ARIMA 모델을 이용한 항공운임예측에 관한 연구

서상석,박종우,송광석,조승균 한국유통과학회 2014 유통과학연구 Vol.12 No.2

Purpose – In recent years, many firms have attempted various approaches to cope with the continual increase of aviation transportation. The previous research into freight charge forecasting models has focused on regression analyses using a few influence factors to calculate the future price. However, these approaches have limitations that make them difficult to apply into practice: They cannot respond promptly to small price changes and their predictive power is relatively low. Therefore, the current study proposes a freight charge–forecasting model using time series data instead a regression approach. The main purposes of this study can thus be summarized as follows. First, a proper model for freight charge using the autoregressive integrated moving average (ARIMA) model, which is mainly used for time series forecast, is presented. Second, a modified ARIMA model for freight charge prediction and the standard process of determining freight charge based on the model is presented. Third, a straightforward freight charge prediction model for practitioners to apply and utilize is presented. Research design, data, and methodology – To develop a new freight charge model, this study proposes the ARIMAC(p,q) model, which applies time difference constantly to address the correlation coefficient (autocorrelation function and partial autocorrelation function) problem as it appears in the ARIMA(p,q) model and materialize an error-adjusted ARIMAC(p,q). Cargo Account Settlement Systems (CASS) data from the International Air Transport Association (IATA) are used to predict the air freight charge. In the modeling, freight charge data for 72 months (from January 2006 to December 2011) are used for the training set, and a prediction interval of 23 months (from January 2012 to November 2013) is used for the validation set. The freight charge from November 2012 to November 2013 is predicted for three routes – Los Angeles, Miami, and Vienna – and the accuracy of the prediction interval is analyzed using mean absolute percentage error (MAPE). Results – The result of the proposed model shows better accuracy of prediction because the MAPE of the error-adjusted ARIMAC model is 10% and the MAPE of ARIMAC is 11.2% for the L.A. route. For the Miami route, the proposed model also shows slightly better accuracy in that the MAPE of the error-adjusted ARIMAC model is 3.5%, while that of ARIMAC is 3.7%. However, for the Vienna route, the accuracy of ARIMAC is better because the MAPE of ARIMAC is 14.5% and the MAPE of the error-adjusted ARIMAC model is 15.7%. Conclusions – The accuracy of the error-adjusted ARIMAC model appears better when a route’s freight charge variance is large, and the accuracy of ARIMA is better when the freight charge variance is small or has a trend of ascent or descent. From the results, it can be concluded that the ARIMAC model, which uses moving averages, has less predictive power for small price changes, while the error-adjusted ARIMAC model, which uses error correction, has the advantage of being able to respond to price changes quickly.

HWE 방법에 의한 CdSe 박막 성장과 광전기적 특성

신영진,홍광준,이상열,유상하,서상석,문종대,김택성,정태수,신용진,이관교,김혜숙,정준우,정경아 한국센서학회 1997 센서학회지 Vol.6 No.4

The CdSe thin films were grown on the Si(100) wafers by a hot wall epitaxy method (HWE). The source and substrate temperature are 600� and 430 respectively. The crystalline structure of epilayers was investigated by double crystal X-ray diffraction(DCXD). Hall effect on the sample was measured by the van der Pauw method and studied on the carrier density and mobility dependence on temperature. From Hall data, the mobility was increased in the temperature range 30K to 150K by impurity scattering and decreased in the temperature range 150K to 293K by the lattice scattering. In order to explore the applicability as a photoconductive cell, we measured the sensitivity(γ), the ratio of photocurrent to darkcurrent(pc/dc), maximum allowable power dissipation(MAPD), spectral response and response time. The results indicated that the photoconductive characteristic were the best for the samples annealed in Cu vapor compare with in Cd, Se, air and vacuum vapour. Then we obtained the sensitivity of 0.99, the value of pc/dc of 1.39 X 10^7, the MAPD of 335mW, and the rise and decay time of l0ms and 9.5ms, respectively

n-CdS_(0.46)Se_(0.54)/p-Cu_92-x)S_(0.46)Se_(0.54) 이종접합 태양전지의 제작과 그 특성에 관한 연구

유상하,최승평,이상열,홍광준,서상석,김혜숙,전승룡,윤은희,문종대,신영진,정태수,신현길,김택성,유기수 全北大學校 基礎科學硏究所 1994 基礎科學 Vol.16 No.-

