• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.141-147
• /
• 2024

Recently, there has been growing interest in personalized services tailored to an individual's preferences. This has led to ongoing research aimed at recognizing and leveraging an individual's personality traits. Among various methods for personality assessment, the OCEAN model stands out as a prominent approach. In utilizing OCEAN for personality recognition, a multi modal artificial intelligence model that incorporates linguistic, paralinguistic, and non-linguistic information is often employed. This paper examines the impact of the margin value set for extracting facial areas from video data on the accuracy of a personality recognition model that uses facial expressions to determine OCEAN traits. The study employed personality recognition models based on 2D Patch Partition, R2plus1D, 3D Patch Partition, and Video Swin Transformer technologies. It was observed that setting the facial area extraction margin to 60 resulted in the highest 1-MAE performance, scoring at 0.9118. These findings indicate the importance of selecting an optimal margin value to maximize the efficiency of personality recognition models.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.8
• /
• pp.759-769
• /
• 2013

Electronic equipment has been applied to virtually every area associated with commercial, industrial, and military applications. Specifically, electronics have been incorporated into avionics components installed in aircraft. This equipment is exposed to dynamic loads such as vibration, shock, and acceleration. Especially, avionics components installed in a helicopter are subjected to simultaneous sine and random base excitations. These are denoted as sine on random vibrations according to MIL-STD-810F, Method 514.5. In the past, isolators have been applied to avionics components to reduce vibration and shock. However, an isolator applied to an avionics component installed in a helicopter can amplify the vibration magnitude, and damage the chassis, circuit card assembly, and the isolator itself via resonance at low-frequency sinusoidal vibrations. The objective of this study is to investigate the dynamic characteristics of an avionics component installed in a helicopter and the structural dynamic modification of its tray plate without an isolator using both a finite element analysis and experiments. The structure is optimized by dynamic loads that are selected by comparing the vibration, shock, and acceleration loads using vibration and shock response spectra. A finite element model(FEM) was constructed using a simplified geometry and valid element types that reflect the dynamic characteristics. The FEM was verified by an experimental modal analysis. Design parameters were extracted and selected to modify the structural dynamics using topology optimization, and design of experiments(DOE). A prototype of a modified model was constructed and its feasibility was evaluated using an FEM and a performance test.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.137-142
• /
• 2024

Recently, deep learning technology has become those methods as de facto standards in the area of medical data representation. But, deep learning inherently requires a large amount of training data, which poses a challenge for its direct application in the medical field where acquiring large-scale data is not straightforward. Additionally, brain signal modalities also suffer from these problems owing to the high variability. Research has focused on designing deep neural network structures capable of effectively extracting spectro-spatio-temporal characteristics of brain signals, or employing self-supervised learning methods to pre-learn the neurophysiological features of brain signals. This paper analyzes methodologies used to handle small-scale data in emerging fields such as brain-computer interfaces and brain signal-based state prediction, presenting future directions for these technologies. At first, this paper examines deep neural network structures for representing brain signals, then analyzes self-supervised learning methodologies aimed at efficiently learning the characteristics of brain signals. Finally, the paper discusses key insights and future directions for deep learning-based brain signal analysis.

• Journal of Navigation and Port Research
• /
• v.39 no.3
• /
• pp.179-184
• /
• 2015

The purpose of this study is to provide appropriate methodology to ensure the safety and integrity of the production riser in offshore structure. In order to select integrity estimation methodology for production riser, level I and II Non-destructive Damage Evaluation (NDE) methods that were applied to existing structures are classified and reviewed. Numerical analysis is performed to verify the applicability and capability on damage detection of reviewed methods. As a result, the damage detection methodology using modal strain energy is more sensitive in detection of the damage than other methods. In practice, the number of sensors is limited due to the environmental and financial conditions. The impact on damage detection performance by reducing the number of sensors is systematically investigated through a series of numerical analyses and the results are discussed. The optimal number of sensor for the integrity estimation of production riser is recommended.

• International Journal of Highway Engineering
• /
• v.19 no.4
• /
• pp.45-52
• /
• 2017

