• 대한원격탐사학회지
• /
• 제23권1호
• /
• pp.7-14
• /
• 2007

Atmospheric correction is one of critical procedures to extract quantitative information related to biophysical variables from hyperspectral imagery. Most atmospheric correction algorithms developed for hyperspectral data have been based upon atmospheric radiative transfer (RT) codes, such as MODTRAN. Because of the difficulty in acquisition of atmospheric data at the time of image capture, the complexity of RT model, and large volume of hyperspectral data, atmospheric correction can be very difficult and time-consuming processing. In this study, we attempted to develop an efficient method for the atmospheric correction of EO-1 Hyperion data. This method uses the pre-calculated look-up-table (LUT) for fast and simple processing. The pre-calculated LUT was generated by successive running of MODTRAN model with several input parameters related to solar and sensor geometry, radiometric specification of sensor, and atmospheric condition. Atmospheric water vapour contents image was generated directly from a few absorption bands of Hyperion data themselves and used one of input parameters. This new atmospheric correction method was tested on the Hyperion data acquired on June 3, 2001 over Seoul area. Reflectance spectra of several known targets corresponded with the typical pattern of spectral reflectance on the atmospherically corrected Hyperion image, although further improvement to reduce sensor noise is necessary.

• 대한공간정보학회지
• /
• 제23권1호
• /
• pp.47-54
• /
• 2015

이 논문에서는 지진에 의한 지각변동 분석에서 측지학적 요소만을 구분하고자 하는 목적으로 GNSS 자료를 전처리하는 전략을 연구하였다. 이를 위해 GNSS 자료처리 결과의 해석에 앞서 GNSS 좌표 시계열에서 나타나는 위신호들을 검출하고 제거하였다. GNSS 관측소는 한반도가 포함된 큰 지각판 위에 위치하므로 판의 운동으로 인한 속도가 좌표 시계열에 포함된다. 그리고 일부 관측소 주변에 위치한 나무들은 계절에 따라 성장변화가 일어나기 때문에 계절적 신호특성이 GNSS 좌표 시계열에 반영된다. 따라서 오일러축에 의한 지각판 운동효과를 정확히 제거하기 위해 축의 위치와 각속도를 한반도 지각판에 맞게 새롭게 추정하였고 이에 대한 검증을 수행하였다. 그리고 1년 주기로 나타나는 계절변동 신호를 추정해 각 관측소의 좌표시계열에 반영하였다. 두 효과를 제거함으로써 지진에 의한 영향을 측지학적으로 분석할 수 있다. 이를 이용해 2011년 동일본 대지진에 의한 지각변위 예비 분석을 수행하였다.

• 농업생명과학연구
• /
• 제53권3호
• /
• pp.147-157
• /
• 2019

In this study, we tried to find out the most appropriate pre-processing method and to verify the feasibility of developing a low-price sensing system for predicting the hardy kiwis sugar content based on VNIRS and subsequent spectral analysis. A total of 495 hardy kiwi samples were collected from three farms in Muju, Jeollabukdo, South Korea. The samples were scanned with a spectrophotometer in the range of 730-2300 nm with 1 nm spectral sampling interval. The measured data were arbitrarily separated into calibration and validation data for sugar content prediction. Partial least squares (PLS) regression was performed using various combinations of pre-processing methods. When the latent variable (LV) was 8 with the pre-processing combination of standard normal variate (SNV) and orthogonal signal correction (OSC), the highest R2 values of calibration and validation were 0.78 and 0.84, respectively. The possibility of predicting the sugar content of hardy kiwi was also examined at spectral sampling intervals of 6 and 10 nm in the narrower spectral range from 730 nm to 1200 nm for a low-price optical sensing system. The prediction performance had promising results with R2 values of 0.84 and 0.80 for 6 and 10 nm, respectively. Future studies will aim to develop a low-price optical sensing system with a combination of optical components such as photodiodes, light-emitting diodes (LEDs) and/or lamps, and to locate a more reliable prediction model by including meteorological data, soil data, and different varieties of hardy kiwi plants.

• 한국지능시스템학회논문지
• /
• 제23권5호
• /
• pp.473-478
• /
• 2013

본 논문에서는 KLAPS(Korea Local Analysis and Prediction System)의 재분석 자료를 이용하여 지능형 뉴로-퍼지 알고리즘 RBFNNs(Polynomial-based Radial Basis Function Neural Networks) 기반 호우특보 판별 모델을 개발한다. 기존의 호우예측 시스템들의 예측능력은 일반적으로 기상데이터의 가공 기법의 영향을 받는다. 본 연구에서는 이를 보완하기 위하여 기상데이터의 전처리를 통한 호우예측 방법을 소개한다. 기상 데이터 전처리 기법은 KLAPS 데이터를 기반으로 지점별 변환, 누적강수량 생성, 시계열 데이터 가공, 호우특보 추출 방식에 의하여 설계된다. 최종적으로, 향후 t(t=1,2,3) 시간 후 6시간 동안 누적강수량에 대해 예측하고 호우특보를 결정하기 위한 정보를 제공한다. 또한 다항식의 형태, 규칙의 개수, 퍼지화 계수와 같은 제안된 모델의 중요 파라미터는 최적화 기법인 차분 진화(Differential Evolution; DE)를 이용하여 최적화한다.

