• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.363-373
• /
• 2020

During last decades numerous studies generating orthoimage have been carried out. Traditional methods require exterior orientation parameters of aerial images and precise 3D object modeling data and DTM (Digital Terrain Model) to detect and recover occlusion areas. Furthermore, it is challenging task to automate the complicated process. In this paper, we proposed a new concept of true orthoimage generation using DL (Deep Learning). DL is rapidly used in wide range of fields. In particular, GAN (Generative Adversarial Network) is one of the DL models for various tasks in imaging processing and computer vision. The generator tries to produce results similar to the real images, while discriminator judges fake and real images until the results are satisfied. Such mutually adversarial mechanism improves quality of the results. Experiments were performed using GAN-based Pix2Pix model by utilizing IR (Infrared) orthoimages, intensity from LiDAR data provided by the German Society for Photogrammetry, Remote Sensing and Geoinformation (DGPF) through the ISPRS (International Society for Photogrammetry and Remote Sensing). Two approaches were implemented: (1) One-step training with intensity data and high resolution orthoimages, (2) Recursive training with intensity data and color-coded low resolution intensity images for progressive enhancement of the results. Two methods provided similar quality based on FID (Fréchet Inception Distance) measures. However, if quality of the input data is close to the target image, better results could be obtained by increasing epoch. This paper is an early experimental study for feasibility of DL-based true orthoimage generation and further improvement would be necessary.

• Journal of KIISE:Databases
• /
• v.32 no.5
• /
• pp.526-535
• /
• 2005

Ontology is a methodology on describing specific concepts and their relationships, and it is being considered important more and more as semantic web and variety of knowledge management systems are being highlighted. Ontology uses the relationships among concerts to represent some concrete semantics of specific concept. When we want to get some useful information from ontology, we severely have to process the transitive relationships because most of relationships among concepts represent transitivity. Technically, it causes recursive calls to process such transitive closure queries with heavy costs. This paper describes the efficient technique for processing transitive closure queries in ontology. To the purpose of it, we examine some approaches of current systems for transitive closure queries, and propose a technique by graph labeling scheme. Basically, we assume large size of ontology, and then we show that our approach gives relative efficiency in processing of transitive closure, queries.

• Feed Journal
• /
• v.4 no.7 s.35
• /
• pp.108-115
• /
• 2006

우리나라는 사계절이 뚜렷한 기후적 환경으로 여름철 한낮의 외부온도가 35℃ 이상이 되는 날이 계속되고, 야간에도 25℃ 이상인 열대야가 지속되는 날이 많다. 이러한 조건하에서 양돈 생산성 향상을 위해서는 돼지의 사육환경과 성장단계별 적절한 사양기술을 투입하여야만 한다. 돼지는 생리적으로 추위에 의한 영향보다는 여름철 더위에 의한 영향을 쉬게 받으며, 이로 인해 자돈의 쇠약, 압사,수태율 저하, 번식장애 등으로 생산성 저하의 원인이 되며, 사육기간 중에 일시적인 고온스트레스가 돼지가 생존하는 동안 능력의 저하를 초래하게 된다. 특히 하절기 양돈장은 우기와 무더위로 인한 돈사내 온도의 급상승과 더불어 습도의 불균형에 의한 환경적 스트레스로 번식능력과 생산성에 크게 영향을 미칠 수 있으며,돼지에 일시적인 고온 스트레스 피해는 장기간 계속되며, 생존하는 동안 능력저하를 초래하기 때문에 농장별 사육여건에 따른 성장저해 요인을 제거하는 안목이 필요한 계절이다. 즉,5~9월 모돈에 고온스트레스가 가해지면 11~12월, 다음해 1월 모돈의 분만율은 최저가 되고 , 이 시기에 생산된 자돈은 추운겨울을 이겨내야 함으로 육성률도 낮아지며, 이로 인해 4~7월의 출하성적은 최저가 되는 것이다. 따라서 모돈 관리는 5~9월이 집중관리가 필요한 시기이기도 하다. 고온 다습한 환경 하에서 어미돼지는 영양불균형과 생체리듬의 파괴로 인하여 신생자돈의 폐사가 증가할 수도 있고,이유 후 1주일 이내 발정 재귀율이 약 30%정도 감소하고 무발정돈이 많이 발생되며, 수태가 되어도 조기 배아사멸 및 흡수로 인하여 수태율이 25%까지 감소될 수 있다. 현재 국내 양돈농가에는 예년과 같이 돼지 조모성질환의 발생이 늘어나고 있고, 어려움을 겪고 있는 농장이 많은 것으로 조사 보고되어지고 있는데, 이는 농장에 사육되는 돈군이 외부환경에 대한 적응능력과 질병에 저항력이 부족하여 쉽게 질병에 노출되어 발생함으로 농장에는 돼지가 스트레스를 받지 않게 외부 환경과 사양관리 측면에 심혈을 기울려 강건한 축군을 유지하려는 노력이 무엇보다 우선되어져야 한다고 생각된다. 따라서 본고에서는 여름철에 돼지 스트레스를 줄이고 생산성을 향상시키기 위해 돼지의 생리변화와 돈사 급수설비와 사료관리 및 사육관리에 대해 알아보고자 한다.

