• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.15-33
• /
• 2021

In this study, the possibility of discriminating Fire blight (FB) infection tested using the hyperspectral imagery. The reflectance of healthy and infected leaves and branches was acquired with 5 nm of full width at high maximum (FWHM) and then it was standardized to 10 nm, 25 nm, 50 nm, and 80 nm of FWHM. The standardized samples were divided into training and test sets at ratios of 7:3, 5:5 and 3:7 to find the optimal bands of FWHM by the decision tree analysis. Classification accuracy was evaluated using overall accuracy (OA) and kappa coefficient (KC). The hyperspectral reflectance of infected leaves and branches was significantly lower than those of healthy green, red-edge (RE) and near infrared (NIR) regions. The bands selected for the first node were generally 750 and 800 nm; these were used to identify the infection of leaves and branches, respectively. The accuracy of the classifier was higher in the 7:3 ratio. Four bands with 50 nm of FWHM (450, 650, 750, and 950 nm) might be reasonable because the difference in the recalculated accuracy between 8 bands with 10 nm of FWHM (440, 580, 640, 660, 680, 710, 730, and 740 nm) and 4 bands was only 1.8% for OA and 4.1% for KC, respectively. Finally, adding two bands (550 nm and 800 nm with 25 nm of FWHM) in four bands with 50 nm of FWHM have been proposed to improve the usability of multispectral image sensors with performing various roles in agriculture as well as detecting FB with other combinations of spectral bands.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1107-1118
• /
• 2021

Climate change brought on by global warming increased the frequency of flood and drought on the Korean Peninsula, along with the casualties and physical damage resulting therefrom. Preparation and response to these water disasters requires national-level planning for water resource management. In addition, watershed-level management of water resources requires flow duration curves (FDC) derived from continuous data based on long-term observations. Traditionally, in water resource studies, physical rainfall-runoff models are widely used to generate duration curves. However, a number of recent studies explored the use of data-based deep learning techniques for runoff prediction. Physical models produce hydraulically and hydrologically reliable results. However, these models require a high level of understanding and may also take longer to operate. On the other hand, data-based deep-learning techniques offer the benefit if less input data requirement and shorter operation time. However, the relationship between input and output data is processed in a black box, making it impossible to consider hydraulic and hydrological characteristics. This study chose one from each category. For the physical model, this study calculated long-term data without missing data using parameter calibration of the Soil Water Assessment Tool (SWAT), a physical model tested for its applicability in Korea and other countries. The data was used as training data for the Long Short-Term Memory (LSTM) data-based deep learning technique. An anlysis of the time-series data fond that, during the calibration period (2017-18), the Nash-Sutcliffe Efficiency (NSE) and the determinanation coefficient for fit comparison were high at 0.04 and 0.03, respectively, indicating that the SWAT results are superior to the LSTM results. In addition, the annual time-series data from the models were sorted in the descending order, and the resulting flow duration curves were compared with the duration curves based on the observed flow, and the NSE for the SWAT and the LSTM models were 0.95 and 0.91, respectively, and the determination coefficients were 0.96 and 0.92, respectively. The findings indicate that both models yield good performance. Even though the LSTM requires improved simulation accuracy in the low flow sections, the LSTM appears to be widely applicable to calculating flow duration curves for large basins that require longer time for model development and operation due to vast data input, and non-measured basins with insufficient input data.

