• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.519-524
• /
• 2006

Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the fuzzy grey morphology operation. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The enhanced fuzzy ART algorithm is used to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• Journal of Advanced Marine Engineering and Technology
• /
• v.27 no.3
• /
• pp.412-420
• /
• 2003

This study describes the merits of PWM control of hydraulic system using high speed on-off valves. Generally, Electro-hydraulic valves can be classified into two classification: valves which are controlled by analog signal and which are controlled by digital. The former includes hydraulic servo valves and proportional valves which require A/D converters as interface to digital computer and too costly and sensitive to oil contamination because of complexity in structures. The latter includes high speed on-off valves which do not require A/D converters because they are normally operated in a pulse width modulation(PWM) method, and are low in price and robust to oil contamination because of their simple structures. The objectives of this study is to analyze the limit cycle which regularly appear in the position control system using 2/2way high speed on-off valves and to give a criterion for the stability of this system. The nonlinear characteristics of PWM and cylinder friction of this system are described by harmonic linearization and the effects of parameter variations to the system stability are simulated.

• The Journal of Korean Physical Therapy
• /
• v.21 no.4
• /
• pp.111-115
• /
• 2009

Purpose: The aim of this study was to present fundamental information regarding clinical prognosis and clinical criteria for therapeutic intervention in stroke patients with focal pons infarction. Methods: Four stroke patients (male: 2, female: 2) who were diagnosed with pons infarction were recruited. All subjects had motor functions evaluated using methods such as the Motricity Index (MI), the Modified Brunnstrom Classification (MBC), Functional Ambulatory Category (FAC), and the Bathel Index (BI). Evaluations were done at least 4 times over a period that was approximately 8~11 months from stroke onset. We compared the final evaluation with the first evaluation. Results: All patients with focal pons infarction showed improvement with time in motor function. The physical strength of all patients was improved to normal or good grades from zero or trace grades in the Motricity Index test. Also, other motor functions such as ambulatory capacity and activities of daily living (ADL) improved with time. Conclusion: Aspects of functional recovery and clinical prognosis are clearly predictable for specific patients with focal pons infarction. In addition, adequate therapeutic interventions can be provided clinical criterion to patients, according to aspect of functional recovery. Accordingly, patients with pons infarction change for the better over time.

• Nuclear Engineering and Technology
• /
• v.55 no.3
• /
• pp.827-838
• /
• 2023

Centrifugal pump is a key part of nuclear power plant systems, and its health status is critical to the safety and reliability of nuclear power plants. Therefore, fault diagnosis is required for centrifugal pump. Traditional fault diagnosis methods have difficulty extracting fault features from nonlinear and non-stationary signals, resulting in low diagnostic accuracy. In this paper, a new fault diagnosis method is proposed based on the improved particle swarm optimization (IPSO) algorithm-based variational modal decomposition (VMD) and relevance vector machine (RVM). Firstly, a simulation test bench for rotor faults is built, in which vibration displacement signals of the rotor are also collected by eddy current sensors. Then, the improved particle swarm algorithm is used to optimize the VMD to achieve adaptive decomposition of vibration displacement signals. Meanwhile, a screening criterion based on the minimum Kullback-Leibler (K-L) divergence value is established to extract the primary intrinsic modal function (IMF) component. Eventually, the factors are obtained from the primary IMF component to form a fault feature vector, and fault patterns are recognized using the RVM model. The results show that the extraction of the fault information and fault diagnosis classification have been improved, and the average accuracy could reach 97.87%.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.11a
• /
• pp.283-289
• /
• 2006

This study is a preparation for the application of FSA (Formal Safety Assessment) to the fire safety of ships. FSA is the new-fashioned methodology proposed to prevent ships from the accidents. To make a base of the fire safety assessment about ship's fire protection design and Classification Society rule, statistical informations for the fire safety engineering are investigated. From results, the necessity of new criterion for ship's fire safety design, the need to study the human behavior in the evacuation from fire, and the development of new fire progress model considering special situations in ships are acknowledged.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.5
• /
• pp.1289-1296
• /
• 1997

To build up a knowledge-based system in an Artifical Inerligence System, selecting an appropriate set of rules is one of the key provlems. In this paper, we discuss a new method for exteacting fuzzy rules diredtly from fuzzy membdrchip function dat for pattern classifcation. The fuzzy rules with variable fuzzy recions are defined by sharing fuzzy space in fuzzy grid.Tehse rules are extracted form memberchop function. Them, optimal input vari-ables for the rules are determined using the number of extracted rules as a criterion. The method is compared with neural networks using Ishibuchi. Finally, in order to demonstrate the cffectiveness of the present method, simulation results are shown.

