• Smart Media Journal
• /
• v.9 no.4
• /
• pp.102-108
• /
• 2020

In this paper, we propose a real-time method of detecting hand motions and extracting the signal frame induced by EF(Electric Field) sensors. The signal induced by hand motion includes not only noises caused by various environmental sources as well as sensor's physical placement, but also different initial off-set conditions. Thus, it has been considered as a challenging problem to detect the motion signal and extract the motion frame automatically in real-time. In this study, we remove the PLN(Power Line Noise) using LPF with 10Hz cut-off and successively apply MA(Moving Average) filter to obtain clean and smooth input motion signals. To sense a hand motion, we use two thresholds(positive and negative thresholds) with offset value to detect a starting as well as an ending moment of the motion. Using this approach, we can achieve the correct motion detection rate over 98%. Once the final motion frame is determined, the motion signals are normalized to be used in next process of classification or recognition stage such as LSTN deep neural networks. Our experiment and analysis show that our proposed methods produce better than 98% performance in correct motion detection rate as well as in frame-matching rate.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.38 no.5
• /
• pp.42-51
• /
• 2001

Vehicle detection is the basic of traffic monitoring. Video based systems have several apparent advantages compared with other kinds of systems. However, In video based systems, shadows make troubles for vehicle detection, especially active shadows resulted from moving vehicles. In this paper, a new method that combines background subtraction and edge detection is proposed for vehicle detection and shadow rejection. The method is effective and the correct rate of vehicle detection is higher than 98% in experiments, during which the passive shadows resulted from roadside buildings grew considerably. Based on the proposed vehicle detection method, vehicle tracking, counting, classification and speed estimation are achieved so that traffic parameters concerning traffic flow is obtained to describe the load of each lane.

• Journal of Korea Society of Industrial Information Systems
• /
• v.5 no.1
• /
• pp.25-30
• /
• 2000

Hangul is regarded as one of the difficult character set due to the large number of classes and the shape similarity among different characters. Most of the conventional researches attempted to recognize the 2,350 characters which are popularly used, but this approach has a problem or low recognition performance while it provides a generality. On the contrary, recognition of a small character set appearing in specific fields like postal address or bank checks is more practical approach. This paper describes a research for recognizing the handwritten Hangul characters appearing in monetary fields. The modular neural network is adopted for the classification and three kinds of feature are tested. The experiment performed using standard Hangul database PE92 showed the correct recognition rate 91.56%.

• The Korean Journal of Health Service Management
• /
• v.14 no.1
• /
• pp.93-102
• /
• 2020

Objectives: This study analyzed the prescription characteristics of medication for acute respiratory diseases before and after pay-for-performance to provide basic data on effective medical quality management policies. Methods: The research data were collected from the 2013-2014 sample cohort of the National Health Insurance Corporation, from Internal Medicine, Pediatrics, Otorhinolaryngology, Family Medicine and General practitioner clinics (classification of disease codes: J00-J06, J20-J22, J40 outpatients). Results: The antibiotics prescription rates decreased from 43.9% in 2013 to 43.5% in 2014 when the major diagnosis was for upper respiratory infections and increased from 62.0% in 2013 to 62.5% in 2014 when the major diagnosis was for lower respiratory infections. Conclusions: There is a need to identify the correct antibiotic prescription method by expanding the current assessment standards. Such standards must include acute lower respiratory infections and minor diagnoses as the current evaluation techniques focus only on the major diagnosis of acute upper respiratory infections.

• Journal of Korean Society of Transportation
• /
• v.19 no.6
• /
• pp.161-170
• /
• 2001

Vehicle detection is the basic of traffic monitoring. Video based systems have several apparent advantages compared with other kinds of systems. However, In video based systems, shadows make troubles for vehicle detection. especially active shadows resulted from moving vehicles. In this paper a new method that combines background subtraction and edge detection is proposed for vehicle detection and shadow rejection. The method is effective and the correct rate of vehicle detection is higher than 98(%) in experiments, during which the passive shadows resulted from roadside buildings grew considerably. Based on the proposed vehicle detection method, vehicle tracking, counting, classification and speed estimation are achieved so that traffic information concerning traffic flow is obtained to describe the load of each lane.

• Korean Journal of Clinical Laboratory Science
• /
• v.46 no.2
• /
• pp.59-63
• /
• 2014

The death toll of Colorectal Carcinoma in Korea was 1,826 and 7,721 in the years 1992 and 2011, respectively. This rate of increase was shown to be more than 4.23 times higher than that of any other form of cancer. Therefore, Colorectal Carcinoma requires various diagnostic methods, and Microsatellite Instability (MSI) was applied as a new diagnostic tool. From this study with several microsatellite markers, only marker #13 was detected and observed D13S160 13% (4/30), D13S292 13% (4/30), D13S153 10% (3/30) in order. From the results of amplication with microsatellite marker, D13S292 37% (11/30), D13S153 33% (10/30), D13S160 33% (10/30) in order were shown. The appearance of a genetic mutation, which depends on the loci of Colorectal Carcinoma, was shown amplication from rectal cancer (3.77) which was higher than that of right Colorectal Carcinoma (2.08) (p<0.018). The genetic mutation with lymph node (4.13) appeared higher than normal (1.93) (p<0.001). There were no great differences in the genetic mutation dependent on disease, histological classification and increased group of serum CEA. Accordingly, it is suggested that the correct primers, which can evaluate MSI well from colorectal carcinoma, should be chosen and that MSI be considered a good prognosis and quality control tool.

• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.88-90
• /
• 2004

Data are a critical utility asset. Collecting correct data on site leads to accurate information. Data, when gathered with foresight & properly formatted, are useful to both existing database and easily transferable to newer, more comprehensive historical outage data. However, when investigating data items options, the task, can be an arduous one, often requiring the efforts of entire committees. This paper firstly discusses the KEPCO's past 10 years of historical outage data which include meterological data, and also by several elements of the National Weather Service, failure rate, outage duration, and probability classification, etc. Then, these collected data are automatically stored in an Outage Data Management System (ODMS), which allows for easy access and display. ODMS has a straight-forward and easy-to-use interface. It lets you to navigate through modules very easily and allows insertion, deletion or editing of data. In particular, this will further provide the KEPCO that not only helps with probabilistic security assessment but also provides a platform for future development of Probability Estimation Program (PEP).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.800-804
• /
• 2005

This paper presents a fuzzy learning rule which is the fuzzified version of LVQ(Learning Vector Quantization). This fuzzy learning rule 3 uses fuzzy learning rates. instead of the traditional learning rates. LVQ uses the same learning rate regardless of correctness of classification. But, the new fuzzy learning rule uses the different learning rates depending on whether classification is correct or not. The new fuzzy learning rule is integrated into the improved IAFC(Integrated Adaptive Fuzzy Clustering) neural network. The improved IAFC neural network is both stable and plastic. The iris data set is used to compare the performance of the supervised IAFC neural network 3 with the performance of backprogation neural network. The results show that the supervised IAFC neural network 3 is better than backpropagation neural network.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.5
• /
• pp.432-441
• /
• 2002

Though many services offer useful information on internet, computer users are not so familiar with such services that they need an assistant system to use the services easily In the case of web sites, for example, the operators answer the users e-mail questions, but the increasing number of users makes it hard to answer the questions efficiently. In this paper, we propose an assistant system which responds to the users questions automatically and helps them browse the Hanmail Net FAQ (Frequently Asked Question) conceptually. This system uses two-level self-organizing map (SOM): the keyword clustering SOM and document classification SOM. The keyword clustering SOM reduces a variable length question to a normalized vector and the document classification SOM classifies the question into an answer class. Experiments on the 2,206 e-mail question data collected for a month from the Hanmail net show that this system is able to find the correct answers with the recognition rate of 95% and also the browsing based on the map is conceptual and efficient.

• 모자간호학회지
• /
• v.4 no.1
• /
• pp.68-79
• /
• 1994

This study measured variables influencing the breast feeding patterns of lactating mothers over a 40 day period In 1993 in the Jeonla area. The Methodology used was a questionnaire covering 92 items based on statistical discriminant analysis. The results were as follows : The successful group was measured against the unsuccessful group over a 4month lactation period ; The successful group was measured over a 4month lactation period ; the unsuccessful less than 4month lactation period. Principal factor analysis was used to generate comparative data factors which were ; 1) nonunderstanding of mother's breast feeding, 2) physical and psychological stress, 3) insufficient milk supply, 4) mother's negative acceptance of baby, 5) lack of spousal support, 6) sore nipple and breast pain, 7) baby's negative acceptance, 8) lack of familial support, 9) baby's diarrhea and watery milk. Discriminant statistical analysis of sever factors included ; 1) insufficient milk supply 2) sore nipple and breast pain, 3) pre-natal planning of breast feeding method, 4) mother's occupation 5) breast feeding method of previous infant, 6) nipple type, and 7) infant birth order. This analysis predicted a 78.9% successful breast feeding. Criterion correlation analysis revealed ; D=-1.780+.165$\times$(Fac3)+.135$\times$(Fac6)+.927$\times$(prenatal planning of breast feeding method)+.900$\times$(mother's occupation)+.675$\times$ (breast feeding method of previous infant)+1.0l4$\times$(nipple type)+.378$\times$(infant birth order). We classified the unsuccessful group as more than .63937 and the successful group less than -.82742 of the D value obtained from the above criterion correlation in order to check the success or the non-success of breast feeding mothers. The rate of correct classification of the grouped cases employing a statistical discriminant analysis was significantly improved to 78.9% when these cases were compared with the actual grouped classification.