• Journal of Popular Narrative
• /
• v.26 no.4
• /
• pp.9-41
• /
• 2020

Park Jong-won's debut film "Guro Arirang," based on a short story of the same title by Lee Moon-yeol, is the first commercial film to deal with labor struggles from a worker's point of view in the wake of the 1987 democratic movement, and a pioneering work in terms of representing female workers the Korean cinema has traditionally turned away from. In this film Park Jong-won tried to win the sympathy of the middle class for labor movement in spite of the red scare which still stood firm in the Korean society at that time. To convey its progressive message in a form acceptable to the middle class public, the film portrays labor issues in the light of universal humanity and ethics, not in terms of class hostility or struggle. Park Jong-won calls this point of view "common sense of normal people" and emphasizes its universality and objectivity. This study critically examines the cinematic strategies to deal with labor issues in a form acceptable to the public in a conventional and commercial film and the ideological implications of the "common sense of normal people" reflected in such strategies. The first chapter of the study reveals that the film destroys the irony of the original story and reduces the complex constellation of the characters to the conflict between pure good and evil, creating a melodramatic composition in which the good falls victim to evil. The tragedies suffered by the workers in the film are of course intended to arouse the audience's strong sympathy and solidarity with them. The second chapter shows that the film's various scenes and episodes converge on the them of compassion and grief, and are mostly based on cultural and real experiences and events that caused great public sensations at that time. Especially in the last decisive scene of the movie, the memory of the June 1987 uprising is strongly recalled. So "Guro Arirang" can be seen as a patchwork of proven cases of compassion and grief. The third chapter examines the implications of the scene where the workers turn back demands for wages and put the issues of human treatment and trust to the forefront at the crucial moment of their struggle. It appeals to universal moral values and sentiments that everyone has to acknowledge and removes the political dimension from the workers' campaign. While the film tends to become a pure story of humanity marginalizing irreconcilable conflicts of class interest, the workers fall to the position of passive victims who can be deeply sympathetic on the one hand, and on the other, are idealized as leaders with noble attitude keeping themselves aloof from the hard reality. As a result, the movie loses its realistic ground and weakens its narrative probability. The scenes reminiscent of the 1987 uprising which evoke the solidarity between working and middle class fail to integrate harmoniously into the whole story of the film and remain only as fragmentary parts of the patchwork of compassion and grief.

• Journal of Apiculture
• /
• v.34 no.3
• /
• pp.245-254
• /
• 2019

We investigated the anti-tumor effects and molecular mechanism of Brazil, China and Korean regional propolis on HeLa ovarian cancer cell line. Each propolis extracts was prepared by ethanol extraction method. Cytotoxicity of propolis extracts was determinated by EZ-cytox cell viability assay. To necessity of anti-tumor effect and molecular mechanism of propolis, we must be adjusting propolis concentration. Due to 100 ㎍/mL of propolis extract were reduced cell viability to less than 50%, we adjusted all of propolis concentration to 100 ㎍/mL. By Western blotting analysis, we confirmed that anti-tumor mechanism of Brazil, China and Korea regional propolis has significantly difference. All of propolis was activated apoptosis related molecules such as PARP, caspase-3. However, cell proliferation signaling molecules including Akt1, ERK and Bcl-2 were reduced the protein expression level. Especially, the expression of tumor suppressor protein p53 was significantly increased in propolis-treated group such as Gyeonggi, Chungbuk, Chungnam, Jeonbuk, Gyeongnam and China. The phosphorylation of Bax which as apoptosis indicator was appeared in propolis-treated group such as Gyeonggi, Gangwon, Chungnam, Gyeongbuk, China. In this results showed that the regional propolis has completely different mechanism in anti-tumor. Thus, propolis extracts may be useful source of functional materials on anti-cancer and it will be able to choose the suitable propolis for cancer therapy by analyzing individual characteristics.

• Journal of Bio-Environment Control
• /
• v.31 no.2
• /
• pp.90-97
• /
• 2022

This study was carried out to investigate the effect of side vent heights on temperature and relative humidity inside and outside the single-span plastic greenhouse (W: 7 m, L: 40 m H: 3.9 m) during natural ventilation. Four different heights (120, 100, 80, 60 cm) of the side vent were used as an experimental condition. Variations of temperature and relative humidity inside and outside the greenhouse and the differences between heights were compared by using one-way ANOVA. In the daytime, the difference in temperature between inside and outside the greenhouse was dropped from 14.0℃ to 7.1℃ as the side vent height increased. The temperature difference in the nighttime was less than 0.2℃ regardless of the height. One-way ANOVA on the temperature difference between heights presented that the statistical significance was founded between all of the combinations of height in the daytime. The difference in relative humidity between inside and outside the greenhouse was grown from -13.8% to -22.2% with a decrease in the side vent height. The humidity difference in the nighttime was less than 1% regardless of the height. One-way ANOVA on the humidity difference revealed that most of the side vent heights showed significance in the daytime but between 100 and 80 cm was not significant. It seemed because the external air became cooler during the experiment with a height of 80 cm. Conclusively, this study empirically demonstrated that the higher side vents resulted in the decrease of differences in temperature and relative humidity between inside and outside the greenhouse, and also the effect of side vent height was statistically significant. This study may be helpful for deciding the height of the side vent effective for controlling temperature and relative humidity in a single-span greenhouse during natural ventilation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.769-771
• /
• 2005

