• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.5
• /
• pp.34-45
• /
• 1997

In this paper, we present hardware implemcntation of self-organizing feature map (SOFM) neural networkwith constant adaptation gain and binary reinforcement function on FPGA. Whereas a tnme-varyingadaptation gain is used in the conventional SOFM, the proposed SOFM has a time-invariant adaptationgain and adds a binary reinforcement function in order to compensate for the lowered abilityof SOFM due to the constant adaptation gain. Since the proposed algorithm has no multiplication operation.it is much easier to implement than the original SOFM. Since a unit neuron is composed of 1adde $r_tracter and 2 adders, its structure is simple, and thus the number of neurons fabricated onFPGA is expected to he large. In addition, a few control signal: ;:rp sufficient for controlling !he neurons.Experimental results show that each componeni ot thi inipiemented neural network operates correctlyand the whole system also works well.stem also works well.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.287-294
• /
• 2007

Many classification algorithms for real world data suffer from a data class imbalance problem. To solve this problem, various methods have been proposed such as altering the training balance and designing better sampling strategies. The previous methods are not satisfy in the distribution of the input data and the constraint. In this paper, we propose a focused sampling method which is more superior than previous methods. To solve the problem, we must select some useful data set from all training sets. To get useful data set, the proposed method devide the region according to scores which are computed based on the distribution of SOM over the input data. The scores are sorted in ascending order. They represent the distribution or the input data, which may in turn represent the characteristics or the whole data. A new training dataset is obtained by eliminating unuseful data which are located in the region between an upper bound and a lower bound. The proposed method gives a better or at least similar performance compare to classification accuracy of previous approaches. Besides, it also gives several benefits : ratio reduction of class imbalance; size reduction of training sets; prevention of over-fitting. The proposed method has been tested with kNN classifier. An experimental result in ecoli data set shows that this method achieves the precision up to 2.27 times than the other methods.

• Journal of Korean Society of Transportation
• /
• v.35 no.4
• /
• pp.348-359
• /
• 2017

Recently, various public transportation activation policies are being implemented in order to mitigate traffic congestion in metropolitan areas. Especially in the metropolitan area, the bus information system has been introduced to provide information on the current location of the bus and the estimated arrival time. However, it is difficult to predict the travel time due to repetitive traffic congestion in buses passing through complex urban areas due to repetitive traffic congestion and bus bunching. The previous bus travel time study has difficulties in providing information on route travel time of bus users and information on long-term travel time due to short-term travel time prediction based on the data-driven method. In this study, the path based long-term bus travel time prediction methodology is studied. For this purpose, the training data is composed of 2015 bus travel information and the 2016 data are composed of verification data. We analyze bus travel information and factors affecting bus travel time were classified into departure time, day of week, and weather factors. These factors were used into clusters with similar patterns using self organizing map. Based on the derived clusters, the reference table for bus travel time by day and departure time for sunny and rainy days were constructed. The accuracy of bus travel time derived from this study was verified using the verification data. It is expected that the prediction algorithm of this paper could overcome the limitation of the existing intuitive and empirical approach, and it is possible to improve bus user satisfaction and to establish flexible public transportation policy by improving prediction accuracy.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.243-257
• /
• 2021

The purpose of this study was to verify the mediating effects of shared leadership between team leader's facilitation competency and team effectiveness. To achieve the purpose, this study conducted a survey of 377 members in the team-operated organization. The collected data were analyzed by using SPSS 26.0. The results were as follows; Firstly, communication and creating of participation climate as a subcomponent of team leader's facilitation competency had a significantly positive effect(+) on team effectiveness(team performance, team commitment). Also the task and systematization had a significantly positive influence(+) on team commitment. Secondly, not only communication and creating of participation climate of team leader's facilitation competency but also task and systematization had a significantly positive effect(+) on the shared leadership. Thirdly, the shared leadership had a significantly positive effect(+) on team effectiveness(team performance, team commitment). Lastly, the shared leadership in the relationship between team leaders' facilitation competency and team effectiveness was confirmed to have a partially mediated effect. This study is meaningful in that it theoretically expanded the facilitation research by finding the relationship between team leaders' facilitation competency and other variables as well as suggested practical implications by presenting directions for the roles and competencies of leader and member required by the modern organization.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.7 no.1
• /
• pp.27-33
• /
• 2012

The purpose of this research is to investigate the effects of Lubric Learning Strategy Program, to solve problems of the Middle School Students' learning, on learning motivation, self-efficacy and self-regulation. The objects of this investigation was 60 students sampled from the first, second and third year students of Y Middle school in Seoul, which was divided equally -30 students each- into experimental group and control group. The progress covered 10 weeks period, a hour and half every week on Tuesdays and Thursdays. The conclusion derived from the results and discussion is as follows: First, the learning motivation of experimental group participated in the Lubric Learning Strategy Program to solve learning problems has changed quite meaningfully compared to the control group. It showed positive changes in all suborn ate variables such as class motivation, continuing motivation, intrinsic motivation, and extrinsic motivation. Second, the self-efficacy of experimental group participated in the Lubric Learning Strategy Program to solve learning problems has changed quite meaningfully compared to the control group. These results showed positive changes in subordinate variables such as preference level to subjects and self-control efficacy, though did not show notable changes in confidence area. However as confidence area doesn't really matter in total score, Lubric Learning Strategy Program is considered to have good influence in self-efficacy. Third, the self-regulation of experimental group participated in the Lubric Learning Strategy Program to solve learning problems has changed quite meaningfully compared to the control group. It showed positive changes in all subordinate variables such as self-control mode and inhibitory will mode. Fourth, the use on learning strategy of experimental group participated in the Lubric Learning Strategy Program to solve learning problems has changed quite meaningfully compared to the control group. These results showed positive changes in subordinate variables such as rehearsal, elaboration, organization and inspection, though did not show notable changes in schedule and control area. However, as the total score of use on learning strategy has changed prominently, Lubric Learning Strategy Program is considered to have good influence in use of learning strategy.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.12
• /
• pp.78-89
• /
• 1999

