• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.27-39
• /
• 2018

Since the global positioning system (GPS) has been included in mobile devices (e.g., for car navigation, in smartphones, and in smart watches), the impact of personal GPS log data on daily life has been unprecedented. For example, such log data have been used to solve public problems, such as mass transit traffic patterns, finding optimum travelers' routes, and determining prospective business zones. However, a real-time analysis technique for GPS log data has been unattainable due to theoretical limitations. We introduced a machine learning model in order to resolve the limitation. In this paper presents a new, three-stage real-time prediction model for a person's daily route activity. In the first stage, a machine learning-based clustering algorithm is adopted for place detection. The training data set was a personal GPS tracking history. In the second stage, prediction of a new person's transient mode is studied. In the third stage, to represent the person's activity on those daily routes, inference rules are applied.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.781-785
• /
• 2016

Learning from human behaviors in the real world is essential for human-aware intelligent systems such as smart assistants and autonomous robots. Most of research focuses on correlations between sensory patterns and a label for each activity. However, human activity is a combination of several event contexts and is a narrative story in and of itself. We propose a novel approach of human activity prediction based on event cognition. Egocentric multi-sensor data are collected from an individual's daily life by using a wearable device and smartphone. Event contexts about location, scene and activities are then recognized, and finally the users" daily activities are predicted from a decision rule based on the event contexts. The proposed method has been evaluated on a wearable sensor data collected from the real world over 2 weeks by 2 people. Experimental results showed improved recognition accuracies when using the proposed method comparing to results directly using sensory features.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2010.05a
• /
• pp.1389-1390
• /
• 2010

• Journal of Nutrition and Health
• /
• v.45 no.6
• /
• pp.511-521
• /
• 2012

The purposes of this study were to assess the physical activity level (PAL) and the total daily energy expenditure (TEE) as well as to evaluate the validity of prediction equation for the estimated energy requirement (EER) in normal weight and overweight or obese children and adolescents. The subjects comprised of 100 healthy Korean students aged between 7-18. The anthropometric data was collected. PAL was calculated from the physical activity diary by the 24-hour recall method, and the resting metabolic rate (RMR) was measured by an open-circuit indirect calorimetry using a ventilated hood system. Daily energy expenditure was PAL multiplied by RMR. EER was calculated by using the prediction equation published in KDRIs. There was no significant difference in the means of age and height between the 46 obese subjects and 54 nonobese subjects. The weight and BMI of the obese group (60.2 kg, $25.3kg/m^2$) were significantly higher than those of the nonobese group (42.4 kg, $18.4kg/m^2$). However, PAL was not significantly different between the two groups (nonobese 1.45, obese 1.46). TEE of the obese group (2,212 kcal/day) was significantly higher than that of the nonobese group (1,774 kcal/day). EER (individual PA) and EER (light PA) were significantly higher than TEE (p < 0,001); however, EER (sedentary PA) was not significantly different with TEE in the two groups. These results showed that the levels of physical activity were the same as the sedentary activity both in the nonobese and obese Korean students; moreover, the predictive equation for EER published in KDRI overestimated the TEE of Korean children and adolescents. Therefore, in further research, a new predictive equation for EER should be developed for Korean children and adolescents through the doubly labeled water method.

• Korean Journal of Poultry Science
• /
• v.23 no.2
• /
• pp.85-98
• /
• 1996

Results of experiments on the nutrient requirements and feeding system of broiler breeder hens were reviewed, and daily requirements of energy and protein were calculated using the prediction equations reported by Scott(1977) and NRC(1981). The experimental reports on daily ME needs of broiler breeder hens were ranged from 400 to 450 kcal, however, the ME needs of caged hens were 92~93% to those of floor-housed hens due to the difference of ME need for activity. The ME needs of broiler breeders decreased with increasing environmental temperature corresponding to a drop of 25 kcal per day for each 5˚C rise. About 80~90% of the daily ME needs were used for body rnaintenance and activity of hens. Experimental results on daily protein needs of broiler breeder hens were ranged from 18 to 22 g, however, calculated protein needs decreased as the BW gain and eggmass output decreased after peak production, and about 60~65% of the daily protein needs were used for egg production. In the current practice, broiler breeder hens are restricted in feed, and consume their daily allowance in the first 2 to 6 h after dawn. The results suggest that eggshell quality can be significantly improved in hens fed during the afternoon when shell calcification is initiated, with no adverse effect on laying rate and fertility of eggs.

• Journal of muscle and joint health
• /
• v.5 no.1
• /
• pp.83-109
• /
• 1998

This study was carried out to identify the Important modifiable risk factors for reduced bone mass and to construct prediction model which can classify women with either low or high bone mass. Through the literature review, individual characteristics such as age, body weight, height, education level, family history, age of menarche, postmenopausal period, gravity, parity, menopausal status, and breast feeding period were identified and factors of life style such as past milk consumption, past physical activity, present daily activity, present calcium intake, alcohol intake, cigarette smoking, coffee consumption were identified as influencing factors of reduced bone mass in women. Four hundred and eighty women aged between 28 and 76 who had given measurement bone mineral density by dual energy x-ray absortiometry in lumbar vertebrae and femur from July to October, 1997 at 4 general hospitals in Seoul and Pusan were selected for this study. Women were excluded if they had a history of any chronic illness such as rheumatoid arthritis, diabetes mellitus, hyperthroidism, & gastrointestinal disorder and any medication such as calcium supplements, calcitonin, estrogen, thyroxine, antacids, & corticosteroids known affect bone. As a result of these exclusion criteria, four hundred and seventeen women were used for analysis. Multiple logistic regression model was developed for estimating the likelihood of the presence or absence of reduced bone mass. A SAS procedure was used to estimate risk factor coefficient. The results are as follows For lumbar spine, the variables significant were age, body weight, menopause status, daily activity, past milk consumption, and past physical activity(p<0.01), while for femoral Ward's triangle, age, body weight, level of education, past milk consumption, past physical activity(p<0.001). Past physical activity, present daily activity and past milk consumption are the most powerful modifiable predictors in vertebrae and femur among the predictors. When the model performance was evaluated by comparing the observed outcome with predicted outcome, the model correctly identified 74.1% of persons with reduced bone mass and 84.5% of persons with normal bone mass in the lumbar vertebrae and 82.9% of persons with reduced bone mass and 75.0% of persons with normal bone mass in the femoral Ward's triangle. On the basis of these results, a number of recommendations for the management of reduced bone mass may be made : First, those woman who are classified as high risk group of the reduced bone mass in the prediction model should examine the bone mineral density to further examine the usefulness of this model. Second, the optimal amount of milk consumption and a regular weight bearing exercise in childhood, adolescence, and early adult should be ensured.