유비쿼터스 컴퓨팅의 기반 설비인 센서 네트워크는 많은 수의 센서 노드들로 구성되며, 각 센서 노드의 하드웨어는 매우 작은 규모이다. 또한 최소한의 전력 소모를 위하여 센서 노드들은 동적으로 재구성되며, 노드들 간의 통신은 무선 네트워크를 통하여 이루어진다. 센서 네트워크는 구축 목적에 따라 네트워크 토폴로지 및 라우팅 방식이 결정되어야 하고, 이와 더불어 센서 노드의 하드웨어와 소프트웨어도 필요에 따라 다양하게 변경되어야 한다. 따라서 센서 네트워즈가 구현되기 전에 시스템 동작과 성능을 예측할 수 있고 소프트웨어 개발 환경도 제공해주는 시뮬레이터가 사용 가능하다면, 시스템 개발 기간을 크게 단축시킬 수 있을 것이다. 기존의 센서 네트워크 시뮬레이터들은 특별한 응용을 위한 특정 기반의 하드웨어와 운영체제에 국한되어 개발되었기 때문에 다양한 센서 네트워크 환경을 지원하기에는 한계가 있으며, 센서 네트워크 설계상의 주요 요소인 전력 소모량 분석이 포함되지 않았다. 따라서 본 연구에서는 특정한 응용이나 운영체제에 제한을 받지 않으면서 다양하게 센서 네트워크 환경을 설계 및 검증할 수 있고 전력 소모량 추정도 가능한 시뮬레이터를 개발하는 것을 목표로 하였다. 본 연구에서 개발한 시뮬레이터는 기계명령어-레일(machine instruction-level)의 이산-사건 시뮬레이션(discrete-event simulation) 기법을 이용함으로써 실제 센서 노드의 프로그램 실행 및 관련 동작들을 세부적으로 예측하는 데 사용될 수 있도록 하였다. 시뮬레이션의 작업부하(Workload)인 명령어 트레이스(instruction trace)로는 ATmega128L 마이크로컨트롤러용으로 크로스 컴파일된 인텔 헥스-레코드 형식(.hex) 또는 S-레코드 형식(.srec)의 파일을 사용한다.들을 해결하고자 프라이버시보호에 새로운 키 생성 방법을 통한 강력한 프로토콜을 제안 한다.하였으나 사료효율은 증진시켰으며, 후자(사양, 사료)와의 상호작용은 나타나지 않았다. 이상의 결과는 거세비육돈에서 1) androgen과 estrogen은 공히 자발적인 사료섭취와 등지방 침적을 억제하고 IGF-I 분비를 증가시키며, 2) 성선스테로이드호르몬의 이 같은 성장에 미치는 효과의 일부는 IGF-I을 통해 매개될 수도 있을을 시사한다. 약 $70 {\~} 90\%$의 phenoxyethanol이 유상에 존재하였다. 또한, 미생물에 대한 항균력도 phenoxyethanol이 수상에 많이 존재할수록 증가하는 경향을 나타내었다. 따라서, 제형 내 oil tomposition을 변화시킴으로써 phenoxyethanol의 사용량을 줄일 수 있을 뿐만 아니라, 피부 투과를 감소시켜 보다 피부 자극이 적은 저자극 방부시스템 개발이 가능하리라 보여 진다. 첨가하여 제조한 curd yoghurt는 저장성과 관능적인 면에서 우수한 상품적 가치가 인정되는 새로운 기능성 신제품의 개발에 기여할 수 있을 것으로 사료되었다. 여자의 경우 0.8이상이 되어서 심혈관계 질환의 위험 범위에 속하는 수준이었다. 삼두근의 두겹 두께는 남녀 각각 $20.2\pm8.58cm,\;22.2\pm4.40mm$으로 남녀간에 유의한 차이는 없었다. 조사대상자의 식습관 상태는 전체 대상자의 $84.4\%$가 대부분이 하루 세끼 식사를 규칙적으로 하고 있었으며 식사속도는 허겁지겁 빨리 섭취하는 경우가 남자는 $31.0\%$, 여자는 $21.4\%$로 나타났고 이들을 제외한 나머지 사람들은 보통 속도 혹은 충분한 시간을 가지고 식사를 하였