• Korean Journal of Animal Reproduction
• /
• v.26 no.2
• /
• pp.193-199
• /
• 2002

This study was conducted to investigate the optimal physiologic mating time in Hanwoo for protection to decrease of reproductivity and improvement of production of offspring. We observed 32 cows that were devide into 4 parts of treatment : T1(12 months of age and 0.5kg daily gain), T2(12 months of age and 0.8kg daily gain), T3(15 months of age and 0.5kg daily gain) and T4(18 months and 0.5kg daily gain). The first heat of treated cows was 263.3$\pm$6.4 days and average weight was 181.1$\pm$11.3kg. It was revealed the conception rates of first insemination were 25%(T1), 75%(T4) and number of insemination of T3 and T4(both 1.5) was lower than T1 and T2(2.3 and 2.4). In return of estrus after heifer's first parturition, they(T1, T2, T3 and T4) showed 66.2 days, 76.7 days, 62.4 days and 68.5 days respectively and the average was 65.7 days. Plasma progesterone(P4) concentration was nearly the same during the observation periods of treated cows and P4 was released just after 12 months. Only 5 cows (15.6%) in 32 were showed normal estrus cycle and ovulation before 12 months. Before and after parturition, P4 concentration was decreased fastly and then there was no detection of P4 from after parturition to 40 days after milking. P4 would be released again on 45 day after parturition. The results were summarized as that the optimal mating time of Hanwoo heifers was decided by the 14 months of age, 110 cm height and 265kg weight.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.4 no.1
• /
• pp.110-118
• /
• 2002

This study was conducted to investigate the physiology of optimal reproductive age in Hanwoo for protection to decrease of reproductivity and improvement of production of offspring. Thirty two cows were devided into 4 groups of treatments : T1(12 months of age and 0.5kg daily gain), T2(12 months of age and 0.8kg daily gain), T3(15 months of age and 0.5kg daily gain) and T4(18 months of age and 0.5kg daily gain). The days of the first heat of treated cows were 263.3±6.4 days and average weight was 181.1±11.3kg. The conception rates of first insemination were 25%(T1) and 75%(T4), and the number of insemination of T3 and T4(both 1.5) was lower than those of T1 and T2(2.3 and 2.4), respectively. With regard to estrus return after the first parturition, T1, T2, T3 and T4 showed 66.2,76.7, 62.4 and 68.5 days, respectively, indicating the average days of estrus return was 65.7. Plasma progesterone(P4) concentration was nearly the same during the observation periods of treated cows and P4 began to be detected after 12months. Only 5(15.6%) out of 32cows showed normal estrus cycle and ovulation before 12 months. During the peri-parturition period, P4 concentration was rapidly decreased and there was no detection of P4 from parturition to 40 days after milking. P4 would be released again on 45 day after parturition. The results imply that the optimal reproductive age of Hanwoo heifers would be around at the 14 months of age, 110cm height and 265kg weight.

