• 대한산업공학회지
• /
• 제33권4호
• /
• pp.402-409
• /
• 2007

Markov Chains has proven to be effective in predicting human behaviors in the areas of web site assess, multimedia educational system, and driving environment. In order to extend an application area of predicting human behaviors using Markov Chains, this study was conducted to investigate whether Markov Chains could be used to predict human behavior in selecting mobile phone menu item. Compared to the aforementioned application areas, this study has different aspects in using Markov Chains : m-order 1-step Markov Model and the concept of Power Law of Learning. The results showed that human behaviors in predicting mobile phone menu selection were well fitted into with m-order 1-step Markov Model and Power Law of Learning in allocating history path vector weights. In other words, prediction of mobile phone menu selection with Markov Chains was capable of user's actual menu selection.

• 한국의상디자인학회지
• /
• 제21권4호
• /
• pp.195-211
• /
• 2019

In this paper, Capstone Design Education Program Learning Model was developed and recommended in order to foster convergent talents armed with practical competences and real cooperative capabilities. In this era of convergence and creativity, the fashion world needs human resources with cooperative skills and true professional abilities. A case analysis, an in-depth interview, and 1,2 test method were used for data acquisition and analysis. The summary of this study is described below. First, this program needs to complement the NCS fashion design learning module. Second, material changes to creativity and practical competencies - knowledge, skills, and attitudes - of the students are assessed after applying Capstone Design to the NCS fashion design learning model. Third, the process of converging fashion curriculum with IT and electronic technology, developing a fashion design learning program, and applying the Capstone Design was tested to prove the effectiveness of convergent fashion design education. Among the changes observed between the trial and control groups, it was confirmed that sub-factors of creative personality, i.e. self-assurance and openness, were increased along with knowledge, core competences including communication capability, and self-directed learning capability. The greatest improvement on the technological side was observed in IT literacy while ability to respond to changes was also increased. Besides, effects were demonstrated in behavioral factors such as initiative, spirit of challenge, experience, and openness. Lastly, the Capstone Design Education Program Learning Model was proposed in order to foster convergent talents in the fashion world.

• 사상체질의학회지
• /
• 제20권3호
• /
• pp.1-13
• /
• 2008

1. Objectives This study was purposed to find Dong's thoughts about the eight items of the "The Great Learning(Ta hsueh)" 2. Methods It was researched through comparative and overall study on the Dong-mu's thoughts in "Gyukchigo(格致藁)" 3. Results (1) Dongmu reinterpreted the eight items of the "The Great Learning(Ta hsueh)" as the relations between the subject and the object from the ontologic assumption of Affairs Mind Body Objects as the principle of existence and correlation, summarized into four categories, and classified into the individual and subjective affairs, and the universal and objective affairs. The four categories of the eight items of the "The Great Learning(Ta hsueh)" are correlated with the individual and the universal ethics of behavior, and connected with the element for overcoming the individual inclination of mind and wickedness. (2) After the individual and subjective human was established, the eight items of the "The Great Learning(Ta hsueh)" were classified into two categories, and coupled up with each two items('Being sincere in their thoughts' with 'Extending to the utmost their knowledge', 'Rectifying their hearts' with 'Investigating things', 'Cultivating their persons' with 'Illustrating illustrious virtue throughout the kingdom', 'Regulating their families' with 'Ordering their own states'). Being based on this, 'Being sincere in their thoughts', 'Rectifying their hearts', 'Cultivating their persons' and 'Regulating their families' were understood as four individual and subjective human-basic-essential activity. Especially, mind, heart, body and family(power) were regarded as the four basic element in human existence and activity, and in correlation with universe and society, set up as the subjective element in Dongmu's epistemology, theory of nature and emotion, theory of morality and theory of moral cultivation.

