• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4105-4121
• /
• 2021

Recently, malware classification based on Deep Neural Networks (DNN) has gained significant attention due to the rise in popularity of artificial intelligence (AI). DNN-based malware classifiers are a novel solution to combat never-before-seen malware families because this approach is able to classify malwares based on structural characteristics rather than requiring particular signatures like traditional malware classifiers. However, these DNN-based classifiers have been found to lack robustness against malwares that are carefully crafted to evade detection. These specially crafted pieces of malware are referred to as adversarial examples. We consider a clever adversary who has a thorough knowledge of DNN-based malware classifiers and will exploit it to generate a crafty malware to fool DNN-based classifiers. In this paper, we propose a DNN-based malware classifier that becomes resilient to these kinds of attacks by exploiting Generative Adversarial Network (GAN) based data augmentation. The experimental results show that the proposed scheme classifies malware, including AEs, with a false positive rate (FPR) of 3.0% and a balanced accuracy of 70.16%. These are respective 26.1% and 18.5% enhancements when compared to a traditional DNN-based classifier that does not exploit GAN.

• Geomechanics and Engineering
• /
• v.30 no.2
• /
• pp.107-121
• /
• 2022

Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.27-34
• /
• 2023

This paper studied the 3D modeling process for the restoration of the 'Three-story Stone Pagoda of Bulguksa Temple in Gyeongju', a stone pagoda from the Unified Silla Period, using artificial intelligence (AI). Existing 3D modeling methods generate numerous verts and faces, which takes a considerable amount of time for AI learning. Accordingly, a method of performing more efficient 3D modeling by lowering the number of verts and faces is required. To this end, in this study, the structure of the stone pagoda was deeply analyzed and a modeling method optimized for AI learning was studied. In addition, it is meaningful to propose a new 3D modeling methodology for the restoration of stone pagodas in Korea and to secure a data set necessary for artificial intelligence learning.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.4 no.2
• /
• pp.79-85
• /
• 2023

The Tibetan Plateau is home to the only alpine crane species, the black-necked crane (Grus nigricollis). Conservation efforts are severely hampered by a lack of knowledge on the spatial distribution and breeding habitats of this species. The ecological niche modeling framework used to predict the spatial distribution of this species, based on the maximum entropy and occurrence record data, allowed us to generate a species-specific spatial distribution map in Ladakh, Trans-Himalaya, India. The model was created by assimilating species occurrence data from 486 geographical sites with 24 topographic and bioclimatic variables. Fourteen variables helped forecast the distribution of black-necked cranes by 96.2%. The area under the curve score for the model training data was high (0.98), indicating the accuracy and predictive performance of the model. Of the total study area, the areas with high and moderate habitat suitability for black-necked cranes were anticipated to be 8,156 km² and 6,759 km², respectively. The area with high habitat suitability within the protected areas was 5,335 km². The spatial distribution predicted using our model showed that the majority of speculated conservation areas bordered the existing protected areas of the Changthang Wildlife Sanctuary. Hence, we believe, that by increasing the current study area, we can account for these gaps in conservation areas, more effectively.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.361-370
• /
• 2020

Automatic building material recognition has been a popular research interest over the past decade because it is useful for construction management and facility management. Currently, the extensively used methods for automatic material recognition are mainly based on 2D images. A terrestrial laser scanner (TLS) with a built-in camera can generate a set of coloured laser scan data that contains not only the visual features of building materials but also other attributes such as material reflectance and surface roughness. With more characteristics provided, laser scan data have the potential to improve the accuracy of building material recognition. Therefore, this research aims to develop a TLS-based building material recognition method by combining machine learning techniques. The developed method uses material reflectance, HSV colour values, and surface roughness as the features for material recognition. A database containing the laser scan data of common building materials was created and used for model training and validation with machine learning techniques. Different machine learning algorithms were compared, and the best algorithm showed an average recognition accuracy of 96.5%, which demonstrated the feasibility of the developed method.