• 한국군사과학기술학회지
• /
• 제21권1호
• /
• pp.124-132
• /
• 2018

This paper presents a shelf life assessment for K-1 military gas masks in the Republic of Korea using test data of Chemical Materiels Stockpile Reliability Program(CSRP). For the shelf life assessment, over 2,500 samples between 2006 and 2015 were collected from field tests and analyzed to estimate a probability of proper and improper functionality using Bayesian estimation. For this, three stages were considered; a pre-processing, a processing and an assessment. In the pre-processing, major components which directly influence the shelf life of the mask were statistically analyzed and selected by applying principal component analysis from all test components. In the processing, with the major components chosen in the previous stage, both proper and improper probability of gas masks were computed by applying Bayesian estimation. In the assessment, the probability model of the mask shelf life was analyzed with respect to storage periods between 0 and 29 years resulting in between 66.1 % and 100 % performances in accuracy, sensitivity, positive predictive value, and negative predictive value.

• 전자공학회논문지B
• /
• 제30B권2호
• /
• pp.8-18
• /
• 1993

A multi-font, multi-size and high speed character recognition system is designed. The design principles are simpilcity of algorithm, adaptibility, learnability, hierachical data processing and attention by feed back. For the multi-size character recognition, the extracted character images are normalized. A hierachical classifier classifies the feature vectors. Feature is extracted by applying the directional receptive field after the directional dege filter processing. The hierachical classifier is consist of two pre-classifiers and one decision making classifier. The effect of two pre-classifiers is prediction to the final decision making classifier. With the pre-classifiers, the time to compute the distance of the final classifier is reduced. Recognition rate is 95% for the three documents printed in three kinds of fonts, total 1,700 characters. For high speed implemention, a multiprocessor system with the ring structure of four transputers is implemented, and the recognition speed of 30 characters per second is aquired.

• 제어로봇시스템학회논문지
• /
• 제12권8호
• /
• pp.752-758
• /
• 2006

A GPS receiver provides much information such as calculated position, speed, heading, status of satellites, current time errors, etc. It is well-known that GPS signals from GPS receiver mounted on moving vehicle are often distorted, contaminated by various noises, and blocked by tunnel or tall buildings. The phenomenon often obstructs correct navigation especially when a vehicle keeps stopping or is moving in low speed. Therefore it is needed to pre-process the signals to adapt it to various applications. In this paper, an algorithm to pre-process the signals is proposed. For this, GPS data obtaining from uNAV GPS receiver are analyzed and classified based on dynamic characteristic. Then, the proposed algorithm is applied to the data and some test results are shown to verify the usefulness of the algorithm.

• 한국IT서비스학회지
• /
• 제19권5호
• /
• pp.83-91
• /
• 2020

Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2754-2767
• /
• 2019

Cloud computing is widely used in information spreading and processing, which has provided a easy and quick way for users to access data and retrieve service. Generally, in order to prevent the leakage of the information, the data in cloud is transferred in the encrypted form. As one of the traditional security technologies, access control is an important part for cloud security. However, the current access control schemes are not suitable for cloud, thus, it is a vital problem to design an access control scheme which should take account of complex factors to satisfy the various requirements for cipher text protection. We present a novel access control scheme based on proxy re-encryption(PRE) technology (PreBAC) for cipher text. It will suitable for the protection of data confidently and information privacy. At first, We will give the motivations and related works, and then specify system model for our scheme. Secondly, the algorithms are given and security of our scheme is proved. Finally, the comparisons between other schemes are made to show the advantages of PreBAC.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.30-39
• /
• 1994

A 1-chip high quality binarizing VLSI image processor (which has 8 bit ADC. 6 bit flash ADC, 15K standard cell, and 1K word ROM) based on 10 MIPS 16 bit DSP is implemented for FAX. This image processor(IP) performs image pre-processing. image quality improvement in copying and sending mode, and mixed image processing based on the fuzzy theory. And smoothing in sub-scan direction is applied for normal receiving mode data so the received data is enhanced like fine mode data. Each algorithm is processed with the same type of image processing window and 2-D image processing is implemented with a 1-D line buffer. The fabricated chip is applied to a FAX machine and image quality improvement is verified.