• 한국철학논집
• /
• 제56호
• /
• pp.151-180
• /
• 2018

유가사상가들이 도덕과 지식의 측면에서 최고의 이상적 인간형으로 설정한 성인(聖人)은 "선천적으로 신비한 능력을 타고나는 것인가, 아니면 후천적으로 노력을 통해 그런 경지에 도달할 수 있는가?" 이 문제에 대해 논리적 정합성을 제시하는 것이야 말로 맹자 이후 유학자들의 주요 이슈였으며, 많은 사상가들은 이 문제에 대해 다양한 답변을 시도해 왔다. 일반적으로 성인은 선천적으로 타고난다는 입장과 배움(學)과 지식(知)들 통해서 성인의 경지에 이를 수 있다는 입장의 두 가지 학설이 존재한다. 유학은 어떤 학문 체계 보다 인간의 배움과 지식을 중요시한다. 사실 "논어"의 주요 내용에서 우리는 윤리 도덕적 가치의 집합인 인(仁)에 관한 대화보다 공자가 꾸준히 강조하고 제자들을 칭찬하는 용어인 배움(學)에 대한 표현이 더 많이 등장하고 있음을 확인하기도 한다. 유학 사상사적인 측면에서 볼 때 배움과 지식을 통해 성인이 될 수 있다는 견해는 공자 이후 맹자와 순자에 이르기 까지 절대적 지지를 받는 학설로 여겨진 것으로 보인다. 그러나 한당시대에 이르러 인간의 내면에 대한 세분화된 견해를 정립하는 것을 시도하게 되는데, 한유와 왕충 등의 사상가들은 '성인은 이미 선천적으로 결정된 것이지, 인간의 노력으로 도달할 수 없다'는 견해를 피력하였다. 그리고 다시 송대 성리학 시기 정이천은 이 문제에 대해 깊이 있는 논의를 제시하고, 치밀하고 자세한 설명구조를 확립하는데, 즉 선진시대 사상가들의 견해를 계승하여 '배움과 지식을 통해 그리고 인간의 노력으로 성인이 될 수 있다'는 사유를 제시한다. 성인에 대한 이런 이해 방식은 송대 성리학의 주류를 형성하게 되었으며, 주자 이후 유학사상의 핵심이론으로 자리매김하게 된다. 이 글은 유학의 기본 테제라 할 수 있는 성인과 관련된 문제에 대한 정이(程?, 1033-1107)의 사유를 정리한 것이다. 그는 기본적으로 '성인가학이지(聖人可學而至)' 즉, 배움을 통해 聖人에 도달할 수 있다는 견해를 피력하고 있으며, 이와 관련하여 태어나면서 성인인 경지에 대한 표현법인 생지(生知)와 배움과 지식을 통해 성인에 도달할 수 있다는 입장의 학지(學知), 최상의 지혜(上智)와 최악의 어리석음(下愚) 등의 용어들에 대해 구체적이고 깊이 있는 논의를 제공하고 있다. 논자는 이글에서 논제와 관련된 문제(안연, 자질과 성품의 문제, 지혜와 어리석음의 관계) 등에 대해 주로 정이천의 "유서(遺書)"의 "안자소호하학론(顔子所好何學論)"과 기타 논저 그리고 유학사상 관련 텍스트를 중심으로 성인론의 특징을 고찰하였다. 정이천이 인간은 누구나 성인이 될 수 있다는 견해를 논리와 방법론을 정립하면서 제시한 그의 학설은 송대 성리학의 주요 과제로 자리 잡게 되었으며, 주자학의 주요체계로 포함되어 오늘날 정통의 이론으로 평가받고 있다.

