• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.16-25
• /
• 2016

Turnaround time (called, TAT) for imaging test, which is necessary for making a medical diagnosis, is directly related to the patient's waiting time and it is one of the important performance criteria for medical services. In this paper, we measured the TAT from major imaging tests to see it met the reference point set by the medical institutions. Prediction results from the algorithm of classification regression tree (called, CART) showed "clinics", "diagnosis", "modality", "test month" were identified as main factors for timely processing. This study had a contribution in providing means of prevention of the delay on medical services in advance.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.285-292
• /
• 2019

Path planning is an important problem to solve in robotics and there has been many related studies so far. In the previous research, we proposed the Heterogeneous-Ants-Based Path Planner (HAB-PP) for the global path planning of mobile robots. The conventional path planners using grid map had discrete state transitions that constrain the only movement of an agent to multiples of 45 degrees. The HAB-PP provided the smoother path using the heterogeneous ants unlike the conventional path planners based on Ant Colony Optimization (ACO) algorithm. The planner, however, has the problem that the optimization of the path once found is fast but it takes a lot of time to find the first path to the goal point. Also, the HAB-PP often falls into a local optimum solution. To solve these problems, this paper proposes an improved ant-inspired path planner using the Rapidly-exploring Random Tree-star ($RRT^*$). The key ideas are to use $RRT^*$ as the characteristic of another heterogeneous ant and to share the information for the found path through the pheromone field. The comparative simulations with several scenarios verify the performance of the improved HAB-PP.

• Safety and Health at Work
• /
• v.6 no.4
• /
• pp.279-288
• /
• 2015

Background: In this study, the measurement of job stress of electric overhead traveling crane operators and quantification of the effects of operator and workplace characteristics on job stress were assessed. Methods: Job stress was measured on five subscales: employee empowerment, role overload, role ambiguity, rule violation, and job hazard. The characteristics of the operators that were studied were age, experience, body weight, and body height. The workplace characteristics considered were hours of exposure, cabin type, cabin feature, and crane height. The proposed methodology included administration of a questionnaire survey to 76 electric overhead traveling crane operators followed by analysis using analysis of variance and a classification and regression tree. Results: The key findings were: (1) the five subscales can be used to measure job stress; (2) employee empowerment was the most significant factor followed by the role overload; (3) workplace characteristics contributed more towards job stress than operator's characteristics; and (4) of the workplace characteristics, crane height was the major contributor. Conclusion: The issues related to crane height and cabin feature can be fixed by providing engineering or foolproof solutions than relying on interventions related to the demographic factors.

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.557-570
• /
• 2019

In this study, a novel hierarchical approach is investigated to extract coronary vessel from X-ray angiogram. First, we propose to combine Decimation-free Directional Filter Bank (DDFB) and Homographic Filtering (HF) in order to enhance X-ray coronary angiographic image for segmentation purposes. Because the blood vessel ensures that blood flows in only one direction on vessel branch, the DDFB filter is suitable to be used to enhance the vessels at different orientations and radius. In the combination with HF filter, our method can simultaneously normalize the brightness across the image and increases contrast. Next, a coarse-to-fine strategy for iterative segmentation based on Otsu algorithm is applied to extract the main coronary vessels in different sizes. Furthermore, we also propose a new approach to segment very small vessels. Specifically, based on information of the main extracted vessels, we introduce a new method to extract junctions on the vascular tree and level of nodes on the tree. Then, the window based segmentation is applied to locate and extract the small vessels. Experimental results on our coronary X-ray angiography dataset demonstrate that the proposed approach can outperform standard method and attain the accuracy of 71.34%.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.261-265
• /
• 2019

We analyze the failure rate change of a conventional bidirectional converter and a modified one which moves an output capacitor towards propulsion battery. We analysis of the circuit structural homogeneity and the difference between both converters, and confirm that the capacitor working voltage is reduced by changing the capacitor position. After obtaining the capacitor failure rate according to voltage stress factor and operating temperature, it is applied to the fault-tree of the bidirectional converter to obtain the overall failure rate of the converter. We analyzes the advantages and disadvantages of design changes by comparing and analyzing the failure rate and mean time between failures (MTBF) according to operating temperature and capacitance value.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.860-880
• /
• 2024

Breast cancer is a major health concern affecting women and men globally. Early detection and accurate classification of breast cancer are vital for effective treatment and survival of patients. This study addresses the challenge of accurately classifying breast tumors using machine learning classifiers such as MLP, AdaBoostM1, logit Boost, Bayes Net, and the J48 decision tree. The research uses a dataset available publicly on GitHub to assess the classifiers' performance and differentiate between the occurrence and non-occurrence of breast cancer. The study compares the 10-fold and 5-fold cross-validation effectiveness, showing that 10-fold cross-validation provides superior results. Also, it examines the impact of varying split percentages, with a 66% split yielding the best performance. This shows the importance of selecting appropriate validation techniques for machine learning-based breast tumor classification. The results also indicate that the J48 decision tree method is the most accurate classifier, providing valuable insights for developing predictive models for cancer diagnosis and advancing computational medical research.

