Garuda - Garba Rujukan Digital

Enhancing Multi-Layer Perceptron Performance with K-Means Clustering Doughlas Pardede; Aulia Ichsan; Sugeng Riyadi
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 1 (2024): Article Research Volume 6 Issue 1, January 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i1.3600

Machine learning plays a crucial role in identifying patterns within data, with classification being a prominent application. This study investigates the use of Multilayer Perceptron (MLP) classification models and explores preprocessing techniques, particularly K-Means clustering, to enhance model performance. Overfitting, a common challenge in MLP models, is addressed through the application of K-Means clustering to streamline data preparation and improve classification accuracy. The study begins with an overview of overfitting in MLP models, highlighting the significance of mitigating this issue. Various techniques for addressing overfitting are reviewed, including regularization, dropout, early stopping, data augmentation, and ensemble methods. Additionally, the complementary role of K-Means clustering in enhancing model performance is emphasized. Preprocessing using K-Means clustering aims to reduce data complexity and prevent overfitting in MLP models. Three datasets - Iris, Wine, and Breast Cancer Wisconsin - are employed to evaluate the performance of K-Means as a preprocessing technique. Results from cross-validation demonstrate significant improvements in accuracy, precision, recall, and F1 scores when employing K-Means clustering compared to models without preprocessing. The findings highlight the efficacy of K-Means clustering in enhancing the discriminative power of MLP classification models by organizing data into clusters based on similarity. These results have practical implications, underlining the importance of appropriate preprocessing techniques in improving classification performance. Future research could explore additional preprocessing methods and their impact on classification accuracy across diverse datasets, advancing the field of machine learning and its applications

Analysis of Logistic Regression Regularization in Wild Elephant Classification with VGG-16 Feature Extraction Aulia Ichsan; Sugeng Riyadi; Doughlas Pardede
Journal of Computer Networks, Architecture and High Performance Computing Vol. 6 No. 2 (2024): Articles Research Volume 6 Issue 2, April 2024
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/cnahpc.v6i2.3789

The research article explores the intersection of image-based wildlife classification and logistic regression regularization, focusing on the classification of wild elephant species. It begins by highlighting the significance of ecological research in biodiversity monitoring and conservation and introduces Convolutional Neural Networks (CNNs) as potent tools for feature extraction from images. The VGG-16 model is particularly emphasized for its ability to capture hierarchical representations of visual features crucial for classification tasks. The integration of VGG-16 feature extraction with logistic regression regularization is proposed as a compelling approach, offering a balance between sophisticated feature representation and efficient classification algorithms. The literature review delves into image-based wildlife classification, emphasizing the role of CNNs, especially VGG-16, in extracting discriminative features. It discusses the fusion of VGG-16 features with logistic regression and the challenges in this field, such as dataset annotation and environmental variability. The method section outlines the dataset acquisition, feature extraction using the VGG-16 architecture, and model configuration using logistic regression with lasso and ridge regularization. The process of finding the optimal regularization parameter (lambda) and model evaluation through cross-validation is detailed. Results showcase the optimal lambda values for lasso and ridge regularization and compare the performance of logistic lasso and logistic ridge models. Misclassification analysis reveals factors influencing classification accuracy, including feature variability and contextual complexity. The discussion reflects on the implications of the findings, emphasizing the importance of lambda selection and addressing challenges in wildlife classification. It suggests avenues for further research, such as advanced modeling techniques and feature engineering approaches. In conclusion, the study contributes to advancing wildlife classification efforts by leveraging state-of-the-art techniques and sheds light on opportunities to enhance classification accuracy in wildlife conservation.

RANCANG BANGUN WEBSITE MENGGUNAKAN CONTENT MANAGEMENT SYSTEM (CMS)/WORDPRESS UNTUK UMKM Aulia Ichsan, S.T., M.Kom.; Said Hambali Takhir; Doughlas Pardede; Sugeng Riyadi; Mhd Harry Azhari As’ad
Pengabdian Deli Sumatera Vol 4 No 1 (2025): Artikel Pengabdian Juli 2025
Publisher : LLPM Universitas Deli Sumatera

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

Pelaku usaha mikro, kecil, dan menengah (UMKM) di Indonesia masih banyak yang belum memanfaatkan teknologi digital, khususnya website, sebagai sarana pemasaran dan pengembangan bisnis. Permasalahan utama yang dihadapi adalah keterbatasan pengetahuan teknis serta anggapan bahwa pembuatan website memerlukan keahlian pemrograman yang tinggi. Kegiatan pengabdian kepada masyarakat ini bertujuan memberikan pelatihan praktis kepada pelaku UMKM dalam membangun website secara mandiri menggunakan Content Management System (CMS) WordPress. Kegiatan dilaksanakan pada Sabtu, 27 September 2025, pukul 09.00 WIB di Aula Lantai I Gedung Universitas Deli Sumatera, dengan melibatkan lima dosen sebagai mentor/coach. Metode yang digunakan meliputi ceramah interaktif, demonstrasi langsung, dan praktik mandiri peserta. Hasil kegiatan menunjukkan peningkatan pemahaman dan kemampuan peserta dalam membuat serta mengelola website menggunakan WordPress. Peserta mampu menginstalasi WordPress, memilih tema, menambahkan konten, serta mengelola halaman bisnis secara mandiri. Kegiatan ini diharapkan mendorong digitalisasi UMKM sehingga meningkatkan jangkauan pasar dan daya saing usaha.

