• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.491-496
• /
• 2003

This paper proposes modeling of human behavior and a method of finding irregular human behavior. At first, human behavior model is proposed by paying attention to habitual human behavior at home. Generally, it is difficult to obtain the information of individual life pattern because of high cost for setting sensors such as cameras to observe human action. Therefore we capture turning on/off consumer electronic equipments as actual human behavior action, where some or many consumer electric equipments were used such as television, room light, video and so on in our daily life. Noting that are some relations between turning on/off those consumer electric equipments and our action, we proposes how to construct a human behavior knowledge by analyzing human behavior based on observation of human habitual life. Also an algorithm to identify on find irregular behavior different from habitual life behavior are described. Finally, the significance of the proposed method is shown by some experimental results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.93.4-93
• /
• 2001

Based on input and output data pairs of nonlinear systems, this paper proposes a simple and effective Just-In-Time (JIT) method, called Direct JIT Control, for nonlinear control design. It uses an inverse model of controlled plant to compute an initial control action, and then adapts the initial control action by adding a fine-tuning control action, depended on the errors between the real outputs and the expected reference signals. Meanwhile, the proposed JIT method accomplishes the adaptation of the inverse model just simply by means of the refreshment of input and output data pairs. In addition, the JIT modeling technique guarantees this method to obtain an approximate inverse model of the controlled nonlinear plant in the neighborhood of a query. Based on a ...

• The Journal of Advanced Prosthodontics
• /
• 제4권4호
• /
• pp.218-226
• /
• 2012

PURPOSE. The purpose of this study was to propose finite element (FE) modeling methods for predicting stress distributions on teeth and mandible under chewing action. MATERIALS AND METHODS. For FE model generation, CT images of skull were translated into 3D FE models, and static analysis was performed considering linear material behaviors and nonlinear geometrical effect. To find out proper boundary and loading conditions, parametric studies were performed with various areas and directions of restraints and loading. The loading directions are prescribed to be same as direction of masseter muscle, which was referred from anatomy chart and CT image. From the analysis, strain and stress distributions of teeth and mandible were obtained and compared with experimental data for model validation. RESULTS. As a result of FE analysis, the optimized boundary condition was chosen such that 8 teeth were fixed in all directions and condyloid process was fixed in all directions except for forward and backward directions. Also, fixing a part of mandible in a lateral direction, where medial pterygoid muscle was attached, gave the more proper analytical results. Loading was prescribed in a same direction as masseter muscle. The tendency of strain distributions between the teeth predicted from the proposed model were compared with experimental results and showed good agreements. CONCLUSION. This study proposes cost efficient FE modeling method for predicting stress distributions on teeth and mandible under chewing action. The proposed modeling method is validated with experimental data and can further be used to evaluate structural safety of dental prosthesis.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 춘계 학술대회 논문집
• /
• pp.31-35
• /
• 2001

Simulation --- The ideal tool for BPR. Work now and CASE tools are static modeling tools. Based on our own customers surveys, we have discovered that the use of process modeling tools thus far has focused on modeling the current(What-Is) state of a business. We have found that 90 percent of reengineering projects, the modeling tools of choice have been flowcharting tools. Static models offer help in understanding the overall nature of an existing process. However, static models can not really help you see the step by step motions towards completion of your goals. In static modeling, you see two pictures in time, usually taken at the current state and final state models of your reengineering project. Static models are usually not object oriented, therefore can not show facility or office layout and movement of entities and objects throughout the facility. However, this does not mean that static modeling does not have its application nor add value to the user as in a few success stories. Simulation helps the team analyze the complex aspects of the project. Many times a plan that looks good on paper might turn out entirely different when put into action. Therefore, simulation helps you look at how situations might work before actual implementation. In particular, computer simulation models help you view a reengineered condition before they are rolled-out. Items such as a lead time and resource allocation.

