• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1247-1247
• /
• 2001

Constituents of animal biofluids such as milk, blood and urine contain information specifically related to metabolic and health status of the ruminant animals. Some changes in composition of biofluids can be attributed to disease response of the animals. Mastitis is a major problem for the global dairy industry and causes substantial economic losses from decreasing milk production and reducing milk quality. The purpose of this study was to investigate potential of NIRS combined with multivariate analysis for cow's mastitis diagnosis based on NIR spectra of milk, blood and urine. A total of 112 bulk milk, urine and blood samples from 4 Holstein cows were analyzed. The milk samples were collected from morning milking. The urine samples were collected before morning milking and stored at -35$^{\circ}C$ until spectral analysis. The blood samples were collected before morning milking using a catheter inserted into the carotid vein. Heparin was added to blood samples to prevent coagulation. All milk samples were analyzed for somatic cell count (SCC). The SCC content in milk was used as indicator of mastitis and as quantitative parameter for respective urine and blood samples collected at same time. NIR spectra of blood and milk samples were obtained by InfraAlyzer 500 spectrophotometer, using a transflectance mode. NIR spectra of urine samples were obtained by NIR System 6500 spectrophotometer, using 1 mm sample thickness. All samples were divided into calibration set and test set. Class variable was assigned for each sample as follow: healthy (class 1) and mastitic (class 2), based on milk SCC content. SIMCA was implemented to create models of the respective classes based on NIR spectra of milk, blood or urine. For the calibration set of samples, SIMCA models (model for samples from healthy cows and model for samples from mastitic cows), correctly classified from 97.33 to 98.67% of milk samples, from 97.33 to 98.61% of urine samples and from 96.00 to 94.67% of blood samples. From samples in the test set, the percent of correctly classified samples varied from 70.27 to 89.19, depending mainly on spectral data pretreatment. The best results for all data sets were obtained when first derivative spectral data pretreatment was used. The incorrect classified samples were 5 from milk samples,5 and 4 from urine and blood samples, respectively. The analysis of changes in the loading of first PC factor for group of samples from healthy cows and group of samples from mastitic cows showed, that separation between classes was indirect and based on influence of mastitis on the milk, blood and urine components. Results from the present investigation showed that the changes that occur when a cow gets mastitis influence her milk, urine and blood spectra in a specific way. SIMCA allowed extraction of available spectral information from the milk, urine and blood spectra connected with mastitis. The obtained results could be used for development of a new method for mastitis detection.

• 패션비즈니스
• /
• 제21권6호
• /
• pp.1-15
• /
• 2017

This study examines the various responses of Chinese consumers, depending on the nationality of the fashion advertising model featured in an advertisement; it explores the effects of a congruence between self-image and advertising image (CSIAI) on consumer attitudes. This study was conducted by collecting data online; 200 samples selecting a Korean model and 200 samples selecting a Chinese model with a fashion brand were analyzed. A structural equation model confirms the conceptual framework for the influence of CSIAI on consumer attitudes and purchase intentions. The results show that the perceived CSIAI of consumers positively influences their attitude toward the advertising and the brand, and further, that advertising and brand attitudes significantly affect the purchase intention of consumers. This positive relationship is moderated by the nationality of the model. These findings suggest that the nationality of the model can serve as an important retail mix for global marketers. Other results and management implications are also discussed.

• Journal of the Korean Data and Information Science Society
• /
• 제23권3호
• /
• pp.587-593
• /
• 2012

We study Bayesian estimates for finite population proportions in multinomial problems. To do this, we consider a three-stage hierarchical Bayesian model. For prior, we use Dirichlet density to model each cell probability in each cluster. Our method does not require complicated computation such as Metropolis-Hastings algorithm to draw samples from each density of parameters. We draw samples using Gibbs sampler with grid method. We apply this algorithm to a couple of simulation data under three scenarios and we estimate the finite population proportions using two kinds of approaches We compare results with the point estimates of finite population proportions and their standard deviations. Finally, we check the consistency of computation using differen samples drawn from distinct iterates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4028-4042
• /
• 2021

Aiming at the problem of software defect prediction difficulty caused by insufficient software defect marker samples and unbalanced classification, a semi-supervised software defect prediction model based on a tri-training algorithm was proposed by combining feature normalization, over-sampling technology, and a Tri-training algorithm. First, the feature normalization method is used to smooth the feature data to eliminate the influence of too large or too small feature values on the model's classification performance. Secondly, the oversampling method is used to expand and sample the data, which solves the unbalanced classification of labelled samples. Finally, the Tri-training algorithm performs machine learning on the training samples and establishes a defect prediction model. The novelty of this model is that it can effectively combine feature normalization, oversampling techniques, and the Tri-training algorithm to solve both the under-labelled sample and class imbalance problems. Simulation experiments using the NASA software defect prediction dataset show that the proposed method outperforms four existing supervised and semi-supervised learning in terms of Precision, Recall, and F-Measure values.

