• ETRI Journal
• /
• 제33권4호
• /
• pp.569-579
• /
• 2011

This paper presents a novel approach for human activity recognition (HAR) using the joint angles from a 3D model of a human body. Unlike conventional approaches in which the joint angles are computed from inverse kinematic analysis of the optical marker positions captured with multiple cameras, our approach utilizes the body joint angles estimated directly from time-series activity images acquired with a single stereo camera by co-registering a 3D body model to the stereo information. The estimated joint-angle features are then mapped into codewords to generate discrete symbols for a hidden Markov model (HMM) of each activity. With these symbols, each activity is trained through the HMM, and later, all the trained HMMs are used for activity recognition. The performance of our joint-angle-based HAR has been compared to that of a conventional binary and depth silhouette-based HAR, producing significantly better results in the recognition rate, especially for the activities that are not discernible with the conventional approaches.

• 한국ITS학회 논문지
• /
• 제22권6호
• /
• pp.32-48
• /
• 2023

자율주행기술의 발달은 점차 개인화된 통행을 유도하며, 자율주행차량으로의 전환으로 인한 도로운영 측면에서 교통 영향력은 개인차량을 이용한 수요에 의해 가장 큰 영향력을 받는다. 따라서, 교통 영향력 검토를 위해서는 개인통행특성 이해를 기반한 통행발생량 산정이 필요하다. 개인 통행특성 반영이 가능한 Activity-based model(ABM)은 개인의 모든 이동을 다루므로 통행과 통행 사이의 관계에 대한 이해가 선행되어야 한다. 하지만, ABM은 실제 수요예측에서 데이터 구득문제와 같이 많은 한계점이 있다. 따라서, 본 연구에서는 가구통행실태조사자료를 기반으로 통행간 관계를 설명할 수 있는 Tour-based 모형을 활용하였다. 또한, 샘플조사 자료의 전수화를 위해 차량등록대수 및 인구수 데이터를 활용하여 개인차량발생량 보정방안을 제시하였다. 통행발생량 분석결과, KTDB와 비교하였을 때 본 연구에서 전체통행발생량은 약 13% 높았으며, 업무통행의 경우 약 9% 차이로 합리적인 오차수준으로 분석되었다. 결과적으로 본 연구의 궁극적인 목표인 도로운영 측면의 자율주행차량 도입에 따른 수요예측을 위해 Activity-based 모형 구축에 앞서 개인통행특성을 반영할 수 있는 Tour를 기반으로 발생량 보정방안으로 활용될 수 있다.

• 한국음향학회지
• /
• 제30권6호
• /
• pp.324-329
• /
• 2011

본 논문에서는 조건 사후 최대 확률 (conditional maximum a posteriori, CMAP)과 음성 스펙트럼 변이 조건을 기반으로 한 새로운 음성 검출기 (voice activity detection, VAD)를 제안한다. 제안된 음성 검출기는 통계적 모델을 기반으로 한 우도비 테스트 (likelihood ratio test, LRT)의 문턱값을 결정하는데 조건 사후 최대 확률과 스펙트럼 변이의 상태 값을 조건부 확률로 부과한다. 제안된 알고리즘을 다양한 잡음 환경에서 기존의 CMAP 기반의 음성 검출기와 비교한 결과 전체적으로 향상된 성능을 보였으며 특히 SNR이 낮은 조건에서 향상 폭이 컸다.

• 한국조경학회지
• /
• 제23권1호
• /
• pp.95-109
• /
• 1995

All human spatial behavior and psychological stress are affected by the 'Privacy'of each space. This Paper deals with the theoretical review of 'privacy'concept and establishment of 'Privacy Model' that can be a useful design tool. 'Privacy Index(Pl)' model of 10 point scale, which is based on 'Hierarchic system of Privacy' in urban spaces by Chermeyeff and Alexander(1963), was established as a hypothetical model in this study. And'Activity Suitability', based on each hierarchy of primacy level, was investigated at each site to construct the validity of 'Privacy Model'. Total 67 sites were investigated by on.-site questionnaire in 3 types of outdoor spaces, (Park), (Campus), and (Garden) respectively. The major results are as follows; 1. The P7rivacy level of earth spaces, distributed from to in and . and (Groun Private> spaces are dominant In , spaces are dondnant 2, Privacy level, based on , showed higher privacy level than that of . This means the criteria of each privacy level should be modified for more specific space. The . could be derived from the (Activity Suitability) of each space. 3.The cognition of privacy level. by user group, showed no significant difference in dach group by sex, age, education, and job, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• 한국환경교육학회지:환경교육
• /
• 제19권2호
• /
• pp.96-107
• /
• 2006

Inquiry has great value in environmental education(EE). Being able to see the world environmentally through 'inquiry-based environmental education' can be an important value and goal of EE. In this study, we intended to develop an EE program of measuring activity of dissolved oxygen(DO), based on the theory of 'inquiry-based EE'. Especially, we recognized the potential that DO meter can be used in 'inquiry-based EE', and we tried to develop a model of inquiry-based EE using DO meter. As a result of this research, we present specific models of inquiry-based EE about how to perform measuring activity of DO and how to use the DO meter in laboratories and streams from the perspective of inquiry of water environment. In the process of program development, we considered organization of the inquiry process, use of concept and knowledge, scientific inquiry and insightful inquiry, integration, sustain-ability, content components of 'Environmental Studies for EE', developmental level and in-forest of students. The developed EE model is a scientific inquiry model, pursuing 'explanation' based on data collection. Through this model, we tried to make students see water environment more deeply. The developed program can be applied to various water environments, like laboratories, streams, ponds, etc. It can be more effective inquiry activity if we perform measuring activities simultaneously with PH, electrical conductivity, and turbidity meters.