PURPOSES : This study was initiated to estimate the utilities of usage attributes of BRT and Bimodal Trams using a conjoint analysis method in order to identify the important features pertaining to the use of BRT and Bimodal Trams. METHODS : For this purpose, important attributes and those level in the use of BRT and Bimodal Trams in the city of Sejong were identified. Next, a profile questionnaire pertaining to BRT and Bimodal Trams was designed for the conjoint analysis, and a survey was conducted in the city of Sejong. Using SPSS software, conjoint analysis was performed to identify the important attributes vis-$\acute{a}$-vis the use of BRT and Bimodal Trams in the city of Sejong. Finally, the utilities for individual attributes were calculated based on the models estimated by the conjoint analysis. RESULTS : The results of the conjoint analysis were used to identify the important attributes. With regard to the usage of BRT, users indicated that fare was the most important attribute with the highest utility. In the case of Bimodal Trams, the users indicated that the number of seats and internal environment were the most important attributes with the highest utilities. CONCLUSIONS : Based on the results of the conjoint analysis, the important attributes pertaining to the use of BRT and Bimodal Trams in the city of Sejong were identified. Our study indicates that BRT in the city of Sejong needs to be upgraded to improve the utilities of the important attributes. Currently, Bimodal Trams has not been introduced completely in the city of Sejong. However, in the future, when the introduction of Bimodal Trams is completed, the important attributes should be emphasized in order to improve the quality of its service.

• Journal of Aerospace System Engineering
• /
• v.10 no.4
• /
• pp.1-10
• /
• 2016

This study analyzes the fabric skin of a wind turbine blade. The fabric skin is a membrane structure that was analyzed using a static Fluid Structure Interaction (FSI) method. For this study the blade of large 5 MW wind turbine was selected. In order to examine the validity of the analysis, a variety of reference data were used. Before conducting static FSI analysis, a Computational Fluid Dynamics (CFD) analysis and modal analysis were done. Then interaction analysis was conducted. FSI analysis was done with imported Aerodynamic data that resulted from the CFD analysis. The resulting observations about the membrane structure, inherent tensions, deformation of the final structure, and aerodynamic forces caused by deformation are reported.

• Transactions of the KSME C: Technology and Education
• /
• v.3 no.3
• /
• pp.183-191
• /
• 2015

In this study, the finite element analysis was carried out to investigate dynamic characteristics of the AGF(Active Gurney Flap) which is under development for reducing vibration and noise of the helicopter rotor system. The Gurney flap is a kind of small flat plate, mounted normal to the lower surface of the airfoil near to the trailing edge. An electric motor, L-shaped linkages and flap parts were integrated into a rotor bade, and 3~5/rev control was given to the AGF to reduce the vibration in the fixed frame. Thus, an explicit time integration method was adopted to investigate the dynamic response of the AGF with considering both centrifugal force due to the rotor rotation and active control input, and it can be seen that the vertical displacement of the AGF was satisfied to meet the design requirement.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.93-102
• /
• 2011

This paper presents a walking guidance system for blind pedestrians in an outdoor environment using just one single camera. Unlike many existing travel-aid systems that rely on stereo-vision, the proposed system aims to get necessary information of the road environment by using just single camera fixed at the belly of the user. To achieve this goal, a top-view image of the road is used, on which obstacles are detected by first extracting local extreme points and then verified by the polar edge histogram. Meanwhile, user motion is estimated by using optical flow in an area close to the user. Based on these information extracted from image domain, an audio message generation scheme is proposed to deliver guidance instructions via synthetic voice to the blind user. Experiments with several sidewalk video-clips show that the proposed walking guidance system is able to provide useful guidance instructions under certain sidewalk environments.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.35 no.4
• /
• pp.409-415
• /
• 2011

A gimbal system in observation reconnaissance aircraft was fabricated by assembling many parts and bearings. This system consists of a camera module and a stabilization gimbal that supports the camera module. During the flight for recording images, the gimbal system experiences various accelerations with wide frequencies. Although base excitation of stabilization gimbal results in vibration of the camera module, the camera module must be able to capture the correct and clear image even while vibrating. Hence, it is important to know the natural frequencies and vibration modes of the gimbal system with the camera module. Considering bearings as spring elements, the vibration characteristic of the gimbal system was analyzed by finite element method. In addition, harmonic response analysis was performed to determine the correct transmissibility of acceleration for the camera module in the frequency range of 0-500 Hz.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.273-280
• /
• 2007

This paper presents a new 3D sound toolkit called $EVE-Sound^{TM}$ that consists of pre-processing tool for environment simplification preserving sound effect and 3D sound API for real-time rendering. It is designed so that it can allow users to interact with complex 3D virtual environments by audio-visual modalities. $EVE-Sound^{TM}$ toolkit would serve two different types of users: high-level programmers who need an easy-to-use sound API for developing realistic 3D audio-visually rendered applications, and the researchers in 3D sound field who need to experiment with or develop new algorithms while not wanting to re-write all the required code from scratch. An interactive virtual environment application is created with the sound engine constructed using $EVE-Sound^{TM}$ toolkit, and it shows the real-time audio-visual rendering performance and the applicability of proposed $EVE-Sound^{TM}$ for building interactive applications with complex 3D environments.