• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.239-245
• /
• 2018

So far, various researches have been conducted on evaluation of e-learning software, but subjective evaluation criteria are formed according to the classification presented from the viewpoint of the researcher rather than systematized form according to related standards. In addition, standards for software evaluation are continuously being supplemented for practical use, so it is urgent to establish evaluation bases by establishing evaluation criteria. Therefore, in order to establish the quality evaluation standard of e-learning software, this study analyzes the quality requirements of e-learning software based on the usability system among the quality characteristics of ISO/IEC 25000 series. This evaluation standard is distinguished by the fact that the evaluation standard of e-learning software that reflects the latest trend of related standardization has been established and practical utilization has been improved. It can be used effectively for quality evaluation and certification of e-learning software in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.373-379
• /
• 2016

This study examined the level-differentiated mathematic classes to offer basic data for effective college mathematics curriculum. Using the Kolb Learning Style, this study surveyed 213 college engineering students in 6 level-differentiated classes in one university and analyzed the significant consequence. The results showed that the ranking of the Learning Style in a superior mathematic class is Diverger, Accommodator, Assimilator, and Converger. Second, the ranking of the Learning Style in the inferior mathematics class was Accommodator, Diverger, Assimilator, and Converger. Third, for effective class of superior mathematics class, professors need to give sufficient time to analyze mathematics problems by the students themselves. Fourth, for an effective class of inferior mathematic class, professors need to use experimental and diverse teaching method to enhance the students' concentration and learning achievement. Based on this study, professors should develop teaching methods that fit the students' Learning Style and the properties of college mathematics curriculum.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.1
• /
• pp.141-148
• /
• 2018

In recent years, there has been a movement to create a learning city where people can learn and enjoy what they want whenever, wherever, and whenever, so that the self-realization of individuals and the quality of life can be enhanced to improve the competitiveness of the city as a whole, It is becoming active. Many developed countries in the world are supporting projects to build learning cities by utilizing schools and public facilities, thereby providing local residents with opportunities for self-growth and solving community problems. In Korea, too, there are various programs using idle facilities. However, there is a lack of education programs for local residents and learning programs by partnership with local communities. It is when spatial and software strategies are needed to build a successful learning city. Therefore, we want to systematically organize the spatial data of the facilities that can be learned, analyze the current problems, and explore various ways to utilize them. We also analyze the programs that residents need to implement real and efficient learning cities.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.6
• /
• pp.139-149
• /
• 2014

Much research has been conducted in educational robot, a new instructional technology, for K- 12 education. Several studies have shown that educational robot provides effective learning opportunities for students in both content areas of STEM(science, technology, engineering, and mathematics) and critical academic skills, such as collaboration, problem solving and communication skills. However, most studies to date on applications of educational robots have been conducted outside the formal education setting. This study analyzed the influence of using robots in an elementary school science class in Korea with regard to science learning motivation. A total of 121 students in fourth and fifth grades participated in the study. The experimental group was taught using robots in the science class, while the control group was taught using traditional methods. Analysis of covariance (ANCOVA) was conducted to compare the between-group differences in learning motivation before and after the experiment; an interview was also conducted for the experimental group. The study results showed a significant improvement (p<.05) in both learning motivation in the experimental compared with the control group. There was also positive response to learning with a robot. This study will play an important role in research on the use of educational robot in formal education in the future.

• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• Journal of Environmental Health Sciences
• /
• v.47 no.5
• /
• pp.462-471
• /
• 2021

Background: The number of synthesized chemicals has rapidly increased over the past decade. For many chemicals, there is a lack of information on toxicity. With the current movement toward reducing animal testing, the use of toxicity big data and deep learning could be a promising tool to screen potential toxicants. Objectives: This study identified potential chemicals related to reproductive and estrogen receptor (ER)-mediated toxicities for 1135 cleaning products and 886 laundry products. Methods: We listed chemicals contained in cleaning and laundry products from a publicly available database. Then, chemicals that potentially exhibited reproductive and ER-mediated toxicities were identified using the European Union Classification, Labeling and Packaging classification and ToxCast database, respectively. For chemicals absent from the ToxCast database, ER activity was predicted using deep learning models. Results: Among the 783 listed chemicals, there were 53 with potential reproductive toxicity and 310 with potential ER-mediated toxicity. Among the 473 chemicals not tested with ToxCast assays, deep learning models indicated that 42 chemicals exhibited ER-mediated toxicity. A total of 13 chemicals were identified as causing reproductive toxicity by reacting with the ER. Conclusions: We demonstrated a screening method to identify potential chemicals related to reproductive and ER-mediated toxicities utilizing chemical toxicity big data and deep learning. Integrating toxicity data from in vivo, in vitro, and deep learning models may contribute to screening chemicals in consumer products.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.253-263
• /
• 2021

Machine learning is the process of constructing a cost function using learning data used for learning and an artificial neural network to predict the data, and finding parameters that minimize the cost function. Parameters are changed by using the gradient-based method of the cost function. The more complex the digital signal and the more complex the problem to be learned, the more complex and deeper the structure of the artificial neural network. Such a complex and deep neural network structure can cause over-fitting problems. In order to avoid over-fitting, a weight decay regularization method of parameters is used. We additionally use the value of the cost function in this method. In this way, the accuracy of machine learning is improved, and the superiority is confirmed through numerical experiments. These results derive accurate values for a wide range of artificial intelligence data through machine learning.

• Journal of the Korean GEO-environmental Society
• /
• v.22 no.10
• /
• pp.13-19
• /
• 2021

Cracks in asphalt pavement occur due to changes in weather or impact from vehicles, and if cracks are left unattended, the life of the pavement may be shortened, and various accidents may occur. Therefore, studies have been conducted to detect cracks through images in order to quickly detect cracks in the asphalt pavement automatically and perform maintenance activity. Recent studies adopt machine-learning models for detecting cracks in asphalt road pavement using a Convolutional Neural Network. However, their practical use is limited because they require high-performance computing power. Therefore, this paper proposes a framework for detecting cracks in asphalt road pavement by applying a small deep learning model applicable to mobile devices. The small deep learning model proposed through the case study was compared with general deep learning models, and although it was a model with relatively few parameters, it showed similar performance to general deep learning models. The developed model is expected to be embedded and used in mobile devices or IoT for crack detection in asphalt pavement.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.668-673
• /
• 2021

As the fourth industrial revolution begins in earnest, related technologies are becoming a hot topic. Hardware development is accelerating to make the most of technologies such as high-speed wireless communication, and related companies are growing rapidly. Artificial intelligence often uses desktops in general for related research, but it is mainly used for the learning process of deep learning and often transplants the generated models into devices to be used by including them in programs, etc. However, it is difficult to produce results for devices that do not have sufficient power or performance due to excessive learning or lack of power due to the use of models built to the desktop's performance. In this paper, we analyze efficiency using boards with several Neural Process Units on sale before developing the performance of deep learning to match embedded boards, and deep learning accelerators that can increase deep learning performance with USB, and present a simple development direction possible using embedded boards.