• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.6
• /
• pp.306-313
• /
• 2005

Conditional branch prediction is an important technique for improving processor performance. Branch mispredictions, however, waste a large number of cycles, inhibit out-of-order execution, and waste electric power on mis-speculated instructions. Hence, the branch predictor with higher accuracy is necessary for good processor performance. In global-history-based predictors like gshare and GAg, many mispredictions come from commit update of the history. Some works on this subject have discussed the need for speculative update of the history and recovery mechanisms for branch mispredictions. In this paper, we present a simple mechanism for recovering the branch history after a misprediction. The proposed mechanism adds an age_counter to the original predictor and doubles the size of the branch history register. The age_counter counts the number of outstanding branches and uses it to recover the branch history register. Simulation results on the Simplescalar 3.0/PISA tool set and the SPECINTgS benchmarks show that gshare and GAg with the proposed recovery mechanism improved the average prediction accuracy by 2.14$\%$ and 9.21$\%$, respectively and the average IPC by 8.75$\%$ and 18.08$\%$, respectively over the original predictor.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Journal of Korean Academy of Nursing
• /
• v.30 no.3
• /
• pp.776-790
• /
• 2000

Every year the number of the elderly increases in Korea thanks to the improvemen of social and economical levels and the development of medicine. However, many problems such as insufficent care and the isolation of the elderly have been commonplace. This trend exists not only because of increased lifespan but also the changing social structure of the nuclear family. Accordingly, inspite of the development of medicine, geriatric diseases including circulatory diseases are increasing in proportion of elderly population, as well as the severity. Therefore, it is important to emphasize that health care programs provide the best possible health care and functional capacities in terms of healthy elderly lifestyles. Especially, the phenomena of aging and geriatric diseases taking place with the elderly naturally are affected by lifestyle and the drastic changes in exercise patterns. This study aims to improve geriatric health by introducing a rhythmic movement program for the elderly to estabilish a health-promoting self-care system and by developing quality of life, perceived health status, their physical and physiological functions and emotional state. The theoretical framework used in this dissertation is derived from the Health-Promoting Self-Care System Model (Simmons, 1990), which integrates the Self-Care Deficit Nursing Theory (Orem, 1985), the interaction model of Client Health Behavior (Cox, 1982) and the Health Promotion Model (Pender, 1987). As a quasi-experimental design, the nonequivalent control group pretest-posttest design is utilized for this study. The subjects of this study consist of 64 people, over 65 years old who live in 2 nursing homes for the aged located in S city , Kyong-gi province and volunteered for this study from July, 12, 1999 to September, 17, 1999. They are divided into two groups：33 in the experimental group and 31 in the control group. The experimental group particpated in the Rhythmic Movement Program at the nursing home, which was comprised of 45 minutes a session, 5 sessions a week during 9 weeks. In order to measure the results of the Rhythmic Movement Program, aspects of perceived health status, balance, flexibility, grip strength, leg strength, heart rate, blood pressure, depression, anxiety and the quality of life were measured before and after participating in the Rhythimic Movement Program for the experimental group after 9 weeks, as well as the control group. The collected data were processed by SPSS PC+ and analyzed by the X2 test, t-test, ANCOVA and the Pearson Correlation Coefficient. The results of this study are as follows: 1. The perceived health status conditions in the experimental group show statistically significant improvement when compared to the control group (F=17.51, p=.000). 2. The physical and physiological functions, that is, balance (F=17.51, p=.000), flexibility (F=8.01, p=.006), grip strength (F=3.21, p=.018) and leg strength (F=25.78, p=.000) in the experimental group are higher than the control group. The vital signs, that is, the number of heart rate (F=.022, p=.884), systolic pressure (F=1.73 p=.193), and diastolic pressure (F=2.74, p=.103) in the experimental group compared to the control group decreased, but doesn't show statistically significant differences. Immune responses (F=5.13, p=.003) showed statistically significant increases in the experimental group when compared to the control group. 3. The emotional state are improved, that is, degree of depression (F=11.56, p=.001) and degree of anxiety (F=9.14, p=.004) in the experimental group showed statistically significant decreases. 4. The quality of life in the experimental group (F=3.03, p=.037) showed statistically significant differences compared to the control group. 5. The observations of the relationships among the perceived health status, emotional state , the quality of life, the relationships between the perceived health status, the degree of depression (r=-.653, p=.000) and the degree of anxiety (r=-.786, p=.000) were in contrary propotions, while the relationships between the perceived health status and the quality of life (r=.234, p=.008) were in direct propotion. In conclusion, the Rhythmic Movement Program used in this study for geriatric nursing care is simple and safe for application to the elderly and shows significant effects by implementing 5 sessions a week for 9 weeks. The Rhythmic Movement Program improves the quality of life, maintains as well as improves the physical and physiological fuctions and emotional state, therefore this program is strongly recommended for positive applications for independant geriatric nursing health care.