Article Per Year (5 Year)
p-Index From 2021 - 2026
1.037
P-Index
This Author published in this journals
All Journal International Journal of Artificial Intelligence Research Journal of Applied Data Sciences Jurnal Sains Informatika Terapan (JSIT) Jurnal Komtekinfo
Rani, Larissa Navia
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Applied Data Sciences

 1 
Automated Pixel-Level Concrete Defect Detection using U-Net Architecture: A Comparative Study with Clustering-Based Segmentation Hendri, Halifia; Rani, Larissa Navia; Enggari, Sofika; Ramadhanu, Agung; Hadi, Febri
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1298

Abstract

Concrete surface defect detection is a critical aspect of maintaining the integrity and safety of infrastructure in civil engineering. Traditional manual inspection methods are time-consuming, prone to human subjectivity, and often limited by physical accessibility, necessitating the development of robust automated solutions. This paper presents an automated pixel-level concrete surface defect detection system utilizing the U-Net deep learning architecture. The primary contribution and novelty of our approach lie in optimizing the network's encoder-decoder structure with skip connections to effectively capture both broad contextual features and precise spatial localization. This overcomes the critical limitations of existing traditional methods, which frequently struggle with complex concrete background textures, inherent noise, and uneven illumination. To validate our approach, the proposed U-Net model is systematically compared against a widely used baseline method, K-Means clustering combined with Gray-Level Co-occurrence Matrix (GLCM) texture analysis. The evaluation was conducted using a comprehensive dataset consisting of 1000 high-resolution concrete images. Experimental results reveal that the deep learning architecture vastly outperforms the traditional baseline. Specifically, the U-Net model achieved an outstanding F1-Score of 92.47%, a precision of 93.18%, and a mean Intersection over Union (mIoU) of 86.55%. In stark contrast, the K-Means and GLCM approach only yielded an F1-Score of 69.83% and an mIoU of 54.21%. These quantitative findings demonstrate that the proposed U-Net-based system not only successfully minimizes false segmentations but also provides a highly reliable, efficient, and scalable computational framework. Ultimately, this research delivers a practical solution that can be seamlessly integrated into continuous automated structural health monitoring systems, paving the way for safer and more proactive civil infrastructure management.
Development of New Identification Formula to Extract Organic Fertilizer Content Based on Organic Fertilizer Image Ramadhanu, Agung; Mardison, Mardison; Hendri, Halifia; Hadi, Febri; Rani, Larissa Navia; Yuhandri, Yuhandri
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1300

Abstract

Traditional laboratory techniques for examining the nutrient content of organic fertilizers, specifically nitrogen (N), phosphorus (P), and potassium (K), are expensive, time-intensive, and pose environmental hazards. To address these issues, this paper presents a novel, non-destructive, image-based classification algorithm to identify fertilizer nutrient content. The proposed technique integrates color space conversion, unsupervised clustering, texture extraction, and an adapted New Identification Weighting (NIW) method. The NIW is derived from prior probability-based distance measurements and optimized with a balancing weighting factor to improve analytical stability across heterogeneous agricultural images. First, RGB images of fertilizers are converted into the perceptually uniform CIE L*a*b color space, which enhances color distinction under varying lighting conditions. Next, the images are segmented using K-Means clustering, followed by Gray-Level Co-occurrence Matrix (GLCM) extraction to capture textural and structural features. A key innovation of this research is the NIW method, functioning as an adaptive feature prioritization tool that assesses each features contribution to nutrient classification, effectively overcoming the limitations of previous a priori approaches. The system was tested on a dataset of 500 organic fertilizer images, achieving an overall classification accuracy of 97%, demonstrating its effectiveness and robustness. This approach offers a highly accurate and interpretable alternative to conventional chemical testing, making it a feasible, scalable, and affordable field tool for smart farming. By enabling on-site nutrient analysis, it strongly supports sustainable agricultural practices. Future work will focus on enhancing the systems flexibility to varying environmental conditions and integrating this approach into mobile-based diagnostic devices to facilitate real-time decision-making in agriculture.
Co-Authors Enggari, Sofika Febri Hadi Halifia Hendri Jamhur, Annisak M, Mardison Mardison Mardison Muhammad, L. J. Rahim, Muhamad Aulia Ramadhanu, Agung Sarjon Defit Yuhandri Yuhandri, Yuhandri