Development and Evaluation of Digital Image-Based Tomato Leaf Disease Classification Model Using Transfer Learning Muhammad Rasyid; Sugeng Riyadi; Irwan Daniel
InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Vol 10, No 1 (2025): InfoTekJar September
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/infotekjar.v10i1.11915

Leaf diseases in tomato plants (Solanum lycopersicum), including Early Blight, Late Blight, and Leaf Mold, can cause substantial reductions in crop yield if not detected at an early stage. Conventional manual detection methods are constrained by limitations in speed, consistency, and accuracy, particularly under field conditions. This study proposes a tomato leaf disease classification framework leveraging a transfer learning approach, in which the Inception V3 architecture functions as a feature extractor and the Random Forest algorithm serves as the classifier. The dataset employed comprises four categories of tomato leaf images—Early Blight, Late Blight, Leaf Mold, and Healthy—which were stratified into training (80%) and testing (20%) subsets. All images were resized to 299×299 pixels, normalized, and subjected to optional data augmentation. Feature representations were extracted from the Global Average Pooling layer of Inception V3 pretrained on the ImageNet dataset and subsequently input into a Random Forest classifier with hyperparameters optimized via grid search. Experimental evaluation demonstrated that the proposed model achieved an accuracy of 94.3%, surpassing the performance of a conventional CNN (89.2%) and a Random Forest classifier without transfer learning (76.5%). The confusion matrix analysis revealed the highest classification performance for the Healthy and Late Blight categories, whereas the Leaf Mold category exhibited a higher misclassification rate due to its visual symptom similarity to Early Blight. The findings of this research indicate that a hybrid methodology combining deep learning-based feature extraction and classical machine learning algorithms is highly effective for agricultural image classification in scenarios with limited datasets. Furthermore, the proposed approach holds significant potential for integration into web- or mobile-based decision support systems, enabling rapid and accurate plant disease detection in practical agricultural settings.

Evaluasi Model Machine Learning Pada Deteksi Kematangan Buah Tomat Berdasarkan Warna dia adillia; Sugeng Riyadi; Doughlas Pardede
Jurnal Nasional Teknologi Komputer Vol 6 No 3 (2026): Juli 2026
Publisher : CV. Hawari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61306/jnastek.v6i3.496

Penentuan tingkat kematangan buah tomat sering kali dilakukan secara visual, sehingga cenderung subjektif dan menghasilkan evaluasi yang kurang stabil. Penelitian ini bertujuan untuk menilai dan membandingkan kinerja algoritma K-Nearest Neighbors (KNN), Decision Tree, dan Random Forest dalam mengklasifikasikan tingkat kematangan buah tomat berdasarkan fitur warna RGB guna mendapatkan model dengan performa terbaik. Kumpulan data yang digunakan mencakup 300 gambar buah tomat yang dibagi menjadi tiga kategori, yaitu mentah, setengah matang, dan matang. Seluruh gambar melewati tahap Pre-pocessing yang mencakup penghapusan latar belakang, pengubahan ukuran dan ekstraksi fitur dengan menggunakan metode Mean RGB Color Feature Extraction. Dataset selanjutnya dipisahkan menjadi 80% data pelatihan dan 20% data pengujian dengan menggunakan Random Sampling yang diulang sebanyak 10 kali melalui Stratified Sampling. Evaluasi model dilakukan menggunakan Area Under Curve (AUC), Accuracy, F1-Score, Precision, Recall, Confusion Matrix, dan ROC Analysis. Hasil penelitian menunjukkan bahwa KNN memperoleh nilai AUC tertinggi sebesar 100%, sedangkan Random Forest memperoleh nilai Accuracy, F1-Score, Precision, dan Recall tertinggi, yaitu masing-masing sebesar 96,7%. Hasil Confusion Matrix menunjukkan bahwa Random Forest memiliki performa yang lebih seimbang pada ketiga kelas, sementara kesalahan klasifikasi terutama terjadi pada kelas setengah matang yang memiliki karakteristik warna yang berdekatan dengan kelas lainnya. Berdasarkan keseluruhan metrik evaluasi, Confusion Matrix, dan ROC Analysis, Random Forest ditetapkan sebagai model terbaik. Hasil penelitian ini menunjukkan bahwa fitur warna RGB dan algoritma Random Forest berpotensi digunakan untuk mengidentifikasi tingkat kematangan buah tomat secara lebih objektif, konsisten, dan efisien serta dapat dikembangkan untuk mendukung sistem sortasi berbasis citra digital.

