• Imaging Science in Dentistry
• /
• v.49 no.1
• /
• pp.19-26
• /
• 2019

Purpose: It has been proposed that using new prediction methods, such as neural networks based on dental data, could improve age estimation. This study aimed to assess the possibility of exploiting neural networks for estimating age by means of the pulp-to-tooth ratio in canines as a non-destructive, non-expensive, and accurate method. In addition, the predictive performance of neural networks was compared with that of a linear regression model. Materials and Methods: Three hundred subjects whose age ranged from 14 to 60 years and were well distributed among various age groups were included in the study. Two statistical software programs, SPSS 21 (IBM Corp., Armonk, NY, USA) and R, were used for statistical analyses. Results: The results indicated that the neural network model generally performed better than the regression model for estimation of age with pulp-to-tooth ratio data. The prediction errors of the developed neural network model were acceptable, with a root mean square error (RMSE) of 4.40 years and a mean absolute error (MAE) of 4.12 years for the unseen dataset. The prediction errors of the regression model were higher than those of the neural network, with an RMSE of 10.26 years and a MAE of 8.17 years for the test dataset. Conclusion: The neural network method showed relatively acceptable performance, with an MAE of 4.12 years. The application of neural networks creates new opportunities to obtain more accurate estimations of age in forensic research.

• Journal of Veterinary Clinics
• /
• v.14 no.2
• /
• pp.287-296
• /
• 1997

Serial ultrasonographic examinations were daily performed on 8 bitches (5 Maltese and 3 Yorkshire terrier) from day 15 until parturition to determine the size of gestational structures. Gestational age was timed from the day of ovulation (day 0), which was estimated to occur when plasma progesterone concentration was first increased above 4.0 ng/ml. When the size of fetal and extra-fetal structures according to gestational age was measured, there was a difference between Maltese and Yorkshire terrier in extra-fetal structures (P<0.001), and no difference in fetal structrures (P<0.001). The correlations between the gestational age and the growth in fetal and extra-fetal structures were examined by regression analysis. The extra-fetal structure which showed high correlation from day 20 to 35 was inner chorionic cavity diameter in two breeds. The fetal structures which showed high correlation from day 36 until parturition was fetal head diameter in two breeds. In conclusions inner chorionic cavity diameter was the most accurate for estimation of gestational age and prediction of whelping day from day 20 to 35, and fetal head diameter from day 36 to parturitions respectively. Ultrasonography is very useful tool to evaluate the gestational age and to predict the whelping day in pet dogs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.483-486
• /
• 2020

Age estimation and gender classification for human is a classic problem in computer vision. Almost research focus just only one task and the models are too heavy to run on low-cost system. In our research, we aim to apply multitasking learning to perform both task on a lightweight model which can achieve good precision on embedded system in the real time.

• Journal of Environmental Science International
• /
• v.10 no.3
• /
• pp.173-178
• /
• 2001

The aim of this paper is to evaluate users benefit values of theme park using Travel Cost Method with special reference to Woobang Tower Land in Taegu for the estimation of economic values. This research is mainly based on questionnaire survey of 100 users of the theme park. Socio-economic factors such as income, year of education, annual income, age and money(travel cost) are analysed from 5 residential areas of the respondents. Multiple regression analysis was used for the evaluation of annual number of park visitings based on the analysis. The regression model shows NV = $\alpha$+$\beta_1$TC+$\beta_2$INC+$\beta_3$EDU+$\beta_4$AGE (NV : Annual Number of Visitings, TC : Travel Cost, INC : Annual Income, EDU : Years of Education, AGE : Age). Regarding to visitors demand curve based on the equation showed that annual economic values of Woobang Tower Land was estimated as 50billion Korean Won.

• Journal of Environmental Science International
• /
• v.27 no.7
• /
• pp.555-560
• /
• 2018

This study conducted to analyze the growth characteristics of old Prunus yedoensis on Jeju island. The diameter growth per year was measured using a DTRS-2000 instrument. The DBH, ground DBH and height of the investigated P. yedoensis were 137 cm, 143 cm, and 15.5 m, respectively. Our analysis showed that the age of the old P. yedoensis was 93 years. An annual diameter growth of $2.85mm{\pm}0.96$ was observed. The result of age estimation, about $265{\pm}64$ years in P. yedoensis on Jeju island. This information could be useful to understand the annual diameter growth characteristics the P. yedoensis distributed on Jeju island.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.987-998
• /
• 2016

Auto insurance is an insurance product that requires the proper application of pricing techniques due to intense market competition and the rate regulations of financial authorities. Especially, population change according to aging and rating faction segmentation mainly affect the pricing process. This study suggests a pricing optimization methodology through the proper estimation of age factors. To properly estimate the future distribution of age factor, age change, renewal and conversion of customers are considered as main effects for the optimization of estimation and application. The properness and effectiveness for the suggested method will be proved by a comparison of results applied (one for current distribution and the other for future distribution) at the off-balance process. This study suggests an appropriate risk estimation methodology based on optimization that uses the proper estimation of future distribution to protect from the over or under estimation of risk.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.3
• /
• pp.376-383
• /
• 2012

