• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.124-132
• /
• 2002

In this paper, we present a vision algorithm and method for input image improvement and preprocessing of dented and raised characters on the sidewall of tires. we define optical condition between reflect coefficient and reflectance by the physical vector calculate. On the contrary this work will recognize the engraved characters using the computer vision technique. Tire input images have all most same grey levels between the characters and backgrounds. The reflectance is little from a tire surface. therefore, it's very difficult segment the characters from the background. Moreover, one side of the character string is raised and the other is dented. So, the captured images are varied with the angle of camera and illumination. For optimum Input images, the angle between camera and illumination was found out to be with in 90$^{\circ}$. In addition, We used complex filtering with low-pass and high-pass band filters to improve input images, for clear input images. Finally we define equation reflect coefficient and reflectance. By doing this, we obtained good images of tires for pattern recognition.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.80-90
• /
• 2002

Clustering is a useful technique for grouping data points such that points within a single group/cluster have similar characteristics. Many clustering algorithms have been developed and used in engineering applications including pattern recognition and image processing etc. Recently, it has drawn increasing attention as one of important techniques in data mining. However, clustering algorithms such as K-means and Fuzzy C-means suffer from difficulties. Those are the needs to determine the number of clusters apriori and the clustering results depending on the initial set of clusters which fails to gain desirable results. In this paper, we propose a new clustering algorithm, which solves mentioned problems. In our method we use evolutionary algorithm to solve the local optima problem that clustering converges to an undesirable state starting with an inappropriate set of clusters. We also adopt a new measure that represents how well data are clustered. The measure is determined in terms of both intra-cluster dispersion and inter-cluster separability. Using the measure, in our method the number of clusters is automatically determined as the result of optimization process. And also, we combine heuristic that is problem-specific knowledge with a evolutionary algorithm to speed evolutionary algorithm search. We have experimented our algorithm with several sets of multi-dimensional data and it has been shown that one algorithm outperforms the existing algorithms.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.3
• /
• pp.439-448
• /
• 1996

Extraction and selection of the informative features play a central role in pattern recognition. This paper describes a modified back-propagation algorithm that performs selection of the informative features and trains a neural network simultaneously. The algorithm is mainly composed of three repetitive steps : training, connection pruning, and input unit elimination. Afer initial training, the connections that have small magnitude are first pruned. Any unit that has a small number of connections to the hidden units is deleted,which is equivalent to excluding the feature corresponding to that unit.If the error increases,the network is retraned,again followed by connection pruning and input unit elimination.As a result,the algorithm selects the most im-portant features in the measurement space without a transformation to another space.Also,the selected features are the most-informative ones for the classification,because feature selection is tightly coupled with the classifi-cation performance.This algorithm helps avoid measurement of redundant or less informative features,which may be expensive.Furthermore,the final network does not include redundant parameters,i.e.,weights and biases,that may cause degradation of classification performance.In applications,the algorithm preserves the most informative features and significantly reduces the dimension of the feature vectors whiout performance degradation.

• Journal of Preventive Medicine and Public Health
• /
• v.30 no.3 s.58
• /
• pp.643-664
• /
• 1997

This study is to provide evidence-based recommendations for the most-effective treatments of benign prostatic hyperplasia based on patient preference or clinical need, and to meta-analyze the Korean literatures for the development of BPH treatment guidelines. For these analyses, extensive literature searches (208 articles), with priority given to the Korean Journal of Urology, were conducted from 1960 to August, 1996. Meta-analysis, like all statistical analysis, has two main functions: data summarization (qualitative meta-analysis) and smoothing o. pattern recognition (quantitative meta-analysis). As well, critical reviews and syntheses with the mean and 90-percent confidence intervals for the likelihood were used to evaluate empirical evidence and significant outcomes of the BPH treatment literatures (106 articles). For this task, the Methodologic Panel for BPH Guidelines was composed of multidisciplinary experts in the field. The results of the study were summarized as follows: For all that watchful waiting is an appropriate treatment strategy for the majority of patients with prostatism, we couldn't find the Korean literatures which carried this article. The literatures on alpha-1-adrenergic receptor blockers provide no evidence to suggest that any one alpha blocker is more effective than another. The finasteride reduces the size of the prostate, on average, and leads to a small yet perceptible reduction in sysptoms. Of all treatment options, prostate surgery with transurethral resection of the prostate (TURP), transurethral incision of the prostate (TUIP), and so on, offers the best chance for symptom improvement. However, surgery also has the highest rates of significant complications. Therefore, surgery need not always be a treatment of last resort. Balloon dilation of the prostatic urethra is clearly less effective than surgery in relieving symptoms, but it is associated with fewer complications. Emerging technologies for treating BPH include lasers, coils, stents, thermal therapy and hyperthermia. Established technologies will also be reanalyzed as results of new trials are reported. Although this study has some limitations due to lacking for good quality literatures, ' it provides a cornerstone for our medical research. It represents the most current scientific knowledge regarding the clinical epidemiology including treatment of BPH. It will be revised and updated as needed.

