• Journal of Korean Society of Transportation
• /
• v.14 no.4
• /
• pp.49-76
• /
• 1996

Until recently, the inductive loop detecters(ILD) have been used to collect a traffic information in a part of traffic manangment and control. The ILD is able to collect a various traffic data such as a occupancy time and non-occupancy time, traffic volume, etc. The occupancy time of these is very important information for traffic control algorithms, which is required a high accuracy. This accuracy may be improved by classifying a vehicle type with ILD. To classify a vehicle type based on a Analog Digital Converted data collect form ILD, this study used a typical and modifyed statistic method and General Learning Vector Quantization unsuperviser neural network model and a hybrid model of GLVQ and statistic method, As a result, the hybrid model of GLVQ neural network model is superior to the other methods.

• Journal of the Korean Society for Library and Information Science
• /
• v.28
• /
• pp.267-286
• /
• 1995

불리언 논리에 기초한 현재 정보검색 시스템은 두 가지 본질적인 문제점 - 1)부정확하거나 불완전한 질의 표현과 2)일관성 없는 색인 - 이 있다. 많은 연구자들이 신경망조직(neural network) 이 정보경색에 있어서 불완전한 질의표현 문제를 해결할 수 있다고 주장해 온 반면 일관성 없는 문제는 아직 해결하지 못한 채 남아있다. 본고에서는 이러한 두 가지 문제점을 해결하기 위해 신경망 조직과 귀납학습이 소개되고 있다. 또한 이 논문에서는 신경망 조직이 어떻게 귀납학습과 통합해서 효율적인 정보 검색시스템에 응용될 수 있는지를 보여주고 있다.

• The Journal of Information Systems
• /
• v.15 no.4
• /
• pp.211-224
• /
• 2006

This study investigates the application of data mining techniques such as artificial neural networks, rough sets, and induction teaming to the intrusion detection systems. To maximize the effectiveness of data mining for intrusion detection systems, we introduced the asymmetric costs with false positive errors and false negative errors. And we present a method for intrusion detection systems to utilize the asymmetric costs of errors in data mining. The results of our empirical experiment show our intrusion detection model provides high accuracy in intrusion detection. In addition the approach using the asymmetric costs of errors in rough sets and neural networks is effective according to the change of threshold value. We found the threshold has most important role of intrusion detection model for decreasing the costs, which result from false negative errors.

• Journal of Intelligence and Information Systems
• /
• v.4 no.2
• /
• pp.1-21
• /
• 1998

귀납적 학습방법들의 분류성능을 비교 평가하기 위하여 대표적 분류문제의 하나인 신용평가 문제를 사용하였다. 분류기로서 사용된 귀납적 학습방법론들은 통계학의 다변량 판별분석(MDA), 기계학습 분야의 C4.5, 신경망의 다계층 퍼셉트론(MLP) 및 Cascade Correlation Network(CCN)의 4 가지이며, 학습자료로는 국내 3개 신용평가기관이 발표한 신용등급 및 공포된 재무제표를 사용하였다. 신용등급 예측의 정확도에 의한 분류성능을 평가하였는데 연도별 평가와 시계열 평가의 두 가지를 실시하였다. Cascade Correlation Network이 가장 좋은 분류성능을 보였지만 4가지 분류기들 사이에 통계적으로 유의한 차이는 발견되지 않았다. 이는 사용된 학습자료가 갖는 한계로 인한 것으로 추정되지만, 성능평가 과정에 있어 학습자료의 전처리 과정이 분류성과의 제고에 매우 유효함이 입증되었다.

• Communications of Mathematical Education
• /
• v.30 no.2
• /
• pp.161-178
• /
• 2016

Mathematics problem based learning(PBL), which has recently attracted much attention, is a teaching and learning method to increase mathematical ability and help learning mathematical concepts and principles through problem solving using students' mathematical prerequisite knowledge. In spite of such a quite attention, it is not easy to apply and practice PBL actually in school mathematics. Furthermore, the recent instructional situations or environments has focused on student's self construction of their learning and its process. Because of this reason, to whom is related to mathematics education including math teachers, investigation and recognition on the degree of students' acquisition of mathematical thinking skills and strategies(for example, inductive and deductive thinking, critical thinking, creative thinking) is an very important work. Thus, developing mathematical thinking skills is one of the most important goals of school mathematics. In particular, recently, connection or integration of one subject and the other subject in school is emphasized, and then mathematics might be one of the most important subjects to have a significant role to connect or integrate with other subjects. While considering the reason is that the ultimate goal of mathematics education is to pursue an enhancement of mathematical thinking ability through the enhancement of problem solving ability, this study aimed to implement basically what is the meaning of the integrated thinking ability in problem based learning theory in Mathematics. In addition, using historical materials, this study was to develop mathematical materials and a sample of a concrete instructional guideline for enhancing integrated thinking ability in problem based learning program.

