Article Per Year (5 Year)
p-Index From 2020 - 2025
1.048
P-Index
This Author published in this journals
All Journal Jurnal Inotera MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Indonesian Journal of Science, Technology, and Humanities Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics
Zharifah Muthiah
Unknown Affiliation
Religion Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Health Professions Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mathematics Mechanical Engineering Social Sciences

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

Found 6 Documents
Search

 1 
Image Data Acquisition and Classification of Vannamei Shrimp Cultivation Results Based on Deep Learning Melinda Melinda; Zharifah Muthiah; Fitri Arnia; Elizar Elizar; Muhammad Irhmasyah
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 23 No 3 (2024)
Publisher : LPPM 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.
Hotspot Detection Pada Citra Termal Wajah Anak Autis Dan Normal Berbasis Otsu Thresholding Zharifah Muthiah; Yayang Hafifah; Melinda Melinda; Ramzi Adriman
Indonesian Journal of Science, Technology and Humanities Vol. 2 No. 1 (2024): IJSTECH - June 2024
Publisher : PT. INOVASI TEKNOLOGI KOMPUTER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60076/ijstech.v2i1.442

Abstract

Gangguan Spektrum Autisme (ASD) adalah kelainan neurologis yang memengaruhi keterampilan komunikasi penting untuk kehidupan sehari-hari dan sering kali menimbulkan kesulitan dalam situasi sosial. Saat ini, diagnosis ASD masih sangat bergantung pada metode manusia dan kekurangan tanda-tanda biologis yang pasti. Diagnosis dini ASD memiliki dampak positif yang signifikan, terutama pada anak-anak. Teknik deep learning, khususnya dalam analisis citra medis wajah, telah menjadi fokus penelitian baru dalam deteksi ASD. Penggunaan citra termal sebagai metode pasif untuk menganalisis sinyal fisiologis terkait dengan ASD telah diusulkan. Dalam penelitian sebelumnya, telah dikembangkan model deep learning untuk mengklasifikasi wajah anak autis menggunakan citra termal, dengan data mentah 17 wajah termal autis dan 17 wajah termal anak normal. Namun, penelitian tersebut tidak memberikan informasi mengenai perbedaan secara signifikan antara citra termal wajah anak autis dan normal, dan hanya menggunakan arsitektur CNN secara umum. Penelitian ini bertujuan untuk mengisi celah tersebut dengan menganalisis perbedaan data kelas anak autis dan normal menggunakan Otsu Thresholding Hotspot Detection. Hasil Hotspot Detection menggunakan metode Otsu Thresholding menunjukkan bahwa citra kelompok anak autis adalah sebesar 99.466059, sedangkan untuk kelompok anak normal adalah sebesar 88.850546, mengindikasikan perbedaan yang signifikan antara kedua kelompok. Dengan demikian, dataset citra termal anak autis menunjukkan nilai hotspot detection yang lebih tinggi dibandingkan dengan anak normal.
Analysis Based on Arduino Uno Producing a Baracuda Smoking Tool With a Smoke Concentration and Temperature Monitoring System Oktalia Triananda Lovita; Khairuman; Zharifah Muthiah; Rossiana Ginting
Jurnal Inotera Vol. 10 No. 1 (2025): January-June 2025
Publisher : LPPM Politeknik Aceh Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31572/inotera.Vol10.Iss1.2025.ID459

Abstract

A smoked barracuda fish product smoking device with closed circulation using a temperature monitoring system and smoke concentration based on Arduino Uno has been created. The design of the cold smoking device is divided into three parts, namely the combustion area, the smoke pipe, and the smoking chamber. Smoke drift of (25.53%-32.45)%. The average length of the fish was 16.7 cm and the average weight of the barracuda fish was 192.3 grams. 10 barracuda fish were put into the smoking room. The lowest water content value for smoked barracuda fish, namely 25.53%, occurred at a smoking time of 6 hours and the highest water content for smoked barracuda fish, namely 32.45%, occurred at a smoking time of 3 hours. The efficiency of the time needed to smoke mackerel on the water content was 6 hours compared to a smoking time of 3 hours. This means that the longer the smoking, the lower the water content value in smoked mackerel.
Image Data Acquisition and Classification of Vannamei Shrimp Cultivation Results Based on Deep Learning Melinda Melinda; Zharifah Muthiah; Fitri Arnia; Elizar Elizar; Muhammad Irhmasyah
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 3 (2024)
Publisher : LPPM 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.
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.
Thermal Image Classification of Autistic Children Using Res-Net Architecture Ahmadiar, Ahmadiar; Melinda, Melinda; Muthiah, Zharifah; Zainal, Zulfan; Mina Rizky, Muharratul
Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics Vol. 7 No. 1 (2025): February
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35882/365fkd59

Abstract

The thermal Image Classification Method has been widely used for significant applications in many fields, including thermal images of the face. This study presents a method for thermal facial classification in children with autism spectrum disorder (ASD). Children with ASD have a neurological disorder that affects communication skills essential in daily life and often causes difficulties in social situations. As we know, the diagnosis of ASD currently still relies on human methods and does not yet have definite biological markers. Early diagnosis of ASD has a significant positive impact, especially in children. Deep learning techniques, especially in facial medical image analysis, have become a new research focus in ASD detection. Initial screening using a Convolutional Neural Network (CNN) model with a transfer learning approach offers great potential for early diagnosis of ASD. The use of thermal imaging as a passive method to analyze ASD-related physiological signals has been proposed. In previous research, a deep learning model was developed to classify the faces of autistic children using thermal images. Therefore, this study aims to create a new Thermal Image Classification model for Autistic Children Using Res-Net Architecture. The architectures applied are ResNet-18, ResNet-34, and ResNet-50. As a comparison system, several of the same parameter values are used: epoch 100, batch size 2, SGD, Cross-entropy, learning rate 0.001, and momentum 0.9. The study test results show that the results of ResNet-18 are 97.22%, ResNet-34 99.22%, and ResNet-50 99.41%. Based on these results, ResNet-50 has the highest value.
Co-Authors Ahmadiar, Ahmadiar Elizar Elizar Elizar Elizar, Elizar Fitri Arnia Fitri Arnia Irhmasyah, Muhammad Khairuman Melinda Melinda Melinda Melinda Melinda Melinda Mina Rizky, Muharratul Muhammad Irhmasyah Oktalia Triananda Lovita Ramzi Adriman Rossiana Ginting Yayang Hafifah Zainal, Zulfan