• Journal of Korean Academy of Nursing
• /
• v.43 no.1
• /
• pp.1-10
• /
• 2013

Purpose: The purpose of this study was to develop a prediction model for the characteristics of older adults with depression using the decision tree method. Methods: A large dataset from the 2008 Korean Elderly Survey was used and data of 14,970 elderly people were analyzed. Target variable was depression and 53 input variables were general characteristics, family & social relationship, economic status, health status, health behavior, functional status, leisure & social activity, quality of life, and living environment. Data were analyzed by decision tree analysis, a data mining technique using SPSS Window 19.0 and Clementine 12.0 programs. Results: The decision trees were classified into five different rules to define the characteristics of older adults with depression. Classification & Regression Tree (C&RT) showed the best prediction with an accuracy of 80.81% among data mining models. Factors in the rules were life satisfaction, nutritional status, daily activity difficulty due to pain, functional limitation for basic or instrumental daily activities, number of chronic diseases and daily activity difficulty due to disease. Conclusion: The different rules classified by the decision tree model in this study should contribute as baseline data for discovering informative knowledge and developing interventions tailored to these individual characteristics.

• Journal of Korean Academy of Nursing
• /
• v.46 no.5
• /
• pp.663-674
• /
• 2016

Purpose: The purposes of this study were to develop and test a prediction model for caregiving experiences including caregiving satisfaction and burden in dementia family caregivers. Methods: The stress process model and a two factor model were used as the conceptual frameworks. Secondary data analysis was done with 320 family caregivers who were selected from the Seoul Dementia Management Survey (2014) data set. In the hypothesis model, the exogenous variable was patient symptomatology which included cognitive impairment, behavioral problems, dependency in activity of daily living and in instrumental activity of daily living. Endogenous variables were caregiver's perception of dementia patient's unmet needs, caregiving satisfaction and caregiving burden. Data were analysed using SPSS/WINdows and AMOS program. Results: Caregiving burden was explained by patient symptomatology and caregiving satisfaction indicating significant direct effects and significant indirect effect from unmet needs. The proposed model explained 37.8% of the variance. Caregiving satisfaction was explained by patient symptomatology and unmet needs. Mediating effect of unmet needs was significant in the relationship between patient symptomatology and caregiving satisfaction. Conclusion: Results indicate that interventions focusing on relieving caregiving burden and enhancing caregiver satisfaction should be provided to caregivers with high levels of dementia patients' unmet needs and low level of caregiving satisfaction.

• Advances in Computational Design
• /
• v.4 no.2
• /
• pp.73-90
• /
• 2019

The growth in the number of single-member households is a critical issue worldwide, especially among the elderly. For those living alone, who may be unaware of their health status or routines that could improve their health, a continuous healthcare monitoring system could provide valuable feedback. Assessing the performance adequacy of activities of daily living (ADL) can serve as a measure of an individual's health status; previous research has focused on determining a person's daily activities and extracting the most frequently performed behavioral patterns using camera recordings or wearable sensing techniques. However, existing methods used to extract common patterns of an occupant's activities in the home fail to address the spatio-temporal dimensions of human activities simultaneously. Though multiple sequence alignment (MSA) offers some advantages - such as inherent containment of the spatio-temporal data in sequence format, and rapid identification of hidden patterns - MSA has rarely been used to extract in-home ADL routines. This research proposes a method to extract a household occupant's ADL routines from a cumulative spatio-temporal data log of occupancy collected using a non-intrusive method (i.e., a tomographic motion detection system). The findings from an occupant's 28-day spatio-temporal activity log demonstrate the capacity of the proposed approach to identify routine patterns of an occupant's daily activities and to reveal the order, duration, and frequency of routine activities. Routine ADL patterns identified from the proposed approach are expected to provide a basis for detecting/evaluating abrupt or gradual changes of an occupant's ADL patterns that result from a physical or mental disorder, and can offer valuable information for home automation applications by enabling the prediction of ADL patterns.

• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.98-105
• /
• 2021

As the average life expectancy is rising, the population is aging and the number of chronic diseases is increasing. This has increased the importance of healthy life and health management, and interest in mobile health services is on the rise thanks to the development of ICT(Information and communication technologies) and the smartphone use expansion. In order to meet these interests, many mobile services related to daily health are being launched in the market. Therefore, in this study, the characteristics of users who actually use mobile health services were analyzed and a predictive model applied with machine learning modeling was developed. As a result of the study, we developed a prediction model to which the decision tree and ensemble methods were applied. And it was found that the mobile health service users' continued use can be induced by providing features that require frequent visit, suggesting achievable activity missions, and guiding the sensor connection for user's activity measurement.