• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• Journal of Multimedia Information System
• /
• 제5권2호
• /
• pp.99-104
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.281-281
• /
• 2015

Shallow landslide often occurs in areas of this topography where subsurface soil water flow paths give rise to excess pore-water pressures downslope. Recent hillslope hydrology studies have shown that subsurface topography has a strong impact in controlling the connectivity of saturated areas at the soil-bedrock interface. In this study, the physically based SHALSTAB model was used to evaluate the effects of three soil thicknesses (i.e. average soil layer, soil thickness to weathered soil and soil thickness to bedrock soil layer) and subsurface flow reflecting three soil thicknesses on shallow landslide prediction accuracy. Three digital elevation models (DEMs; i.e. ground surface, weathered surface and bedrock surface) and three soil thicknesses (average soil thickness, soil thickness to weathered rock and soil thickness to bedrock) at a small hillslope site in Jinbu, Kangwon Prefecture, eastern part of the Korean Peninsula, were considered. Each prediction result simulated with the SHALSTAB model was evaluated by receiver operating characteristic (ROC) analysis for modelling accuracy. The results of the ROC analysis for shallow landslide prediction using the ground surface DEM (GSTO), the weathered surface DEM and the bedrock surface DEM (BSTO) indicated that the prediction accuracy was higher using flow accumulation by the BSTO and weathered soil thickness compared to results. These results imply that 1) the effect of subsurface flow by BSTO on shallow landslide prediction especially could be larger than the effects of topography by GSTO, and 2) the effect of weathered soil thickness could be larger than the effects of average soil thickness and bedrock soil thickness on shallow landslide prediction. Therefore, we suggest that using BSTO dem and weathered soil layer can improve the accuracy of shallow landslide prediction, which should contribute to more accurately predicting shallow landslides.

• 신재생에너지
• /
• 제17권1호
• /
• pp.50-60
• /
• 2021

This study investigated the reference case in the UK where legality and sustainability were systematically established for forest biomass represented by wood pellets. The UK is the country that best utilizes the trade value of wood pellets based on sustainability, with bioenergy accounting for 31% of total renewable energy production. The UK imported wood pellet, estimated 8,697 thousand tons in 2019. The UK government has continuously improved the renewable generation policy system to ensure the sustainability of wood pellets. The weighted average greenhouse gas emissions of a UK biomass power plant that received a Renewable Obligation Certificate (ROC) in 2018-19 was 26.71 gCO2e/MJ. These power plants are expected to meet the upper limit of 72.2 gCO2e/MJ by 2025. To issue an ROC, the biomass power plant must demonstrate that 70% of its total biofuel usage is sustainable. The UK uses the Sustainable Biomass Program (SBP) certification system, which is gradually expanding to other European countries, to prove the sustainability of biomass energy fuels. Global wood pellet production with SBP certification in 2019 was 10.5 Mt. This trend has significant implications for introducing additional sustainability into the wood pellet policy of South Korea.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1203-1212
• /
• 2017

Intrusion detection systems (IDSs) are crucial in this overwhelming increase of attacks on the computing infrastructure. It intelligently detects malicious and predicts future attack patterns based on the classification analysis using machine learning and data mining techniques. This paper is devoted to thoroughly evaluate classifier ensembles for IDSs in IEEE 802.11 wireless network. Two ensemble techniques, i.e. voting and stacking are employed to combine the three base classifiers, i.e. decision tree (DT), random forest (RF), and support vector machine (SVM). We use area under ROC curve (AUC) value as a performance metric. Finally, we conduct two statistical significance tests to evaluate the performance differences among classifiers.

• 대한방사선기술학회지:방사선기술과학
• /
• 제39권4호
• /
• pp.549-555
• /
• 2016

본 연구는 다운증후군 위험도의 예측을 위해 통합선별검사를 실시한 산모를 대상으로, 각 표지자의 유의성에 대한 평가를 하였다. 초음파로 측정한 NT 영상, 산모혈청 PAPP-A, AFP, uE3, hCG, 인히빈 A의 상관성을 후향적으로 분석하였다. 그 결과 NT, uE3, hCG, 인히빈 A와 유의한 상관관계를 보였다(p<.001). ROC분석에서 인히빈 A의 AUC가 0.851로 다운증후군의 가장 큰 예측인자로 분석되었으며. cut-off value 1.33 MoM(민감도 87.5%, 특이도 71.5%)으로 결정되었다. 결론적으로 통합선별검사에서 인히빈 A가 다운증후군을 예측하는 가장 유용한 인자로 나타났다. 이에 각 표지자(parameter)들의 cut-off value를 바탕으로 통합선별검사의 단점을 보완한다면 다운증후군 선별의 독립적인 지표로 사용될 수 있을 것으로 사료된다.

