• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.11-19
• /
• 2009

A RAM-based Neural Net(RBNN) which has multi-discriminators is more effective than RBNN with a discriminator. Experience Sensitive Cumulative Neural Network and 3-D Neuro System(3DNS) that accumulate the features point improved the performance of BNN, which were enabled to train additional and repeated patterns and extract a generalized pattern. In recognition process of Neural Net with multi-discriminator, the selection of class was decided by the value of MRD which calculates the accumulated sum of each class. But they had a saturation problem of its memory cells caused by learning volume increment. Therefore, the decision of MRD has a low performance because recognition rate is decreased by saturation. In this paper, we propose the method which improve the MRD ability. The method consists of the optimum MRD and the matching ratio prototype to generalized image, the cumulative filter ratio, the gap of prototype response MRD. We experimented the performance using NIST database of NIST without preprocessor, and compared this model with 3DNS. The proposed MRD method has more performance of recognition rate and more stable system for distortion of input pattern than 3DNS.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.2
• /
• pp.87-96
• /
• 2023

Recently, research on predicting the treatment results of diseases using deep learning technology is also active in the medical community. However, small patient data and specific deep learning algorithms were selected and utilized, and research was conducted to show meaningful results under specific conditions. In this study, in order to generalize the research results, patients were further expanded and subdivided to derive the results of a study predicting mortality after lung cancer diagnosis for men and women in their 80s, 90s, and 100s. Using AutoML, which provides large-scale medical information and various deep learning algorithms from the Health Insurance Review and Assessment Service, five algorithms such as Decision Tree, Random Forest, Gradient Boosting, XGBoost, and Logistic Registration were created to predict mortality rates for 84 months after lung cancer diagnosis. As a result of the study, men in their 80s and 90s had a higher mortality prediction rate than women, and women in their 100s had a higher mortality prediction rate than men. And the factor that has the greatest influence on the mortality rate was analyzed as the treatment period.

• Journal of The Korean Association For Science Education
• /
• v.43 no.2
• /
• pp.87-98
• /
• 2023

In this study, we investigated the change in science core competency perception of high school students and the reason for change when science inquiry classes were conducted using eight 'skills' of the 2015 revised science curriculum. Fifteen first-year high school students in Jeollanam-do participated in the science inquiry class of this study, and the class was conducted for 20 hours (5 hours a day for four days). The inquiry activities used in the class consisted of four activity stages (research problems, research methods, research results, and conclusions) and each stage was constructed to include at least one 'skill (Problem Recognition, Model Development and Use, Inquiry Design and Performance, Data Collection, Analysis and Interpretation, Mathematical Thinking and Computer Application, Conclusion and Evaluation, Evidence-based Discussion and Demonstration, and Communication)'. As a result of the study, students' perception of the five science core competencies increased statistically significantly at the significance level of 0.01 through inquiry classes and more than 93% of students recognized that their science core competencies improved through the classes. However, since the class of this study was conducted for a small number of students, it is difficult to generalize the effect of the class, and so it is necessary to conduct a quantitative study for many students.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.303-314
• /
• 2023

Voice conversion, a technology that allows an individual's speech data to be regenerated with the acoustic properties(tone, cadence, gender) of another, has countless applications in education, communication, and entertainment. This paper proposes an approach based on the StarGAN-VC model that generates realistic-sounding speech without requiring parallel utterances. To overcome the constraints of the existing StarGAN-VC model that utilizes one-hot vectors of original and target speaker information, this paper extracts feature vectors of target speakers using a pre-trained version of Rawnet3. This results in a latent space where voice conversion can be performed without direct speaker-to-speaker mappings, enabling an any-to-any structure. In addition to the loss terms used in the original StarGAN-VC model, Wasserstein distance is used as a loss term to ensure that generated voice segments match the acoustic properties of the target voice. Two Time-Scale Update Rule (TTUR) is also used to facilitate stable training. Experimental results show that the proposed method outperforms previous methods, including the StarGAN-VC network on which it was based.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.3B
• /
• pp.279-289
• /
• 2006

The reconstruction of low dimension nonlinear behavior from the hydrologic time series has been an active area of research in the last decade. In this study, we present the applications of a powerful state space reconstruction methodology using the method of Support Vector Machines (SVM) to the Great Salt Lake (GSL) volume. SVMs are machine learning systems that use a hypothesis space of linear functions in a Kernel induced higher dimensional feature space. SVMs are optimized by minimizing a bound on a generalized error (risk) measure, rather than just the mean square error over a training set. The utility of this SVM regression approach is demonstrated through applications to the short term forecasts of the biweekly GSL volume. The SVM based reconstruction is used to develop time series forecasts for multiple lead times ranging from the period of two weeks to several months. The reliability of the algorithm in learning and forecasting the dynamics is tested using split sample sensitivity analyses, with a particular interest in forecasting extreme states. Unlike previously reported methodologies, SVMs are able to extract the dynamics using only a few past observed data points (Support Vectors, SV) out of the training examples. Considering statistical measures, the prediction model based on SVM demonstrated encouraging and promising results in a short-term prediction. Thus, the SVM method presented in this study suggests a competitive methodology for the forecast of hydrologic time series.

