• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.791-801
• /
• 2021

In this paper, an educational case that can be applied as artificial intelligence literacy education for preservice teachers and incumbent teachers was studied. To this end, a case of educating the operating principle of an artificial neural network that recognizes images is proposed. This training case focuses on the basic principles of artificial neural network operation and implementation, and applies the method of finding parameter optimization solutions required for artificial neural network implementation in a spreadsheet. In this paper, we focused on the artificial neural network of supervised learning method. First, as an artificial neural network principle education case, an artificial neural network education case for recognizing two types of images was proposed. Second, as an artificial neural network extension education case, an artificial neural network education case for recognizing three types of images was proposed. Finally, the results of analyzing artificial neural network training cases and training satisfaction analysis results are presented. Through the proposed training case, it is possible to learn about the operation principle of artificial neural networks, the method of writing training data, the number of parameter calculations executed according to the amount of training data, and parameter optimization. The results of the education satisfaction survey for preservice teachers and incumbent teachers showed a positive response result of over 70% for each survey item, indicating high class application suitability.

• Journal of Life Science
• /
• v.31 no.4
• /
• pp.410-417
• /
• 2021

Next-generation sequencing (NGS) is a high-throughput technique for sequencing large numbers of DNA fragments that are prepared from a genome. This sequencing technique has been used to elucidate whole genome sequences of living organisms and to analyze complementary DNA (cDNA) or chromatin immunoprecipitated DNA (ChIPed DNA) at the genome level. After NGS, the use of proper tools is important for processing and analyzing data with reasonable parameters. However, handling large-scale sequencing data and programing for data analysis can be difficult. The Galaxy platform, a public web service system, provides many different tools for NGS data analysis, and it allows researchers to analyze their data on a web browser with no deep knowledge about bioinformatics and/or programing. In this study, we explain the procedure for preparing chromatin immunoprecipitation-sequencing (ChIP-seq) libraries and steps for analyzing ChIP-seq data using the Galaxy platform. The data analysis steps include the NGS data upload to Galaxy, quality check of the NGS data, premapping processes, read mapping, the post-mapping process, peak-calling and visualization by window view, heatmaps, average profile, and correlation analysis. Analysis of our histone H3K4me1 ChIP-seq data in K562 cells shows that it correlates with public data. Thus, NGS data analysis using the Galaxy platform can provide an easy approach to bioinformatics.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.175-186
• /
• 2021

The roles and functions of domestic public libraries are diversifying, but various problems have emerged due to internally biased book lending. In addition, due to the 4th Industrial Revolution, public libraries have introduced a book recommendation system focusing on popular books, but the variety of books that users can access is limited. Therefore, in this study, the public library unborrowed book recommendation system was implemented limiting its spatial scope to Duryu Library in Daegu City to enhance the satisfaction of public library users, by using the loan records data (213,093 cases), user information (35,561 people), etc. and utilizing methods like cluster analysis, topic modeling, content-based filtering recommendation algorithm, and conducted a survey on actual users' satisfaction to present the possibility and implications of the unborrowed book recommendation system. As a result of the analysis, the majority of users responded with high satisfaction, and was able to find the satisfaction was relatively high in the class classified by specific gender, age, occupation, and usual reading. Through the results of this study, it is expected that some problems such as biased book lending and reduced operational efficiency of public libraries can be improved, and limitations of the study was also presented.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.51-63
• /
• 2021

Identifying characters who appear in a story and analyzing their relationships is essential to understanding the story. This paper aims to identify the two actants (or character roles) as Helper and Opponent in Greimas's Actantial model by identifying Subject (i.e., protagonist) and analyzing the emotional interactions between the Subject and the two actants (Helper/Opponent). Our proposed method consists of three steps. First, we identify objects (i.e., characters) appearing in the text story. Next, we extract relational information through the interaction of the characters, and then classify emotions in the text expressed as relational information. Finally, we represent the flow of emotional relations among characters as a directed graph. The node with the highest degree is considered as the Subject because it includes the most relational information. The node that sends the most positive/negative emotions to the Subject is considered as the Helper/Oppenent, respectively. Our research contributes to the computer-based narrative understanding by providing a computational method that automatically extracts the three key character roles (Subject, Helper, and Opponent) from the text story.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.77-87
• /
• 2021

