• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2060-2077
• /
• 2019

Recently, mobile healthcare services have attracted significant attention because of the emerging development and supply of diverse wearable devices. Smartwatches and health bands are the most common type of mobile-based wearable devices and their market size is increasing considerably. However, simple value comparisons based on accumulated data have revealed certain problems, such as the standardized nature of health management and the lack of personalized health management service models. The convergence of information technology (IT) and biotechnology (BT) has shifted the medical paradigm from continuous health management and disease prevention to the development of a system that can be used to provide ground-based medical services regardless of the user's location. Moreover, the IT-BT convergence has necessitated the development of lifestyle improvement models and services that utilize big data analysis and machine learning to provide mobile healthcare-based personal health management and disease prevention information. Users' health data, which are specific as they change over time, are collected by different means according to the users' lifestyle and surrounding circumstances. In this paper, we propose a prediction model of user physical activity that uses data characteristics-based long short-term memory (DC-LSTM) recurrent neural networks (RNNs). To provide personalized services, the characteristics and surrounding circumstances of data collectable from mobile host devices were considered in the selection of variables for the model. The data characteristics considered were ease of collection, which represents whether or not variables are collectable, and frequency of occurrence, which represents whether or not changes made to input values constitute significant variables in terms of activity. The variables selected for providing personalized services were activity, weather, temperature, mean daily temperature, humidity, UV, fine dust, asthma and lung disease probability index, skin disease probability index, cadence, travel distance, mean heart rate, and sleep hours. The selected variables were classified according to the data characteristics. To predict activity, an LSTM RNN was built that uses the classified variables as input data and learns the dynamic characteristics of time series data. LSTM RNNs resolve the vanishing gradient problem that occurs in existing RNNs. They are classified into three different types according to data characteristics and constructed through connections among the LSTMs. The constructed neural network learns training data and predicts user activity. To evaluate the proposed model, the root mean square error (RMSE) was used in the performance evaluation of the user physical activity prediction method for which an autoregressive integrated moving average (ARIMA) model, a convolutional neural network (CNN), and an RNN were used. The results show that the proposed DC-LSTM RNN method yields an excellent mean RMSE value of 0.616. The proposed method is used for predicting significant activity considering the surrounding circumstances and user status utilizing the existing standardized activity prediction services. It can also be used to predict user physical activity and provide personalized healthcare based on the data collectable from mobile host devices.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.65-70
• /
• 2019

The purpose of this study is to understand the college students' needs for software curriculum which based on surveys from educational satisfaction of the software lecture evaluation, as well as to find out the improvement plan by applying the text content analysis method. The research method used the text content analysis program to calculate the frequency of words occurrence, key words selection, co-occurrence frequency of key words, and analyzed the text center and network analysis by using the network analysis program. As a result of this research, the decent points of the software education network are mentioned with 'lecturer' is the most frequently occurrence after then with 'kindness', 'student', 'explanation', 'coding'. The network analysis of the shortage points has been the most mention of 'lecture', 'wish to', 'student', 'lecturer', 'assignment', 'coding', 'difficult', and 'announcement' which are mentioned together. The comprehensive network analysis of both good and shortage points has compared among key words, we can figure out difference among the key words: for example, 'group activity or task', 'assignment', 'difficulty on level of lecture', and 'thinking about lecturer'. Also, from this difference, we can provide that the lack of proper role of individual staff at group activities, difficult and excessive tasks, awareness of the difficulty and necessity of software education, lack of instructor's teaching method and feedback. Therefore, it is necessary to examine not only how the grouping of software education (activities) and giving assignments (or tasks), but also how carried out group activities and tasks and monitored about the contents of lectures, teaching methods, the ratio of practice and design thinking.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.139-152
• /
• 2019

In the fourth industrial revolution and the era of convergence and integration, on the situation that the internal colleges are needed active change included in the improvement of educational quality, I tested it on the purpose of empirical analysis with SPSS v.18 how colleges' efforts on the first periodic Organization Evaluation And Accreditation System(OEAAS) affects on the Perceived Management Performances on the perspective of BSC. As the test result, the Degree of Awareness of Colleges' Efforts on the OEAAS affects on just Colleges' Learning and on Growth. The Degree Propriety of Preparation of the OEAAS affects on Customer Performance, on Internal Process Performance, and, on Finance Performance. And the Degree of Satisfaction of Internal Assessment affects on all of BSC 4 performances. The results of this research could be used on making the management idea of colleges' performance on the OEAAS. In the future, it would be needed advanced researches which are able to make relatedness to the expanse of management performance with the OEAAS.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• Journal of Korean Library and Information Science Society
• /
• v.50 no.2
• /
• pp.149-168
• /
• 2019

The purpose of this study is to analyze the characteristics of teacher librarians' efficacy and to propose some ways to enhance their efficacy. To do this, questionnaires on 30 teacher librarians who participated in the level 1 certification program of K university in 2018 were conducted. The results showed that their average efficacy was 3.38, the efficacy of teaching method was 3.60, the collective efficacy was 3.38, and the personal efficacy was 3.18. They had high personal efficacy on classroom management, the willingness to lead poor students and the possibility of problem student guidance, and collective efficacy on conflict management with fellow teachers and parents. On the other hand, personal efficacy in problem analysis and guidance for problem students, difficult contents and course instruction were low. Also, the collective efficacy of the conflict between the manager and the education office was low. They have a strong willingness to improve teaching methods for students and showed high efficacy about student synchronization and preparation for teaching. However, they were aware of the lack of learning skills and the lack of various teaching methods. The variables influencing their efficacy were graduation, education level, school size, and degree. Especially, the higher the education level, the more confident and enthusiastic about teaching problemmatic students and disadvantaged students. In addition, teacher librarians with high academic standards showed high confidence in conflict resolution with peers and parents and teaching methods. The improvement direction to enhance their efficacy in this study are increasing the ratio of teacher education in the field of education, reforming teacher librarians training before appointment, establishing supervision organizations for school libraries and improving their professionalism by going to graduate school.