• 한국노년학
• /
• v.32 no.2
• /
• pp.415-429
• /
• 2012

This study attempts to develop the scale of 'Caregiving Affirmation Scale' for Korean Caregivers for the Aged and to testify the possibility of generalizing the scare. Mixed methods of qualitative and quantitative researches were used to achieve the purpose of the study. The steps of developing the scale were proceeded as follows: Firstly, 40 items were identified through the qualitative study and the literature reviews. Secondly, the content validity was verified through the professional group survey in addition to confirm the questionnaire items by the 1st survey. And thirdly, the construct validity and concurrent validity of the factors of 'Caregiving Satisfaction' were explored by performing the 2nd survey. As the results of the study, the total 16 items of 'Caregiving Affirmation scale' identified with the four sub-factors as follows; 1) Improvement of the care skill and a sense of fulfillment; 2) Possibility of contributions to other persons; 3) Acceptance of the aged; and 4) Improvement of Self-value. The reliability value of Cronbach's α was 0.89 with the high internal consistency and the confirmatory factor analysis showed the relationship between the items and each factor were also statistically significant. Thus, the content validity was verified. Also the correlation with the affirmative care recognition and the life satisfaction was 0.65, which meant the concurrent validity exists. The Caregiving Affirmation Scale for Korean Family Caregivers for the aged is expected to be used at the social welfare practice settings for the aged.

• 한국노년학
• /
• v.39 no.2
• /
• pp.285-304
• /
• 2019

The purpose of this study was to investigate the effects of leisure-based occupational therapy on leisure satisfaction, activities of daily living, and rehabilitation motivation in elderly patients with chronic diseases. In the study, Subjects were assigned to either the control or experimental group. The experimental group consisted of 10 and the control group of 14 patients. The experimental group receive a Leisure-based occupational therapy intervention, and the control group receive a conventional occupational therapy intervention. Leisure satisfaction, activities of daily living, and rehabilitation motivation were measured to Canadian occupational performance measure(COPM), Korean Activities of Daily Living(K-ADL·K-IADL), and Patient Questionnaire of Rehabilitation Motivation(PAREMO). Evaluation scores were compared before and after intervention to determine whether or not there were differences over time. And we examined the correlation between the variables. The results of this study were as follows: 1) The leisure-based occupational therapy has a significant effect on leisure satisfaction and rehabilitation motivation(p<.01). 2) The conventional occupational therapy has a significant effect on activities of daily living(p<.01). 3) There was a significant correlation between ADL and IADL(p<.01). 4) There was a significant correlation between leisure satisfaction and Rehabilitation Motivation(p<.01). Implications for occupational therapy include that we must offer appropriate approach with considering the interests and value of patients to them. And proposing studies to demonstrate the efficacy of occupational therapy approaches.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.121-122
• /
• 2023

As containerized maritime transport began in earnest, the size of container ships has steadily increased, and recently, the operation of 24,000 TEU-class vessels has become regular. However, concerns about the efficiency and productivity of such mega container ships from a port operational perspective have continued to be raised. The 10^th Busan International Port Conference requested an in-depth study on the trends of container ship enlargement by analyzing the order status of ultra-large container ships from major global liners. Generally, the factor that drives the upsizing of ships is the realization of economies of scale that lowers transportation costs per TEU, which leads to a higher level of cost reduction per unit transportation compared to the increase in fuel consumption due to transporting large amounts of cargo with a single ship. However, it is necessary to examine whether this trend of container vessel enlargement is feasible for port operations. To this end, this study compares and analyzes the productivity and efficeiency of different ship sizes to evaluate the effect of ship size on port operations.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.35 no.6
• /
• pp.128-137
• /
• 2023

In this study, the bearing pressure on the rubble mound of a gravity-based harbor structure with an arbitrarily shaped bottom was targeted. Assuming that the bottom of the structure is a rigid body, the rubble mound was modeled as a linear spring uniformly distributed on the bottom that resists compression only, and the bearing pressure evaluation formula was derived. It was confirmed that there were no errors in the derivation process by showing that when the bottom was square, the derived equation was converted to the equation used in the design. In addition, the validity of the derived equation was proven by examining the behavior and convergence value of the bearing pressure when an arbitrarily shaped bottom converges into a square one. In order to examine the adequacy of the method used in the current design, the end bearing pressure for the pre-designed breakwater cross-section was calculated and compared with the values in the design document. As a result, it was shown that the method used for design was not appropriate as it gave unsafe results. In particular, the difference was larger when the eccentricity of the vertical load was large, such as in the case of extreme design conditions.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.72-73
• /
• 2023

As containerized maritime transport began in earnest, the size of container ships has steadily increased, and recently, the operation of 24,000 TEU-class vessels has become regular. However, concerns about the efficiency and productivity of such mega container ships from a port operational perspective have continued to be raised. The 10th Busan International Port Conference requested an in-depth study on the trends of container ship enlargement by analyzing the order status of ultra-large container ships from major global liners. Generally, the factor that drives the upsizing of ships is the realization of economies of scale that lowers transportation costs per TEU, which leads to a higher level of cost reduction per unit transportation compared to the increase in fuel consumption due to transporting large amounts of cargo with a single ship. However, it is necessary to examine whether this trend of container vessel enlargement is feasible for port operations. To this end, this study compares and analyzes the productivity and efficeiency of different ship sizes to evaluate the effect of ship size on port operations.