• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.11
• /
• pp.7439-7446
• /
• 2015

The purpose of this study was to find the risk factors of injury by FMS and to investigate the effects of 12-weeks' combined training program on body imbalance, physical fitness, muscle strength and FMS score in woman rugby players of the national team. Fourteen subjects were woman rugby national players to participate in the 17th Incheon Asian Games. These players tested FMS and performed 12 weeks' (May~Aug, 2014) combined training program (4days, 120min${\geq}$). Statistical evaluation was undertaken using paired t-test (pre vs. post). The results of this study were as follows; Frist, the score of FMS test on Deep Squat, Hurdle Step, Active Straight Leg Raise, and Trunk Stability Push up were significantly increased after 12 weeks' combined training program (p<.05), and also Inline Lunge (p<.01) and Rotary Stability (p<.001) were significantly increased. However, Shoulder Mobility was not significantly increased(p=.104) although the tendency of increased was FMS score. Second, the sum of the entire item was significantly increased after combined training(p<.001). These results suggest that 12-weeks' combined training program has effect of improving FMS score and low-injury risk in woman rugby national players. Therefore, we consider that FMS have effect on prevention of athletic injury and improvement of athletic performance in woman rugby national players.

• Asia Marketing Journal
• /
• v.11 no.3
• /
• pp.125-149
• /
• 2009

Many studies have been conducted to find the causal factors that influence salesforce performance and turnover behavior. This study focuses on the turnover intention of salesperson. Specifically this study argues that the causal relationship among job performance, job stress and turnover intention will be mediated by job conflict of salesperson. We develop the hypotheses from the conceptual framework and empirically test them for the salespersons of lifetime insurance companies. Based on the previous studies and conceptual framework developed in this study, we derive 8 hypotheses. <Figure 1> shows the conceptual framework from which hypotheses are derived. Hypotheses for the empirical test are as follows: H1: Job performance will have negative impact on the turnover intention. H2: Job performance will have negative impact on the job conflict. H3: Job stress will have the positive relationship with the turnover intention. H4: Job stress will have the positive relationship with the job conflict. H5: Job conflict will have the positive relationship with the turnover intention. H6: The negative impact of job performance on the job conflict will be moderated by job education/training. H7: The positive impact of job stress on the job conflict will be moderated by job training. H8: The positive impact of job conflict on the turnover intention will be moderated by the switching costs. To test the 8 hypotheses, we estimate the level of fitness and parameters of structure equation model by using AMOS 5.0. <Table 1> shows the results of empirical tests for hypotheses. <Table 2> shows the moderating effect of job training. <Table 3> shows the moderating effect of switching costs. This empirical study finds interesting results. The job training has the moderating effect on the causal relationship between job performance and job conflict. But it is found that the job training has not the moderating effect on the causal relationship between job performance and job conflict. These results may be due to the fact that Korean insurance company mainly focuses on training of the job skill and knowledge, not motivational elation of salesforce.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.269-271
• /
• 2019

우리에겐 익숙하고 쉽게 느껴지지만, 누군가에겐 어려운 것들이 존재한다. 예로 시각 장애인에게는 거리를 돌아다니는 것, 거리를 달린다는 것은 상당한 용기가 필요한 일이다. 경북대학교 재학 중인 시각 장애인 김경훈 학우는 자신의 유튜브 채널에 등교하는 거리에 익숙해지도록 여러 번 걸어 다니며 연습하는 모습의 영상을 올린 적이 있다. 또 다른 시각장애인은 국민 청원에 트레이닝에 대한 지원 요청을 한 적이 있다. 우리는 이런 사례들을 조사하여 거리에 나가지 않아도, 위험요소를 생각하지 않아도 할 수 있는, 그 누구도 차별 받지 않고 모두가 자연스럽게 운동에 집중할 수 있는 홈 트레이닝 시스템을 구현하였다.

