• Journal of Korea Multimedia Society
• /
• v.21 no.5
• /
• 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
• /
• v.5 no.2
• /
• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• 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.

• New & Renewable Energy
• /
• v.17 no.1
• /
• 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
• /
• v.13 no.5
• /
• 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.

• Journal of radiological science and technology
• /
• v.39 no.4
• /
• pp.549-555
• /
• 2016

This study was an evaluation of the significance of each parameter through aimed at pregnant women subjected to screening test(integrated test) in predicting risk of Down syndrome. We retrospectively analysed the correlation of risk of Down's syndrome with Nuchal Translucency(NT) images measured by ultrasound, Pregnancy Associated Plasma Protein A(PAPP-A), alpha-fetoprotein(AFP), unconjugated estriol(uE3), human chorionic gonadotrophin(hCG) and Inhibin A by maternal serum. As a result, a significant correlation with NT, uE3, hCG, Inhibin A is revealed with Down's syndrome risk(P<.001). In ROC analysis, AUC of Inhibin A is analysed as the biggest predictor of Down's syndrome(0.859). And the criterion for cut-off was inhibin A 1.4 MoM(sensitivity 81.8%, specificity 75.9%). In conclusion, Inhibin A was the most useful in parameters to predict Down's syndrome in the integrated test. If we make up for the weakness based on the cut-off value of parameters they will be able to be used as an independent indicator in the risk of Down's syndrome screening.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.3
• /
• pp.61-69
• /
• 2015

This study presents a probabilistic knowledge discovery method to interpret heart rate variability (HRV) based on time and frequency domain indexes, extracted using discrete wavelet transform. The knowledge induction algorithm was composed of two phases: rule generation and rule estimation. Firstly, a rule generation converts numerical attributes to intervals using ROC curve analysis and constructs a reduced ruleset by comparing consistency degree between attribute-value pairs with different decision values. Then, we estimated three measures such as rule support, confidence, and coverage to a probabilistic interpretation for each rule. To show the effectiveness of proposed model, we evaluated the statistical discriminant power of five rules (3 for atrial fibrillation, 1 for normal sinus rhythm, and 1 for both atrial fibrillation and normal sinus rhythm) generated using a data (n=58) collected from 1 channel wireless holter electrocardiogram (ECG), i.e., HeartCall$^{(R)}$, U-Heart Inc. The experimental result showed the performance of approximately 0.93 (93%) in terms of accuracy, sensitivity, specificity, and AUC measures, respectively.

• Imaging Science in Dentistry
• /
• v.48 no.2
• /
• 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
• /
• v.16 no.4
• /
• 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
• /
• v.21 no.1
• /
• 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.