• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.177-179
• /
• 2021

This paper proposes a method of estimating location of a target point at which an interactive robot gazes in an indoor space. RGB images are extracted from low-cost web-cams, user head pose is obtained from the face detection (Openface) module, and geometric configurations are applied to estimate the user's gaze direction in the 3D space. The coordinates of the target point at which the user stares are finally measured through the correlation between the estimated gaze direction and the plane on the table plane.

• Journal of Research and Publication Ethics
• /
• v.4 no.1
• /
• pp.23-29
• /
• 2023

Purpose: While prior research has identified ethical issues in marketing research, more research needs to identify specific ethical behaviors that marketing researchers should adopt. This research addresses this gap by identifying a few ethical behaviors that marketing researchers should consider. Research design, data and methodology: The present study has a justification to collect adequate textual data in the current literature using screening process based on the marketing ethics topics and themes, and ethical behaviors of marketing researchers. Results: Based on the literature analysis, a marketing ethics model, which included the principles of fairness, honesty, responsibility, and respect for stakeholders. Since the rise of e-commerce and technology, a growing demand for a method to analyze website user behavior has been growing. Researchers in the field of marketing are responding to this demand by creating innovative interactive platforms. Conclusions: The term "ethical practices in market research" refers to a collection of best practices that, when followed, increase the likelihood that the research carries out is ethical, fair, and accurate. Because there needs to be more theoretical work done on the topic, there should be more empirical studies on ethical behaviors in marketing research.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.680-683
• /
• 2022

본 논문은 가상 환경에서 사용자 및 로봇이 손을 이용하여 직관적으로 가상 물체와 상호작용하도록 하는 파지 방법을 제안한다. 제안한 방법은 사람 손과 로봇 손의 구조적인 차이를 고려하여 사람과 로봇에게 범용적으로 적용할 수 있도록 물리적 상호작용이 가능한 입자를 가상 손에 붙이고, 이를 이용하여 가상 물체를 파지하는 방법이다. 제안한 파지 방법을 사람과 로봇에 적용하여 실험한 결과, 임의의 다양한 물체를 직관적으로 파지할 수 있었고 높은 성공률을 보였다.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.573-577
• /
• 2015

Safety is paramount for construction industry throughout the world. Human errors which contribute to more than half of construction accidents, could be proactively prevented through effective education and training methods. Although Virtual Reality (VR) and Augmented Reality (AR) have gained much attention in various disciplines, few studies applied them for construction safety education. This research presents a new approach in construction safety education by utilizing VR and AR. The vision of aligning teaching & learning strategies is examined in order to ensure the potential benefits of the new method. This innovative approach shifts safety education from "Listen, and I will forget. See, and I may remember" towards "Practice, and I understand".

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.752-753
• /
• 2023

본 논문에서는 손가락 관절의 운동범위와 MediaPipe 손 추적기를 이용하여 3 차원 손 추적 방법을 설계하였다. MediaPipe 손 추적기가 추정한 신뢰할 수 있는 2 차원 좌표를 바탕으로 손 랜드마크의 깊이를 추정한 후, 손가락 관절 운동범위와 부합한 결과를 도출하였다. 본 논문에서 제안한 3 차원 손 추적 방법은 전용 하드웨어 없이 동작하며 기존의 3 차원 손 추적기에 비해 보다 직관적인 인간-컴퓨터 인터페이스 확산에 긍정적 영향을 줄 것으로 기대한다.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.360-374
• /
• 2024

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a low-dimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources.

• International journal of advanced smart convergence
• /
• v.13 no.3
• /
• pp.191-198
• /
• 2024

This paper presents an alternative solution for applying MetaHuman facial animations using MediaPipe, providing a versatile option to the Live Link iPhone system. Our approach involves capturing facial expressions with various camera devices, including webcams, laptop cameras, and Android phones, processing the data for landmark detection, and applying these landmarks in Unreal Engine Blueprint to animate MetaHuman characters in real-time. Techniques such as the Eye Aspect Ratio (EAR) for blink detection and the One Euro Filter for data smoothing ensure accurate and responsive animations. Experimental results demonstrate that our system provides a cost-effective and flexible alternative for iPhone non-users, enhancing the accessibility of advanced facial capture technology for applications in digital media and interactive environments. This research offers a practical and adaptable method for real-time facial animation, with future improvements aimed at integrating more sophisticated emotion detection features.

