• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.327-333
• /
• 2019

The Fuel-cut driving is started when the acceleration pedal released with transmission gear engaged. Fuel economy of the vehicle improves by active fuel-cut driving. A deep-learning technique is proposed to predict fuel-cut driving with vehicle speed, acceleration and road gradient data in the study. It's 3~10 of hidden layers and 10~20 of variables and is applied to the 9600 data obtained in the test driving of a vehicle in the road of 12km. Its accuracy is about 84.5% with 10 variables, 7 hidden layers and Relu as activation function. Its error is regarded from the fact that the change rate of input data is higher than the rate of fuel consumption data. Therefore the accuracy can be better by the normalizing process of input data. It's unnecessary to get the signal of vehicle injector or OBD, and a deep-learning technique applied to the data to be got easily, like GPS. It can contribute to eco-drive for the computing time small.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.81-89
• /
• 2019

In order to foster talented people needed for the 4th Industrial Revolution, learner-centered classes that meet the characteristics and needs of students are needed. In particular, the learner-centered student-active class is more meaningful for gifted students who have diverse needs and interests. In order to meet these demands, this study developed a learner-centered science gifted education teaching-learning model based on flipped learning, and analyzed various results revealed after applying the developed program to the gifted class. Based on the results, we proposed a plan for more efficient operation of future learner-centered science gifted education programs.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.21 no.1
• /
• pp.1-15
• /
• 2019

The purpose of this study is to develop ICT utilization learning materials for a chapter titled 'Environment Friendly Clothing and Reform of Clothing' in technology and home economics textbooks for Year 2 students in middle school. The research methods were selected from ten types of junior high school technology textbooks, which were revised in 2009, and mainly focused on items such as jeans, shirts, shirts, cardigans, and skirts, Using selected textiles and basic design t-shirts, five works were made using structural and decorative details. The results of this study are as follows. First, textile products shown in the chapter 'Environment Friendly Clothing and Reform of Clothing' are most commonly worn and found in daily life. With regard to a reuse method, structural changes to clothing are proposed. For example, cases relating to the changing of a neckline or the use of a shirt or a sleeve are presented. There are some decoration methods adapted in reuse; using ornaments, such as spangles and emblems, patchwork, shirring and the constucting of collages. Second, following the plan, 5 items are designed with T-shirts, shirts, cardigans and skirts. For the T-shirt design, other fabrics including organza and neoplan are used from design point of view, in addition to reused textile products. Detailed structural changes of necklines, sleeves and collars and detailed and the ornamentation method including shirring, smoking, patchwork and collages are used. Third, this study proposes 6 categories (profile, design planning, diagram, reused textile product, production method and order and pictures of T-shirts developed) under the title of 'T-shirt Made Out of Disposed Clothing', selecting a blog as active teaching and learning material as a part of the ICT utilization in educational settings.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.25-33
• /
• 2019

Recently, universities have been strengthening software basic education to be active in the era of the fourth industrial revolution. Non-majored students need a variety of teaching methods because they have low knowledge of programming or a lack of connectivity with major courses. Therefore, in this paper, a learning model applying the step-by-step blind programming practice based on the Demonstration Modeling Making model was designed and applied to the actual lecture. As a result of analyzing the problem solving ability of the learner, it was confirmed that the learner's self - solving ratio increased as parking progressed. In the following study, it is necessary to analyze the learner's learning results in various aspects and to study effective teaching methods according to the difficulty of the learning contents.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.127-132
• /
• 2021

Korea is both a resource-poor country and a energy-consuming country. In addition, the use and dependence on electricity is very high, and more than 20% of total energy use is consumed in buildings. As research on deep learning and machine learning is active, research is underway to apply various algorithms to energy efficiency fields, and the introduction of building energy management systems (BEMS) for efficient energy management is increasing. In this paper, we constructed a database based on energy usage by device per household directly collected using smart plugs. We also implement algorithms that effectively analyze and predict the data collected using RNN and LSTM models. In the future, this data can be applied to analysis of power consumption patterns beyond prediction of energy consumption. This can help improve energy efficiency and is expected to help manage effective power usage through prediction of future data.

