• ETRI Journal
• /
• v.39 no.5
• /
• pp.643-651
• /
• 2017

Human age estimation is one of the key factors in the field of Human-Robot Interaction/Human-Computer Interaction (HRI/HCI). Owing to the development of deep-learning technologies, age recognition has recently been attempted. In general, however, deep learning techniques require a large-scale database, and for age learning with variations, a conventional database is insufficient. For this reason, we propose an age estimation method using artificially generated data. Image data are artificially generated through 3D information, thus solving the problem of shortage of training data, and helping with the training of the deep-learning technique. Augmentation using 3D has advantages over 2D because it creates new images with more information. We use a deep architecture as a pre-trained model, and improve the estimation capacity using artificially augmented training images. The deep architecture can outperform traditional estimation methods, and the improved method showed increased reliability. We have achieved state-of-the-art performance using the proposed method in the Morph-II dataset and have proven that the proposed method can be used effectively using the Adience dataset.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.11
• /
• pp.1034-1037
• /
• 2015

In recent years in the field of robotics, various methods have been developed to create an intimate relationship between people and robots. These methods include speech, vision, and biometrics recognition as well as gesture-based interaction. These recognition technologies are used in various wearable devices, smartphones and other electric devices for convenience. Among these technologies, gesture recognition is the most commonly used and appropriate technology for wearable devices. Gesture recognition can be classified as contact or noncontact gesture recognition. This paper proposes contact gesture recognition with IMU and EMG sensors by using the hidden Markov model (HMM) twice. Several simple behaviors make main gestures through the one-stage HMM. It is equal to the Hidden Markov model process, which is well known for pattern recognition. Additionally, the sequence of the main gestures, which comes from the one-stage HMM, creates some higher-order gestures through the two-stage HMM. In this way, more natural and intelligent gestures can be implemented through simple gestures. This advanced process can play a larger role in gesture recognition-based UX for many wearable and smart devices.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.3
• /
• pp.652-669
• /
• 2014

This paper concerns the kinematic characteristics of a coupling device in a deep-seabed mining system. This coupling device connects the buffer system and the flexible pipe. The motion of the buffer system, flexible pipe and mining robot are affected by the coupling device. So the coupling device should be considered as a major factor when this device is designed. Therefore, we find a stable kinematic device, and apply it to the design coupling device through this study. The kinematic characteristics of the coupling device are analyzed by multi-body dynamics simulation method, and finite element method. The dynamic analysis model was built in the commercial software DAFUL. The Fluid Structure Interaction (FSI) method is applied to build the deep-seabed environment. Hydrodynamic force and moment are applied in the dynamic model for the FSI method. The loads and deformation of flexible pipe are estimated for analysis results of the kinematic characteristics.

• Journal of the Society of Naval Architects of Korea
• /
• v.46 no.6
• /
• pp.659-666
• /
• 2009

Recently, there are several problems in space, contiguity and facility of the existing harbors issued due to the trend of enlarging the container capacity of the large container vessel, the Mobile Harbor has been proposed conceptually as an effective solution for those problems. This concept is a kind of transfer loader of the containers from the large container ship, which is a floating barge with a catamaran type in the underwater part, and so prompt maneuverability and work effectiveness. For the safe mooring of two floating bodies, a container and the mobile harbor, in the near sea apart from the quay, a robot arm mooring facility specially devised would be designed and verified through comparison study under various environmental sea condition in the inner and outer harbor. DP system (Dynamic Positioning System) using the azimuth thruster and a pneumatic fender, etc, will be considered as a next research topic for the mooring security of multi-body floaters.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.5
• /
• pp.581-587
• /
• 2021

In recent years, contamination of drinking water sources has emerged as a serious social problem, such as a large number of impurities in tap water or groundwater or the supply of suitable water due to rust of pipes. Although the government and public institutions are implementing various measures to protect water sources, they cannot improve water quality in a short period of time because of the enormous cost involved. Therefore, in recent years, preference has been given to a device that converts tap water, which is hard water, into soft water by installing a separate water softener at the faucet from which tap water is discharged. However, the existing filtration device has a problem that filtration performance is gradually lowered when impurities accumulate in the filter, requiring continuous filter replacement. In this study, the optimal design of the filter housing was performed to develop a water softener that can be washed when impurities accumulate on the filter inside the water softener connected to the faucet. For optimal design of the filter housing, fluid and fluid-structural interaction analysis were performed on the design pressure to determine the shape and thickness of the housing, and design review was performed through prototype.

