• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.383-396
• /
• 2009

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.57-62
• /
• 2010

Recently, decision tree techniques have been studied in terms of quick searching and extracting of massive data in medical fields. Although many different techniques have been developed such as CART, C4.5 and CHAID which are belong to a pie in Clermont decision tree classification algorithm, those methods can jeopardize remained data by the binary method during procedures. In brief, C4.5 method composes a decision tree by entropy levels. In contrast, CART method does by entropy matrix in categorical or continuous data. Therefore, we compared C4.5 and CART methods which were belong to a same pie using breast cancer data to evaluate their performance respectively. To convince data accuracy, we performed cross-validation of results in this paper.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.11 no.2
• /
• pp.110-118
• /
• 1997

This paper describes the dissipation factor measuring techniques of insulating oil on operating pole transformers by using digital signal processor. After applying voltage to the condenser which is in¬stalled in a transformer, acquiring source voltage and current of condenser and using cross-correla¬tion techniques, we can check the dissipation factor of insulating oil. To improve measuring accuracy and the speed of process, we use hardware such as TMS320C31 DSP board and software such as cross -correlation techniques. We simulated the measuring accuracy and the degree of the noise effect of this new measuring techniques by using computer simulation, and compared the simplified measuring devices with Schering bridge on degraded insulating oil. The result showed that this measuring tech¬nique can be used as diagnostic method on the pole transformers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1416-1419
• /
• 2015

최근 건강에 대한 일반인들의 관심이 증가하면서 스마트 헬스케어 시장 규모가 기하급수적으로 커지고 있다. 특히 탈모 관련 헬스케어 시장의 경우, 국내 탈모 인구의 증가로 인해 탈모의 예방이나 관리 등 탈모 관련 어플리케이션이 빠르게 등장하고 있다. 모발 밀도는 탈모의 정도를 판단하기 위한 가장 기본적인 모발 특징 중 하나이지만, 모발의 밀도를 측정하기 위한 명확한 영상처리 기법이나 소프트웨어의 개발은 여전히 미진한 상태이다. 이에 본 논문에서는 스마트폰에 탈부착이 가능한 포터블 카메라에서 촬영된 두피 모발 현미경 영상에서 모발의 밀도를 측정하고 이를 기반으로 사용자 중심의 탈모 진단 플랫폼을 구축하고자 한다. 모발 밀도의 측정은 Contrast Stretching과 Morphology Processing을 이용한 전처리, 스켈레톤 이미지의 변환, 그리고 라인 끝점 검색 알고리즘의 적용 등 크게 세 단계로 진행된다. 제안하는 기법의 성능 평가를 위해, 50배율 포터블 카메라로 촬영한 두피 영상 30개에 대해 밀도 측정을 수행하였으며 그 결과 92.88%의 정확도를 얻었다. 결과적으로 제안하는 기법은 단순 두피 현미경 영상으로 탈모의 지표가 될 수 있는 모발 밀도를 측정하는 데 충분히 효과적임을 알 수 있다.

• Journal of Internet Computing and Services
• /
• v.23 no.1
• /
• pp.31-38
• /
• 2022

An electrocardiogram(ECG) is a recoding of electrical signals of the heart's cyclic activity and an important body information for diagnosing myocardial rhythm. Large amount of information are generated continuously and a significant period of cumulative signal is required for the purpose of diagnosing a specific disease. Therefore, research on compression including clinically acceptable lossy technique has been developed to reduce the amount of information significantly. Recently, wearable smart heart monitoring devices that can transmit electrocardiogram(ECG) are being developed. The use of electrocardiogram, an important personal information for healthcare service, is rapidly increasing. However, devices generally have limited capability and power consumption for user convenience, and it is often difficult to apply the existing compression method directly. It is essential to develop techniques that can process and transmit a large volume of signals in limited resources. A method for compressing and transmitting the ECG signals efficiently by using the cumulative average (template) of the unit waveform is proposed in the paper. The ECG is coded lovelessly using template matching. It is analyzed that the proposed method is superior to the existing compression methods at high compression ratio, and its complexity is not relatively high. And it is also possible to apply compression methods to template matching values.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.57-62
• /
• 2015

