• Journal of Environmental Science International
• /
• v.30 no.10
• /
• pp.811-820
• /
• 2021

The population variation of Spanish mackerel (Scomberomorus niphonius) according to its major prey abundance was analyzed using monthly catches of coastal set net fisheries in the southern waters off Gyeongsangnam-do and eastern waters off Gyeongsangbuk-do of Korea from 2006 to 2019. The abundance of Spanish mackerel and its prey species fluctuated almost simultaneously with time lags of +2 to -2 months between the set net fisheries in the southern and eastern waters. The generalized additive model revealed that the abundance of Spanish mackerel was influenced by its prey species such as hairtail and anchovy in southern waters, and common mackerel and horse mackerel in eastern waters. The model deviance explained 49% and 42% of Spanish mackerel abundance in southern and eastern waters respectively. These results suggest that the abundance of Spanish mackerel is affected by seasonal migratory prey fish species in the coastal areas and can be linked to their northerly migration.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.4
• /
• pp.59-64
• /
• 2008

We need to use the strength of each Species Distribution Model(SDM) because presence location data were only collected due to time and economic limitations in Korea. This study investigated and compared GAM(Generalized Additive Model) which is one of presence-absence models with Maxent(Maximum Entropy Model) which is one of presence only models according to location data(presence/absence data). The target species was Fisher(Martes pennanti) which is an endangered species in California, USA. We implemented environmental data such as topography, climate and vegetation, and applied models to sub-regions and study area. The results of this study were as follows. Firstly, GAM which used real presence and absence data was better than GAM which used pseudo-absence data and Maxent which used presence-only data. Secondly, Maxent was better than GAM when presence-only data were used. Lastly, each model which applied to different regions didn't predict other area well due to the difference of habitat environment and over-predicted outside of study area. We need to select an optimal model to predict a suitable habitat according to the type and distribution of location data.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.5D
• /
• pp.649-654
• /
• 2008

In the definition of non additive path, the sum of travel costs of links making up the path is not equal to the path cost. There are a variety of cases that non-additivity assumption does not hold in transportation fields. Nonetheless, traffic equilibrium models are generally built up on the fundamental hypothesis of additivity assumption. In this case traffic equilibrium models are only applicable within restrictive conditions of the path cost being linear functions of link cost. Area-wide road pricing is known as an example of realistic transportation situations, which violates such additivity assumption. Because travel fare is charged at the moment of driver's passing by exit gate while identified at entry gate, it may not be added linearly proportional to link costs. This research proposes a novel Wordrop type of traffic equilibrium model in terms of area-wide road pricing schemes. It introduces binary indicator variable for the sake of transforming non-additive path cost to additive. Since conventional shortest path and Frank-Wolfe algorithm can be applied without route enumeration and network representation is not required, it can be recognized more generalized model compared to the pre-proposed approaches. Theoretical proofs and case studies are demonstrated.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1215-1224
• /
• 2016

Climate information of the high resolution grid units is an important factor to explain the phenomenon in a variety of research field. Statistical linear interpolation models are computationally inexpensive and applicable to any climate data compared to the dynamic simulation method at regional scales. In this paper, we considered four different linear-based statistical interpolation models: general linear model, generalized additive model, spatial linear regression model, and Bayesian spatial linear regression model. The climate variable of interest was the daily mean temperature, where the spatial variability was explained using geographic terrain information: latitude, longitude, elevation. The data were collected by weather stations in January from 2003 and 2012. In the sense of RMSE and correlation coefficient, Bayesian spatial linear regression model showed better performance in reflecting the spatial pattern compared to the other models.

• Journal of the Korean Geographical Society
• /
• v.51 no.2
• /
• pp.219-233
• /
• 2016

In social science fields, statistical models are used almost exclusively for causal explanation, and explanatory modeling has been a mainstream until now. In contrast, predictive modeling has been rare in the fields. Hence, we focus on constructing the predictive non-parametric model, instead of the explanatory model. Gangnam-gu, Seoul was chosen as a study area and we collected single-family house sales data sold between 2011 and 2014. We applied non-parametric models proposed in machine learning area including generalized additive model(GAM), random forest, multivariate adaptive regression splines(MARS) and support vector machines(SVM). Models developed recently such as MARS and SVM were found to be superior in predictive power for house price estimation. Finally, spatial autocorrelation was accounted for in the non-parametric models additionally, and the result showed that their predictive power was enhanced further. We hope that this study will prompt methodology for property price estimation to be extended from traditional parametric models into non-parametric ones.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.510-517
• /
• 2016

Recent developments in the field of separation of mixed signals into music/voice components have attracted the attention of many researchers. Recently, iterative kernel back-fitting, also known as kernel additive modeling, was proposed to achieve good results for music/voice separation. To obtain minimum mean square error (MMSE) estimates of short-time Fourier transforms of sources, generalized spatial Wiener filtering (GW) is typically used. In this paper, we propose an advanced music/voice separation method that utilizes a generalized weighted ${\beta}$-order MMSE estimation (WbE) based on iterative kernel back-fitting (KBF). In the proposed method, WbE is used for the step of mixed music signal separation, while KBF permits kernel spectrogram model fitting at each iteration. Experimental results show that the proposed method achieves better separation performance than GW and existing Bayesian estimators.

