• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.95-106
• /
• 2021

The purpose of this study is to derive major topics in content R&D and provide directions for academic development by exploring research trends over the past 20 years using topic modeling targeting 9,858 papers published in the Journal of the Korean Contents Association. To secure the reliability and validity of the extracted topics, not only the quantitative evaluation technique but also the qualitative technique were applied step-by-step and repeated until a corpus of the level agreed upon by the researchers was generated, and detailed analysis procedures were presented accordingly. As a result of the analysis, 8 core topics were extracted. This shows that the Korean Contents Association is publishing convergence and complex research papers in various fields without limiting to a specific academic field. Also, before 2012, the proportion of topics in the field of engineering and technology appeared relatively high, while after 2012, the proportion of topics in the field of social sciences appeared relatively high. Specifically, the topic of 'social welfare' showed a fourfold increase in the second half compared to the first half. Through topic-specific trend analysis, we focused on the turning point in time at which the inflection point of the trend line appeared, explored the external variables that affected the research trend of the topic, and identified the relationship between the topic and the external variable. It is hoped that the results of this study can provide implications for active discussions in domestic content-related R&D and industrial fields.

• Journal of the Korean Institute of Gas
• /
• v.26 no.6
• /
• pp.9-15
• /
• 2022

In order to verify the durability of the high-pressure hydrogen tank in the operating pressure range, a hydraulic rupture test should be performed. However, if the bubbles generated by the initial injection process of water are attached to the inner wall of the tank and remain, a sudden pressure change of the bubbles during the rupture of the pressurized tank may cause shock and noise. Therefore, in this study, the flow velocity required to remove the bubbles remaining on the inner wall of the tank was predicted through simplified formulas, and the shape of the injection nozzle to maintain the flow velocity was determined based on the shape of the hydrogen tank for the hydrogen bus. In addition, a numerical model was developed to predict the change in flow velocity according to the inlet pressure, and an experiment was performed through a model tank to prove the validity of the prediction result. As a result of the experiment, the flow velocity near the tank wall was similar to the predicted value of the analysis model, and when the inlet pressure was 1.5 to 5.5 bar, the minimum size of the removable bubble was predicted to be about 2.2 to 4.6 mm.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.313-320
• /
• 2022

The light buoy installed on the sea is always flexible, because it is affected by the weather as well as passing vessels. The position of the light buoy can be cached through the AtoN AIS (Automatic Identification System) and RTU (Remote Terminal Unit). This study analyzed the position data of the light buoys for the last five years (2017-2021), as well as the distribution of the light buoys within the maximum separated position. As a result, there was a basic error of 17.9% in the position data. Additionally, the separated position error of 197 light buoys to be analyzed was 70.64%, and the AtoN RTU was worse than the AtoN AIS by equipment. On the other hand, as a result of the plotting the position data of the light buoy, it was classified into four types. The most common percussion center type, the percussion center dichotomous type in which the position is divided into two zones based on the chimney, the central movement type with a fluctuating center, and the drag type, in which the position is deviated from the center for a certain period. Except for Type-1, the type was determined according to the position at which the light buoy was installed. This study is the first to analyze the position data of the light buoy, and it is expected that it will contribute to the improvement of the quality of the position data of the light buoy.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Journal of Navigation and Port Research
• /
• v.47 no.1
• /
• pp.10-17
• /
• 2023

A series of studies on the development of autonomous surface ships have been promoted in domestic and foreign countries. One of the main technologies for the development of autonomous ships is path-following control, which is closely related to securing the safety of ships at sea. In this regard, the path-following performance of an autonomous ship should be first evaluated at the design stage. The main aim of this study was to develop a visual and quantitative evaluation method for the path-following control performance of an autonomous ship at the design stage. This evaluation technique was developed using a computational fluid dynamics (CFD)-based path-following control model together with a line-of-sight (LOS) guidance algorithm. CFD software was utilized to visualize waves around the ship, performing path-following control for visual evaluation. In addition, a quantitative evaluation was carried out using the difference between the desired and estimated yaw angles, as well as the distance difference between the planned and estimated trajectories. The results demonstrated that the ship experienced large deviations from the planned path near the waypoints while changing its course. It was also found that the fluid phenomena around the ship could be easily identified by visualizing the flow generated by the ship. It is expected that the evaluation method proposed in this study will contribute to the visual and quantitative evaluation of the path-following performance of autonomous ships at the design stage.