• 지식경영연구
• /
• 제24권4호
• /
• pp.219-235
• /
• 2023

디지털 기술의 발전과 코로나19의 영향으로 기업의 혁신과 조직문화가 변화하고 있으며, HRD(Human Resource Development) 분야에서 스마트 러닝의 중요성이 부각되고 있다. 본 연구에서는 HRD 담당자의 관점에서 스마트 러닝을 구성하는 요인들의 상대적인 중요성을 밝히는 것을 목적으로 하였다. 선행 문헌 검토를 통해 현 상황에 가장 부합하는 스마트 러닝 계층 및 요인을 도출하고, AHP 방법을 활용하여 해당 요인의 상대적 중요도를 파악하였다. 결과적으로 1계층 요인에서는 '학습 활동', '교육 활동', '학습 콘텐츠', '평가 방법 및 평가', '학습 시간 및 공간' 순으로 중요도가 확인 되었다. 2계층 전체 요인에서는 '교육 전략', '학습 결과', '학습 과업', '학습 목표', '학습 지원'이 상위 5위에 나타나는 요인으로 확인되었다. 본 연구 결과는 스마트 러닝 개념을 재정립하고, 추후 연구를 위한 학술적 프레임워크를 제안한 점에서 의의를 가진다. 또한, 실무적으로는 HRD 담당자들이 스마트 러닝을 개선하고 향상시키기 위해 어떤 요인에 주력해야 하는지에 대한 유용한 정보를 제공하는데 기여할 것으로 기대된다.

• 한국인터넷방송통신학회논문지
• /
• 제22권5호
• /
• pp.177-183
• /
• 2022

최근 COVID-19로 인해 홈 트레이닝의 관심도가 증가하고 있다. 이에 따라 HAR(human activity recognition) 기술을 홈 트레이닝에 적용한 연구가 진행되고 있다. 기존 HAR 분야의 논문에서는 동적인 자세보다는 앉기, 일어서기와 같은 정적인 자세들을 분석한다. 본 논문은 동적인 운동 자세를 분석하여 사용자의 운동 자세 정확도를 보여주는 딥러닝 모델을 제안한다. AI hub의 피트니스 이미지를 blaze pose를 사용하여 사람의 자세 데이터를 분석한다. 3개의 딥러닝 모델: RNN(recurrnet neural networks), LSTM(long short-term memory networks), CNN(convolution neural networks)에 대하여 실험을 진행한다. RNN, LSTM, CNN 모델의 f1-score는 각각 0.49, 0.87, 0.98로 CNN 모델이 가장 적합하다는 것을 확인하였다. 이후 연구로는, 다양한 학습 데이터를 사용하여 더 많은 운동 자세를 분석할 예정이다.

• 인터넷정보학회논문지
• /
• 제21권4호
• /
• pp.127-135
• /
• 2020

The purpose of this study is to develop a human activity recognition (HAR) system, which distinguishes 13 activities, including five activities commonly dealt with in conventional HAR researches and eight activities from the Eastern-Asian culture. The eight special activities include floor-sitting/standing, chair-sitting/standing, floor-lying/up, and bed-lying/up. We used a 3-axis accelerometer sensor on the wrist for data collection and designed a machine learning model for the activity classification. Data clustering through preprocessing and feature extraction/reduction is performed. We then tested six machine learning algorithms for recognition accuracy comparison. As a result, we have achieved an average accuracy of 99.7% for the 13 activities. This result is far better than the average accuracy of current HAR researches based on a smartwatch (89.4%). The superiority of the HAR system developed in this study is proven because we have achieved 98.7% accuracy with publically available 'pamap2' dataset of 12 activities, whose conventionally met the best accuracy is 96.6%.

• 로봇학회논문지
• /
• 제8권1호
• /
• pp.20-28
• /
• 2013

Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.

• ETRI Journal
• /
• 제39권5호
• /
• 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.

• 한국안전학회지
• /
• 제37권2호
• /
• pp.97-105
• /
• 2022

Human casualties from fires are increasing worldwide. The majority of human deaths occur during the evacuation process, as occupants panic and are unaware of the location of the fire and evacuation routes. Using an Internet of Things (IoT) sensor and reinforcement learning, we propose a method to find the safest evacuation route by considering the fire location, flame speed, occupant position, and walking conditions. The first step is detecting the fire with IoT-based devices. The second step is identifying the occupant's position via a beacon connected to the occupant's mobile phone. In the third step, the collected information, flame speed, and walking conditions are input into the reinforcement learning model to derive the optimal evacuation route. This study makes it possible to provide the safest evacuation route for individual occupants in real time. This study is expected to reduce human casualties caused by fires.