Previous wavelet network structures are determined by considering the relationship between wavelet windows distribution of training patterns that are transformed into time-frequency space. Because it is separated two algorithms that determines wavelet network structure and that modifies parameters of network, learning process that minimizes output error of network is executed after the network structure is determined. But this method has some weakness that training patterns must be transformed into time-frequency space by additional preprocessing and the network structure should be fixed during learning process. In this paper, we propose a new constructing method for wavelet network structure by using differences between the output and the desired response without preprocessing. Because the algorithm perform network construction and error minimizing process simultaneously, it can determine the number of hidden nodes adaptively as with the complexity of problems. In addition, the network structure is optimized by inserting new hidden nodes in the area that has maximum error and extracting hidden nodes that has no effect to the output of network. This algorithm has no constraint condition that all training patterns must be known, because it removes preprocessing procedure for training patterns and it can be applied effectively to systems that has time varying outputs.

• Archives of design research
• /
• v.15 no.1
• /
• pp.143-152
• /
• 2002

As the Internet has been a daily instrument of our lives, the numbers of Internet users are increasing rapidly. Especially, we have to pay special attention to about rapid increasing of juvenile users. In the 1990's, Kids are growing up literally surrounded by new technologies and mu1timedia experiences. For these kids, most of the techno1ologies that we adults find surprising or even incredible are a part of their everyday landscape, a fact of life. Currently, only few of research and discussion has gone into understanding this field. And most of these web sites, set importance on furnishing information only. So educational characters of web are not manifested fully as well as children soon get board with learning with Internet so that feel difficulties in searching and accepting information. At this point, we must try to develop educational sites Not only to show information but also to offer a rich and entertaining time for kids while providing playful teaming and increased technological fluency. Fer this purpose, Web site should be all about combining play with learning. Site navigation should be easy and the pages load quickly. The page download time is also being considerable, which could send kids withy mouse-fingers looking for entertainment elsewhere. Everything about the site must have a familiar feel, uses adequate colors to be satisfied with the juveniles. Multimedia can help the communications in the websites. To maximize the educational effect, technological research and continues invest are need, in addition to usability test.

• Journal of Gifted/Talented Education
• /
• v.26 no.2
• /
• pp.365-387
• /
• 2016

This study examined the effects of students'perceptions of classroom on self-regulatory strategy use, persistent intention, and achievement in an online Science gifted program. The sample included 434 middle and high school students who participated in the 3-months online gifted program. Participants volunteerly surveyed on their perceptions of classroom (appeal, challenge, choice, meaningfulness, academic self-efficacy), self-regulatory strategy use, and persistent intention. Student achievement data was collected from online learning system. Multiple Regression was conducted to analyze the effect of students'perceptions of classroom on various dependent variables. The results of this study showed that (1) students use of rehearsal strategy was positively related to academic self-efficacy among the sub-variables of students'perceptions of classroom and the use of rehearsal strategy was negatively related to challenge; (2) the use of elaboration strategy was positively related to challenge and meaningfulness; (3) the use of time management strategy was positively related to academic self-efficacy and the use of resource management strategy was positively related to challenge; and (4) students' persistent intention was related to appeal, challenge and meaningfulness, achievement was related to challenge.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.572-587
• /
• 2008

The Self-organizing Feature Map(SOFM) that is one of unsupervised neural networks is a very powerful tool for data clustering and visualization in high-dimensional data sets. Although the SOFM has been applied in many engineering problems, it needs to cluster similar weights into one class on the trained SOFM as a post-processing, which is manually performed in many cases. The traditional clustering algorithms, such as t-means, on the trained SOFM however do not yield satisfactory results, especially when clusters have arbitrary shapes. This paper proposes automatic clustering on trained SOFM, which can deal with arbitrary cluster shapes and be globally optimized by graph cuts. When using the graph cuts, the graph must have two additional vertices, called terminals, and weights between the terminals and vertices of the graph are generally set based on data manually obtained by users. The Proposed method automatically sets the weights based on mode-seeking on a distance matrix. Experimental results demonstrated the effectiveness of the proposed method in texture segmentation. In the experimental results, the proposed method improved precision rates compared with previous traditional clustering algorithm, as the method can deal with arbitrary cluster shapes based on the graph-theoretic clustering.

• Journal of Gifted/Talented Education
• /
• v.24 no.3
• /
• pp.445-462
• /
• 2014

The purpose of the present study is to compare paper and pencil test utilized to identify gifted students so far to the recently introduced teacher observation-recommendation system. More specifically, this study compared intelligence, career patterns, and self- regulated learning abilities of gifted students who were identified through those two different identification system to explore the possibility of the newly introduced teacher observation-recommendation system. The results show that there was no significant difference in the aspect of overall IQ score. However, students who were identified through the observation-recommendation system showed significantly higher scores at some subscores of intelligence test, such as vocabulary application, comprehension, and schematization. In the aspects of career patterns, about 72% of gifted students who were identified through the previous paper and pencil test belonged to the 'investigative' category of Holland. But more diverse career patterns such as enterprising, social, realistic, conventional including investigative categories were found in those students who were identified by the observation-recommendation system. There were also significant differences in the self-regulated learning abilities between two groups of students. Practical implications of the study were discussed in depth.