• Smart Media Journal
• /
• v.13 no.2
• /
• pp.32-43
• /
• 2024

Game agents which are behavioral agent for game playing are a crucial component of game satisfaction. However it takes a lot of time and effort to create game agents for various game levels, environments, and players. In addition, when the game environment changes such as adding contents or updating characters, new game agents need to be developed and the development difficulty gradually increases. And it is important to have a game agent that can be customized for different levels of players. This is because a game agent that can play games of various levels is more useful and can increase the satisfaction of more players than a high-level game agent. In this paper, we propose a method for learning and controlling the level of play of game agents that can be rapidly developed and fine-tuned for various game environments and changes. At this time, reinforcement learning applies a policy-based distributed reinforcement learning method IMPALA for flexible processing and fast learning of various behavioral structures. Once reinforcement learning is complete, we choose actions by sampling based on Softmax-Temperature method. From this result, we show that the game agent's play level decreases as the Temperature value increases. This shows that it is possible to easily control the play level.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.1
• /
• pp.15-28
• /
• 2024

This paper proposes a method to acquire image data inside tunnel structures and a method to structure the acquired image data. By improving the conditions by which image data are acquired inside the tunnel structure, high-quality image data can be obtained from area type tunnel scanning. To improve the data acquisition conditions, a longitudinal rail of the tunnel can be installed on the tunnel ceiling, and image data of the entire tunnel structure can be acquired by moving the installed rail. This study identified 0.5 mm cracked simulation lines under a distance condition of 20 m at resolutions of 3,840 × 2,160 and 720 × 480 pixels. In addition, the proposed image-data-structuring method could acquire image data in image tile units. Here, the image data of the tunnel can be structured by substituting the application factors (resolution of the acquired image and the tunnel size) into a relationship equation. In an experiment, the image data of a tunnel with a length of 1,000 m and a width of 20 m were obtained with a minimum overlap rate of 0.02% to 8.36% depending on resolution and precision, and the size of the local coordinate system was found to be (14 × 15) to (36 × 34) pixels.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.1
• /
• pp.75-86
• /
• 2024

Objective : The purpose of this study was to examine the effects of an occupational therapy program on the school readiness, focusing on adaptation skills and daily life skills, in children with developmental delays. Methods : The study involved a boy with developmental delay, aged 5 years and 8 months. The program was conducted twice a week, with a total of 8 sessions spread over 4 weeks. The Canadian Occupational Performance Measure (COPM) was employed, targeting class preparation and use of the toilet. Pre-post tests and follow-up evaluations were carried out to compare changes. Data analysis involved video recordings of the subject's performance. Results : The COPM results indicated improvements in both the performance and satisfaction levels for class preparation and toilet use. Processing skills showed seven improvements in class preparation and eight improvements in toilet use during post-testing. Activity performance observations further confirmed improvements in both class preparation and toilet use during post-test and follow-up evaluations. Conclusion : Occupational therapy improves school readiness (adaptation skill, daily living activity skill) for children with developmental delays, and has a positive effect on overall school readiness.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.112-118
• /
• 2009

This paper proposes a rapid detection algorithm of a salient region for music video browsing system, which can be applied to mobile device and digital video recorder (DVR). The input music video is decomposed into the music and video tracks. For the music track, the music highlight including musical chorus is detected based on structure analysis using energy-based peak position detection. Using the emotional models generated by SVM-AdaBoost learning algorithm, the music signal of the music videos is classified into one of the predefined emotional classes of the music automatically. For the video track, the face scene including the singer or actor/actress is detected based on a boosted cascade of simple features. Finally, the salient region is generated based on the alignment of boundaries of the music highlight and the visual face scene. First, the users select their favorite music videos from various music videos in the mobile devices or DVR with the information of a music video's emotion and thereafter they can browse the salient region with a length of 30-seconds using the proposed algorithm quickly. A mean opinion score (MOS) test with a database of 200 music videos is conducted to compare the detected salient region with the predefined manual part. The MOS test results show that the detected salient region using the proposed method performed much better than the predefined manual part without audiovisual processing.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.6
• /
• pp.572-577
• /
• 2009

Large corpus-based concatenating Text-to-Speech (TTS) systems can generate natural synthetic speech without additional signal processing. To prune the redundant speech segments in a large speech segment DB, we can utilize a decision-tree based triphone clustering algorithm widely used in speech recognition area. But, the conventional methods have problems in representing the acoustic transitional characteristics of the phones and in applying context questions with hierarchic priority. In this paper, we propose a new clustering algorithm to downsize the speech DB. Firstly, three 13th order MFCC vectors from first, medial, and final frame of a phone are combined into a 39 dimensional vector to represent the transitional characteristics of a phone. And then the hierarchically grouped three question sets are used to construct the triphone trees. For the performance test, we used DTW algorithm to calculate the acoustic similarity between the target triphone and the triphone from the tree search result. Experimental results show that the proposed method can reduce the size of speech DB by 23% and select better phones with higher acoustic similarity. Therefore the proposed method can be applied to make a small sized TTS.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.5
• /
• pp.221-228
• /
• 2008