Pemanfaatan Metode SVM dalam klasifikasi kualitas Jamur Tiram berdasaran Citra Digital Daniel Zalukhu; Aulia Ichsan; Sugeng Riyadi
Jurnal Nasional Teknologi Komputer Vol 6 No 3 (2026): Juli 2026
Publisher : CV. Hawari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61306/jnastek.v6i3.498

Jamur tiram merupakan salah satu komoditas hortikultura yang memiliki nilai ekonomi tinggi dan banyak dikonsumsi oleh masyarakat. Penentuan kualitas jamur tiram umumnya masih dilakukan secara manual melalui pengamatan visual, sehingga rentan terhadap subjektivitas dan ketidakkonsistenan hasil. Penelitian ini bertujuan untuk menerapkan metode Support Vector Machine (SVM) dalam mengklasifikasikan kualitas jamur tiram berdasarkan citra digital. Dataset penelitian berupa citra jamur tiram yang dikelompokkan ke dalam dua kelas, yaitu jamur berkualitas baik dan jamur berkualitas buruk. Proses penelitian dilakukan menggunakan aplikasi Orange Data Mining, dimulai dari impor citra menggunakan widget Import Images, ekstraksi fitur menggunakan Image Embedding berbasis Convolutional Neural Network (CNN) pralatih, kemudian dilanjutkan dengan proses klasifikasi menggunakan algoritma Support Vector Machine (SVM). Evaluasi model dilakukan menggunakan metode 10-fold Cross Validation melalui widget Test & Score, dengan parameter pengujian meliputi Accuracy, Precision, Recall, dan F1-Score, serta analisis hasil klasifikasi menggunakan Confusion Matrix. Hasil penelitian menunjukkan bahwa metode SVM mampu mengklasifikasikan kualitas jamur tiram berdasarkan fitur citra digital dengan tingkat kinerja yang baik. Pemanfaatan Image Embedding menghasilkan representasi fitur yang efektif sehingga meningkatkan kemampuan SVM dalam membedakan kualitas jamur tiram. Kata kunci: Support Vector Machine, Klasifikasi Citra, Jamur Tiram, Orange Data Mining, Image Embedding.

Klasifikasi Gambar Hewan Peliharaan Menggunakan CNN Berbasis Deep Learning Leon Anugerah Vebrian Batee; Sugeng Riyadi; Irwan Daniel
Jurnal Nasional Teknologi Komputer Vol 6 No 3 (2026): Juli 2026
Publisher : CV. Hawari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61306/jnastek.v6i3.499

Perkembangan teknologi kecerdasan buatan dalam bidang pengolahan citra digital telah mendorong pemanfaatan metode deep learning untuk melakukan klasifikasi gambar secara otomatis. Klasifikasi citra hewan peliharaan menjadi salah satu penerapan penting dalam computer vision karena dapat membantu proses identifikasi objek secara cepat dan akurat. Penelitian ini bertujuan untuk membangun model klasifikasi gambar hewan peliharaan menggunakan Convolutional Neural Network (CNN) dengan arsitektur InceptionV3 melalui Orange Data Mining. Dataset yang digunakan terdiri dari 2.283 gambar kucing dan anjing dalam format JPG. Tahapan penelitian meliputi pengumpulan dataset, preprocessing citra, ekstraksi fitur menggunakan Image Embedding berbasis InceptionV3, pembagian data menjadi data pelatihan dan data pengujian, proses pelatihan model, serta evaluasi performa menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil pengujian menunjukkan bahwa model CNN dengan arsitektur InceptionV3 memperoleh nilai accuracy sebesar 99,0%, precision sebesar 99,0%, recall sebesar 99,0%, dan F1-score sebesar 99,0%. Berdasarkan hasil tersebut dapat disimpulkan bahwa model CNN dengan arsitektur InceptionV3 mampu memberikan tingkat akurasi yang sangat tinggi dalam klasifikasi gambar hewan peliharaan. Penelitian ini menunjukkan bahwa pemanfaatan Orange Data Mining dengan fitur Image Embedding berbasis InceptionV3 efektif digunakan dalam proses klasifikasi citra digital dan memiliki potensi untuk dikembangkan lebih lanjut pada berbagai aplikasi computer vision berbasis kecerdasan buatan. Kata Kunci: Convolutional Neural Network (CNN), InceptionV3, Deep Learning, Klasifikasi Citra, Orange Data Mining.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search