• 한국지진공학회논문집
• /
• 제25권2호
• /
• pp.71-81
• /
• 2021

This paper presents a real-time, false-pick filter based on deep learning to reduce false alarms of an onsite Earthquake Early Warning (EEW) system. Most onsite EEW systems use P-wave to predict S-wave. Therefore, it is essential to properly distinguish P-waves from noises or other seismic phases to avoid false alarms. To reduce false-picks causing false alarms, this study made the EEWNet Part 1 'False-Pick Filter' model based on Convolutional Neural Network (CNN). Specifically, it modified the Pick_FP (Lomax et al.) to generate input data such as the amplitude, velocity, and displacement of three components from 2 seconds ahead and 2 seconds after the P-wave arrival following one-second time steps. This model extracts log-mel power spectrum features from this input data, then classifies P-waves and others using these features. The dataset consisted of 3,189,583 samples: 81,394 samples from event data (727 events in the Korean Peninsula, 103 teleseismic events, and 1,734 events in Taiwan) and 3,108,189 samples from continuous data (recorded by seismic stations in South Korea for 27 months from 2018 to 2020). This model was trained with 1,826,357 samples through balancing, then tested on continuous data samples of the year 2019, filtering more than 99% of strong false-picks that could trigger false alarms. This model was developed as a module for USGS Earthworm and is written in C language to operate with minimal computing resources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.53-60
• /
• 2022

In a group-testing method, instead of testing a sample, for example, blood individually, a batch of samples are pooled and tested simultaneously. If the pooled test is positive (or defective), each sample is tested individually. However, if negative (or good), the test is terminated at one pooled test because all samples in the batch are negative. This paper considers a queueing system with a two-stage group-testing policy. Samples arrive at the system according to a Poisson process. The system has a single server which starts a two-stage group test in a batch whenever the number of samples in the system reaches exactly a predetermined size. In the first stage, samples are pooled and tested simultaneously. If the pooled test is negative, the test is terminated. However, if positive, the samples are divided into two equally sized subgroups and each subgroup is applied to a group test in the second stage, respectively. The server performs pooled tests and individual tests sequentially. The testing time of a sample and a batch follow general distributions, respectively. In this paper, we derive the steady-state probability generating function of the system size at an arbitrary time, applying a bulk queuing model. In addition, we present queuing performance metrics such as the offered load, output rate, allowable input rate, and mean waiting time. In numerical examples with various prevalence rates, we show that the second-stage group-testing system can be more efficient than a one-stage group-testing system or an individual-testing system in terms of the allowable input rates and the waiting time. The two-stage group-testing system considered in this paper is very simple, so it is expected to be applicable in the field of COVID-19.

• 농약과학회지
• /
• 제16권2호
• /
• pp.151-162
• /
• 2012

본 연구에서는 분석대상 농약의 선정, 분석대상 식품의 선정, 분석대상 식품의 수집, 추출방법의 최적화를 통해 잔류농약 섭취 수준 평가를 위한 한국형 총식이섭취조사(Total Diet Study, TDS) 모델을 확립하였다. 또한 총식이섭취조사 모델 확립을 위해 필요한 각각의 항목에, 기준을 설정하여 확립된 모델에 의한 잔류농약 수준을 모니터링 하였다. 모니터링은 1단계에서는 총 102종의 대표식품, 2단계에서는 총 70종의 대표식품, 3단계에서는 12종의 대표식단과 109종의 대표식품을 대상으로 98종 농약에 대해 $GC-{\mu}ECD$, GC-MSD, 그리고 LC-MS/MS를 이용하여 분석을 실시하였다. 그 결과 검출된 농약들은 모두 잔류허용기준(Maximum Residue Limit, MRL) 이하의 잔류량을 보였으나 검출된 잔류농약이 해당 작물에 대해 잔류허용기준이 설정되어 있지 않은 경우도 있었다. 한국형 총식이섭취조사 모델을 확립함은 소비자들에게 안전한 먹거리 제공, 농산물의 안전성 확보 및 농산물 생산자들의 농약 사용에 대한 지속적인 정보 제공의 역할을 할 수 있는 자료를 제공하게 될 것이다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제2권1호
• /
• pp.41-60
• /
• 1998

This paper derives a consistent and bias corrected extension of Akaike's Information Criterion (AIC), $AIC_{bc}$, based on Kullback-Leibler information. This criterion has terms that penalize the overparametrization more strongly for small and large samples than that of AIC. The overfitting problem of the asymptotically efficient model selection criteria for small and large samples will be overcome. The $AIC_{bc}$ also provides a consistent model order selection. Thus, it is widely applicable to data with small and/or large sample sizes, and to cases where the number of free parameters is a relatively large fraction of the sample size. Relationships with other model selection criteria such as $AIC_c$ of Hurvich, CAICF of Bozdogan and etc. are discussed. Empirical performances of the $AIC_{bc}$ are studied and discussed in better model order choices of a linear regression model using a Monte Carlo experiment.

• Geomechanics and Engineering
• /
• 제18권4호
• /
• pp.373-389
• /
• 2019

It is important to study the problem of durability for tunnel structures. As a main influence on the durability of tunnel structures, carbonation-induced corrosion is studied. For the complicated environment of tunnel structures, based on the data samples from real engineering examples, the intelligent method (genetic programming) is used to construct the service life prediction model of tunnel structures. Based on the model, the prediction of service life for tunnel structures in carbonation environments is studied. Using the data samples from some tunnel engineering examples in China under carbonation environment, the proposed method is verified. In addition, the performance of the proposed prediction model is compared with that of the artificial neural network method. Finally, the effect of two main controlling parameters, the population size and sample size, on the performance of the prediction model by genetic programming is analyzed in detail.