• Smart Structures and Systems
• /
• v.30 no.5
• /
• pp.501-511
• /
• 2022

Three-dimensional (3D) models have become crucial for improving civil infrastructure analysis, and they can be used for various purposes such as damage detection, risk estimation, resolving potential safety issues, alarm detection, and structural health monitoring. 3D point cloud data is used not only to make visual models but also to analyze the states of structures and to monitor them using semantic data. This study proposes automating the generation of high-quality 3D point cloud data and removing noise using deep learning algorithms. In this study, large-format aerial images of civilian infrastructure, such as cut slopes and dams, which were captured by drones, were used to develop a workflow for automatically generating a 3D point cloud model. Through image cropping, downscaling/upscaling, semantic segmentation, generation of segmentation masks, and implementation of region extraction algorithms, the generation of the point cloud was automated. Compared with the method wherein the point cloud model is generated from raw images, our method could effectively improve the quality of the model, remove noise, and reduce the processing time. The results showed that the size of the 3D point cloud model created using the proposed method was significantly reduced; the number of points was reduced by 20-50%, and distant points were recognized as noise. This method can be applied to the automatic generation of high-quality 3D point cloud models of civil infrastructures using aerial imagery.

• Korean Journal of Agricultural Science
• /
• v.50 no.4
• /
• pp.799-808
• /
• 2023

Globally, abnormal climate phenomena have led to an increase in rainfall intensity, consequently causing a rise in flooding-related damages. Agricultural areas, in particular, experience significant annual losses every year due to a lack of research on flooding in these regions. This study presents a comprehensive analysis of the flood event that occurred on July 16, 2017, in the agricultural area situated in Sindaedong, Heungdeok-gu, Cheongju-si. To achieve this, the EPA (United States Environmental Protection Agency) Storm Water Management Model (SWMM) was employed to generate runoff data by rainfall information. The produced runoff data facilitated the identification of flood occurrence points, and the analysis results exhibited a strong correlation with inundation trace maps provided by the Ministry of the Interior and Safety (MOIS). The detailed output of the SWMM model enabled the extraction of time-specific runoff information at each inundation point, allowing for a detailed understanding of the inundation status in the agricultural area over different time frames. This research underscores the significance of utilizing the SWMM model to simulate inundation in agricultural areas, thereby validating the efficacy of flood alerts and risk management plans. In particular, the integration of rainfall data and the SWMM model in flood prediction methodologies is expected to enhance the formulation of preventative measures and response strategies against flood damages in agricultural areas.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.319-328
• /
• 2024

Semi-supervised learning is a good way to train a classification model using a small number of labeled and large number of unlabeled data. We applied semi-supervised learning to a synthetic aperture radar(SAR) image classification model with a limited number of datasets that are difficult to create. To address the previous difficulties, semi-supervised learning uses a model trained with a small amount of labeled data to generate and learn pseudo labels. Besides, a lot of number of papers use a single fixed threshold to create pseudo labels. In this paper, we present a semi-supervised synthetic aperture radar(SAR) image classification method that applies different thresholds for each class instead of all classes sharing a fixed threshold to improve SAR classification performance with a small number of labeled datasets.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.21-29
• /
• 2024

Fueled by international efforts towards AI standardization, including those by the European Commission, the United States, and international organizations, this study introduces a AI-driven framework for analyzing advancements in drone technology. Utilizing project data retrieved from the NTIS DB via the "drone" keyword, the framework employs a diverse toolkit of supervised learning methods (Keras MLP, XGboost, LightGBM, and CatBoost) enhanced by BERTopic (natural language analysis tool). This multifaceted approach ensures both comprehensive data quality evaluation and in-depth structural analysis of documents. Furthermore, a 6T-based classification method refines non-applicable data for year-on-year AI analysis, demonstrably improving accuracy as measured by accuracy metric. Utilizing AI's power, including GPT-4, this research unveils year-on-year trends in emerging keywords and employs them to generate detailed summaries, enabling efficient processing of large text datasets and offering an AI analysis system applicable to policy domains. Notably, this study not only advances methodologies aligned with AI Act standards but also lays the groundwork for responsible AI implementation through analysis of government research and development investments.