Claim Missing Document
Check
Articles

Found 5 Documents
Search

Tomato Leaf Diseases Classification using Convolutional Neural Networks with Transfer Learning Resnet-50 Muslih; Krismawan, Andi Danang
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 9, No. 2, May 2024
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v9i2.1939

Abstract

This research delves into the critical domain of Tomato Leaf Disease classification using advanced machine learning techniques. Specifically, a comparative evaluation was conducted between a Base CNN model devoid of ResNet-50 integration and a Proposed Method harnessing the capabilities of ResNet-50. The results elucidated a notable enhancement in performance metrics when leveraging ResNet-50, with the Proposed Method consistently achieving exceptional accuracy scores of 99.96%, 99.98%, and 99.96% across data splits of 90:10, 80:20, and 70:30, respectively. Furthermore, the ResNet-50 integration significantly augmented key metrics, including recall, precision, and F1-Score, thereby accentuating its pivotal role in enhancing sensitivity and positive predictive value for tomato leaf disease classification. As for prospective research trajectories, this study highlights potential avenues for refinement, encompassing the exploration of ensemble techniques amalgamating diverse architectural frameworks, advanced data augmentation methodologies, and broader disease classification scopes. Collectively, this research underscores the transformative potential of ResNet-50 in agricultural diagnostics, advocating for continued exploration and innovation to fortify global food security and sustainable farming practices. Future research could explore ensemble techniques, advanced data augmentation, broader disease classification scopes, and interdisciplinary collaborations to develop comprehensive diagnostic tools for sustainable farming practices and global food security.
A text security evaluation based on advanced encryption standard algorithm Bima, Aristides; Irawan, Candra; Laksana, Deddy Award Widya; Krismawan, Andi Danang; Isinkaye, Folasade Olubusola
Journal of Soft Computing Exploration Vol. 4 No. 4 (2023): December 2023
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v4i4.274

Abstract

This research approach analysis and examines a number of advanced encryption standard (AES) performance factors, including as encryption and decryption speed, processing resource, consumption, and resilience, to cryptanalysis attacks. The study’s findings demonstrate that AES is successful in providing high-level data security, particularly when used in the CBC (Cipher Block Chaining) operating mode. Performance is dependent on the length of the key that is utilized. Increasing the level of security through the use of longer keys may result in an increase in the amount of time needed for encryption. The experimental results show that the highest results from the data are as follows the length of the encryption time is 0.00005317 seconds, the length of the decryption time is 0.00000882 seconds, the results of BER and CER are 0, the results of entropy are 7.44237, and the results of avalanche influence are 54.86%.
Eye disease classification using deep learning convolutional neural networks Rachmawanto, Eko Hari; Sari, Christy Atika; Krismawan, Andi Danang; Erawan, Lalang; Sari, Wellia Shinta; Laksana, Deddy Award Widya; Adi, Sumarni; Yaacob, Noorayisahbe Mohd
Journal of Soft Computing Exploration Vol. 5 No. 4 (2024): December 2024
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v5i4.493

Abstract

This study begins with the analysis of the growing challenge of accurately diagnosing eye diseases, which can lead to severe visual impairment if not identified early. To address this issue, we propose a solution using Deep Learning Convolutional Neural Networks (CNNs) enhanced by transfer learning techniques. The dataset utilized in this study comprises 4,217 images of eye diseases, categorized into four classes: Normal (1,074 images), Glaucoma (1,007 images), Cataract (1,038 images), and Diabetic Retinopathy (1,098 images). We implemented a CNN model using TensorFlow to effectively learn and classify these diseases. The evaluation results demonstrate a high accuracy of 95%, with precision and recall rates significantly varying across classes, particularly achieving 100% for Diabetic Retinopathy. These findings highlight the potential of CNNs to improve diagnostic accuracy in ophthalmology, facilitating timely interventions and enhancing patient outcomes. For future research, expanding the dataset to include a wider variety of ocular diseases and employing more sophisticated deep learning techniques could further enhance the model's performance. Integrating this model into clinical practice could significantly aid ophthalmologists in the early detection and management of eye diseases, ultimately improving patient care and reducing the burden of ocular disorders.
KLASIFIKASI PENYAKIT DAUN TOMAT BERBASIS ALGORITMA K-NEAREST NEIGHBOR Muslih, Muslih; Krismawan, Andi Danang
Semnas Ristek (Seminar Nasional Riset dan Inovasi Teknologi) Vol 8, No 01 (2024): SEMNAS RISTEK 2024
Publisher : Universitas Indraprasta PGRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/semnasristek.v8i01.7141

Abstract

Penelitian ini mendalami tantangan dalam pemantauan kesehatan tanaman tomat, yang memiliki peran penting dalam industri pertanian dan perekonomian petani di seluruh dunia. Penyakit-penyakit seperti busuk akar dan hawar daun merupakan ancaman serius yang dapat merusak hasil panen dan mengurangi kualitas tanaman tomat. Dalam upaya mengatasi tantangan ini, penelitian ini menggunakan algoritma K-Nearest Neighbor (KNN) sebagai metode analisis klasifikasi penyakit pada daun tomat. Evaluasi dilakukan melalui tiga percobaan dengan variasi nilai K (K=1, 2, dan 3). Hasilnya menunjukkan bahwa meskipun K=1 mencapai akurasi tertinggi, nilai K=3 memberikan keseimbangan yang baik antara akurasi, kompleksitas model, dan ketahanan terhadap overfitting. Dengan akurasi rata-rata sebesar 88%, model KNN dengan nilai K=3 menjadi pilihan yang handal dalam mengidentifikasi penyakit daun tomat dengan tingkat akurasi yang memadai, memungkinkan pemantauan yang cermat terhadap kesehatan tanaman tomat untuk pemenuhan kebutuhan pangan dunia yang berkelanjutan.
Enhancing MPEG-1 Video Quality Using Discrete Wavelet Transform (DWT) with Coefficient Factor and Gamma Adjustment Krismawan, Andi Danang; Susanto, Ajib; Rachmawanto, Eko Hari; Muslih, Muslih; Sari, Christy Atika; Ali, Rabei Raad
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 2 (2025): JUTIF Volume 6, Number 2, April 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.2.4422

Abstract

Low-quality video caused by compression artifacts, noise, and loss of detail remains a significant challenge in video processing, affecting applications in streaming, surveillance, and medical imaging. Existing enhancement techniques often struggle with excessive noise amplification or high computational complexity, making them inefficient for real-time applications. This study proposes an improved video enhancement method using Discrete Wavelet Transform (DWT) with optimized coefficient factor and gamma adjustment. DWT is a mathematical approach that decomposes video frames into frequency subbands, enabling selective enhancement of important details. To analyze the impact of different wavelets, this study evaluates Coif5, db1, sym4, and sym8 wavelets. The sym8 wavelet, known for its high symmetry and ability to minimize artifacts, achieves the best results in preserving fine details and structural integrity. The coefficient factor is dynamically adjusted to sharpen details while preventing noise amplification, and gamma adjustment is applied to optimize brightness and contrast. The proposed method was evaluated using Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). Experimental results show that sym8 wavelet with gamma 0.7 and coefficient factor 0.3 provides the best balance, achieving an MSE of 0.062, a PSNR of 12.050 dB, and an SSIM of 0.674, outperforming Coif5, db1, and sym4 wavelets. The results indicate that wavelet selection significantly impacts video enhancement performance, with sym8 providing superior contrast enhancement and noise suppression. This study contributes to real-time video processing and AI-based applications, ensuring enhanced visual quality with minimal computational overhead.