• Journal of Internet Computing and Services
• /
• v.13 no.4
• /
• pp.23-31
• /
• 2012

Nowadays, recognizing human activities is an important subject; it is exploited widely and applied to many fields in real-life, especially in health care and context aware application. Research achievements are mainly focused on activities of daily living which are useful for suggesting advises to health care applications. Falling event is one of the biggest risks to the health and well-being of the elderly especially in independent living because falling accidents may be caused from heart attack. Recognizing this activity still remains in difficult research area. Many systems equipped wearable sensors have been proposed but they are not useful if users forget to wear the clothes or lack ability to adapt themselves to mobile systems without specific wearable sensors. In this paper, we develop a novel method based on analyzing the change of acceleration, orientation when the fall occurs and measure their similarity to featured fall patterns. In this study, we recruit five volunteers in our experiment including various fall categories. The results are effective for recognizing fall activity. Our system is implemented on G1 smart phone which are already plugged accelerometer and orientation sensors. The popular phone is used to get data from accelerometer and results showthe feasibility of our method and significant contribution to fall detection.

• Korean Journal of Food Science and Technology
• /
• v.34 no.6
• /
• pp.947-953
• /
• 2002

Two types of electronic nose were used for investigating the quality of dried lavers stored at 5, 15, and $30^{\circ}C$ RH of 32, 43, and 75%. The electronic nose is composed of metal oxide sensors, and GC is based on SAW sensor. Quality change in dried lavers was described in terms of the sensitivities $(R_{gas}/R_{air})$ of the sensors. Principal component analysis (PCA) was carried out using data obtained from six metal oxide sensors. The first principal component scores were correlated with quality changes of dried lavers. As storage time increased, the stored laver cluster separated from that of fresh lavers. A chromatogram was obtained from GC based on SAW sensor. Olfactory image, A $VaporPrint^{TM}$ image for pattern recognition, showed a significant difference between the stored and the fresh samples. Dried lavers during storage at $30^{\circ}C$ and 75% had bacterial counts of $5.7{\times}10^6\;CFU/g$ after 8 day. Increase of microbial count correlated with the response of electronic nose $(r^2=0.87)$. Whereas, color values showed no correlation.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.28 no.5
• /
• pp.649-658
• /
• 1995

In order to estimate the level of genetic differences among the pleuronectid species, mitochondrial DNAs were isolated from four species: brown sole, Limanda herensteini; marbled sole, Limanda Yokohamae; stone flounder, Kareius bicoloratus; starry flounder, Platichthys stellatus, and the number of nucleotide substitutions was calculated by the restriction fragment length polymorphisms (RFIPs) generated by f4 sin base recognition restriction endonucleases. Total lengths of the mitochondrial DNA were measured as about 17.6 kbp in all species. Ten different composite genotypes were observed in brown sole, four different genotypes in marbled sole, and two different genotypes in starry flounder. However, only one genotype was observed in stone flounder. The calculated haplotypic diversity value of brown sole was higher than that of marbled sole. The average number of nucleotide substitutions per sites in four species was estimated to be 0.0045 in the intraspecies, 0.0344 in the interspecies, and 0.0457 in the genera, respectively. From these results, we could estimate that the genetic differences among interspecies were not influenced by nucleotide substitutions but genetical discontinuous.