• Korean Journal of Animal Reproduction
• /
• v.22 no.4
• /
• pp.367-373
• /
• 1998

A survey was carried out to investigate the effect of the herd size on the reproductive traits of Hanwoo(Korean native cows). Data on the reproductive traits of 670 Korean native cows were collected from January, 1996 to December, 1997 and analyzed by the herd size. The results obtained were summarized as follows: 1. The average ages at first breeding were 437.9, 425.5 and 452.9 days in herd size 1 (less than 20 heads), 2 (21∼50 heads) and 3 (more than 51 heads), respectively (the over all average was 443.0 days). However, there was no significant difference between herd sizes (p＞0.05). 2. The average ages at first conception were 452.8, 438.4 and 467.1 days in herd size 1, 2 and 3, respectively (the over all average was 460.0 days). However, there was no significant difference between herd sizes (p＞0.05). 3. The average ages at first calving were 741.2, 730.2 and 755.9 days in herd size 1, 2 and 3, respectively (the over all average was 746.6 days). However, there was no significant difference between herd sizes (p＞0.05). 4. The average days to first estrus after calving was 70.1 days and it was shortest in herd size 3 (64.8 days) and longest in herd size 1(82.1 days). 5. The average numbers of services per conception were 1.54, 1.61 and 1.48 in herd size 1, 2, and 3, respectively (the over all average was 1.53). However, there was no significant difference between herd sizes (p＞0.05). 6. The average days to first conception after calving were 115.6, 99.1 and 80.6 days in herd size 1, 2 and 3, respectively (the over all average was 91.2 days). There was a trend that it was shorter as the herd size increased(p＜0.05). 7. The average length of calving interval was 375.3 days and it was shortest in herd size 3 (367. 4 days) and longest in herd size 1 (389.5 days).

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.558-563
• /
• 2015

There have recently been various services that use indoor location estimation technologies. Representative methods of location estimation include fingerprinting and triangulation, but they lack accuracy. Various kinds of research which apply existing location estimation methods like AOA, TOA, and TDOA are being done to solve this problem. In this paper, we study the location estimation algorithm based on AOA using a RSSI difference in indoor environments. We assume that there is a single AP with four antennas, and estimate the angle of arrival based on the RSSI value to apply the AOA algorithm. To compensate for RSSI, we use a recursive averaging filter, and use the corrected RSSI and the Pythagorean theorem to estimate the angle of arrival. The results of the experiment, show an error of 18% because of the radiation pattern of the four non-directional antennas arranged at narrow intervals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.758-761
• /
• 2007

Digital signal processing technique is applied in wide fields such as speech processing, image processing and spectrum analysis. Therefore, in order to do frequency selective operation digital filter is used in stead of analog filter and sharp filter characteristics can be implemented. Since finite impulse response (FIR) digital filter as nonrecursive type represents linear phase response characteristics and is always stable and is used in fields regarding wave information importantly such as data transmission. And due to frequency characteristics, in order to remove the Gibbs phenomenon generating around a discontinuous point, filter is designed through window function method. Therefore, in this paper to improve performance of FIR digital filter, a modified window function was applied. And the proposed method was compared with conventional methods using peak side-lobe and transition properties in simulations.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.4
• /
• pp.382-391
• /
• 2020

In this study, we used artificial intelligence algorithms for the prediction of dissolved oxygen in Jindong Bay. To determine missing values in the observational data, we used the Bidirectional Recurrent Imputation for Time Series (BRITS) deep learning algorithm, Auto-Regressive Integrated Moving Average (ARIMA), a widely used time series analysis method, and the Long Short-Term Memory (LSTM) deep learning method were used to predict the dissolved oxygen. We also compared accuracy of ARIMA and LSTM. The missing values were determined with high accuracy by BRITS in the surface layer; however, the accuracy was low in the lower layers. The accuracy of BRITS was unstable due to the experimental conditions in the middle layer. In the middle and bottom layers, the LSTM model showed higher accuracy than the ARIMA model, whereas the ARIMA model showed superior performance in the surface layer.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11C
• /
• pp.917-924
• /
• 2008

Motion estimation and compensation in the spatial domain check the searching area of specified size in the previous frame and search block to minimize the difference with current block. When we check the searching area, it consumes the most encoding times due to increasing the complexity. We can solve this fault by means of motion estimation using shifting matrix in the transform domain instead of the spatial domain. We derive so the existed shifting matrix to a new recursion equation that we decrease more computations. We modify simply vertical shifting matrix and horizontal shifting matrix in the transform domain for motion estimation of half-pixel accuracy. So, we solve increasing computation due to bilinear interpolation in the spatial domain. Simulation results prove that motion estimation by the proposed algorithm in DCT-based transform domain provides higher PSNR using fewer bits than results in the spatial domain.