi proses desain motif. Motif tekstil terdiri dari banyak kelompok, sehingga diperlukan metode klasifikasi multi kelas untuk mengelompokkan motif-motif tersebut. Artikel ini memaparkan kinerja tiga metode Support Vector Machine (SVM) multi kelas: One Against One (OAO), Directed Acyclic Graph (DAG) dan One Against All (OAA) pada klasifikasi motif dari citra tekstil, dimana Wavelet Gabor digunakan sebagai pengekstraksi fitur. Kinerja SVM diukur berdasarkan parameter akurasi dan fitur Gabor diekstraksi dengan skala dan orientasi yang berbeda. Tujuan penelitian ini adalah menentukan kinerja SVM dan pengaruh jumlah skala dan orientasi Gabor yang digunakan pada klasifikasi motif tekstil. Pada simulasi digunakan 120 citra tekstil yang terbagi menjadi tiga kategori motif: bunga, kotak dan polkadot. Akurasi pengelompokan SVM mencapai kisaran 90%-100%, bahkan untuk citra yang terpotong. Pengujian dengan k-fold validation menunjukkan bahwa SVM DAG lebih baik daripada SVM OAO dan SVM OAA, dengan akurasi mencapai 78%. AbstractTexture is a repetition of a specific pattern concatenation in an image. The Texture can be defined as a repetition of pattern in an image.  The texture is easy for the human to classify, but it is not easy for a machine. Automatic texture classification is useful and required in many fields such as textile industry, automatic aircraft landing, photography and art. In the textile industry, automatic texture classification can enhance the efficiency of motif designing process. The textile motif is various and should be grouped into more than two classes; therefore a multiclass classification is required. This article discusses the performance of multiclass Support Vector Machine (SVM): One Against One (OAO), Directed Acyclic Graph (DAG) and One Against All (OAA) in classifying textile motifs, in which the Gabor Filter was used to extract the texture features. The SVM performance was measured in terms of accuracy, while the Gabor features were extracted in a different combination of scales and orientations. The purpose of the work is to measure the SVM performance and determine the effect of using various Gabor scales and orientations in textile motifs classification. We used 120 textile images with three motifs: flower, boxes and polka dot. The SVM accuracy of 90%-100% was achieved; even for cropped textile images. Using the k-fold validation, the accuracy of SVM DAG was 78%, higher than those of SVM OAO and SVM OAA
Kombinasi Metode Nilai Ambang Lokal dan Global untuk Restorasi Dokumen Jawi Kuno Saddami, Khairun; Arnia, Fitri; Away, Yuwaldi; Munadi, Khairul
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 7 No 1: Februari 2020
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2020701741

Abstract

Dokumen Jawi kuno merupakan warisan budaya yang berisi informasi penting tentang peradaban masa lalu yang dapat dijadikan pedoman untuk masa sekarang ini. Dokumen Jawi kuno telah mengalami penurunan kualitas yang disebabkan oleh beberapa faktor seperti kualitas kertas atau karena proses penyimpanan. Penurunan kualitas ini menyebabkan informasi yang terdapat pada dokumen tersebut menghilang dan sulit untuk diakses. Artikel ini mengusulkan metode binerisasi untuk membangkitkan kembali informasi yang terdapat pada dokumen Jawi kuno. Metode usulan merupakan kombinasi antara metode binerisasi berbasis nilai ambang lokal dan global. Metode usulan diuji terhadap dokumen Jawi kuno dan dokumen uji standar yang dikenal dengan nama Handwritten Document Image Binarization Contest (HDIBCO) 2016. Citra hasil binerisasi dievaluasi menggunakan metode: F-measure, pseudo F-measure, peak signal-to-noise ratio, distance reciprocal distortion, dan misclasification penalty metric. Secara rata-rata, nilai evaluasi F-measure dari metode usulan mencapai 88,18 dan 89,04 masing-masing untuk dataset Jawi dan HDIBCO-2016. Hasil ini lebih baik dari metode pembanding yang menunjukkan bahwa metode usulan berhasil meningkatkan kinerja metode binerisasi untuk dataset Jawi dan HDIBCO-2016. AbstractAncient Jawi document is a cultural heritage, which contains knowledge of past civilization for developing a better future. Ancient Jawi document suffers from severe degradation due to some factors such as paper quality or poor retention process. The degradation reduces information on the document and thus the information is difficult to access. This paper proposed a binarization method for restoring the information from degraded ancient Jawi document. The proposed method combined a local and global thresholding method for extracting the text from the background. The experiment was conducted on ancient Jawi document and Handwritten Document Image Binarization Contest (HDIBCO) 2016 datasets. The result was evaluated using F-measure, pseudo F-measure, peak signal-to-noise ratio, distance reciprocal distortion, dan misclassification penalty metric. The average result showed that the proposed method achieved 88.18 and 89.04 of F-measure, for Jawi and HDIBCO-2016, respectively. The proposed method resulted in better performance compared with several benchmarking methods. It can be concluded that the proposed method succeeded to enhance binarization performance.
Improved Histogram of Oriented Gradient (HOG) Feature Extraction for Facial Expressions Classification Ramiady, Luthfiar; Arnia, Fitri; Oktiana, Maulisa; Novandri, Andri
Jurnal Rekayasa Elektrika Vol 20, No 3 (2024)
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17529/jre.v20i3.34044