• Korean Journal of Soil Science and Fertilizer
• /
• v.32 no.2
• /
• pp.147-154
• /
• 1999

This study was carried out to obtain reasonable management method of salt-affected soil for ecological restoration in the reclaimed land. Chemical properties of reclaimed soil was investigated base on reclamation years. Ionic acitivity in soil and satruration extract were analyzed to estimate the effect of salt interception by planting ground treatment. The soil porperties of reclaimed land was saline-sodic soil with $11.3dSm^{-1}$ of electrical conductivity, 34.8% of exchangeable sodium percent in first reclamation year. Electrical conductivity, exchangeable sodium and exchangeable chlorine were remarkedly decreased during six years after reclamation but chemical properties of reclaimed soil was unsuitable status for tree growth. Exchangeable sodium perecnt was higher in the neighborhood parks and street tree sites than in the buffer green spaces and was higher in subsoil than in topsoil of profile in all sites. Content of soduim, chloride and sulfate in saturation extract were more than other ions. Content of soduim and chloride were higher in the neighborhood parks and street tree sites than in the buffer green spaces and were higher in subsoil than in topsoil. Content of calcium plus magnesium of soil was higher in the buffer green space than in the neighborhood park and street tree but content of calcium and magnesium in saturation extract were higher, as result from exchangeable sodium, in the neighborhood parks and street tree sites than in the buffer green spaces. Concentration of salt in soil showed the difference with mounding height and planting ground treatment. The lowest concentration of salt appeared in buffer green spaces and street tree sites was the highest. Salt interception by mounding height in the same planting ground treatment was more effective 120cm of mounding height than 70cm of mounding height.

• Korean Journal of Environment and Ecology
• /
• v.29 no.5
• /
• pp.777-784
• /
• 2015

This study verified the correlations between vegetation factors, such as the number of individual species and species diversity, and soil factors in Chamaecyparis obtusa (CO) stands in Jeollanam-do. Also, the site environmental factors that affect the annual growth of CO ring width were analyzed. Positive correlations were found between the species diversity index and Cation Exchange Capacity (CEC), available phosphate, and exchangeable $K^+$ (P<0.01). In addition, strong positive correlations were also found between the number of species that appeared in the study site and CEC, available phosphorus, exchangeable $K^+$ and exchangeable $Mg^{2+}$ (P<0.01). Tree ring growth showed strong correlations with the nutrient holding capacity and fertility of soil, including available phosphate, exchangeable $K^+$, CEC, and electrical conductivity (P<0.01). The explanatory variables of tree ring growth in CO were composed of exchangeable $K^+$, organic matter content, and soil pH. The regression model had a high level of explanatory power, 74.4%. In this model, the annual growth of CO ring width increased when exchangeable $K^+$ and organic matter content were higher but decreased when soil pH was lower. According to the analysis, it is found that the annual growth of CO ring width was significantly affected by soil fertility, including available phosphate, exchangeable $K^+$, CEC, and electrical conductivity. In addition, the soil fertility of CO stands seems to be significantly affected by the supply of fallen leaves from the understory vegetation of CO.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.5
• /
• pp.417-425
• /
• 2018

This paper proposes a safety management method that extracts ETA (event tree analysis) based scenario and combines ICT technology to reduce serious disasters occurring workplace for shipbuilding and offshore plant. The statistics of Safety and Health Agency and (previous)Ministry of Public Safety and Security show that the most frequent accident among the serious disasters related to shipbuilding and offshore plant is falling. The main cause of accidents is absence of a safety belt and safety belt ring. To solve these problems, we create ETA based scenarios to derive results based on safety considerations. Based on these results, we propose a solution by applying ICT technology for accident prevention. Deriving ETA based scenarios and ICT technology, the proposed solutions include a system for detecting the wearing of safety belts and safety helmets, a system for detecting whether or not the safety belts are connected, and a hook system for measuring safety distances. These safety related systems can reduce the probability of death of workers. By preventing accidents using the proposed method, we can reduce serious disasters in shipbuilding and offshore plant and establish systematic safety management.