• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.179-186
• /
• 2023

For the future prosperity of any society, the sound growth of children is essential. Autism Spectrum Disorder (ASD) is a neurobehavioral disorder which has an impact on social interaction of autistic child and has an undesirable effect on his learning, speaking, and responding skills. These children have over or under sensitivity issues of touching, smelling, and hearing. Its symptoms usually appear in the child of 4- to 11-year-old but parents did not pay attention to it and could not detect it at early stages. The process to diagnose in recent time is clinical sessions that are very time consuming and expensive. To complement the conventional method, machine learning techniques are being used. In this way, it improves the required time and precision for diagnosis. We have applied TFLite model on image based dataset to predict the autism based on facial features of child. Afterwards, various machine learning techniques were trained that includes Logistic Regression, KNN, Gaussian Naïve Bayes, Random Forest and Multi-Layer Perceptron using Autism Spectrum Quotient (AQ) dataset to improve the accuracy of the ASD detection. On image based dataset, TFLite model shows 80% accuracy and based on AQ dataset, we have achieved 100% accuracy from Logistic Regression and MLP models.

• Journal of Agricultural Extension & Community Development
• /
• v.8 no.1
• /
• pp.25-40
• /
• 2001

The purposes of the study were to identify satisfaction and achievement of learning by female learner's characteristics, and to suggest measures to improve quality of education in internet education programs. In order to determine the educational effectiveness associated with the characteristics of learners, this study attempted to employ two way approaches by observing the degree of achievement for learning, which represents an instructor-oriented approach, and the degree of satisfaction for education, which represents a learner-oriented approach to enhance the quality of internet education for female learners. As an approach to evaluate the educational effectiveness, the degree of achievement in learning(Tyler's classical approach), and the degree of satisfaction for education (Scriven's consumer-oriented evaluation model) were utilized. A survey form was developed by the researcher after reviewing the various tools originated from Boshier, Cross, Gagne and Choi, and distributed to a panel of judges that examined the content validity of the instrument. The sample for the study consisted of 160 female learners from three universities in Seoul and capital area, and the survey form was used to collect data for this study. The SPSS WIN program was used in analyzing the data and a series of statistical tests were conducted including frequency, percentile, t-test, ANOVA, correlation, multiple regression, and factor analysis. The statistical significance level was 0.05. The following conclusion were drawn from this study of female internet education. First, it was evident that female internet learners tend to utilize information from internet, and this can be interpreted as participants' positive attitude, and voluntary participation. Second, educational facilities and services should be improved in the future, because the level of satisfaction was low in these areas compared to curriculum and educational methodology. Third, the participating factors influenced by the level of satisfaction for education of learner characteristics were the 'formation of inter-personal relationship and willingness to change' and the 'needs for education on internet', thus appeared that both social and educational needs influenced the level of satisfaction for education. Fourth, the degree of achievement in learning was higher in the order of 1) attitude 2) function 3) knowledge, thus, attitude change was the most important in achievement of learning. Fifth, the individual background that influenced the level of achievement in learning were age and educational experience. As for the individual level of achievement for learning, the younger and more educated group were more satisfied.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.3 s.309
• /
• pp.39-49
• /
• 2006

This paper proposes a hand-posture recognition method using reinforcement learning for the performance improvement of vision-based hand-posture recognition. The difficulties in vision-based hand-posture recognition lie in viewing direction dependency and self-occlusion problem due to the high degree-of-freedom of human hand. General approaches to deal with these problems include multiple camera approach and methods of limiting the relative angle between cameras and the user's hand. In the case of using multiple cameras, however, fusion techniques to induce the final decision should be considered. Limiting the angle of user's hand restricts the user's freedom. The proposed method combines angular features and appearance features to describe hand-postures by a two-layered data structure and reinforcement learning. The validity of the proposed method is evaluated by appling it to the hand-posture recognition system using three cameras.

• Journal of Engineering Education Research
• /
• v.13 no.6
• /
• pp.180-187
• /
• 2010

Design and management of information and industrial engineering (DMIIE) is a project-oriented junior/senior class that integrates the methodologies of industrial and information engineering in order to solve real-world problems. It examines social issues, engineering approaches to solve the problems and business models that can generate sustainable value for society. This course help students use their engineering knowledge to assess and solve the problems faced by local community. By conducting real-world projects, students get an opportunity to refine their oral and written communication skills. In this paper, the experience of DMIIE course is presented. The effects of the community-based learning for a senior design course are discussed. The possibility of using this blended type of design course to meet the ABEEK outcomes is also stated.