• Journal of Information Processing Systems
• /
• v.7 no.3
• /
• pp.459-472
• /
• 2011

The vast number of biomedical literature is an important source of biomedical interaction information discovery. However, it is complicated to obtain interaction information from them because most of them are not easily readable by machine. In this paper, we present a method for extracting biomedical interaction information assuming that the biomedical Named Entities (NEs) are already identified. The proposed method labels all possible pairs of given biomedical NEs as INTERACTION or NO-INTERACTION by using a Maximum Entropy (ME) classifier. The features used for the classifier are obtained by applying various NLP techniques such as POS tagging, base phrase recognition, parsing and predicate-argument recognition. Especially, specific verb predicates (activate, inhibit, diminish and etc.) and their biomedical NE arguments are very useful features for identifying interactive NE pairs. Based on this, we devised a twostep method: 1) an interaction verb extraction step to find biomedically salient verbs, and 2) an argument relation identification step to generate partial predicate-argument structures between extracted interaction verbs and their NE arguments. In the experiments, we analyzed how much each applied NLP technique improves the performance. The proposed method can be completely improved by more than 2% compared to the baseline method. The use of external contextual features, which are obtained from outside of NEs, is crucial for the performance improvement. We also compare the performance of the proposed method against the co-occurrence-based and the rule-based methods. The result demonstrates that the proposed method considerably improves the performance.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.52 no.6
• /
• pp.307-315
• /
• 2003

This paper proposes a novel simulation method of WPGS (Wind Power Generation System). The rotation speed control method of turbine under variable wind speed using the pitch control is proposed. Moreover, when wind speed exceeds the cut-out wind speed, the turbine will be stopped by controlling pitch angle to 90$^{\circ}$, otherwise it will be controlled to steady-state operation. For the purpose of effective simulation, the SWRW (Simulation method for WPGS using Real Weather condition) is used for the utility interactive WPGS simulation in this paper, in which those of three topics for the WPGS simulation: user-friendly method, applicability to grid-connection and the utilization of the real weather conditions, are satisfied. It is impossible to consider the real weather conditions in the WPGS simulation using the EMTP type of simulators and PSPICE, etc. External parameter of the real weather conditions is necessary to ensure the simulation accuracy. The simulation of the WPGS using the real weather conditions including components modeling of wind turbine system is achieved by introducing the interface method of a non-linear external parameter and FORTRAN using PSCAD/EMTDC in this paper. The simulation of long-term, short-term, over cut-out and under cut-out wind speeds will be peformed by the proposed simulation method effectively. The efficiency of wind power generator, power converter and flow of energy are analyzed by wind speed of the long-term simulation. The generator output and current supplied into utility can be obtained by the short-term simulation. Finally, transient-state of the WPGS can be analyzed by the simulation results of over cut-out and under cut-out wind speeds, respectively.

• Korean Journal of Computational Design and Engineering
• /
• v.15 no.2
• /
• pp.85-93
• /
• 2010

This paper proposes a CAE data translation and visualization technique that can verify time-varying continuous analysis simulation in a virtual reality (VR) environment. In previous research, the use of CAE analysis data has been problematic because of the lack of any interactive simulation controls for visualizing continuous simulation data. Moreover, the research on post-processing methods for real-time verification of CAE analysis data has not been sufficient. We therefore propose a scene graph based visualization method and a post-processing method for supporting interoperability of continuous CAE analysis data. These methods can continuously visualize static analysis data independently of any timeline; it can also continuously visualize dynamic analysis data that varies in relation to the timeline. The visualization system for continuous simulation data, which includes a CAE middleware that interfaces with various formats of CAE analysis data as well as functions for visualizing continuous simulation data and operational functions, enables users to verify simulation results with more realistic scenes. We also use the system to do a performance evaluation with regard to the visualization of continuous simulation data.