Penulis: Agung Teguh Wibowo Almais; Adi Susilo; Agus Naba; Moechammad Sarosa; Alamsyah Muhammad Juwono; Cahyo Crysdian

Nama Jurnal: IEEE Access

Tahun: 2024

Volume: 12

Issue: Tidak ada

Halaman: 146190 - 146201

Deskripsi: Objective: To determine the characteristics of a building after a natural disaster using image input through the integration of image analysis techniques. Methods: Several image analysis techniques, including GLCM and PCA, were employed. The GLCM process converts image input into numerical values using 8 different angles and pixel distances of 1 and 0.5 pixels. The numerical values from GLCM are then processed by PCA to extract information stored in the images of buildings post-disaster. Results: The PCA process revealed different information between images processed with GLCM at 1 pixel distance and those at 0.5 pixel distance. Validation by surveyors confirmed that the accurate information corresponding to real images was obtained from GLCM with a 0.5 pixel distance, indicating severe damage. The PCA results using GLCM at 0.5 pixel distance produced 2D and 3D visualizations with dominant coordinates in the severely damaged cluster, with a value range (n) of n ≥ 2. Conclusion: Based on these findings, the integration of image analysis techniques, specifically GLCM and PCA, can be used to determine the level of damage to buildings after a natural disaster.

Pendahuluan: Infrastructure resilience to natural disasters is one of the biggest challenges faced by modern society. Disasters such as earthquakes, storms, and floods can cause significant structural damage to buildings, resulting in huge economic losses and, more importantly, loss of human life [1], [2]. Therefore, post-disaster structural damage assessment is very important to ensure the safety and sustainability of building structures. In this context, an integrated approach using the Gray Level Co-occurrence Matrix (GLCM) and Principal Component Analysis (PCA) offers untapped potential in structural damage assessment. Wildeman has shown that non-destructive methods such as PCA and GLCM can provide valuable insight into the structural condition of buildings [3]. In addition, the GLCM-PCA integration can be a decision making to determine the level of building damage after natural disasters with the latest development, in his research, Mohammad Aljanabi explained that in civil engineering the latest knowledge to determine building damage is found in the decision-making stage [4]. According to Aklouche et al. PCA has been used extensively in multivariate data analysis to reduce data dimensions while retaining most of the information that matters [5]. Meanwhile, GLCM, as a texture analysis tool, has proven effective in identifying patterns of damage to materials [6]. However, integrating these two methods in the context of post- disaster structural damage assessment is rarely explored. Although there have been advances in structural damage assessment techniques, significant research gaps remain. Most previous studies have focused on using individual methods to detect damage, which are often insufficient to capture the complexity of damage incurred in natural disasters [7]. In addition, existing research often does not fully use Product Lifecycle Data (PLD) which can improve the accuracy of damage assessment [8]. This research aims to overcome these shortcomings by integrating GLCM and PCA, thus providing a more robust and accurate method for post-disaster structural damage assessment. Furthermore, this research can also make a significant contribution to the field of post-disaster structural damage assessment with several innovative aspects: Combining GLCM and PCA for the first time as an integrated method in structural damage assessment, provides a new perspective in damage data analysis. The proposed model promises improved accuracy in damage detection, which is critical for emergency intervention and post-disaster reconstruction. Given the large data and computationally intensive requirements of the Convolutional Neural Network (CNN) method, introducing automation in the damage assessment process significantly reduces the time required. Assist stakeholders (the government) in distributing more objective assistance with the condition of victims affected by natural disasters. The content of this article explains the following: the background to the use of GLCM-PCA to assess the extent of damage to buildings after natural disasters and the use of GLCM-PCA in several studies in “Related Works.” Then the “Method” describes the steps of GLCM-PCA. “Results and discussion,” describes the experimental process of GLCM-CA using Python programming language to assess the extent of sector damage after natural disasters and validate results. Finally, the “conclusion” summarizes the results of the experiment and opportunities for future research.

Kata Kunci: Principal component analysis, Buildings, Disasters, Feature extraction