• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.444-447
• /
• 2022

In recent years, computer vision image classification tasks have become faster and better due to deeper neural network architectures. But while most image classification tasks are designed to classify images based on specific image features (such as distinguishing between cats and dogs), there are not many classification models that have been trained to distinguish between time periods such as day and night or different seasons of the year. And while some research has been done into distinguishing between seasons in images of the same location, this paper presents a varied approach to the problem of seasonal classification of generic images. Three methods for seasonal image classification, from simple feature extraction, to building a convolutional neural network, to transfer learning were studied and the accuracy results were compared and analyzed.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.05a
• /
• pp.139-144
• /
• 2002

계절변동조정방법인 X-12-ARIMA방법을 이용할 때에는 우리 실정에 적합한 옵션을 선택하고, 우리만에 특수한 명절과 조업일수영향을 사전에 조정해야한다. 본고에서는 명절과 조업일수영향을 측정하는 모형을 설정하고, 이것으로 추정된 사전조정요인을 원계열에서 제거했을 때 계절변동 및 계절변동조정계열의 안정성이 향상되었는가를 진단하고, 분류별로 적합한 X-12-ARIMA방법의 옵션을 제안하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.8
• /
• pp.3726-3734
• /
• 2012

This study evaluated the behavior of pollutants based on the seasonal change by selecting the branch river's factors that influence the outflow of pollutants in Soyang lake basin. The analysis method was the factor analysis that classified the factors of the drainage area influencing the outflow of pollutants, and evaluated selected representative factors. As a result of the study, SS and T-P factors should be classified as similar factors to the storm water runoff, and the improvement of water must be strived through managing source of pollution at the time of no rain. Second, as the result of the influence from the factors, spring and winter seasons usually exert 36% influence and summer and fall exert over 90% significant influence that the improvement of water through managing source of water seems possible. At last, the prediction about delivery pollution load considering the outflow characteristic of pollutants at the drainage area based on seasonal change by regarding selected factors as independent variables is possible.

• Ocean and Polar Research
• /
• v.32 no.4
• /
• pp.411-426
• /
• 2010

The seasonal variations in the zooplankton community of the southern coastal waters of Korea were investigated seasonally in May, August, November 2005, and February 2006. A total of 74 taxa were sampled, with an average abundance ranging from 2,426~23,793 indiv./$m^3$, among which Noctiluca scintillans predominated. Noctiluca scintillans, Acartia omorii, Acartia erythraea, Paracalanus parvus s. l., Centropages abdominalis, Tortanus forcipatus, and Pseudevadne tergestina were the most abundant species detected. Zooplankton diversity was high around the inner regions during the summer, but it was relatively low in the stations located in the outer regions in the autumn. Non-metric multidimensional scaling (nMDS) revealed significant differences in the structures of the zooplankton community among the three regions. Our results showed that the seasonal variations in zooplankton communities in the southern coastal waters of Korea were attributable to seasonal changes in temperature, salinity, chlorophyll a concentrations, and N. scintillans blooms; additionally, this particularly study area might have been specifically influenced by the appearance of the Tsushima Warm Current.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.94-97
• /
• 2009

연 및 계절강수량의 정확한 예보는 수자원관리에 매우 중요하다. 예보 정확도를 높이기 위한 다양한 연구가 계속 진행되어 왔다. 그럼에도 불구하고 강수자료가 가지는 매우 큰 불확실성 때문에 예보의 정확도 향상은 계속되는 숙제로 우리에게 남아 있다. 이를 개선하기 위하여 본 연구에서는 군집화 기법을 이용한 연 및 계절 강수량 예측개선에 대한 연구 결과를 제시하였다. 이를 위하여 연강수량, 계절강수량 및 월강수량의 예측을 위하여 전구에서 일어나는 각종 기후 인자들과의 상관성 분석은 대단히 중요하다. 전 세계적으로 어느 특정 지역에서의 선행 기후인자 변화 양상이 우리나라의 강수량에 높은 상관성을 가지며 영향을 미친다면 예측을 위한 매우 유용한 정보라 하겠으나 국내 강수량과 기후 지수 사이의 선형 상관성은 매우 낮을 뿐만 아니라 지체상관성도 특정 지체에서 매우 큰 상관성을 보이는 인자를 찾기 어려움을 알 수 있다. 이를 극복하기 위하여 본 연구에서는 k-mean clustering을 이용하여 우리나라 주변의 기후조건을 분류하고 기후조건에 따른 강수량의 변화를 분석하였다. 남중국해역($105^{\circ}E\;^{\sim}\;135^{\circ}E$, $0^{\circ}N\;^{\sim}\;35^{\circ}N$), 우리나라 연안 해역 ($110^{\circ}E\;^{\sim}\;150^{\circ}E$, $20^{\circ}N\;^{\sim}\;40^{\circ}N$), 인도양 해역 ($75^{\circ}E\;^{\sim}\;105^{\circ}E$, $0^{\circ}N\;^{\sim}\;25^{\circ}N$) 및 아라비아 해역 ($45^{\circ}E\;^{\sim}\;75^{\circ}E$, $0^{\circ}N\;^{\sim}\;30^{\circ}N$ 평균 해수면 온도 변화에 따라 8개 군집으로 분류한 분석결과로 분석결과 2008년도는 그룹 5에 해당하며 그룹 5의 기후 상태는 근해와 남중국해역의 평균 해수면 온도가 평년보다 낮고 인도양 해역과 아라비아 해역의 평균 해수면 온도는 평년값과 비슷한 상태를 나타낸다. 그룹 5에 해당하는 기후조건에서 차년의 강수평균은 평년값 보다 적음을 보였다. 이러한 특성은 전체 유역에 걸쳐 동일하게 나타났다. 이에 대한 계절적 평균 분포는 군집 5에 대한 차년도 강수의 평균 계절분포는 전체적으로 평년값보다 낮게 나타났다. 이에 근거하여 올해 연 평균 강수량은 평년값보다 적을 것이며 전체 계절에 대하여도 평년값보다 적은 강수량이 올 것으로 판단된다. 이는 기상청의 2009년 봄철 기후전망과 유사한 예측 결과를 보여준다.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.21 no.4
• /
• pp.144-157
• /
• 2016