• Journal of KIISE:Software and Applications
• /
• v.26 no.11
• /
• pp.1261-1269
• /
• 1999

다층 퍼셉트론은 다양한 응용 분야에 성공적으로 적용되고 있는 대표적인 신경회로망 모델이다. 그러나 다층 퍼셉트론의 학습에서 나타나는 플라토에 기인한 느린 학습 속도와 지역 극소는 실제 응용문제에 적용함에 있어서 가장 큰 문제로 지적되어왔다. 이 문제를 해결하기 위해 여러 가지 다양한 학습알고리즘들이 개발되어 왔으나, 계산의 비효율성으로 인해 실제 문제에는 적용하기 힘든 예가 많은 등, 현재까지 만족할 만한 해결책은 제시되지 못하고 있다. 본 논문에서는 다층퍼셉트론의 베이시스 함수로 사용되는 시그모이드 함수를 보다 일반화된 형태로 정의하여 사용함으로써 학습에 있어서의 플라토를 완화하고, 지역극소에 빠지는 것을 줄이는 접근방법을 소개한다. 본 방법은 기존의 변형된 가중치 수정식을 사용한 학습 속도 향상의 방법들과는 다른 접근 방법을 택함으로써 기존의 방법들과 함께 사용하는 것이 가능하다는 특징을 갖고 있다. 제안하는 방법의 성능을 확인하기 위하여 간단한 패턴 인식 문제들에의 적용 실험 및 기존의 학습 속도 향상 방법을 함께 사용하여 시계열 예측 문제에 적용한 실험을 수행하였고, 그 결과로부터 제안안 방법의 효율성을 확인할 수 있었다. Abstract A multilayer perceptron is the most well-known neural network model which has been successfully applied to various fields of application. Its slow learning caused by plateau and local minima of gradient descent learning, however, have been pointed as the biggest problems in its practical use. To solve such a problem, a number of researches on learning algorithms have been conducted, but it can be said that none of satisfying solutions have been presented so far because the problems such as computational inefficiency have still been existed in these algorithms. In this paper, we propose a new learning approach to minimize the effect of plateau and reduce the possibility of getting trapped in local minima by generalizing the sigmoidal function which is used as the basis function of a multilayer perceptron. Adapting a new approach that differs from the conventional methods with revised updating equation, the proposed method can be used together with the existing methods to improve the learning performance. We conducted some experiments to test the proposed method on simple problems of pattern recognition and a problem of time series prediction, compared our results with the results of the existing methods, and confirmed that the proposed method is efficient enough to apply to the real problems.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.5
• /
• pp.111-120
• /
• 2018

Recently, Domestic public construction projects are experiencing a great deal of disputes because of the growing uncertainty about the criteria for calculating the prolongation cost. In addition, researchers have been studying various systems and proper cost estimates in an effort to reduce the uncertainty of these systems and the occurrence of disputes. However, there is no standard yet for social consensus. Meanwhile, The study on the classification system according to the recognition standard of accounting has been systematically studied. As a result, the concepts of accrual and cash basis are defined separately. The purpose of this study is to verify the possibility of applying the concept of 'accrual basis' to the Standard for calculation of prolongation cost. Therefore, As a result of analyzing the occurrence pattern of Job-site overhead cost, it is confirmed that actual costs can not be calculated by the cash-basis method. In particular, the implications of the necessity of the accrual-basis method should be more strictly indicated in the case of items such as indirect labor costs and welfare benefits. In addition, the contractor 's claim report and the appraisal report were examined. As a result, it was confirmed that the calculation situations of prolongation costs are biased to the cash-basis method. In this way, it is suggested that necessary to supplement the calculation standard of the actual costs from the point of view of accrual basis.

• Convergence Security Journal
• /
• v.21 no.2
• /
• pp.57-66
• /
• 2021

Deep neural networks (DNNs) provide excellent performance for image, speech, and pattern recognition. However, DNNs sometimes misrecognize certain adversarial examples. An adversarial example is a sample that adds optimized noise to the original data, which makes the DNN erroneously misclassified, although there is nothing wrong with the human eye. Therefore studies on defense against adversarial example attacks are required. In this paper, we have experimentally analyzed the success rate of detection for adversarial examples by adjusting various parameters. The performance of the ensemble defense method was analyzed using fast gradient sign method, DeepFool method, Carlini & Wanger method, which are adversarial example attack methods. Moreover, we used MNIST as experimental data and Tensorflow as a machine learning library. As an experimental method, we carried out performance analysis based on three adversarial example attack methods, threshold, number of models, and random noise. As a result, when there were 7 models and a threshold of 1, the detection rate for adversarial example is 98.3%, and the accuracy of 99.2% of the original sample is maintained.