• Trans-
• /
• v.14
• /
• pp.1-33
• /
• 2023

In the Web 3.0 era, the third generation of web technologies that uses blockchain technology to give creators ownership of data, metaverse is a crucial trend for developing a creator economy. Web 3.0 aims for a value in which content creators are compensated from participation without being dependent on the platform. Blockchain NFT technology is crucial in metaverse, a vital component of Web 3.0, to ensure the ownership of digital assets. Based on the theory that investigates the concept and characteristics of metaverse, this study identifies five features of the metaverse based NFT art ①'Continuity', ②'Presence', ③ 'Concurrency', ④'Economy', ⑤ 'Application of technology'. By focusing on metaverse based NFT art <Hybrid Nature> case study, we analyzed how the concepts and characteristics of the metaverse and NFT art were reflected in the work. This study focuses on the concept of NFT art, which is emerging at the intersection of art, technology and industry, and emphasizes the importance of finding creative, aesthetic, and cultural values rather than the NFT art's potential for financial gain. It is still in its early stage for academic studies to focus on the aesthetic qualities of NFT art. Future academics and researchers can find this study to gain deeper understanding of the traits and artistic, creative aspects of metaverse based NFT art.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.133-153
• /
• 2023

In this paper, we propose a novel approach to investigating brain-signal measurement technology using Electroencephalography (EEG). Traditionally, researchers have combined EEG signals with bio-signals (BSs) to enhance the classification performance of emotional states. Our objective was to explore the synergistic effects of coupling EEG and BSs, and determine whether the combination of EEG+BS improves the classification accuracy of emotional states compared to using EEG alone or combining EEG with pseudo-random signals (PS) generated arbitrarily by random generators. Employing four feature extraction methods, we examined four combinations: EEG alone, EG+BS, EEG+BS+PS, and EEG+PS, utilizing data from two widely-used open datasets. Emotional states (task versus rest states) were classified using Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) classifiers. Our results revealed that when using the highest accuracy SVM-FFT, the average error rates of EEG+BS were 4.7% and 6.5% higher than those of EEG+PS and EEG alone, respectively. We also conducted a thorough analysis of EEG+BS by combining numerous PSs. The error rate of EEG+BS+PS displayed a V-shaped curve, initially decreasing due to the deep double descent phenomenon, followed by an increase attributed to the curse of dimensionality. Consequently, our findings suggest that the combination of EEG+BS may not always yield promising classification performance.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.207-216
• /
• 2024

As big data was built due to the 4th Industrial Revolution, personalized services increased rapidly. As a result, the amount of personal information collected from online services has increased, and concerns about users' personal information leakage and privacy infringement have increased. Online service providers provide privacy policies to address concerns about privacy infringement of users, but privacy policies are often misused due to the long and complex problem that it is difficult for users to directly identify risk items. Therefore, there is a need for a method that can automatically check whether the privacy policy is safe. However, the safety verification technique of the conventional blacklist and machine learning-based privacy policy has a problem that is difficult to expand or has low accessibility. In this paper, to solve the problem, we propose a safety verification technique for the privacy policy using the GPT-3.5 API, which is a generative artificial intelligence. Classification work can be performed evenin a new environment, and it shows the possibility that the general public without expertise can easily inspect the privacy policy. In the experiment, how accurately the blacklist-based privacy policy and the GPT-based privacy policy classify safe and unsafe sentences and the time spent on classification was measured. According to the experimental results, the proposed technique showed 10.34% higher accuracy on average than the conventional blacklist-based sentence safety verification technique.