• 한국산업정보학회논문지
• /
• 제20권3호
• /
• pp.61-69
• /
• 2015

본 논문에서는 이산 웨이블릿 변환을 통해 추출된 시간 영역과 주파수 영역의 특징들을 활용하여 심박수변이도를 확률적인 지식으로 분석할 수 있는 방법을 제안하였다. 제안된 방법에서 지식획득 알고리즘은 규칙생성과 규칙평가 단계로 구성되어 있으며, 규칙생성에서는 ROC 분석을 통해 수치적인 속성값을 이산화된 구간으로 변환하고, 서로 다른 의사결정값을 포함하는 구간들 사이에 일관성 정도를 비교함으로써 감축된 규칙-집합을 생성한다. 이때 규칙-집합 내에 각 규칙에 대해서 확률적 해석을 위한 3가지 척도를 추정하였다. 제안된 모형의 효과성은 심혈관질환 병력을 가진 58명의 심전도 데이터로부터 심방세동을 식별할 수 있는 5가지 규칙을 생성하였고, 이들 규칙의 분별력을 평가하였다. 실험결과, 제안된 모형으로부터 생성된 지식은 4가지 성능평가 척도에 대해서 각각 93%의 정확도를 보여주었다.

• Imaging Science in Dentistry
• /
• 제48권2호
• /
• pp.87-96
• /
• 2018

Purpose: The present study aimed to evaluate which of the following imaging methods best assessed misfit at the tooth-restoration interface: (1) bitewing radiographs, both conventional and digital, performed using a photostimulable phosphor plate (PSP) and a charge-coupled device (CCD) system; (2) panoramic radiographs, both conventional and digital; and (3) cone-beam computed tomography (CBCT). Materials and Methods: Forty healthy human molars with class I cavities were selected and divided into 4 groups according to the restoration that was applied: composite resin, composite resin with liner material to simulate misfit, dental amalgam, and dental amalgam with liner material to simulate misfit. Radiography and tomography were performed using the various imaging methods, and the resulting images were analyzed by 2 calibrated radiologists. The true presence or absence of misfit corresponding to an area of radiolucency in regions subjacent to the esthetic and metal restorations was validated with microscopy. The data were analyzed using a receiver operating characteristic (ROC) curve, and the scores were compared using the Cohen kappa coefficient. Results: For bitewing images, the digital systems (CCD and PSP) showed a higher area under the ROC curve (AUROC) for the evaluation of resin restorations, while the conventional images exhibited a larger AUROC for the evaluation of amalgam restorations. Conventional and digital panoramic radiographs did not yield good results for the evaluation of resin and amalgam restorations (P<.05). CBCT images exhibited good results for resin restorations(P>.05), but showed no discriminatory ability for amalgam restorations(P<.05). Conclusion: Bitewing radiographs (conventional or digital) should be the method of choice when assessing dental restoration misfit.

• Genomics & Informatics
• /
• 제16권4호
• /
• pp.26.1-26.12
• /
• 2018

Shigella spp. constitutes some of the key pathogens responsible for the global burden of diarrhoeal disease. With over 164 million reported cases per annum, shigellosis accounts for 1.1 million deaths each year. Majority of these cases occur among the children of the developing nations and the emergence of multi-drug resistance Shigella strains in clinical isolates demands the development of better/new drugs against this pathogen. The genome of Shigella flexneri was extensively analyzed and found 4,362 proteins among which the functions of 674 proteins, termed as hypothetical proteins (HPs) had not been previously elucidated. Amino acid sequences of all these 674 HPs were studied and the functions of a total of 39 HPs have been assigned with high level of confidence. Here we have utilized a combination of the latest versions of databases to assign the precise function of HPs for which no experimental information is available. These HPs were found to belong to various classes of proteins such as enzymes, binding proteins, signal transducers, lipoprotein, transporters, virulence and other proteins. Evaluation of the performance of the various computational tools conducted using receiver operating characteristic curve analysis and a resoundingly high average accuracy of 93.6% were obtained. Our comprehensive analysis will help to gain greater understanding for the development of many novel potential therapeutic interventions to defeat Shigella infection.

• Asian-Australasian Journal of Animal Sciences
• /
• 제21권1호
• /
• pp.19-24
• /
• 2008

The purpose of this study was to detect expression of genes related to egg production in Taiwan Country chickens by suppression subtractive hybridization. Liver samples of mRNA extraction from two Taiwan Country chicken strains (L2 and B), originated from the same population but with very distinct egg production rates after long-term selection for egg and meat production respectively. Two-way subtraction was performed. The hepatic cDNA from the low egg production chickens (B) was subtracted from the hepatic cDNA from the high egg production strain (L2). The reversed subtraction (L2 from B) was also performed. The resulting differentially expressed gene fragments were cloned and sequenced. We sequenced 288 clones from the forward subtraction and 96 clones from the reverse subtraction. These genes were subjected to further screening to confirm the differential expression between the two genetic breeds of chickens. The apolipoprotein B (apoB) was expressed to a greater extent in the liver of the L2 than in the B line chickens. The 5-aminoimidazole- 4-carboxamide ribonucleotide formyltransferase/IMP cyclohydrolase (PURH) was expressed to a greater extent in the liver of the B than in the L2 strain chickens. We demonstrated that both apoB and PURH were more highly expressed in the liver than that in other tissues (muscle, ovary, and oviduct) in laying Taiwan Country chickens. Taken together, these data suggest that after the selection for egg production, expression of apoB and PURH genes were also changed. Whether the changed expression of these genes is directly related to egg production is not known, but these two genes may be useful markers for egg laying performance in Taiwan Country chickens.