• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.481-492
• /
• 2023

This study explores how to build a Korean dataset to extract information from text using generative large language models. In modern society, mixed information circulates rapidly, and effectively categorizing and extracting it is crucial to the decision-making process. However, there is still a lack of Korean datasets for training. To overcome this, this study attempts to extract information using text-based zero-shot learning using a generative large language model to build a purposeful Korean dataset. In this study, the language model is instructed to output the desired result through prompt engineering in the form of "system"-"instruction"-"source input"-"output format", and the dataset is built by utilizing the in-context learning characteristics of the language model through input sentences. We validate our approach by comparing the generated dataset with the existing benchmark dataset, and achieve 25.47% higher performance compared to the KLUE-RoBERTa-large model for the relation information extraction task. The results of this study are expected to contribute to AI research by showing the feasibility of extracting knowledge elements from Korean text. Furthermore, this methodology can be utilized for various fields and purposes, and has potential for building various Korean datasets.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.153-155
• /
• 2007

Korea Meteorological Administration (KMA) has operationally produced Atmospheric Motion Vector (AMV) from the consecutive MTSAT-1R satellite image dataset. Comparing with radiosonde data, our current AMV scheme shows more than 10 m/s RMSE. Therefore we need to improve continuously its accuracy. Many AMV producers have stated that the bad performance of the Height Assignment (HA) algorithm is the main reason of degrading the accuracy of AMV. The uncertainties in AMV HA can occur in the algorithm itself, used NWP profiles, and the performance of Radiative Transfer Model (RTM) etc. This study introduces currently operated AMV HA schemes and the impacts of NWP profile data and RTM that these schemes use were investigated. Finally we analyzed the relationship between vectors by vector tracking and heights assigned to each vector by using collocated wind profile dataset with radiosonde data. This study is a preliminary work to improve the accuracy of AMV by removing or decreasing the uncertainties in AMV estimation.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.22-35
• /
• 2011

Incheon Bay has a suitable condition for tidal power generation due to the high tidal range by topographical effect. Therefore a study on the technology development for tidal energy utilization has been promoted since 2006. It is needed to deduce optimal alternatives to determine the suitable location of facilities for tidal power generation and to reduce the environmental damage from development. In order to carry out efficiently this mission, spatial information system is essential to manage and use various spacial elements related to the development and conservation. In this study, for the development of tidal energy, spatial data could be defined as three kinds of dataset. Fundamental dataset is defined as spatial data such as tide, tidal current, wave, erosion and sedimentation. Framework dataset is composed of topographical map, facility map and bathymetry. The reference dataset is composed of marine ecology and environment having the characteristics of thematic map. This study is mainly aimed at establishing methodology of conceptual spatial data modeling classifying as essential data model and optional data model through the definition of the components of spatial data.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.309-316
• /
• 2018

Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

• Journal of Radiation Protection and Research
• /
• v.46 no.4
• /
• pp.184-193
• /
• 2021

Background: The radionuclides released by the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident 9 years ago are still being monitored by various research teams and the Japanese government. Comparison of different surveys' results could help evaluate the exposure doses and the mechanism of radiocesium behavior in the urban environment in the area. In this study, we clarified the relationship between land use and temporal changes in the ambient dose rates (air dose rates) using big data. Materials and Methods: We set a series of 1 × 1 km² meshes within the 80 km zone of the FDNPP to compare the different survey results. We then prepared an analysis dataset from all survey meshes to analyze the temporal change in the air dose rate. The selected meshes included data from all survey types (airborne, fixed point, backpack, and carborne) obtained through the all-time survey campaigns. Results and Discussion: The characteristics of each survey's results were then evaluated using this dataset, as they depended on the measurement object. The dataset analysis revealed that, for example, the results of the carborne survey were smaller than those of the other surveys because the field of view of the carborne survey was limited to paved roads. The location factor of different land uses was also evaluated considering the characteristics of the four survey methods. Nine years after the FDNPP accident, the location factor ranged from 0.26 to 0.49, while the half-life of the air dose rate ranged from 1.2 to 1.6. Conclusion: We found that the decreasing trend in the air dose rate of the FDNPP accident was similar to the results obtained after the Chernobyl accident. These parameters will be useful for the prediction of the future exposure dose at the post-accident.

• Safety and Health at Work
• /
• v.14 no.3
• /
• pp.259-266
• /
• 2023

Background: Recent research on occupational injuries in companies has faced difficulties in obtaining representative data, leading to studies relying on surveys or case studies. Moreover, it is difficult to find studies on how a company's industry characteristics affect occupational injuries. This study aims to address these limitations. Methods: We collected 11 years of disclosure data from 1,247 listed companies in the Korean stock market and combined it with their occupational injury histories collected by the Republic of Korea Occupational Safety and Health Agency (KOSHA) to build a dataset. We attempted to analyze a linear panel model by dividing the dataset into manufacturing, construction, and other industries. Results: The higher proportion of full-time employees and better job skills correlate with lower occupational injuries in other industries. The wage increase reduces occupational injuries in manufacturing and other industries, but the substitution effect produces the opposite outcome in construction. Also, foreign ownership and credit ratings increase effectively reduce occupational injuries mainly in the manufacturing industry. Conclusion: Our results suggest that in explaining the relationship between corporate characteristics and occupational injuries, it is necessary to consider the nature of the industry more closely, and in particular, employment and labor policies for preventing occupational injuries need to be selectively applied according to industry. In addition, to improve the limitations and increase the usability of the research results, further detailed studies are needed in the future.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.59-70
• /
• 2020

This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.