A number of scientific researches are currently being conducted on the potential health hazards of power frequency electric and magnetic field (EMF). There exists a non-objective and psychological belief that they are harmful, although no scientific and objective proof of such exists. This possible health risk from ELF magnetic field (MF) exposure, especially for children under 17 years of age, is currently one of Korea's most highly contested social issues. Therefore, to assess the magnetic field exposure levels of those children in their general living environments, the personal MF exposure levels of 436 subjects were measured for about 6 years using government funding. Using the measured database, estimation formulas were developed to predict personal MF exposure levels. These formulas can serve as valuable tools in estimating 24-hour personal MF exposure levels without directly measuring the exposure. Three types of estimation formulas were developed by applying evolutionary computation methods such as genetic algorithm (GA) and genetic programming (GP). After tuning the database, the final three formulas with the smallest estimation error were selected, where the target estimation error was approximately 0.03 ${\mu}T$. The seven parameters of each of these three formulas are gender (G), age (A), house type (H), house size (HS), distance between the subject's residence and a power line (RD), power line voltage class (KV), and the usage conditions of electric appliances (RULE).

• Journal of Veterinary Clinics
• /
• v.25 no.6
• /
• pp.501-505
• /
• 2008

Serial ultrasonographic examinations were performed on 9 Miniature Schnauzer bitches from day 15 of gestation until parturition to determine the ultrasonographic measurement of gestational structures. Ovulation was designated the day that plasma progesterone concentration exceeded 4.0 ng/ml (day 0). Extra-fetal structures were measured from day 17 or 18 to 60. Outer uterine diameter (OUD) increased from $6.50{\pm}1.06mm$ ($Mean{\pm}SD$) to $50.89{\pm}5.62mm$, inner chorionic cavity diameter (ICCD) increased from $2.10{\pm}0.15mm$ to $37.15{\pm}4.36mm$, and length of placenta (PL) increased from $7.50 {\pm}1.41mm$ to $40.62{\pm}3.27mm$. OUD and ICCD were significantly and linearly relative to gestational age especially through day 37, whereas PL was not significantly relative to gestational age. Of the extra-fetal structures, ICCD was the most accurate for estimation of gestational age before day 38 of gestation. Fetal structures increased at a linear rate to parturition. Fetal crown-rump length (CRL) increased from $2.55{\pm}0.07mm$ on day 22 to $85.25{\pm}9.89mm$ on day 48. Fetal head diameter (HD) increased from $3.43{\pm}0.64mm$ on day 27 to $25.06{\pm}0.41mm$ on day 63. Fetal body diameter (BD) increased from $ 5.96{\pm}0.84mm$ on day 30 to $43.76{\pm}3.36mm$ on day 63. Of the fetal structures, HD was the most accurate for estimation of gestational age after day 38 to parturition.

• Korean Journal of Exercise Nutrition
• /
• v.24 no.1
• /
• pp.9-13
• /
• 2020

[Purpose] This preliminary study aimed to develop a regression model to estimate the resting metabolic rate (RMR) of young and middle-aged Koreans using various easy-to-measure dependent variables. [Methods] The RMR and the dependent variables for its estimation (e.g. age, height, body mass index, fat-free mass; FFM, fat mass, % body fat, systolic blood pressure, diastolic blood pressure, mean arterial pressure, pulse pressure, and resting heart rate) were measured in 53 young (male n = 18, female n = 16) and middle-aged (male n = 5, female n = 14) healthy adults. Statistical analysis was performed to develop an RMR estimation regression model using the stepwise regression method. [Results] We confirmed that FFM and age were important variables in both the regression models based on the regression coefficients. Mean explanatory power of RMR₁ regression models estimated only by FFM was 66.7% (R²) and 66.0% (adjusted R²), while mean standard errors of estimates (SEE) was 219.85 kcal/day. Additionally, mean explanatory power of RMR₂ regression models developed by FFM and age were 70.0% (R²) and 68.8% (adjusted R²), while the mean SEE was 210.64 kcal/day. There was no significant difference between the measured RMR by the canopy method using a metabolic gas analyzer and the predicted RMR by RMR₁ and RMR₂ equations. [Conclusion] This preliminary study developed a regression model to estimate the RMR of young and middle-age healthy Koreans. The regression model was as follows: RMR₁ = 24.383 × FFM + 634.310, RMR₂ = 23.691 × FFM - 5.745 × age + 852.341.

• Journal of the Korea Institute of Building Construction
• /
• v.12 no.1
• /
• pp.87-97
• /
• 2012

This paper presents a method of estimating the setting time of cement mortar incorporating recycled aggregate powder (RP) and cement kiln dust (CKD) at various curing temperatures by applying an equivalent age method. To estimate setting time, the equivalent age using apparent activation energy (Ea) was applied. Increasing RP and CKD leads to a shortened initial and final set. Ea at the initial set and final set obtained by Arrhenius function showed differences in response to mixture type. These were estimated to be from 10~19 KJ/mol in all mixtures, which is smaller than those of conventional mixture ranging from 30~50 KJ/mol. Based on the application of Ea to Freisleben Hansen and Pederson's equivalent age function, equivalent age is nearly constant, regardless of curing temperature and RP contents. This implies that the concept of maturity is applicable in estimating the setting time of concrete containing RP and CKD. A high correlation was observed between estimated setting time and measured setting time. A multiregression model was provided to determine setting time reflecting RP and CKD. Thus, the setting time estimation method studied herein can be applicable to concrete incorporating RP and CKD in the construction field.