• Korean Journal of Cognitive Science
• /
• v.28 no.2
• /
• pp.111-131
• /
• 2017

The connectionist model is one approach to studying language processing from a computational perspective. And building a representation in the connectionist model study is just as important as making the structure of the model in that it determines the level of learning and performance of the model. The connectionist model has been constructed in two different ways: localist representation and distributed representation. However, the localist representation used in the previous studies had limitations in that the unit of the output layer having a rare target activation value is inactivated, and the past distributed representation has the limitation of difficulty in confirming the result by the opacity of the displayed information. This has been a limitation of the overall connection model study. In this paper, we present a new method to induce distributed representation with local representation using abstraction of information, which is a feature of restricted Boltzmann machine, with respect to the limitation of such representation of the past. As a result, our proposed method effectively solves the problem of conventional representation by using the method of information compression and inverse transformation of distributed representation into local representation.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.1-6
• /
• 2019

Neural networks have been used to predict the direction of stock index movement from past data. The conventional research that predicts the upward or downward movement of the stock index predicts a rise or fall even with small changes in the index. It is highly likely that losses will occur when trading ETFs by use of the prediction. In this paper, a neural network model that predicts the movement direction of the daily KOrea composite Stock Price Index (KOSPI) to reduce ETF trading losses and earn more than a certain amount per trading is presented. The proposed model has outputs that represent rising (change rate in index ${\geq}{\alpha}$), falling (change rate ${\leq}-{\alpha}$) and neutral ($-{\alpha}$ change rate < ${\alpha}$). If the forecast is rising, buy the Leveraged Exchange Traded Fund (ETF); if it is falling, buy the inverse ETF. The hit ratio (HR) of PNN1 implemented in this paper is 0.720 and 0.616 in the learning and the evaluation respectively. ETF trading yields a yield of 8.386 to 16.324 %. The proposed models show the better ETF trading success rate and yield than the neural network models predicting KOSPI.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1295-1303
• /
• 2022

As the role of water distribution networks (WDNs) becomes more important, identifying abnormal events (e.g., pipe burst) rapidly and accurately is required. Since existing approaches such as field equipment-based detection methods have several limitations, model-based methods (e.g., machine learning based detection model) that identify abnormal events using hydraulic simulation models have been developed. However, no previous work has examined the impact of data uncertainties on the results. Thus, this study compares the effects of measurement error-induced pressure data uncertainty in WDNs. An artificial neural network (ANN) is used to predict nodal pressures and measurement errors are generated by using cumulative density function inverse sampling method that follows Gaussian distribution. Total of nine conditions (3 input datasets × 3 output datasets) are considered in the ANN model to investigate the impact of measurement error size on the prediction results. The results have shown that higher data uncertainty decreased ANN model's prediction accuracy. Also, the measurement error of output data had more impact on the model performance than input data that for a same measurement error size on the input and output data, the prediction accuracy was 72.25% and 38.61%, respectively. Thus, to increase ANN models prediction performance, reducing the magnitude of measurement errors of the output pressure node is considered to be more important than input node.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.81-86
• /
• 2024

The Image Signal Processor (ISP) converts RAW images captured by the camera sensor into user-preferred sRGB images. While RAW images contain more meaningful information for image processing than sRGB images, RAW images are rarely shared due to their large sizes. Moreover, the actual ISP process of a camera is not disclosed, making it difficult to model the inverse process. Consequently, research on learning the conversion between sRGB and RAW has been conducted. Recently, the ParamISP[1] model, which directly incorporates camera parameters (exposure time, sensitivity, aperture size, and focal length) to mimic the operations of a real camera ISP, has been proposed by advancing the simple network structures. However, existing studies, including ParamISP[1], have limitations in modeling the camera ISP as they do not consider the degradation caused by lens shading, optical aberration, and lens distortion, which limits the restoration performance. This study introduces Positional Encoding to enable the camera ISP neural network to better handle degradations caused by lens. The proposed positional encoding method is suitable for camera ISP neural networks that learn by dividing the image into patches. By reflecting the spatial context of the image, it allows for more precise image restoration compared to existing models.