• Therapeutic Science for Rehabilitation
• /
• v.8 no.2
• /
• pp.79-88
• /
• 2019

Objective : Aphasia interferes with communication between the patient and conversation partner. Adequate communication is essential not only for the patient but also for caregiver education and training Method : This study examined the benefits of parental education and group training in terms of improving the communication of six aphasic patients and their caregivers(family members). Caregiver education provided caregivers with information on stroke and aphasia, and group training was conducted according to the experimental learning cycle. Result : As a result, communication increased in terms of sending and receiving messages or interactive communication. Furthermore, the questionnaire analysis showed that caregivers learned more about aphasia and had confidence in using facilitation strategies. Conclusion : Giving educational opportunities to patients and caregivers promotes caregiver's knowledge and positively interacts.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.165-173
• /
• 2019

Recently, a variety of programs for elementary school students that utilize play in their curricula are supported. In this study, we are trying to draw up ways to activate play education based on the elements necessary for the play education to be effectively provided on the field and the current operational status. In order to achieve the research goal, nine participants of play experts and parents were selected for the focus group interview (FGI). The FGI consist of five questions: (1) opinions on the establishment and joint operation of the organization to support play and parents' education; (2) opinions based on experience in participating in existing training programs; (3) activation plan of play & education program; (4) competencies required by members of the organization; (5) evaluation of program for quality improvement. Through the FGI survey, we drew ideas for the operation of play & education programs to promote positive growth and support systemic programs of both preschoolers and elementary students. In order for play & education to be active in the field of education, a center where play & education and parents' education can be conducted at the same time should be established and operated so that the education can be integrated with play. Based on these findings, we proposed follow-up research in the direction of achieving specific goals and enhancing the quality of play education.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.457-475
• /
• 2021

As Korean society enters an aged society, there is an increasing situation in which various generations coexist in the workplace. This study aimed to analyze corporate reverse mentoring in light of generational exchange. Through the case study methods using literature research and interviews, we categorized the objectives of starting reverse mentoring programs in domestic and foreign companies, and analyzed the possibility of generational exchange with the cases of company A in the US and B in Korea extracted by purposive sampling. Based on social exchange theory, organizational age theory, and generational solidarity theory, the analysis framework presented three propositions: 1) mutual benefit 2) balanced contribution, and 3) sustainability. As a result of the case analyses, there were three main objectives of introducing reverse mentoring: learning IT/social media, promoting corporate diversity, and understanding new trends in the younger generation. In the case of A company in the US and B company in Korea, there was a similarity in mutual benefit and balanced contribution. However, regarding sustainability, there was room for improvement in company B in Korea unlike company A in the US. We expect that reverse mentoring will provide important criteria for success in terms of generational exchange within organizations where various generations coexist in the future.

• Science of Emotion and Sensibility
• /
• v.24 no.1
• /
• pp.37-44
• /
• 2021

A study was conducted on the effects of improving concentration by obscuring the peripheral vision using a blindfold that only covers the left and right sides of the field of view. The blindfold was trapezoidal in shape (5 × 4.8 cm in length and width) and was fixed to the left and right sides of the glasses with fixing clips. The material was a black-colored polypropylene (PP) and weighed 2.3 g including the clip. Qualitative and quantitative evaluations were performed on 50 healthy college students during the 15 days of using a blindfold. The qualitative analysis was performed utilizing a questionnaire regarding the improvement of concentration and the structure of the blindfold. EEG was measured while watching a learning video that required attention for quantitative analysis, and signal power and ERD/S analyses were performed for the mid β band (15-20 Hz) at the F4 position, which was the frontal lobe. The results showed that 40 of the 50 people reported improved concentration when they wore a vision shield, and 80% of the total subjects found it to be effective. From the quantitative evaluation, the ERS peak (p = 0.023) and the ERD + ERS peak value showed a significant difference (p = 0.017). In conclusion, concentration still improved even if only the left and right visual fields were used. Thus, it is expected that blindfolding could be used in various environments that require concentration.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.403-410
• /
• 2020

In addition to the research on noise removal and super-resolution using the data restoration (Output result) function of Autoencoder, research on the performance improvement of clustering using the dimension reduction function of autoencoder are actively being conducted. The clustering function and data restoration function using Autoencoder have common points that both improve performance through the same learning. Based on these characteristics, this study conducted an experiment to see if the autoencoder model designed to have excellent data recovery performance is superior in clustering performance. Skip connection technique was used to design autoencoder with excellent data recovery performance. The output result performance and clustering performance of both autoencoder model with Skip connection and model without Skip connection were shown as graph and visual extract. The output result performance was increased, but the clustering performance was decreased. This result indicates that the neural network models such as autoencoders are not sure that each layer has learned the characteristics of the data well if the output result is good. Lastly, the performance degradation of clustering was compensated by using both latent code and skip connection. This study is a prior study to solve the Hanja Unicode problem by clustering.