• Journal of the Optical Society of Korea
• /
• v.14 no.4
• /
• pp.376-382
• /
• 2010

We propose a novel method to precisely detect car license plates by locating main characters, which are printed with large font size. The regions of the main characters are directly detected without detecting the plate region boundaries, so that license regions can be detected more precisely than by other existing methods. To generate a binary image, multiple thresholds are applied, and segmented regions are selected from multiple binarized images by a criterion of size and compactness. We do not employ any character matching methods, so that many candidates for main character groups are detected; thus, we use a neural network to reject non-main character groups from the candidates. The relation of the character regions and the intensity statistics are used as the input to the neural network for classification. The detection performance has been investigated on real images captured under various illumination conditions for 1000 vehicles. 980 plates were correctly detected, and almost all non-detected plates were so stained that their characters could not be isolated for character recognition. In addition, the processing time is fast enough for a commercial automatic license plate recognition system. Therefore, the proposed method can be used for recognition systems with high performance and fast processing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1243-1263
• /
• 2018

The two-stage linear discrimination analysis (TSLDA) is a feature extraction technique to solve the small size sample problem in the field of image recognition. The TSLDA has retained all subspace information of the between-class scatter and within-class scatter. However, the feature information in the four subspaces may not be entirely beneficial for classification, and the regularization procedure for eliminating singular metrics in TSLDA has higher time complexity. In order to address these drawbacks, this paper proposes an improved two-stage linear discriminant analysis (Improved TSLDA). The Improved TSLDA proposes a selection and compression method to extract superior feature information from the four subspaces to constitute optimal projection space, where it defines a single Fisher criterion to measure the importance of single feature vector. Meanwhile, Improved TSLDA also applies an approximation matrix method to eliminate the singular matrices and reduce its time complexity. This paper presents comparative experiments on five face databases and one handwritten digit database to validate the effectiveness of the Improved TSLDA.

• The Research Journal of the Costume Culture
• /
• v.17 no.6
• /
• pp.1068-1082
• /
• 2009

The purpose of this study was to investigate empirically the consumer behavior regarding the purchase of millinery items in relation to their evaluation criterion and demographic characteristics. The survey was carried out to 395 individuals in their 20s and over who were quota sampled according to age and gender. The collected data were statistically treated with the SPSS 12.0 program in terms of descriptive statistics, cross tabulation, t-test, one-way ANOVA, factor analysis, Cronbach's $\alpha$ coefficient and Duncan-test. The 20s and 50s over were more interested in hat products than other ages. Female consumers obtained the most information about hat products from store visits, TV and magazines. On the other hand, male consumers had it from the acquaintances and internet. Younger consumers more often utilized internet to have it. Their main purchase location was department stores. The younger purchased it more in traditional market, the older purchased it more in mega wholesale market or discount store. The consumers of hat products considered the intrinsic classification most when buying hats. The evaluation criteria employed by them were aesthetics, quality, and external attributes. Hat consumers were more concerned about aesthetics attributes than the other two criteria. Female consumers and consumers who are more interested in the hat and have a higher level of education and income considered aesthetics attributes most important.

• Hwankyungkyoyuk
• /
• v.23 no.1
• /
• pp.50-63
• /
• 2010

This study is a qualitative case study aiming at understanding and finding out influential factors and barriers when school teachers choose Environmental Education as their Creative Discretionary Activities. To do this, this study focuses on the process of two teachers' choices of the Creative Discretionary Activities in two other elementary schools. The results of this research are follows. Two teachers' choices are affected by several influential factors, divided into external factors and internal factors. External influential factors include culture of school and education, media, chief education officers, parents and school. Internal influential factors are teachers' value and philosophy of education, teachers' experiences, teachers' capacity. These influential factors' forces aren't the same with each other. These influential factors, are influenced by educational, social, national, local, and school level indicated by Taylor et al's (1974) classification criterion. Especially, however, Korea's particular educational environment focusing on university entrance examination strongly affects teachers' choice. School factors also has a big strong effect on teachers' choice. Among others internal actors are the most serious influential factor affecting on teachers' choice.