• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.65-73
• /
• 2023

In this paper, we propose a data augmentation method based on CNN(Convolutional Neural Network) learning for efficiently obtaining concrete crack image datasets. Real concrete crack images are not only difficult to obtain due to their unstructured shape and complex patterns, but also may be exposed to dangerous situations when acquiring data. In this paper, we solve the problem of collecting datasets exposed to such situations efficiently in terms of cost and time by using vector and thickness-based data augmentation techniques. To demonstrate the effectiveness of the proposed method, experiments were conducted in various scenes using U-Net-based crack detection, and the performance was improved in all scenes when measured by IoU accuracy. When the concrete crack data was not augmented, the percentage of incorrect predictions was about 25%, but when the data was augmented by our method, the percentage of incorrect predictions was reduced to 3%.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.11 no.4
• /
• pp.501-508
• /
• 2023

Addressing urban noise problems, this study develops eco-friendly, inorganic sound-absorbing panels, overcoming the limitations of traditional PMMA and cement-based panels. These conventional panels pose safety risks due to flammability and environmental concerns due to carbon emissions. Utilizing industrial waste, the research comprises two phases: initial tests for physical and performance characteristics (fluidity, density, compressive strength, sound absorption) and subsequent development of optimized panel mixtures. This approach aims to replace existing panels with sustainable, effective alternatives, significantly contributing to safer, environmentally responsible urban infrastructure. The findings of this study have implications for the sound panel market, offering novel solutions for noise control while aligning with environmental and safety standards.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.5
• /
• pp.761-773
• /
• 2023

This paper proposes a method to increase the power-analysis resistance of the neural network model's feedforward process by replacing the exponential-based activation function, used in the deep-learning field, with an approximated function especially at the multi-layer perceptron model. Due to its nature, the feedforward process of neural networks calculates secret weight and bias, which already trained, so it has risk of exposure of internal information by side-channel attacks. However, various functions are used as the activation function in neural network, so it's difficult to apply conventional side-channel countermeasure techniques, such as masking, to activation function(especially, to exponential-based activation functions). Therefore, this paper shows that even if an exponential-based activation function is replaced with approximated function of simple form, there is no fatal performance degradation of the model, and than suggests a power-analysis resistant feedforward neural network with exponential-based activation function, by masking approximated function and whole network.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.843-847
• /
• 2023

In this paper, we propose a model for detecting efficient fire identification to prevent fires that can lead to various industrial accidents, farmland and large forest fires, with the widespread use of various chemicals and flammable substances as modern technology advances. This paper presents an algorithm that can detect fire smoke in a high-efficiency and short time using images, and an algorithm based on SVM(Support Vector Machine) and K fold cross-verification technologies. By analyzing images, fire and smoke detection algorithms have relatively superior detection performance compared to existing algorithms, and the analysis of fire and smoke characteristics detected in this paper is analyzed stably and efficiently and is expected to be used in various fields that may be exposed to fire risks in the future.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.882-896
• /
• 2023

Pupose: The purpose is to prepare safety management and seismic reinforcement measures that can effectively improve the potential risks of earthquake-resistant design and the deficiencies of safety guidance and inspection of factory facilities in national industrial complexes. Method: In this study, problems and improvement measures were derived through investigation and analysis of overall earthquake disaster safety management, such as safety management status and management system in preparation for earthquake disasters in national industrial complexes. was implemented to suggest improvement plans based on facility types and structural characteristics. Result: In conclusion, the problems of safety management and seismic reinforcement in preparation for earthquake disasters in national industrial complexes were summarized and classified into four types (seismic performance evaluation and related system supplementation, authority of tenant companies and local governments, seismic reinforcement and safety management support measures, organizational structure capacity building) to derive improvement measures. Conclusion: Based on this, seismic reinforcement measures that companies in national industrial complexes should implement in preparation for earthquake disasters were prepared, and detailed plans for each measure were presented.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_2
• /
• pp.771-783
• /
• 2023