• The Mathematical Education
• /
• v.60 no.2
• /
• pp.159-172
• /
• 2021

The purpose of this study is to compare and analyze the effects of physical manipulative and exploratory geometry software on the spatial sense for 5^th grade elementary school students in learning nets. For this purpose, ton experimental group used Geofix, an operational learning tool, and the experimental group used Cabri 3D, an exploratory geometry software to learn the nets of solids. The comparison group was learned by worksheet only without any manipulative or software. Spatial sense tests were conducted before and after to determine the level, and eye tracking were used to analyze the strategies of students in solving nets problems. As a result, it was confirmed that the using Geofix group was the most effective for the spatial sense, and Cabri 3D could also be a good tool for learning the nets of solids. In addition, after learning the nets of solids, the analytical strategy, which was the most effective strategy for students' solving strategies, increased. In the process of solving spatial tasks such as the spatial sense tasks, eye tracking technology become a very useful tool for exploring students' strategies, so it is expected that objective and useful data will be collected through more active use in the future.

• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.552-560
• /
• 2021

With the recent development of the art distribution system, interest in art investment is increasing rather than seeing art as an object of aesthetic utility. Unlike stocks and bonds, the price of artworks has a heterogeneous characteristic that is determined by reflecting both objective and subjective factors, so the uncertainty in price prediction is high. In this study, we used LSTM Recurrent Neural Network deep learning model to predict the auction winning price by inputting the artist, physical and sales charateristics of the Korean artist. According to the result, the RMSE value, which explains the difference between the predicted and actual price by model, was 0.064. Painter Lee Dae Won had the highest predictive power, and Lee Joong Seop had the lowest. The results suggest the art market becomes more active as investment goods and demand for auction winning price increases.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.4
• /
• pp.183-189
• /
• 2021

In recent years, active research has been devoted toward developing a monitoring system using ambient vibration data in order to quantitatively determine the deterioration occurring in a structure over a long period of time. This study developed a low-cost edge computing system that detects the abnormalities in structures by utilizing the dynamic characteristics acquired from the structure over the long term for ensemble learning. The system hardware consists of the Raspberry Pi, an accelerometer, an inclinometer, a GPS RTK module, and a LoRa communication module. The structural abnormality detection afforded by the ensemble learning using dynamic characteristics is verified using a laboratory-scale structure model vibration experiment. A real-time distributed processing algorithm with dynamic feature extraction based on the experiment is installed on the Raspberry Pi. Based on the stable operation of installed systems at the Community Service Center, Pohang-si, Korea, the validity of the developed system was verified on-site.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.347-353
• /
• 2022

In the restaurant industry, start-ups are active due to high demand from consumers and low entry barriers. However, the restaurant industry has a high closure rate, and in the case of franchises, there is a large deviation in sales within the same brand. Thus, research is needed to prevent the closure of food franchises. Therefore, this study examines the factors affecting franchise sales and uses machine learning techniques to predict the success and failure of franchises. Various factors that affect franchise sales are extracted by using Point of Sale (PoS) data of food franchise and public data in Gangnam-gu, Seoul. And for more valid variable selection, multicollinearity is removed by using Variance Inflation Factor (VIF). Finally, classification models are used to predict the success and failure of food franchise stores. Through this method, we propose success and failure prediction model for food franchise stores with the accuracy of 0.92.

• Journal of Sasang Constitutional Medicine
• /
• v.33 no.4
• /
• pp.1-9
• /
• 2021

Objectives The purpose of this study was to check whether the classification of the individual's Body Mass Index (BMI) could be predicted by analyzing the voice data constructed at the Korean medicine data center (KDC) using machine learning. Methods In this study, we proposed a convolutional neural network (CNN)-based BMI classification model. The subjects of this study were Korean adults who had completed voice recording and BMI measurement in 2006-2015 among the data established at the Korean Medicine Data Center. Among them, 2,825 data were used for training to build the model, and 566 data were used to assess the performance of the model. As an input feature of CNN, Mel-frequency cepstral coefficient (MFCC) extracted from vowel utterances was used. A model was constructed to predict a total of four groups according to gender and BMI criteria: overweight male, normal male, overweight female, and normal female. Results & Conclusions Performance evaluation was conducted using F1-score and Accuracy. As a result of the prediction for four groups, The average accuracy was 0.6016, and the average F1-score was 0.5922. Although it showed good performance in gender discrimination, it is judged that performance improvement through follow-up studies is necessary for distinguishing BMI within gender. As research on deep learning is active, performance improvement is expected through future research.