To estimate array shape with reference sources in SONAR systems, nearfield signal modeling is required for the reference sources near a towed array. Array shape estimation method based on the nearfield signal modeling generally exploits the spatial covariance matrix of the received reference sources. Among those method, nearfield eigenvector method uses the eigenvector corresponding to the maximum eigenvalue as a steering vector of the reference source. In this paper, we propose a simplified subspace fitting method based on the nearfield signal modeling with spherical wave modeling. Furthermore, we analyze performance of the array shape estimation methods based on the nearfield signal modeling for various environments. The results of the numerical experiments indicate that the simplified subspace fitting method and the nearfield eigenvector method with single reference source shows almost similar performance. Furthermore, the simplified subspace fitting method with 2 reference sources consistently estimates the shape of the array regardless of the incident angle of the reference sources, whereas the nearfield eigenvector method cannot apply for the case of 2 reference sources.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.2
• /
• pp.9-25
• /
• 2024

Objective : Children with autism spectrum disorder (ASD) commonly suffer from feeding disorders. Major feeding problems include mealtime behavior problems, picky eating, and a lack of food variety can lead to nutritional problems, developmental and social limitations, and stress for the caregivers. A review of the latest literature was conducted to gain an in-depth understanding of assessment tools for feeding disorders in children with ASD. Method : This study analyzed assessments to identify feeding problems in ASD based on previous studies searched through keywords such as ASD, ASD feeding problem, and ASD feeding evaluation. Results : The ASD feeding disorder assessment was divided into direct and indirect assessments. Indirect assessment, in which caregivers measure a child's situation using questionnaires, is mainly used. The assessment of feeding disorders in children with ASD was divided into 1) mealtime behavior, 2) sensory processing, 3) food consumption, and 4) others. Conclusion : As the main feeding disorder characteristics of children with ASD are very diverse, a comprehensive evaluation is necessary but is still limited. Swallowing rehabilitation experts, such as occupational therapists, should apply comprehensive assessment tools based on a basic understanding of the feeding problems, behaviors, and sensations in ASD.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.1
• /
• pp.32-41
• /
• 2024

In the construction industry, not only safety accidents, but also various complex risks such as construction delays, cost increases, and environmental pollution occur, and management technologies are needed to solve them. Among them, process risk management, which directly affects the project, lacks related information compared to its importance. This study tried to develop a MATM tunnel process risk classification system to solve the difficulty of risk information retrieval due to the use of different classification systems for each project. Risk collection used existing literature review and experience mining techniques, and DB construction utilized the concept of natural language processing. For the structure of the classification system, the existing WBS structure was adopted in consideration of compatibility of data, and an RBS linked to the work species of the WBS was established. As a result of the research, a risk classification system was completed that easily identifies risks by work type and intuitively reveals risk characteristics and risk factors linked to risks. As a result of verifying the usability of the established classification system, it was found that the classification system was effective as risks and risk factors for each work type were easily identified by user input of keywords. Through this study, it is expected to contribute to preventing an increase in cost and construction period by identifying risks according to work types in advance when planning and designing NATM tunnels and establishing countermeasures suitable for those factors.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.479-493
• /
• 2023

The need for safety management has arisen due to the increasing number of years of operated underground structures, such as tunnels and utility tunnels, and accidents caused by those aging infrastructures. However, in the case of privately managed underground utility ducts, there is a lack of detailed guidelines for facility safety and maintenance, resulting in inadequate safety management. Furthermore, the absence of basic design information and the limited space for safety assessments make applying currently used non-destructive testing methods challenging. Therefore, this study suggests non-destructive inspection methods using ultrasonic and impact-echo techniques to assess the quality of underground structures. Thickness, presence of rebars, depth of rebars, and the presence and depth of internal defects are assessed to provide fundamental data for the safety assessment of box-type general underground structures. To validate the proposed methodology, different conditions of concrete specimens are designed and cured to simulate actual field conditions. Applying ultrasonic and impact signals and collecting data through multi-channel accelerometers determine the thickness of the simulated specimens, the depth of embedded rebar, and the extent of defects. The predicted results are well agreed upon compared with actual measurements. The proposed methodology is expected to contribute to developing safety diagnostic methods applicable to general underground structures in practical field conditions.

• Tunnel and Underground Space
• /
• v.34 no.3
• /
• pp.208-217
• /
• 2024

There is so much research effort for developing and implementing deep learning-based surveillance systems to manage health and safety issues in construction sites. Especially, the development of deep learning-based object detection in various environmental changes has been progressing because those affect decreasing searching performance of the model. Among the various environmental variables, the accuracy of the object detection model is significantly dropped under low illuminance, and consistent object detection accuracy cannot be secured even the model is trained using low-light images. Accordingly, there is a need of low-light enhancement to keep the performance under low illuminance. Therefore, this paper conducts a comparative study of various deep learning-based low-light image enhancement models (GLADNet, KinD, LLFlow, Zero-DCE) using the acquired construction site image data. The low-light enhanced image was visually verified, and it was quantitatively analyzed by adopting image quality evaluation metrics such as PSNR, SSIM, Delta-E. As a result of the experiment, the low-light image enhancement performance of GLADNet showed excellent results in quantitative and qualitative evaluation, and it was analyzed to be suitable as a low-light image enhancement model. If the low-light image enhancement technique is applied as an image preprocessing to the deep learning-based object detection model in the future, it is expected to secure consistent object detection performance in a low-light environment.