• Journal of Distribution Science
• /
• v.22 no.2
• /
• pp.103-113
• /
• 2024

Purpose: With the popularity of artificial intelligence (AI) in the service industry and occurrence ofservice failures in AI-based services, understanding human-robot interaction issues in service failure situations is especially important. Some issues which deserve further empirical investigation are whether consumers can develop the same tolerance for chatbots after service failure as they have for human agents, and the relationship between agent type and tolerance is mediated by the mechanisms of perceived warmth and perceived competence. Research Design, Data, and Methodology: This research experimentally collected and analyzed data from 119 university students who had experienced chatbots service failures. Differences in tolerance towards human agents and chatbots after experiencing service failures were explored, with a further examination of the mediating pathways between this relationship via perceived warmth and perceived competence. Results: Consumers are more tolerant ofservice failure with chatbots compared to service failure with human agents. Significant mediation of the relationship between service agent and service failure tolerance by perceived competence, while perceived warmth has no significant mediating effect. Conclusions: This research enhances our understanding of AI-assisted services, human-computer interaction, improves the service functionality of existing smart devices, and deepens the understanding of the relationship between consumer responses and behaviors.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.750-757
• /
• 2020

One of the basic tasks for robots to interact with humans is to quickly and accurately grasp human behavior. Therefore, it is necessary to increase the accuracy of human pose recognition when the robot is estimating the human pose and to recognize it as quickly as possible. However, when the human pose is estimated using deep learning, which is a representative method of artificial intelligence technology, recognition accuracy and speed are not satisfied at the same time. Therefore, it is common to select one of a top-down method that has high inference accuracy or a bottom-up method that has high processing speed. In this paper, we propose two methods that complement the disadvantages while including both the advantages of the two methods mentioned above. The first is to perform parallel inference on the server using multi GPU, and the second is to mix bottom-up and One-class Classification. As a result of the experiment, both of the methods presented in this paper showed improvement in speed. If these two methods are applied to the entertainment robot, it is expected that a highly reliable interaction with the audience can be performed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.611-618
• /
• 2020

In this paper, we propose a design and implementation method of speed quiz content that can be driven by a social robot capable of interacting with humans, and a method of developing an intelligent module necessary for implementation. In addition, we propose a method of implementing speed quiz content through the process of constructing a map by arranging and connecting intelligent module blocks. Recently, software education has become mandatory and interest in programming is increasing. However, programming is difficult for students without basic knowledge of programming languages to directly access, and interest in block-type programming platforms suitable for beginners is growing. The block-type programming platform used in this paper is a platform that supports immediate and intuitive programming by supporting interactions between humans and robots. In this paper, the intelligent module implemented for the speed quiz content was used by blocking it within a block-type programming platform. In order to implement the scenario of the speed quiz content proposed in this paper, we implement a total of three image-based artificial intelligence modules. In addition to the intelligent module, various functional blocks were placed to implement the speed quiz content. In this paper, we propose a method of designing a speed quiz content scenario and a method of implementing an intelligent module for speed quiz content.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.201-204
• /
• 2013

디지털 컨텐츠의 종류와 양이 폭발적으로 증가하면서 컨텐츠 선호도 투표는 강한 파급력을 지니게 되었다. 하지만 컨텐츠 소비자가 직접 투표를 해야 하는 현재의 방법은 사람들의 투표 참여율이 저조하며, 조작 위험성이 높다는 문제점이 있다. 이에 본 논문에서는 컨텐츠 소비자의 얼굴 표정에 드러나는 감정을 인식함으로써 자동으로 컨텐츠 선호도를 추론하는 시스템을 제안한다. 본 논문에서 제안하는 시스템은 기존의 수동 컨텐츠 선호도 투표 시스템의 문제점인 컨텐츠 소비자의 부담감과 번거로움, 조작 위험성 등을 해소함으로써 보다 편리하고 효율적이며 신뢰도 높은 서비스를 제공하는 것을 목표로 한다. 따라서 본 논문에서는 컨텐츠 선호도 추론 시스템을 구축하기 위한 방법을 구체적으로 제안하고, 실험을 통하여 제안하는 시스템의 실용성과 효율성을 보인다.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.555-558
• /
• 2006

감정을 포함하고 있는 음성은 청자로 하여금 화자의 심리상태를 파악할 수 있게 하는 요소 중에 하나이다. 음성신호에 포함되어 있는 감정을 인식하여 사람과 로봇과의 원활한 감성적 상호작용을 위하여 특징을 추출하고 감정을 분류한 방법을 제시한다. 음성신호로부터 음향정보 및 운율정보인 기본 특징들을 추출하고 이로부터 계산된 통계치를 갖는 특징벡터를 입력으로 support vector machine (SVM) 기반의 패턴분류기를 사용하여 6가지의 감정- 화남(angry), 지루함(bored), 기쁨(happy), 중립(neutral), 슬픔(sad) 그리고 놀람(surprised)으로 분류한다. SVM에 의한 인식실험을 한 경우 51.4%의 인식률을 보였고 사람의 판단에 의한 경우는 60.4%의 인식률을 보였다. 또한 화자가 판단한 감정 데이터베이스의 감정들을 다수의 청자가 판단한 감정 상태로 변경한 입력을 SVM에 의해서 감정을 분류한 결과가 51.2% 정확도로 감정인식하기 위해 사용한 기본 특징들이 유효함을 알 수 있다.