• 한국도서관정보학회지
• /
• 제54권1호
• /
• pp.167-190
• /
• 2023

본 연구는 활동이론을 이론적 틀로 활용하여 연구데이터 큐레이션 모델을 분석한 문헌 연구로, 활동이론에서 사용하는 활동의 구성 요소들을 바탕으로 여러 연구데이터 큐레이션 모델을 분석했을 뿐만 아니라 연구데이터 큐레이션 활동을 수행하는데 있어서 도서관계에서 논의가 필요한 현안을 분석하였다. 그리고 이를 기반으로 새로운 연구데이터 큐레이션 개념 모델을 제안하였다. 본 연구는 기존에 제안된 5개의 디지털 큐레이션 생애주기모델이 어떻게 구성되어 있는지 분석하고 각각의 모델에서 산발적으로 제시되는 활동요인들을 분석하여 공통요인을 추출하고 새로운 모델로 통합하여 새로운 연구데이터 큐레이션 개념 모델을 제안하였다. 또한, 도서관 및 리포지토리에서 연구데이터 큐레이션 활동을 수행함에 있어서 고려해야 할 6가지의 현안들을 분석하고 논의하였다. 본 연구에서 제안되는 연구데이터 큐레이션 개념 모델은 총 10단계로 이루어져 있으며, 각 활동의 단계에서 고려해야 할 실천적 문제와 모순을 포함하고 있다.

• Bulletin of the Korean Chemical Society
• /
• 제27권10호
• /
• pp.1531-1536
• /
• 2006

Microsomal prostaglandin $E_2$ synthase (mPGES-1) is an enzyme that is associated with inflammation, pain, fever and cancer. Hologram quantitative structure activity relationship (HQSAR) was conducted on the series of MK-886 compounds acting as mPGES-1 inhibitors. A training set with 24 compounds was used to establish the HQSAR model. The best model was chosen based on the cross-validated correlation coefficient ($q^2$=0.884) and the correlation coefficient($r^2$=0.976). The model was utilized to predict the activity of the eight-test set of compounds giving the predictive $r^2$ value of 0.845. The descriptors of the model are based on fragment distinction (atoms, bond and connectivity) and fragment size (2-5 atoms). The atomic contribution maps generated from HQSAR were useful in identifying the important structural features responsible for the inhibitory activity of MK-886 inhibitors. Based on the generated model, the presence of hydrophobic biphenyl group seems to enhance inhibition of mPGES-1 that is in agreement with the previous experiments. In addition, it seems important for a halogen to be substituted to the biphenyl ring and for an acyl group to be attached to the indole moiety for enhanced activity.

• International Journal of Advanced Culture Technology
• /
• 제9권1호
• /
• pp.210-217
• /
• 2021

In the case of an agile-based project, it was inadequate to perform a comprehensive inspection and evaluation on the establishment and operation of an information system by performing audit only with the audit and inspection elements provided by the existing information system audit and inspection system. In particular, in the case of the test activity area, it was necessary to improve the test activity audit check items to comprehensively check the agile-based development process by applying the existing audit system. To this end, a test activity improvement check model of the agile methodology audit model was presented by applying the repetition concept, a characteristic of the agile methodology. In order to empirically verify the model of this study, a survey was conducted for auditors and designers/developers who have experience in performing agile-based projects and auditing information systems. As a result of the questionnaire on the integrated test and system test in the test stage, more than 70% of the respondents were found to be suitable. More than 80% of the respondents judged that it was appropriate as a result of the questionnaire on "improvement and regression test progress according to integrated test and system test results" and "integrated test and functional actions of components and subsystems".

• 지역연구
• /
• 제10권2호
• /
• pp.61-71
• /
• 1994

Despite of being the criteria to choose the efficient and reasonable alternatioves inactual planning process, the measure of accessibility rarely has applied to practices because each model has unexplicity concept of it and limitations in itself. Accessibility implies transportation system which offers opportunity of movement to overcome spatial separation and, simultaneously, land-use system which represents the location of each activity. Therefore, measures of accessibility have to represent the attractiveness of locations and the interactions of activities, that is, land-use and transportation, with an index. Considering that urban activity is based on the economic efficiency, costs and benfits, accessibility means the economic efficiency of the location of activity and the travel in view of land-use and transport repectively. Combined models that measure accessibility with considering land-use and tranportation simultaneously depend on reasonable concepts, but it is too simple for them to explain the accessibility which resulted from complex interaction of urban activities. Combined urban activity model developed by Kim (1983) and Rho (1989) explains the characteristics of activities in each regions and urban strcture in economic general equilibrium states in the long term of urban system. This model measures a regional accessibility with a dual variable which means the location surplus. This is a more systematic and comprehensive model for calculating the regional accessibility because it considers the interaction of each activity in urban system. It needs efforts to apply the accessibility index as a criterion in actual planning process through finding and quantitification of other explanatory variables to measure it in combined urban activity model.