• Safety and Health at Work
• /
• 제14권4호
• /
• pp.425-430
• /
• 2023

Background: It is acknowledged that legislation acts as a motivator for organizational action on psychosocial risks. Our study aims to provide evidence on the relationship between key occupational safety and health (OSH) policy principles and organizational action on work-related stress, and, in turn, with reported employee job demands and resources and their experience of work-related stress. We focus on Italy where specific legislation and practices on work-related stress were introduced in 2008 which are underpinned by these key OSH policy principles. Methods: Secondary analysis of the Italian samples from the employer ESENER-2 and employee 6th EWCS surveys was conducted, using path analysis in structural equation modeling (SEM) linking the two datasets. Results: We found a strong statistically significant relationship between OSH policy principles and organizational action on work-related stress (C.I. = .62-.78 p < .001). The existence of an organizational action plan on work-related stress was found to be significantly associated with more reported job resources (C.I. = .02-.24, p < .05) but these were not found to be significantly associated with less work-related stress. No significant association was found between having an organizational action plan for work-related stress and reported job demands. However, job demands were significantly related to reported work-related stress (C.I. = .27-.47, p < .001). Conclusions: Findings add support to the call for specific legislation on work-related psychosocial risks and highlight how an organizational OSH culture underpinned by key OSH principles, and awareness/competence development on psychosocial risk management can have a positive effect on organizational action. However, further support needs to be provided to organizations around developing primary prevention interventions at the organizational level with the aim of reducing job demands.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.1017-1021
• /
• 1991

This paper is to explore the potential use of the modeling capacity of neural networks for control applications. The tasks are carried out by two neural networks which act as a plant identifier and a system controller, respectively. Using information stored in the identification network control action has been developed. Without supervising control signals are generated by a gradient type iterative algorithm.

• Journal of Computing Science and Engineering
• /
• 제9권1호
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.

• 제어로봇시스템학회논문지
• /
• 제16권10호
• /
• pp.957-962
• /
• 2010

If we want to recognize the human's emotion via the facial image, first of all, we need to extract the emotional features from the facial image by using a feature extraction algorithm. And we need to classify the emotional status by using pattern classification method. The AAM (Active Appearance Model) is a well-known method that can represent a non-rigid object, such as face, facial expression. The Bayesian Network is a probability based classifier that can represent the probabilistic relationships between a set of facial features. In this paper, our approach to facial feature extraction lies in the proposed feature extraction method based on combining AAM with FACS (Facial Action Coding System) for automatically modeling and extracting the facial emotional features. To recognize the facial emotion, we use the DBNs (Dynamic Bayesian Networks) for modeling and understanding the temporal phases of facial expressions in image sequences. The result of emotion recognition can be used to rehabilitate based on biofeedback for emotional disabled.

• 인터넷정보학회논문지
• /
• 제7권5호
• /
• pp.13-24
• /
• 2006

최근 상황인식 기술은 유비쿼터스 환경에서 중요한 이슈로 떠 오르고 있으며, 연구자들에 의해 많은 연구가 이루어 지고 있다. 상황인식 기술은 상황정보를 획득/가공하여 사용자에게 필요한 서비스와 정보를 제공하는 컴퓨터 시스템이다. 상황인식 시스템은 각종 센서로부터 발생하는 낮은 수준의 상황정보를 높은 수준의 상황정보로 변환하여 사용자에게 원하는 서비스를 제공하는 환경을 만들어 준다. 본 논문에서는 물리적인 스마트 공간에 존재하는 각종 센서로부터 얻어진 하위단계(Low level)의 Event driven 센서정보를 온톨로지 기반 상황정보로 모델링 하여 상위단계(High level) 상황정보로 변환하는 상황인식 모델링과 시스템을 제안한다. 또한 변환된 High level 상황정보는 가상공간에서 ECA(Event Condition, Action) 룰에 따라 사용자에게 언제 어디선지 사용자가 필요로 하는 능동적이고 지능적인 서비스를 제공하고, 스마트 오피스 환경에서 발표 도우미 서비스를 구현하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권3호
• /
• pp.170-177
• /
• 2010

Poker is a game of imperfect information where competing players must deal with multiple risk factors stemming from unknown information while making the best decision to win, and this makes it an interesting test-bed for artificial intelligence research. This paper introduces a new learning AI algorithm with embedded opponent modeling that can be used for these types of situations and we use this AI and apply it to a poker program. The new AI will be based on several graphs with each of its nodes representing inputs, and the algorithm will learn the optimal decision to make by updating the weight of the edges connecting these nodes and returning a probability for each action the graphs represent.