Abstract

Facial expression classification system is one of the implementations of machine learning (ML) that takes facial expression datasets, undergoes training, and then utilizes the trained results to recognize facial expressions in new facial images. The recognized facial expressions include anger, contempt, disgust, fear, happy, sadness, and surprise expressions. The method employed for facial feature extraction utilizes histogram-oriented gradient (HOG). This study proposes an enhancement method for HOG feature extraction by reducing the feature dimension into multiple sub-features based on gradient orientation intervals, referred to as HOG channel (HOG-C). Classifier testing techniques are divided into two methods for comparisonsupport vector machines (SVM) with HOG features and SVM with HOG-C features. The testing results demonstrate that SVM with HOG achieves an accuracy of 99.9% with an average training time of 18.03 minutes, while SVM with HOG-C attains a 100% accuracy with an average training time of 18.09 minutes. The testing outcomes reveal that the implementation of SVM with HOG-C successfully enhances accuracy for facial expression classification.
Unjuk Kerja Pendeteksian Dhamir Raf’a Munfasil pada Citra Al-Qur’an dengan Penggabungan Algoritma Adaboost dan Tranformasi Slant Nargaza, Juanda; Away, Yuwaldi; Arnia, Fitri
Syntax Literate Jurnal Ilmiah Indonesia
Publisher : Syntax Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36418/syntax-literate.v9i4.15486

Abstract

Dalam penelitian ini pendeteksian Pola karakter Dhamir Raf’a Munfasil (DRM) pada citra Al-Qur’an menggunakan metode Transformasi Slant, Adaboosting dan gabungan Slant - Adaboosting yang kemudian di ukur unjuk kerja pendeteksian DRM pada setiap metode. Hasil penelitian menunjukkan bahwa sistem pendeteksian pola Dhamir Raf’a Munfasil pada citra Al-Qur’an menggunakan Transformasi Slant memiliki prescision sebesar 50% dan Recall 90%. Dengan menggunakan Algoritma Adaboosting memiliki prescision sebesar 71% dan Recall 92%. dengan menggunakan gabungan Algoritma tersebut Slant-Adaboost memiliki prescision sebesa 86% dan Recall 93%. Dari hasil perbandingan antara Adaboost dan Gabungan Slant-Adaboost, Slant-Adaboost memiliki tingkat akurasi lebih baik dari pada Adaboost sendiri.
Klasifikasi Kanker Payudara Menggunakan Citra Termal Berdasarkan Filter Gabor Putri, Listia Sukma; Arnia, Fitri; Muharar, Rusdha
Syntax Literate Jurnal Ilmiah Indonesia
Publisher : Syntax Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36418/syntax-literate.v9i4.15487

Abstract

Penelitian ini bertujuan untuk mengambil nilai fitur dari citra termal payudara melalui ekstraksi fitur Filter Gabor, dengan fokus pada mean, variance, kurtosis, skewness, dan entropi, serta untuk mengevaluasi kinerja tiga metode klasifikasi, yaitu K-Nearest Neighbor (KNN), Support Vector Machine (SVM), dan Artificial Neural Network (ANN). Kanker payudara merupakan masalah kesehatan yang serius, terutama bagi perempuan, karena potensial menyebabkan kematian. Dalam upaya mengurangi risiko kematian, penelitian dilakukan untuk mendeteksi kanker secara dini, termasuk menggunakan termografi. Metode ini memanfaatkan suhu dari objek untuk mendeteksi kanker, dimana pola suhu yang berbeda di area payudara yang terkena kanker dapat diamati karena peningkatan aliran darah. Penelitian menggunakan citra termal dari Database for Mastology Research (DMR) sebanyak 150 citra, dengan 108 citra sehat dan 42 citra sakit. Fitur tekstur diekstraksi menggunakan Filter Gabor dengan variasi skala dan sudut orientasi tertentu. Hasilnya diuji dengan beberapa metode klasifikasi, dimana ANN menunjukkan akurasi tertinggi yaitu 88.88%, diikuti oleh KNN dengan 86.66% dan SVM dengan 84.44%. Hasil ini menegaskan bahwa termografi bersama dengan ekstraksi fitur tekstur dan algoritma pembelajaran mesin dapat efektif dalam mendeteksi kanker payudara secara dini, menawarkan potensi diagnosis dini dan manajemen penyakit yang efektif.
Co-Authors Arsy Febrina Dewi Cut Mutia Cut Mutia Dwipayana, Mahendar Elizar Elizar, Elizar Fathurrahman Fathurrahman Fikri, Rizal Iqbal, TWK Muhammad Ira Devi Sara Irhmasyah, Muhammad Khairul Munadi Khairul Munadi Listia Sukma Putri Maghfirah, Hayatun Melinda Melinda Nargaza, Juanda Nasaruddin Nasaruddin Novandri, Andri Nuriza Pramita Nuriza Pramita Oktiana, Maulisa Oktiana, Maulisa Rahmatika, Nisa Adilla Raihan Islamadina Ramadhani Ramadhani Ramiady, Luthfiar Rizki Faulianur Rusdha Muharar Rusdha Muharar, Rusdha Saddami, Khairun Siti Aisyah Syahrul Wahyudi Yunidar Yusni, Y Yuwaldi Away Yuwaldi Away Zharifah Muthiah Zuhar Musliyana, Zuhar