• Journal of Digital Convergence
• /
• v.10 no.11
• /
• pp.395-402
• /
• 2012

This study has been conducted to design and implement smart phone-based application which can keep records effectively to improve athletes' ability. To boost their performance, they need to receive training as realistic as possible. As a way to do that, training should be performed with some fitness equipments, sporting apparatus, facilities, and conditions. However, it is also possible to improve their ability by motivating athletes with checking and recording their performance. This study ascertains that using scoring records actually motivates athletes when comparing the result of youth basketball team using the records keeping system with that of not using it. Accordingly, smart phone-based records keeping application has been designed and developed. Also, through a survey targeting athletic coaches who have used the system, training efficiency has been measured and it turns out that it actually motivates athletes to improve their abilities.

• Journal of the Korean Applied Science and Technology
• /
• v.35 no.2
• /
• pp.412-422
• /
• 2018

The purpose of this study was to investigate effects of 12-weeks aerobic exercise and taekwondo exercise on brain wave activation and brain-derived neurotrophic factors in undergraduate male students. Twenty four male subjects participated in this study. They were separated into a Control group(CG; n=8), Aerobic training group (ATG; n=8) and Taekwondo training group(TTG; n=8). ATG and TTG participated in Aerobic exercise training and Taekwondo exercise training for 12 weeks, 50~80 minutes per day, 3 times a week at 60~80% HRR respectively. All data were analyzed by repeated measures two-way ANOVA. As a result, there were no significant differences in the body composition and brain activation in all groups. However BDNF increased significantly after 12 weeks in the aerobic training groups(ATG). It is suggest that 12 weeks of regular Taekwondo exercise training did not statistically affect brain activation and neurotrophic factors in undergraduate students.

• Journal of Korean Public Health Nursing
• /
• v.25 no.1
• /
• pp.17-27
• /
• 2011

Purpose: The study examined the effect of exercise public health center exercise program on strength, balance, body composition and blood pressure in healthy elderly women. Method: Thirty healthy elderly women were divided into three 12-week exercise groups: Tai-Chi (n=10), silver dance (n=10), and band exercise (n=10). The results were analyzed by two-way repeated ANOVA and paired t-test using SPSS 12.0 program. Results: Body weight and body mass index were significantly decreased in the Tai-Chi and silver dance groups. In addition, there was a significant increase in balance time and reduced diastolic blood pressure in Tai-Chi participant. Grip strength was significantly increased in Tai-Chi and silver dance participants, but there was no effect in the band exercise group. Agility was significantly increased in the band exercise group. Conclusion: Tai-Chi and silver dance may be beneficial to improve fitness of elderly people, although the details remain to be elucidated.

• Journal of Korean Physical Therapy Science
• /
• v.12 no.4
• /
• pp.25-31
• /
• 2005