승화방법에 의해 CdS_0.46Se_0.54 단결정을 성장하여 결정구조를 조사하고, Van der Pauw 방법으로 Hall effect를 측정하여 carrier density의 온도 의존성과 mobility의 온도 의존성을 조사하였다. 성장된 CdS_0.46Se_0.54 단결정을 치환반응하여 n-CdS_0.46Se_0.54/p-Cu_2-xS_0.46Se_0.54 이종접합 태양전지를 제작하였다. Spectral response, 전류-전압특성 및 전력변환 효율을 조사하여 그 결과로부터 개방전압은 0.48V, 단락 전류 밀도는 21mA/㎠, fill factor와 전력변환효율은 각각 0.75와 9.5%를 얻었다. CdS_0.46Se_0.54 single crystal was grown by a sublimation method. The crystal structure and the temperature dependence of carrier density and mobility of CdS_0.46Se_0.54 single crystal were studied. Heterojunction solar cells on n-CdS_0.46Se_0.54/p-Cu_2-xS_0.46Se_0.54 were fabricated by the substitution reaction. The spectral response, the J-U characteristics and the conversion efficiency of the n-CdS_0.46Se_0.54/p-Cu_2-xS_0.46Se_0.54 heterojunction solar cells were studied. The open-cricuit voltage, short-circuit density, fill factor and conversion efficiency of n-CdS_0.46Se_0.54/p-Cu_2-xS_0.46Se_0.54 heterojunction solar cells under 80mW/㎠ illumination were found to be 0.48V, 21mA/㎠, 0.75 and 9.5%, respectively.

CBD 방법에 의한 CdS 박막의 성장과 광전도 특성

홍광준,이상열,유상하,서상석,문종대,신영진,정태수,신현길,김택성,송정훈,유기수 ( K . J . Hong,S . Y . Lee,S . H . You,S . S . Suh,J . D . Moon,Y . J . Shin,T . S . Jeoung,H . K . Shin,T . S . Kim,J . H . Song,K . S . Rheu ) 한국센서학회 1993 센서학회지 Vol.2 No.1

Polycrystalline CdS thin films were grown on ceramic substrate using a chemical bath deposition method. They were annealed at various temperature and X-ray diffraction patterns were measured by X-ray diffractometer in order to study CdS polycrystal structure. Using extrapolation method of X-ray diffraction patterns for the CdS samples annealed in N₂ gas at 5500 it was found hexagonal structure whose lattice constants a_o and c_o were 4.1364 Å and 6.7129 Å, respectively. Its grain size was about 0.35 ㎛. Hall effect on this sample was measured by Van der Pauw method and studied on carrier density and mobility depending on temperature. From Hall data, the mobility was likely to be decreased by piezo electric scattering at temperature range of 33K and 150K and by polar optical scattering at temperature range of 150K and 293K. We measured also spectral response, sensitivity (γ), maximum allowable power dissipation and response time on these samples.

상호 이동성을 갖는 이동 객체의 연속 범위 질의 처리

최길성(Choi Kil-Seong),서상석(Seo Sang-Seok),복경수(Bok Kyoung-Soo),유재수(Yoo Jae-Soo) 한국콘텐츠학회 2004 한국콘텐츠학회 종합학술대회 논문집 Vol.2 No.2

이동 객체의 계속적인 위치 변화로 인해 일정 시간 동안 동일한 질의를 계속적으로 수행하는 연속 질의에 대한 필요성이 증가되고 있다. 이러한 연속 질의는 계속적인 이동 객체의 위치 변화에 따라 서버에서 계속적인 질의 처리를 수행하기 때문에 많은 질의 처리 비용을 소요할 뿐만 아니라 서버 및 네트워크에 많은 부하를 초래할 수 있다. 본 논문에서는 연속 질의의 하나인 연속 범위 질의를 효과적으로 수행하기 위한 질의 처리 기법을 제안한다. 제안하는 질의 처리 기법은 상호 이동 중인 이동 객체에 대한 연속 질의 처리를 수행하기 위해 질의에 대한 응답의 유효성과 질의 결과를 미리 예측한다. 또한, 객체의 동적 변화에 따른 질의 처리를 효과적으로 수행할 수 있도록 한다. Processing the continuous queries which perform the identical query in given time interval is required because of the continuous change of location of the moving object. Thus the continuous query may cause loads to the server or network and take the cost of processing time because the continuous query is performed in server as the moving object's location changes. In this paper, we propose the query processing technique to perform the continuous range query that is a sort of continuous query effectively The proposed query processing technique predicts the query result and the validity of query answer to perform the continuous query for reciprocal moving object. And it enables to process effectively the query that moves dynamically.