• Journal of Preventive Medicine and Public Health
• /
• v.9 no.1
• /
• pp.11-24
• /
• 1976

This study was a part of large scale of a prospective study on attitudes of professional students in medicine, nursing and teaching toward population related issues in Korea. The study was first conducted in May 1974 and then in May 1975 for the 1974 class cohot using a questionaire consisted of attitude scales and other items developed by Lee. The purpose of stuay was twohold, namely, to determine the difference in students among specializations on one hand and between the first and second years in the 1974 class cohot regarding tile subject matter. A one-way analysis of variance was used for attitude scale, and absolute and relative frequency were computed for the analysis of non-attitude scale items by employing Fishers' Ratio and Duncan's multiple range test at 5% level and chi square test at 5% level as significance tests. The hypothesis 'students in health profession are more likely to have positive attitudes toward population related issues progressively as class year advances than students in teaching profession' was tested and the following results were obtained: 1) Nursing students were more likely to display favarable attitudes toward family planning than medical or teaching students although the class cohot showed slightly negative improvement in the second year. Medical and teaching students apperaed to have slightly improved attitudes in the second year. 2) Respondents in general perceived national family planning program as a means of population control and this tendency was more true among nursing students as the class year advances than two other professional groups of students. Students in teaching profession appeared to perceive it more as a means to improve individual family welfare while health students were likely to see as to improve maternal and child health. This tendency was progressively improved as the class year advanced. 3) The majority of students regardless of their respective specializations believed that family planning program should be directed toward the improvement of individual family welfare. No progressive changes in the class cohot were observed. 4) About the plan to use contraceptives in future, no singnificant differences were observes among different specializations nor in different class years. However, the majority was confirmed to have a plan to use contracepives in future. An increasing proportion of the undecided category was observed, as class year advanced among health students. 5) Students in health profession were found to be more favorable about 'more leisure opportunities' as motive for limiting number of children whereas education students indicated the reasons as 'facilitate ambitions' and 'economic base' The progressive changes toward positive direction in both groups were observed as the class years advanced. 6) Attitudes toward induced abortions of the health students were observed to be positively related to class years while an inverse relationship was found in teaching students who showed much less favor in the subject matter than health students. This phenomenon may be due to the different exposure to learning environments unique to respective specializations. 7) Health students were found to have more favorable attitudes toward population education in general than the teaching students. The teaching students appeared to have changed more to the negative direction when they became the second year while no such development was observed in health students. The teaching students seemed to hold a very conservative position with regard to sex education in schools. 8) About the equality of sexes, the nursing group was found to be most favorable while the reverse was true in the teaching group. A change in the negative direction as the class year advanced was found in the teaching group. 9) About questions related to fertility values-the 10 percent of respondents regardless of specialization indicated that they would maintain their single status in future, however no change was observed in the second year. The desired number of children was found to be two by the majority of students in nursing, medicine and teaching in order of high proportion. No changes in a different class year were observed. The childless marriage was seen by nursing students as a problem more than other students, but a slight change in positive direction was found when the nursing students became the second year. In summing, as data supported in the above, students in health profession demonstrated more favorable attitudes toward population related issues than the teaching students and this tendency became more apparent in the second year. It was noticed that health students were more conscious about the health aspect of population and family planning program while the teaching students gave more attention to the socioeconomic aspect. The sex variable seemed to have operated in the item related to the equality of sexes. In conclusion, as data presented in the above, the hypothesis of this study was accepted except in the few items. It should be noted that the limitation of this study is the short duration of the observation in measuring the possible attitude changes. It should include curriculum analysis for the respective specializations in order to indentify the area of curriculum impact on students in future study.