• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.317-322
• /
• 2020

Due to the development of artificial intelligence, it is used as a disaster response support system in the field of disaster. Disasters can occur anywhere, anytime. In the event of a disaster, there are four types of reports: fire, rescue, emergency, and other call. Disaster response according to the 119 call also responds differently depending on the type and situation. In this paper, 1280 data set of 119 calls were tested with 3 classes of SVM, NB, k-NN, DT, SGD, and RF situation classification algorithms using a training data set. Classification performance showed the highest performance of 92% and minimum of 77%. In the future, it is necessary to secure an effective data set by disaster in various fields to study disaster response.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.22-28
• /
• 2021

This is a basic study on the development of deep learning-based algorithms to detect smoke before the smoke detector operates in the event of a ship fire, analyze and utilize the detected data, and support fire suppression and evacuation activities by predicting the spread of smoke before it spreads to remote areas. Proposed algorithms were reviewed in accordance with the following procedures. As a first step, smoke images obtained through fire simulation were applied to the YOLO (You Only Look Once) model, which is a deep learning-based object detection algorithm. The mean average precision (mAP) of the trained YOLO model was measured to be 98.71%, and smoke was detected at a processing speed of 9 frames per second (FPS). The second step was to estimate the spread of smoke using the coordinates of the boundary box, from which was utilized to extract the smoke geometry from YOLO. This smoke geometry was then applied to the time series prediction algorithm, long short-term memory (LSTM). As a result, smoke spread data obtained from the coordinates of the boundary box between the estimated fire occurrence and 30 s were entered into the LSTM learning model to predict smoke spread data from 31 s to 90 s in the smoke image of a fast fire obtained from fire simulation. The average square root error between the estimated spread of smoke and its predicted value was 2.74.

• 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.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1367-1377
• /
• 2020

The purpose of this study is to assess the seismic vulnerability of buildings in Gyeongju city starting with the earthquake that occurred in the city on September 12, 2016, and produce a seismic vulnerability map. 11 influence factors related to geotechnical, physical, and structural indicators were selected to assess the seismic vulnerability, and these were applied as independent variables. For a dependent variable, location data of the buildings that were actually damaged in the 9.12 Gyeongju Earthquake was used. The assessment model was constructed based on random forest (RF) as a mechanic study method and support vector machine (SVM), and the training and test dataset were randomly selected with a ratio of 70:30. For accuracy verification, the receiver operating characteristic (ROC) curve was used to select an optimum model, and the accuracy of each model appeared to be 1.000 for RF and 0.998 for SVM, respectively. In addition, the prediction accuracy was shown as 0.947 and 0.926 for RF and SVM, respectively. The prediction values of the entire buildings in Gyeongju were derived on the basis of the RF model, and these were graded and used to produce the seismic vulnerability map. As a result of reviewing the distribution of building classes as an administrative unit, Hwangnam, Wolseong, Seondo, and Naenam turned out to be highly vulnerable regions, and Yangbuk, Gangdong, Yangnam, and Gampo turned out to be relatively safer regions.

• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.270-272
• /
• 2022

Safety is one of the factors that prevent clinical drugs from being distributed on the market. In the case of neurotoxicity, which is the main cause of safety problems caused by drug side effects, risk assessment of drugs and compounds is required in advance. Currently, experiments for testing drug safety are based on animal experimetns, which have the disadvantage of being time-consuming and expensive. Therefore in order to solve the above problem, a neurotoxic prediction model through an in silico experiment was suggested. In this study, the category of neurotoxicity was expanded using a unified medical language system and various related compound data were obtained based on an integrated database. The SMILES (Simplified Molecular Input Line Entry System) of the obtained compounds were converted into fingerprints and it is used as input of machine learning. The model finally predicts the presence or absence of neurotoxicity. The experiment proposed in this study can reduce the time and cost required for the in vivo experiment. Furthermore, it is expected to shorten the research period for new drug development and reduce the burden of suspension of development.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.958-963
• /
• 2023

Lately, there has been increasing research on the prediction of motion performance using artificial intelligence for the safe design and operation of ships. However, compared to conventional ships, research on small fishing boats is insufficient. In this paper, we propose a model that estimates the motion response essential for calculating the motion performance of small fishing boats using a deep neural network. Hydrodynamic analysis was conducted on 15 small fishing boats, and a database was established. Environmental conditions and main particulars were applied as input data, and the response amplitude operators were utilized as the output data. The motion response predicted by the trained deep neural network model showed similar trends to the hydrodynamic analysis results. The results showed that the high-frequency motion responses were predicted well with a low error. Based on this study, we plan to extend existing research by incorporating the hull shape characteristics of fishing boats into a deep neural network model.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.1
• /
• pp.82-88
• /
• 2024

As the modern maritime industry rapidly progresses through technological advancements, data processing technology is emphasized as a key driver of this development. Natural language processing is a technology that enables machines to understand and process human language. Through this methodology, we aim to develop a model that predicts the proportions of outcomes when entering new written judgments by analyzing the rulings of the Marine Safety Tribunal and learning the cause-providing ratios of previously adjudicated ship collisions. The model calculated the cause-providing ratios of the accident using the navigation applied at the time of the accident and the weight of key keywords that affect the cause-providing ratios. Through this, the accuracy of the developed model could be analyzed, the practical applicability of the model could be reviewed, and it could be used to prevent the recurrence of collisions and resolve disputes between parties involved in marine accidents.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.1-9
• /
• 2020

As pet dogs rapidly increase in number, abandoned and lost dogs are also increasing in number. In Korea, animal registration has been in force since 2014, but the registration rate is not high owing to safety and effectiveness issues. Biometrics is attracting attention as an alternative. In order to increase the recognition rate from biometrics, it is necessary to collect biometric images in the same form as much as possible-from the face. This paper proposes a method to determine whether a dog is facing front or not in a real-time video. The proposed method detects the dog's eyes and nose using deep learning, and extracts five types of directional face information through the relative size and position of the detected face. Then, a machine learning classifier determines whether the dog is facing front or not. We used 2,000 dog images for learning, verification, and testing. YOLOv3 and YOLOv4 were used to detect the eyes and nose, and Multi-layer Perceptron (MLP), Random Forest (RF), and the Support Vector Machine (SVM) were used as classifiers. When YOLOv4 and the RF classifier were used with all five types of the proposed face orientation information, the face recognition rate was best, at 95.25%, and we found that real-time processing is possible.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.57-65
• /
• 2021

A hyper-connected intelligence information society is emerging that creates new value by converging IoT, AI, and Bigdata, which are new technologies of the fourth industrial revolution, in all industrial fields. Everything is connected to the network and data is exploding, and artificial intelligence can learn on its own and even intellectual judgment functions are possible. In particular, the Internet of Things provides a new communication environment that can be connected to anything, anytime, anywhere, enabling super-connections where everything is connected. Artificial intelligence technology is implemented so that computers can execute human perceptions, learning, reasoning, and natural language processing. Artificial intelligence is developing advanced technologies such as machine learning, deep learning, natural language processing, voice recognition, and visual recognition, and includes software, machine learning, and cloud technologies specialized in various applications such as safety, medical, defense, finance, and welfare. Through this, it is utilized in various fields throughout the industry to provide human convenience and new values. However, on the contrary, it is time to respond as intelligent and sophisticated cyber threats are increasing and accompanied by potential adverse functions such as securing the technical safety of new technologies. In this paper, we propose a new data modeling method to enable IoT integrated security control by utilizing artificial intelligence technology as a way to solve these adverse functions.