Chemical Bath Deposition 방법으로 제작한 CdSe 박막의 특성

홍광준,이상열,유상하,서상석,문종대,신영진,정태수,신현길,김택성,송정훈,유기수 全北大學校 基礎科學硏究所 1994 基礎科學 Vol.16 No.-

Chemical bath deposition 방법으로 다결정 CdSe 박막을 세라믹 기판 위에 성장시킨 다음 온도를 변화시켜 열처리하고 X-선 회절무늬를 측정하여 결정구조를 밝혔다. 450℃로 열처리한 시료가 X-선 회절무늬로 부터 외삽법에 의해 a_o와 c_o 는 각각 4.302 Å과 7.014 Å인 육방정계임을 알았다. 이 때 낱알크기는 약 0.3㎛이었다. Van der Pauw 방법으로 Hall 효과를 측정하여 운반자 농도와 이동도의 온도의존성을 연구하였다. 이동도는 33 K 에서 200 K 까지는 압전산란에 의하여, 200 k 에서 293 K 까지는 극성광학산란에 의하여 감소하는 경향이 나타냈다. 광전도 셀의 특성으로 스텍트럼 응답, 감도(γ), 최대허용소비전력 및 응답 시간을 측정하였다. Polycrystalline CdSe thin films were grown on creamic substrate using a chemical bath deposition (CBD) method. They were annealed at various temperature and X-ray diffraction patterns were measured by X-ray diffractometer in order to study CdSe polycrystal structure. Using extrapolation method of X-ray diffraction patterns for the CdSe samples annealed in N_2 gas at 450℃ it was found hexagonal structure whose lattice parameters a_o and c_o were 4.302 Å and 7.014 Å, respectively. It grain size was about 0.3 ㎛. Hall effect on this sample was measured by Van der Pauw method and studied on carrier density and mobility depending on temperature. From Hall data, the mobility was likely to be decreased by piezo electric scattering at temperature range of 33 K and 200 K, and by polar optical potical scattering at temperature range of 200 K and 293 K. We measured also spectral response, sensitivily (γ), maximum allowable power dissipation and response time on these samples.

CBD 방법에 의한 CdS 박막의 성장과 광전도 특성

황광준,이상열,유상하,서상석,문종대,신영진,정태수,신현길,김택성,송정훈,유기수 全北大學校 基礎科學硏究所 1994 基礎科學 Vol.16 No.-

Chemical bath deposition 방법으로 다결정 CdS 박막을 세라믹 기판 위에 성장시킨 다음 온도를 변화시켜 열처리하고 X-선 회절무늬를 측정하여 결정구조를 밝혔다. 550℃로 열처리한 시료의 경우 X-선 회절무늬로 부터 외삽법에 의해 a_。와 c_。는 각각 4.1364 Å과 6.7129 Å인 육방정계임을 알았다. 이 때 낱알크기는 약 0.35㎛이었다. Van der Pauw 방법으로 Hall 효과를 측정하여 운반자 농도와 이동도의 온도의존성을 연구하였다. 이동도는 33 K 에서 150 K 까지는 압전산란에 의하여, 150 K 에서 293 K 까지는 극성광학산란에 의하여 감소하는 경향이 나타냈다. 광전도 셀의 특성으로 스텍트럼 응답, 감도(γ), 최대허용소비전력 및 응답 시간을 측정하였다. Polycrystalline CdS thin films were grown on creamic substrate using a chemical bath deposition method. They were annealed at various temperature and X-ray diffraction patterns were measured by X-ray diffractometer in order to study CdS polycrystal structure. Using extrapolation method of X-ray diffraction patterns for the CdS samples annealed in N_2 gas at 550℃ it was found hexagonal structure whose lattice constants a_o and c_o were 4.1364 Å and 6.7120Å, respectively. Its grain size was about 0.35 ㎛. Hall effect on this sample was measured by Van der Pauw method and studied on carrier density and mobility depending on temperature. From Hall data, the mobility was likely to be decreased by piezo electric scattering at temperature range of 33K and 150K and by polar optical scattering at temperature range of 150K and 293K. We measured also spectral response, sensitivity (γ), maximum allowable power dissipation and response time on these samples.