In this paper, we design fuzzy inference-based deterioration diagnosis system through different image for rapid as well as efficient diagnosis of electrical equipments. When the deterioration diagnosis of the electrical equipment starts, abnormal state of assigned area is detected by comparing with the temperature of the first normal state of the area. Deterioration state of detected area is diagnosed by using fuzzy inference algorithm. In the fuzzy inference algorithm, fuzzy rules are defined by If-then form and are described as look-up table. Both temperature and its ensuing variation are used as input variables. While triangular membership function is used for the fuzzy input variables of fuzzy rules, singleton membership function is used for the output variable of fuzzy rules. The final output is calculated by using the center of gravity of fuzzy inference method. Experimental data acquired from individual electrical equipments is used in order to evaluate the output performance of the proposed system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2019

As the fourth industrial revolution is emerging, many companies are increasingly interested in smart factories and the importance of sensors is being emphasized. In the case that sensors for collecting sensing data fail, the plant could not be optimized and further it could not be operated properly, which may incur a financial loss. For this purpose, it is necessary to diagnose the status of sensors to prevent sensor' fault. In the paper, we propose a scheme to diagnose digital-sensor' fault by analyzing the rising time and falling time of digital sensors through the LSTM(Long Short Term Memory) of Deep Learning RNN algorithm. Experimental results of the proposed scheme are compared with those of rule-based fault diagnosis algorithm in terms of AUC(Area Under the Curve) of accuracy and ROC(Receiver Operating Characteristic) curve. Experimental results show that the proposed system has better and more stable performance than the rule-based fault diagnosis algorithm.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.77-87
• /
• 2023

Wind turbines playing a critical role in renewable energy generation, accurately assessing their operational status is crucial for maximizing energy production and minimizing downtime. This study conducts a comparative analysis of different neural network models for wind turbine condition diagnosis, evaluating their effectiveness using a dataset containing sensor measurements and historical turbine data. The study utilized supervisory control and data acquisition data, collected from 2 MW doubly-fed induction generator-based wind turbine system (Model HQ2000), for the analysis. Various neural network models such as artificial neural network, long short-term memory, and recurrent neural network were built, considering factors like activation function and hidden layers. Symmetric mean absolute percentage error were used to evaluate the performance of the models. Based on the evaluation, conclusions were drawn regarding the relative effectiveness of the neural network models for wind turbine condition diagnosis. The research results guide model selection for wind turbine condition diagnosis, contributing to improved reliability and efficiency through advanced neural network-based techniques and identifying future research directions for further advancements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.6C
• /
• pp.793-800
• /
• 2004

In this paper, we propose a new automatic pipe grading algorithm for an efficient management of transmission pipe under the ground. Since the conventional transmission pipe evaluation was conducted by subjective decision made by an individual operator, it was difficult to grade them by means of numerical methods and also hard to realistically construct numerical database system. To solve these problems, we Int obtain some information on the current condition of pipes' sections by shooting laser beam at a regular rate and then apply grading algorithm after complete calculation of minimum diameter of pipe. We use some of preprocessing techniques to reduce noise and also use various color models to consider special conditions of each inner pipe. The measurement of pipes' minimum diameter and decision of grade are performed through a detailed processing stages. By some experimental results performed in the field, we show that over 90 percent of correct grade decisions are made by the proposed algorithm.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.5
• /
• pp.42-48
• /
• 2017

When concrete structures expose to fire, the structures were damaged accompanied with degradation of material properties of concrete. In order to determine the reuse of fire-damaged concrete structures, it is needed a careful determination considering conditions of fire damage, such as exposure temperature and exposure time, and also potential to restore fire damage. This study investigates on the evaluation of residual material properties of fire-damaged concrete under different post-fire curing regimes. An experimental study was performed on concrete samples to measure the dynamic elastic modulus by the impact resonance vibration method. Upon the experimental results, the evidence of restoration of material properties was confirmed on specific post-fire curing regimes, higher humidity conditions. Additionally, a correlation analysis was performed on the dynamic elastic modulus with the tensile strength for identifying the effects of post-fire curing regimes on both material properties of fire-damaged concrete.