• Journal of the Korean GEO-environmental Society
• /
• v.5 no.2
• /
• pp.51-62
• /
• 2004

Granular compaction piles have the load bearing capacity of the soft ground increase and have the settlement of foundation built on the reinforced soil reduce. The granular compaction group piles also have the consolidation of the soft ground accelerate and have the liquefaction caused by earthquake prevent using the granular materials such as sand, gravel, stone etc. However, this method is one of unuseful methods in Korea. The Granular compaction piles are constructed by grouping it with a raft system. The confining pressure at the center of bulging failure depth is a major variable in relation to estimate for the ultimate bearing capacity of the granular compaction piles. Therefore, a share of loading is determined considering the effect of load concentration ratio between the granular compaction piles and surrounding soils, and varies the magnitude of the confining pressure. In this study, method for the determination of the ultimate bearing capacity is proposed to apply a change of the horizontal pressure considering bulging failure depth, surcharge and loaded area. Also, the ultimate bearing capacity of the granular compaction piles is evaluated on the basis of previous study on the estimation of the ultimate bearing capacity and compared with the results obtained from laboratory scale model tests. And using the result from laboratory model tests, it is studied increase effect of the bearing capacity on the granular compaction piles and variance of coefficient of consolidation for the ground.

• Journal of the Korean Chemical Society
• /
• v.63 no.6
• /
• pp.415-419
• /
• 2019

Fipronil is an insecticide that belongs to the N-phenylpytazole and has been used mainly for an insect pest control. However, it is known that acute poisoning of the human body causes various symptoms such as dizziness, muscle weakness, dyspnea, skin irritation, and increased heart rate. Lately, eggs containing fipronil have been distributed and toxic problems are spreading around the world. In this study, we tried to develop analytical methods to evaluate the exposure of fipronil and fipronil sulfone in animal serum samples. The differences according to mobile phase and the results of liquid - liquid extraction and solid phase extraction pretreatment method were compared. Distilled water (A) and acetonitrile (B) were selected for the mobile phase, and the pretreatment method was determined by solid phase extraction. As a result of the method validation, the intra-day / inter-day accuracies were 82.2~114.1% and the precisions were less than 20%. The detection limit was 0.027 ng/ml for fipronil and 0.087 ng/ml for fipronil sulfone. The linearity obtained was satisfying, with a coefficient of determination (r²) higher than 0.99. The concentrations in some animal sera were determined using the methods of analysis for fipronil and fipronil sulfone in animal sera developed in this study. Using the method developed in this study, it could be used as an analytical method for human bio-monitoring of fipronil and fipronil sulfone as well as animal serum.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.2
• /
• pp.145-152
• /
• 2015

In the study, the effects of damping devices on damping ratio increase and wind-load reduction were investigated based on the computational platform, which is one of the parametric modeling methods. The computational platform helps the designers or engineers to evaluate the efficacy of the numerous alternative structural systems for irregular Super-Tall building, which is crucial in determining the capacity and the number of the supplemental damping devices for adding the required damping ratios to the building. The inherent damping ratio was estimated based on the related domestic and foreign researches conducted by using real wind-load records. Two types of damping devices were considered: One is inter-story installation type passive control devices and the other is mass type active control devices. The supplemental damping ratio due to the damping devices was calculated by means of equivalent static analysis using an equation suggested by FEMA. The optimal design of the damping devices was conducted by using the computational platform. The structural element quantity reduction effect resulting from the installation of the damping devices could be simply assessed by proposing a wind-load reduction factor, and the effectiveness of the proposed method was verified by a numerical example of a 455m high-rise building. The comparison between roof displacement and the story shear forces by the nonlinear time history analysis and the proposed method indicated that the proposed method could simply but approximately estimate the effects of the supplemental damping devices on the roof displacement and the member force reduction.