Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal MIND (Multimedia Artificial Intelligent Networking Database) Journal
MUHAMMAD ICHWAN
Program Studi Informatika, Institut Teknologi Nasional Bandung
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Perbandingan Metode Deep Residual Network 50 dan Deep Residual Network 152 untuk Deteksi Penyakit Pneumonia pada Manusia RIFQI RIZQULLAH EKA PRASETYO; MUHAMMAD ICHWAN
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 6, No 2 (2021): MIND Journal
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v6i2.168-182

Abstract

AbstrakPneumonia merupakan salah satu masalah Kesehatan yang sering dijumpai dan mempunyai dampak yang signifikan di seluruh dunia. Insiden pneumonia dilaporkan meningkat sesuai dengan bertambahnya usia. Pneumonia merupakan diagnosis terbanyak ketiga. Dalam penelitian ini penulis mengidentifikasi citra paru-paru dalam bentuk citra x-ray dengan metode ResNet-50 dan ResNet-152 sebagai ekstrasi ciri dan klasifikasinya. Performa sistem diukur berdasarkan nilai akurasi, presisi, recall, dan f-measure. Eksperimen dilakukan pada dataset paru-paru dengan menggunakan dua metode tersebut dan didapatkan akurasi terbaik pada ResNet-152. Hasil menunjukkan nilai rata-rata terbaik accuracy 89,3%, precision 88,8%, recall 89,6%, dan f-measure 89%. Hasil tersebut dipengaruhi oleh jumlah dataset dari citra training, citra validation, dan citra uji.Kata kunci: Penumonia, Deep Residual Network, RESNET-50, RESNET-152AbstractPneumonia is one of the most common health problems and has a significant impact throughout the world. The incidence of pneumonia is reported to increase with age. Pneumonia is the third most common diagnosis. In this study, the authors identified lung images in the form of x-ray images using the ResNet-50 and ResNet-152 methods as feature extraction and classification. System performance is measured based on the values of accuracy, precision, recall, and f-measure. Experiments were carried out on lung datasets using these two methods and the best accuracy was obtained on ResNet-152. The results show the best average value for accuracy is 89.3%, precision is 88.8%, recall is 89.6%, and f-measure is 89%. These results are influenced by the number of datasets from training images, validation images, and test images.Keywords: Penumonia, Deep Residual Network, RESNET-50, RESNET-152
Implementasi Arsitektur InceptionResNet-v2 dan Squared Hinge Loss (Studi Kasus Klasifikasi Pose Yoga) MUHAMMAD ICHWAN; ANNISA OLGA ZERLINDA
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 7, No 2 (2022): MIND Journal
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v7i2.124-138

Abstract

ABSTRAKAplikasi computer vision dapat digunakan untuk mengurangi kecelakaan yang terjadi ketika melakukan yoga akibat postur tubuh saat melakukan yoga yang tidak tepat. Pada penelitian, dilakukan sebagai langkah awal dalam penentuan model klasifikasi yang digunakan pada aplikasi yang dapat melakukan koreksi postur tubuh saat yoga. Penelitian dilakukan dengan mengklasifikasikan 11 studi kasus pose yoga dengan mengimplementasikan arsitektur InceptionResnet-v2 dan Squared Hinge Loss. Pada hasil yang didapatkan, model dengan kinerja terbaik diperoleh pada learning rate 0.0001, epoch  200, scaling residual InceptionResnet blok A 0.15, blok B 0.1, dan blok C 0.2, serta blok InceptionResnet 5 iterasi, B 10 iterasi, dan C 5 iterasi dengan kinerja arsitektur berdasarkan hasil evaluasi performa model didapatkan 89.98% accuracy, 90.38% precision, 89.79% recall, 89.83% F1 score, and 99% specificity pada pengujian 888 data uji dengan 11 pose yoga berbeda. Rata-rata pengujian waktu klasifikasi 1.301s dan loss 0.9494.Kata kunci: CNN, InceptionResnet-v2, Klasifikasi Citra, Squared Hinge Loss, YogaABSTRACTComputer vision applications can be used to reduce accidents caused by improper posture while doing yoga. In this study, it was carried out as a first step in determining the classification model used in applications that can make corrections to a body posture while doing yoga. The research was conducted to classify 11 case studies of yoga poses by implementing the InceptionResnet-v2 architecture and Squared Hinge Loss. In the results, the model with the best performance was obtained at a learning rate of 0.0001, epoch 200, scaling residual InceptionResnet block A 0.15, block B 0.1, and block C 0.2, and 5 iteration of InceptionResnet block A, 10 iterations of block B, and 5 iterations of block C. The results of the model performance evaluation obtained 89.98% accuracy, 90.38% precision, 89.79% recall, 89.83% F1 score, and 99% specificity in the test of 888 test data with 11 different yoga poses and 1.301s average testing time of the classification model and loss 0.9494.Keywords: CNN, Image Classification, InceptionResnet-v2, Squared Hinge Loss, Yoga
Klasifikasi Citra Bibit Tanaman Menggunakan Convolutional Neural Network Dan Improved Feature Pyramid Network MUHAMMAD ICHWAN; RIZKIKA SITI SYIFA
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 8, No 1 (2023): MIND Journal
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v8i1.1-13

Abstract

AbstrakKlasifikasi bibit tanaman bertujuan untuk membantu mempermudah pengendalian jenis tanaman. Tugas klasifikasi tanaman menggunakan metode manual rentan terhadap kesalahan manusia. Pada penelitian ini, CNN dan Improved FPN diimplementasikan untuk meningkatkan akurasi pada saat melakukan tugas klasifikasi. Peningkatan FPN dilakukan untuk meningkatkan kualitas informasi yang didapatkan fitur, dengan menerapkan Channel Attention Module dan Augmented Bottom-up Pathway. Arsitektur ResNet50 digunakan sebagai backbone konvolusi FPN untuk meningkatkan kemampuan FPN mengekstraksi fitur. CNN kemudian diterapkan pada setiap peta fitur FPN akhir untuk mengklasifikasikan data. Hasil pengujian menunjukkan model memiliki kinerja lebih baik ketika FPN ditingkatkan dengan Channel Attention Module dan Augmented Bottom-up Pathway dengan rasio pengurangan Channel Attention diatur ke nilai 4 dengan akurasi pengujian yaitu 93,11% dan skor F1 yaitu 93%.Kata kunci: bibit tanaman, cnn, fpn, resnet50, channel attention module, augmented bottom-up pathway, klasifikasi citraAbstractPlant seedlings classification aims to help facilitate plant species control. The plant classification task using manual methods is prone to human error. In this study, CNN and Improved FPN were implemented to increase accuracy when performing the classification task. The FPN improvement was done to improve the quality of information obtained by the features, by implementing Channel Attention Module and Augmented Bottom-up Pathway. ResNet50 architecture was used as the convolutional backbone in FPN to enhance the feature extraction capabilities. CNN was then applied to each of FPN final feature maps to classify the data. The test results showed that the model performed better when the FPN was improved with the Channel Attention Module and Augmented Bottom-up Pathway where the Channel Attention reduction ratio was set to 4 with test accuracy of 93.11% and F1 score of 93%.Keywords: plant seedlings, cnn, fpn, resnet50, channel attention module, augmented bottom-up pathway, image classification 
Co-Authors ANNISA OLGA ZERLINDA RIFQI RIZQULLAH EKA PRASETYO RIZKIKA SITI SYIFA