• Journal of the Korean Geographical Society
• /
• v.51 no.2
• /
• pp.201-217
• /
• 2016

We accessed the climate change effects on the distributions of warm-evergreen broad-leaved trees (shorten to warm-evergreens below) in the Korean Peninsula (KP). For this, we first selected nine warm-evergreens with the northern distribution limits at mid-coastal areas of KP and climate variables, coldest month mean temperature and coldest quarter precipitation, known to be important for warm-evergreens growth and survival. Next, species distribution models (SDMs) were constructed with generalized additive model (GAM) algorithm for each warm-evergreen. SDMs projected the potential geographical distributions of warm evergreens under current and future climate conditions in associations with land uses. The nine species were categorized into three groups (mid-coastal, southwest-coastal, and southeast-inland) based on their current spatial patterns. The effects of climate change and land uses on the distributions depend on the current spatial patterns. As considering land uses, the potential current habitats of all warm-evergreens decrease over 60%, showing the highest reduction rate for the Kyungsang-inland group. SDMs forecasted the expansion of potential habitats for all warm-evergreens under climate changes projected for 2050 and 2070. However, the expansion patterns were different among three groups. The spatial patterns of projected coldest quarter precipitation in 2050 and 2070 could account for such differences.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.257-262
• /
• 1996

When we are estimate the smoothing parameter in spline regression model, we deal the diagnostic of influence observations as posteriori analysis. When we use Generalized Maximum Likelihood Function as the estimation method of smoothing parameter, we propose the diagnostic measure for influencial observations in the obtained estimate, and we introduce the finding method of the proper smoothing parameter estimate.

• Journal of Environmental Science International
• /
• v.11 no.10
• /
• pp.1061-1068
• /
• 2002

To identify possible associations with concentrations of ambient air pollutants and daily mortality in Busan, this study assessed the effects of air pollution for the time period 1999-2000. Poisson regression analysis by Generalized Additive Model were conducted considering trend, season, meteorology, and day-of-the-week as confounders in a nonparametric approach. Busan had a 10% increase in mortality in persons aged 65 and older(95% Cl : 1.01-1.10) in association with IQR in $NO_2$(lagged 2 days). An increase of $NO_2$(lagged 2days) was associated with a 4% increase in respiratory mortality(Cl : 1.02-1.11) and CO(lagged 1 day) showed a 3% increase(Cl : 1.00-1.07).

• Journal of Animal Science and Technology
• /
• v.52 no.6
• /
• pp.467-473
• /
• 2010

A total of 4,323,781 records for informal 16 primary linear descriptive traits of dairy cows in Holstein breed from 1988 to 2007 in USA were analyzed to estimate adjustment factors for lactation number and stage. While all factors in the model were highly significant (P < 0.01), major influences on linear type traits were due to lactation number and stage. The frequencies of lactation number 1 through 6 were 58.6, 22.0, 11.8, 4.8, 2.1, and 0.8%, respectively. Further, the frequencies of lactation stage were 0.7, 76.9, 15.3, 4.9, and 2.1%, respectively, for springing, early, medium, late, and dry. To adjust 16 linear traits (stature, dairy form, strength, body depth, rump width, rump angle, legs rear view, leg set, foot angle, fore udder, rear udder height, rear udder width, udder support, udder depth, and front teat placement), additive and multiplicative adjustment factors of lactation number (lactations 2 to 4) and stage (springing, medium, late and dry) were estimated with the solutions in the generalized linear model, assigning lactation 1 and stage early as base class. Additive adjustment factors of lactation number ranged from -1.23 to 2.908, while multiplicative factors ranged from 0.853 to 2.207. Further, additive and multiplicative adjustment factors for lactation stage ranged from -0.668 to 0.785, and from 0.891 to 1.154. Application of adjustment factors to 20 randomly sampled sub-data sets produced the results that additive adjustment factors for both lactation number and stage reduced more mean square of lactation number and stage over 16 linear traits than any combination of adjustments, and leaded additive adjustment factors for both lactation number and stage as a choice of methods for adjustment of informal 16 primary linear type traits collected by classifiers of AI studs.