C.V.D. 방법에 의한 Cd_0.78Zn_0.22 S박막 성장과 광전기적 특성연구

유상하,이상렬,홍광준,서상석,김혜숙,전승룡,윤은희,문종대 조선대학교 기초과학연구소 1993 自然科學硏究 Vol.16 No.1

We had grown Cd_0.78Zn_0.22S polycrystal thin films on slide substrate using chemical vapour deposition(CVD) method. We measured X-ray diffraction patterns in order to study Cd_0.78Zn_0.22S polycrystal structure. We studied its band gap using transmission curves and photocurrent and also analyzed photoluminescence using configurational coordinate model. We measured Hall effect·on this sample by Van der Pauw method and studied on carrier density and mobility depending on temperature.

Chemical Bath Deposition 방법으로 제작한 CdSe 박마의 특성

신영진,홍광준,이상열,유상하,서상석,문종대,신현길,김택성,송정훈,유기수,정태수 한국센서학회 1993 센서학회지 Vol.2 No.1

Polycrystalline CdSe thin films were grown on ceramic substrate using a chemical bath deposition (CBD) method. They were annealed at various temperature and X-ray diffraction patterns were measured by X-ray diffractometer in order to study CdSe polycrystal structure. Using extrapolation method of X-ray diffraction patterns for the CdSe samples annealed in N₂ gas at 450℃ it was found hexagonal structure whose lattice parameters a_o and c_o were 4.302 A and 7.014 A, respectively. Its grain size was about 0.3 ㎛. Hall effect on this sample was measured by Van der Pauw method and studied on carrier density and mobility depending on temperature. From Hall data, the mobility was likely to be decreased by piezo electric scattering at temperature range of 33 K and 200 K, and by polar optical scattering at temperature range of 200 K and 293 K. We measured also spectral response, sensitivity (γ), maximum allowable power dissipation and response time on these samples.

$CuInTe_2$ 단결정 성장과 특성연구(II)

유상하,홍광준,이상렬,신용진,이관교,서상석,김승욱,정준우,신영진,정태수,신현길,김택성,문종대,You S.H.,Hong K.J.,Lee S.Y.,Shin Y.J.,Lee K.K.,Suh S.S.,Kim S.U.,Jeong J.W.,Shin Y.J.,Jeong T.S.,Shin B.K.,Kim T.S.,Moon J.D. 한국결정학회 1997 韓國結晶學會誌 Vol.8 No.1

[ $CuInTe_2$ ] 다결정은 수평전기로에서 합성하고, $CuInTe_2$ 단결정은 수직 Bridgman 방법으로 성장시켰다. $CuInTe_2$ 단결정의 c축에 수직 및 평행한 시료의 광전도도와 광발광특성을 293K에서 20 K의 온도영역에서 측정하였다. 측정된 광전류 봉우리로부터 구한 c축에 수직 및 평행한 시료의 에너지 띠 간격은 상온에서 각각 0.948 eV와 0.952 eV였다. 광전류 봉우리와 광발광 봉우리의 에너지차는 포논에너지이며 상온에서 c축에 수직 및 평행한 시료의 에너지차는 각각 22.12 meV와 21.4 meV였다. 또한 광전류 스펙트럼으로부터 시료의 spin-orbit 상호작용과 결정장 상호작용에 의한 가전자대의 갈라짐 ${\Delta}cr$과 ${\Delta}so$는 각각 0.046, 0.014 eV였다. [ $CuInTe_2$ ] synthesised in a horizontal electric furnace was found to be polycrystalline. Single crystals of $CuInTe_2$ were grown with the vertical Bridgman technique. The photoconductivity and photoluminescence of the crystals were measured in the temperature range 20 to 293 K. From the photocurrent peaks measured for the samples both perpendicular and parallel to c-axis, the energy band gaps of the samples were found to be 0.948 eV and 0.952 eV at room temperature respectively. The energy difference of the photocurrent and photoluminescence peaks of the samples both perpendicular and parallel to the c-axis measured at room temperature was a phonon energy, and its values were 22.12 meV and 21.4 meV respectively. The splitting of the valence band due to spin-orbit and crystal field interaction was calculated from the photocurrent spectra of the samples, The ${\Delta}cr\;and\;{\Delta}so$ are 0.046,0.014 eV respectively.