이 사례연구는 2002년 10월 15일 칼에 의한 좌상으로 경추 3-4번의 불완전 척수손상을 입은 25세의 남자 환자가 최초 병원에서 2002년 12월 한달 간의 치료를 마친 후, 2003년 1월 3일부터 4월 28일까지 태릉에 위치한 N 재활센터에서 주 5회 2시간의 자세조절 훈련, 심폐지구력 훈련, 웨이트 훈련, 스포츠(축구, 소프트 볼), 여가활동(등산)의 프로그램을 적용하여 척추손상 환자의 사회적응을 돕기위한 재활 프로그램의 다양화를 꾀하기 위한 기초 선행 작업으로 시작되었다. 신체능력을 평가하기 위한 측정도구는 관절가동범위(Range of Motion), 수동근력검사(Muscle Manual Test), 경직(Spasticity), 신체체력(Physical Fitness), 발란스(Balance: one leg stand), 상대적인 등속성 하지근력(Isokinetic Muscle Strength) 그리고 신체조성(Body Composition)로 하였다. 재활기간을 통해 처음 시작 일자에서 45일 간격으로 3차례의 측정을(1월 3일부터 4월 28일까지 실시하였다) 실시하였다. 최초 환자의 상태는 부분적으로 일상생활의 도움을 받아야 하는 상태로 동작을 시작하려 할 때 경직이 발생되어 옷을 입고 벗기, 신발 신고 벗기, 운전, 식사, 보행과 계단보행, 경사보행에서 보조자의 도움이 필요했으며, 작은 물건 잡기와 글씨쓰기, 타이핑 작업은 불가능 한 상태였다. 또한 스포츠 활동과 여가활동 역시 불가능 한 상태였다. 3달 15일간의 기간 동안 환자는 복학을 준비하기 위해 적극적으로 치료에 임했으며, 결과는 다음과 같았다. 신체조성은 재활 훈련을 통해 체중, 체지방율(%), 복부지방율(WHR)의 많은 감소를 가져왔다. 경직을 측정하는 Ashworth Scale은 정상에 가깝게 감소하였다. 관절가동범위는 고관절, 무릎, 발목에서 모두 증가하였다. 수동근력검사(0-9)는 많은 향상을 가져왔다. 신체체력능력 항목에서 근지구력의 윗몸일으키기와 팔굽히기, 악근력, 유연성으로 앉아 체간 숙이기, 민첩성으로 사이드 스텝, 순발력의 서전트는 모두 크게 향상되었다. 환자의 일상능력에서도 옷을 입고 벗기, 신발 신고 벗기, 운전, 식사, 보행과 계단보행, 경사보행에서 보조자의 도움이 필요없었으며, 타이핑 작업은 5손가락을 모두 사용하지는 않았지만, 1분에 80타로 큰 향상을 가져왔다. 또한 축구와 소프트볼, 등산을 달에 1회 정도 실시하여 약간의 도움만으로 가능하게 되었다.

• Biomedical Science Letters
• /
• v.19 no.1
• /
• pp.61-69
• /
• 2013

The aim of this study was to evaluate the effect of exercise-based cardiac rehabilitation on pro- and anti-inflammatory markers in patients with acute coronary syndrome (ACS). ACS patients who underwent percutaneous coronary intervention (PCI) and took medicine during phase II of rehabilitation were recruited for study. Subjects were divided into two groups; exercise group (EX, n=21) and a non-exercise group (non-EX, n=13). Supervised exercise program in hospital consisted of treadmill and bicycle exercise was performed three times per week for 6 weeks. Patients of EX received individual counseling, including knowledge of heart disease, risk factor modification, and physical training. Cardiopulmonary fitness, body composition, and biochemical blood factors were analyzed before and after experiment. There was no significant difference in serum levels of hs-CRP and TGF-${\beta}1$ between groups, and between time intervals. But there was a significant decrease in serum levels of IL-18 (P<.001). And there was a significant increase in ratio of IL-18 to IL-10 (P<.01) and serum levels of IL-10 (P<.001). After cardiac rehabilitation, there was significant increase in exercise duration (P<.001), maximal oxygen uptake ($VO_{2peak}$; P<.001) and decrease in submaximal rate-pressure product (sRPP; P<.05) in EX. In conclusion, exercise-based cardiac rehabilitation during phase II in patients with ACS after PCI decreased serum IL-18 (pro-inflammatory) content and ratio of IL-18 to IL-10 in serum (highly related with disease recurrence), and increased serum IL-10 (anti-inflammatory) content. In addition, it led to improved cardiopulmonary fitness.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.417-426
• /
• 2024

In general, the implementation of machine learning requires prior knowledge and experience with deep learning models, and substantial computational resources and time are necessary for data processing. As a result, machine learning encounters several limitations when deployed on embedded processors. To address these challenges, this paper introduces a novel approach where a genetic algorithm is applied to the convolution operation within the machine learning process, specifically for performing a selective convolution operation.In the selective convolution operation, the convolution is executed exclusively on pixels identified by a genetic algorithm. This method selects and computes pixels based on a ratio determined by the genetic algorithm, effectively reducing the computational workload by the specified ratio. The paper thoroughly explores the integration of genetic algorithms into machine learning computations, monitoring the fitness of each generation to ascertain if it reaches the target value. This approach is then compared with the computational requirements of existing methods.The learning process involves iteratively training generations to ensure that the fitness adequately converges.