This study aims to compare the performance of each machine learning model for preparing a grid-based disaster risk map related to flooding in Jung-gu, Ulsan, for Typhoon Chaba which occurred in 2016. Dynamic data such as rainfall and river height, and static data such as building, population, and land cover data were used to conduct a risk analysis of flooding disasters. The data were constructed as 10 m-sized grid data based on the national point number, and a sample dataset was constructed using the risk value calculated for each grid as a dependent variable and the value of five influencing factors as an independent variable. The total number of sample datasets is 15,910, and the training, verification, and test datasets are randomly extracted at a 6:2:2 ratio to build a machine-learning model. Machine learning used random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN) techniques, and prediction accuracy by the model was found to be excellent in the order of SVM (91.05%), RF (83.08%), and KNN (76.52%). As a result of deriving the priority of influencing factors through the RF model, it was confirmed that rainfall and river water levels greatly influenced the risk.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.133-138
• /
• 2024

Lithium-ion batteries are used in many fields due to their high energy density, fast charging conditions, and long cycle life. However, overcharging, over-discharging, physical damage, and use of lithium-ion batteries at high temperatures can reduce battery life and cause damage to people due to fire or explosion due to damage to the protection circuit. In order to reduce the risk of these batteries and improve battery performance, the characteristics of the charging and discharging process must be analyzed and understood. Therefore, in this paper, we analyze the charging and discharging characteristics of lithium-ion batteries using a battery charger and discharger and simulator to reduce the risk of loss of life due to overcharge and overdischarge, as well as casualties from fire and explosion due to damage to the protection circuit.

• Journal of the Korean Society of Radiology
• /
• v.83 no.1
• /
• pp.3-27
• /
• 2022

Cardiac CT has been proven to provide diagnostic and prognostic evaluation of coronary artery disease for cardiovascular risk stratification and treatment decision-making based on rapid technological development and various research evidence. Coronary CT angiography has emerged as a gateway test for coronary artery disease that can reduce invasive angiography due to its high negative predictive value, but the diagnostic specificity is relatively low. However, coronary CT angiography is likely to overcome its limitations through functional evaluation to identify the hemodynamic significance of coronary artery disease by analyzing myocardial perfusion and fractional flow reserve through cardiac CT. Recently, studies have been actively conducted to incorporate artificial intelligence to make this more objective and reproducible. In this review, functional imaging techniques of cardiac computerized tomography are explored.

• Tunnel and Underground Space
• /
• v.34 no.2
• /
• pp.154-168
• /
• 2024

The Tunnel Boring Machine (TBM) disc cutter is subjected to wear and damage during the rock excavation process, and the worn disc cutter should be replaced on time. The manual inspection by workers is generally required to determine the disc cutter replacement. In this case, the workers are exposed to dangerous environments, and the measurements are sometimes inaccurate. In this study, we developed a technology that measures the disc cutter wear in real time. From a series of laboratory tests, a magnetic sensor was selected as the wear sensor, and the real-time disc cutter measurement system was developed integrating wireless communication modules, power supply and data processing board. In addition, the measurement system was verified in actual TBM excavation circumstances. As a result, it was confirmed that the accuracy and stability of the system.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.1-10
• /
• 2024

The research on predicting the routes of ships, which constitute the majority of maritime transportation, can detect potential hazards at sea in advance and prevent accidents. Unlike roads, there is no distinct signal system at sea, and traffic management is challenging, making ship route prediction essential for maritime safety. However, the time intervals of the ship route datasets are irregular due to communication disruptions. This study presents a method to adjust the time intervals of data using appropriate interpolation techniques for ship route prediction. Additionally, a deep learning model for predicting ship routes has been developed. This model is an LSTM model that predicts the future GPS coordinates of ships by understanding their movement patterns through real-time route information contained in AIS data. This paper presents a data preprocessing method using linear interpolation and a suitable deep learning model for ship route prediction. The experimental results demonstrate the effectiveness of the proposed method with an MSE of 0.0131 and an Accuracy of 0.9467.