The community structure of meiobenthos was investigated from seasonal surveys at four stations of Keunso Bay in Taean. Samples of meiobenthos were collected in August, October, 2013 and January, April, 2014. Triplicate faunal samples were collected by using an acryl corer with a 3.6 cm diameter at each station. The mean grain size of the study area ranged from 3.65 ø to 6.35 ø. Total 13 meiofaunal groups were found in the study area. The total density of meiobenthos at each station was be $1,521-7,849ind./10cm^2$. Nematodes were the most dominant faunal group at all stations. The subdominant group were Sarcomastigophorans and benthic harpacticoid copepods. The highest meiofaunal density was shown in spring, whereas the lowest density was recorded in summer. A total of 13 meiobenthic taxa were found, the richest taxa in October at station 2 ($13ind./10cm^2$), and the lowest in April at station 4 ($5ind./10cm^2$). There were seasonal fluctuations in the number of meiobenthic taxa decreasing from summer to spring. The density of meiobenthos gradually decreased as the depth of sediment increased. Seasonal changes in the vertical distribution of meiobenthos in the study area occurred mainly near the sediment surface.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.407-408
• /
• 2019

토지 피복과 관련된 지표면 파라미터는 일반적으로 지표에서 감지되어 위성영상에 나타난 많은 물리적 프로세스에 의존하며 계절적 주기성을 갖는 시간적 변화를 보인다. 하모닉 모형은 복잡한 파형을 정현파 성분의 합으로 표시함으로써 레벨, 주기, 진폭 및 위상 요소를 통한 변동을 분석함으로써 표면에서 관찰되는 계절적 변화 패턴을 모델링하는 데 적합한 모형이다. 본 연구에서는 MODIS NDVI (Normalized Difference Vegetation Index) 시계열 자료를 이용하여 하모닉 패턴의 특성에 따라 토지 피복을 분류하는 방법론을 제안하였다.

• Korean Journal of Environmental Biology
• /
• v.31 no.3
• /
• pp.192-203
• /
• 2013

To understand the seasonal changes in the zooplankton community, we investigated their occurrence patterns and environmental factors during four seasons at 9 stations along the coast of Geumo Archipelago, Yeosu. A total of 44 taxa were sampled, with an abundance ranging from 15~$28,183inds.\;m^{-3}$, among which Noctiluca scintillans predominented. Noctiluca scintillans, Paracalaus parvus s. l., Acartia (Acartiura) omorii, Oithona spp., Aidanosagitta crassa, dedapods larvae, copepods nauplii, and copepodites were the most abundant taxa detected. Species diversity of zooplankton was high in autumn and winter, but it was relatively low in summer and spring. Non-metric multidimensional scaling (nMDS) revealed significant differences in the structures of the zooplankton community among the seasons. Our results showed that the seasonal variation in zooplankton community along the coast of Guemo Archipelago, Yeosu were attributable to seasonal changes in temperature, salinity, and Chl. a concentration. Additionally, this particularly study area might have been specifically influenced by occurs of the neritic species.

• Korean Journal of Environment and Ecology
• /
• v.27 no.5
• /
• pp.529-543
• /
• 2013

In this study, Pteridophytes flora of Jirisan National Park were recorded 135 taxa, and they belong to 21 families, 39 genera, 123 species, 11 varieties and 1 forma. In the field, 38 taxa were not found on literature exists and 22 taxa were newly confirmed. The results obtained from this study were as follows: Deciduous (d), Evergreen (e) and Summer-deciduous (sd) were calculated as 50.0%, 46.3%, 2.2%, respectively and the Deciduous (d) has the highest value compared to the other leaf phenologies. It observed from the life-form spectra that Hemicryptophytes (H) was the most common dormancy form at 44.8%. Geophytes (G), Epiphytes (E), Hydatophytes (HH), Therophytes (Th) and Chamaephytes (Ch) were calculated at 26.1%, 10.5%, 4.5%, 0.8% and 13.4%, respectively.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.581-594
• /
• 2016

We introduce innovations state space exponential smoothing models (ISS-ESM) that can analyze time series with multiple seasonal patterns. Especially, in order to control complex structure existing in the multiple patterns, the model equations use a matrix consisting of seasonal updating parameters. It enables us to group the seasonal parameters according to their similarity. Because of the grouped parameters, we can accomplish the principle of parsimony. Further, the ISS-ESM can potentially accommodate any number of multiple seasonal patterns. The models are applied to predict electricity demand in Korea that is observed on hourly basis, and we compare their performance with that of the traditional exponential smoothing methods. It is observed that the ISS-ESM are superior to the traditional methods in terms of the prediction and the interpretability of seasonal patterns.