• Journal of The Korean Association of Information Education
• /
• v.22 no.4
• /
• pp.447-455
• /
• 2018

The purpose of this study is to investigate the effects of SW education using robot based on card coding on learning motivation and attitude of elementary school students. To do this, we conducted 8-hour SW education based on the CT concept of sequence, repetition, event, and control using the Truetrue, which is coded by command card for the 3rd grade of elementary school students. For the experiment, we examined the learning motivation for SW education and the attitude toward SW education based on the robot in advance. As a result, the students' motivation to learn SW education showed a statistically significant improvement. In addition, the attitude toward robot-based SW education improved statistically significantly as "good, convenient, interesting, easy, friendly, active, special, understandable, easy, simple". These results are expected to contribute to the expansion of education through various approaches of SW education.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.369-374
• /
• 2014

Path generation methods are required for safe and efficient driving in unmanned autonomous vehicles. There are two kinds of paths: global and local. A global path consists of all the way points including the source and the destination. A local path is the trajectory that a vehicle needs to follow from a way point to the next in the global path. In this paper, we propose a novel method for local path generation through machine learning, with an effective curve function used for initializing the trajectory. First, reinforcement learning is applied to a set of candidate paths to produce the best trajectory with maximal reward. Then the optimal steering angle with respect to the trajectory is determined by training an artificial neural network. Our method outperformed existing approaches and successfully found quality paths in various experimental settings, including the cases with obstacles.

• The Journal of the Korea Contents Association
• /
• v.15 no.11
• /
• pp.635-657
• /
• 2015

The current society characterized by knowledge-based information technology and multiculturalism put more emphasis on problem-solving skills, creative thinking, and communication skills than any other periods did. In response to the demand of the current times, multidisciplinary, or convergence courses and majors are being created and conducted in college education, yet, with the lack of specific teaching and learning model for the convergence courses. In this context, this study aimed to examine PBL as an instructional model for the convergent approaches in classroom, since PBL has been regarded as a model for fostering the 21st century learning capabilities for student coupled with the learning principles of authentic tasks, learner-centeredness, collaborative learning. This study, after conducted a PBL course for the general art education during the summer semester of 2014, analyzed the result using data collected from students' reflective journals, in-depth interviews, and SNS posts among the students. The result presented students' enhanced self-respect, increased interest in their learning and communication skills, and their recognition of the value on diversity and empathetic attitudes toward each others. In conclusion, PBL showed its potential as an alternative instructional model for the multidisciplinary and convergent learning in college education.

• Journal of Korean Elementary Science Education
• /
• v.25 no.4
• /
• pp.383-395
• /
• 2006

School science is often criticized as being too remote from both learners' interests and needs and as maintaining scientist-oriented approaches rather than humanistic ones. Although science is mainly taught on the basis of textbooks inside classrooms, the learning of science can not be confined to the boundaries of curriculum and school. Firstly, this paper briefly reviews and characterizes the historical development of science education with a series of analogies, and then suggests a new analogy, a so-called 'Hearts-On' approach to science education which emphasizes the humanistic aspects and the contextual dimension of science education. Secondly, it critically examines how much traditional school science teaching, particularly in physics, is limited in terms of the context of learning (i.e. textbook, laboratory, classroom, local, and global) as well as in terms of the context of the contents (i.e. physical, personal, social, and global). Thirdly, some recent attempts initiated by the author and colleagues are explained as examples of the Hearts-On approach to science education. In particular, a series of community-based science programs led by SNU and the development of a series of books on 'Contextual Physics'(i.e. Body Physics, Wearing Physics, Dining Table Physics, and Sports Physics) are outlined. Finally, the idea of scientific humanism is explored in relation to the context-rich approaches in science education. It is hoped that this paper helps us to reconsider how we can expand the world of science education beyond the boundaries of the curriculum and school and into a more humanistic one.

• Educational Technology International
• /
• v.14 no.1
• /
• pp.55-74
• /
• 2013

The diversity of students is getting increased in the contemporary classroom. To deal with the diversity, differentiated instruction (DI) should be considered as a way of providing alternative approaches to content, process and product according to the students' readiness, interest, and learning needs. Teachers have problems and difficulties in supporting different student's needs. In fact, teachers need proven tools including framework, guidelines or computing systems to help to practice DI in real context. According to the activity theory, tools influence on how people act and think and even their social practice, playing a crucial role in mediating the activities with people. In DI practice, there are also some studies about physical and abstract tools, but they have been not widely utilized by teachers in real schools. It means that more innovative tool to promote DI might be required. Therefore, to design a better tool to mediate the DI activities with teacher, case studies were conducted. In order to elicit the design implications, two physical and two abstract tools for DI practice were analyzed as case studies. Through the analysis of the case studies, eight design implications better to facilitate DI practice were suggested. This study has implications in suggesting design guidelines for teachers' tools to facilitate their DI practice by analyzing case studies in DI practices for an innovative tool in the educational practice.