• School Mathematics
• /
• v.15 no.1
• /
• pp.101-120
• /
• 2013

International comparative studies of students' performance in mathematics have shown that Korean students possess very negative attitudes toward mathematics, while they are ranked as one of the highest in the cognitive achievement of mathematics. This has prompted mathematics educators to seek for a way to improve the quality of mathematics education. In this context, this research has been conducted to investigate the learning style of Korean middle school students under the assumption that it is of essence to understand the characteristics of our students as mathematics learners. For the purpose, in-depth interview had been conducted and sixteen middle students participated in the interview. The students were chosen to represent the average group of their age-cohorts based on their performance in mathematics and their SES. The interview was designed as a semi-structured clinical interview. In the interview, the students were given mathematical tasks dealing with central themes in the domain of function. Each student was given about 30 to 50 minutes to solve the tasks. After an interviewee finished the tasks, s/he was asked to explained how s/he solved the tasks. The researchers asked additional questions to clarify the students' understanding of the mathematical themes in the tasks and to identify their strategies for learning mathematics. The analysis of the in-depth interview has primarily identified the characteristics of the students' understanding of the main themes in function and then has been extended to investigate their characteristic styles for learning mathematics. The analysis of the interview identified the learning styles of the students as 'inductive learning based on prototypical cases', 'repeated practice of exemplar mathematics problems', 'disengaged learning', and 'double standards in learning mathematics'. Based on the results of the analysis, this research presents the implications for the improvement of mathematics education.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.775-782
• /
• 2002

As electronic commerce systems have been widely used, the necessity of adaptive e-commerce agent systems has been increased. These kinds of agents can monitor customer's purchasing behaviors, clutter them in similar categories, and induce customer's preference from each category. In order to implement our adaptive e-commerce agent system, we focus on following 3 components-the monitor agent which can monitor customer's browsing/purchasing data and abstract them, the conceptual cluster agent which cluster customer's abstract data, and the customer profile agent which generate profile from cluster, In order to infer more accurate customer's preference, we propose a 2 layered structure consisting of conceptual cluster and inductive profile generator. Many systems have been suffered from errors in deriving user profiles by using a single structure. However, our proposed 2 layered structure enables us to improve the qualify of user profile by clustering user purchasing behavior in advance. This approach enables us to build more user adaptive e-commerce system according to user purchasing behavior.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.

• Journal of the Korean Society of Earth Science Education
• /
• v.15 no.1
• /
• pp.47-61
• /
• 2022

In this study, We developed VR (Virtual Reality) geological resources based on the Geo Big Data of the Big Data platform that provided by the Korea Institute of Geoscience and Mineral Material (KIGAM). So students selected the theme of lessons by using these resources and we operated Remote classes using the materials that developed as to Virtual Reality. Therefore, the geological theme maps provided by the Geo Big Data Open Platform were reconstructed and produced materials were created for Study about Real Korean geological outcrops grounded in Virtual Reality. And Topographic information data was used to produce class materials for Remote classes. Twenty students were selected by Random sampling, and data were collected by conducting a survey including interviews to confirm the change in students' perception of remote classes in virtual reality geological data development and the effect of the classes, so data were analyzed through inductive categorization. The results of this study are as follows. First, students showed positive responses in terms of interest, utilization, and knowledge utilization as taking remote classes for developing geological data in virtual reality geological data. This is the result of showing the adaptability of diverse and flexible learning getting away from a fixed framework by motivating and encouraging students and inducing cooperation for communication. Second, students recognized distance education in the development of Virtual Reality geological data as 'Realistic hands-on learning process', 'Immersive learning process by motivation', and 'Learning process of acquiring knowledge in the field of earth science'.

• The Journal of the Korea Contents Association
• /
• v.16 no.12
• /
• pp.446-457
• /
• 2016

The purpose of the study was to understand the various aspects of learning experiences of Korean university students on K-MOOC. Analyses on the major motivation of the enrollment in a certain MOOC class, the actual learning experiences in the class and the perception of the achievement of the class were the three main foci of the current study. The study employed inductive content analysis as a major analysis tool. Reflective journals from 94 students who enrolled in K-MOOC classes were collected and analyzed at the end of the semester. The result of this study indicated that most of students selected the specific K-MOOC classes based on their general interests on the topics the class offered. Other factors such as intellectual curiosity, practical reasons for their study or work and popularity were also influential on the selection of MOOC classes. Watching videos, taking quizzes and taking tests were the three major sources of the students' satisfaction. Most students felt that K-MOOC is technically satisfactory. However, some students reported on simple errors and absence of advanced functions in the platform. Students perceived positively on their academic achievements of obtaining knowledge(remembering and understanding), attitudes (receiving), and skills through K-MOOC. This study ultimately showed a new awareness of learning experiences around K-MOOC from the perspective of the students. Future research is needed to understand the relationships between the students' learning experience and the students' performance in MOOC classes.