With the development of the Internet and personal computers, various and complex attacks begin to emerge. As the attacks become more complex, signature-based detection become difficult. It leads to the research on behavior-based log anomaly detection. Recent work utilizes deep learning to learn the order and it shows good performance. Despite its good performance, it does not provide any explanation for prediction. The lack of explanation can occur difficulty of finding contamination of data or the vulnerability of the model itself. As a result, the users lose their reliability of the model. To address this problem, this work proposes an explainable log anomaly detection system. In this study, log parsing is the first to proceed. Afterward, sequential rules are extracted by Bayesian posterior probability. As a result, the "If condition then results, post-probability" type rule set is extracted. If the sample is matched to the ruleset, it is normal, otherwise, it is an anomaly. We utilize HDFS datasets for the experiment, resulting in F1score 92.7% in test dataset.

• Journal of agricultural medicine and community health
• /
• v.46 no.4
• /
• pp.218-229
• /
• 2021

Objectives: The purpose of this study was to suggest the direction of the Healthy Village project for rural residents in accordance with the prolonged COVID-19 by investigating the digital environment for major health problems, the role of a health leader, necessary projects, and non-face-to-face projects for Healthy Village members in the COVID-19 epidemic. Methods: Telephone interview surveys were conducted with 585 residents from November 30, 2020 to December 21, 2020. Results: Health problems perceived by residents were in the order of concerns about infection (48.5%), depression (32.5%), difficulties in using medical services (9.4%), and lack of exercise (7.7%). The role of the health committee in the COVID-19 situation was "encouraging people to follow quarantine rules" with 91.3%. As a necessary health village project, there was a high demand for the provision of health products and mental health projects. 17.9% said that there is a computer or smart device connected to the Internet in their home, and 42.2% said that there is someone in the village who can easily get help if there is a problem in accessing and using Internet information. 36.9% were able to watch videos, and 22.2% were able to use the Internet through public facilities. Conclusion: In a public health crisis, where the provision of public health and medical services to rural residents is not smooth, it is necessary to manage health and quarantine through health leaders in the village, and it is required to establish a digital environment infrastructure that can conduct community participatory health village projects in a non-face-to-face environment.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.281-289
• /
• 2021

This study aims to investigate the influence of the components of the startup ecosystem on the business performance of startups, focusing on the mediating effect of the location environment. By presenting the insight that the popularization of start-ups can be an alternative for job creation thanks to the government's start-up support policy considering the location environment, it is possible to construct an optimal configuration scenario between the components of the start-up ecosystem and the location environment. Furthermore, it is expected to contribute to the improvement of corporate management performance. To achieve this goal, we performed a survey and the subjects were domestic start-up company employees with less than 7 years of experience. The results show that the components of the start-up ecosystem had a significant effect on the business performance of start-up companies and the location environment and on the management performance of start-up companies according to the mediation of the location environment.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.199-204
• /
• 2021

Digital substation refers to a substation that digitizes functions and communication methods of power facilities such as monitoring, measuring, control, protection, and operation based on IEC 61850, an international standard for the purpose of intelligent power grids. Based on the intelligent operating system, efficient monitoring and control of power facilities is possible, and automatic recovery function and remote control are possible in the event of an accident, enabling rapid power failure recovery. With the development of digital technology and the expansion of the introduction of eco-friendly renewable energy and electric vehicles, the spread of direct current distribution systems is expected to expand. MVDC is a system that utilizes direct current lines with voltage levels and transmission capacities between HVDCs applied to conventional transmission systems and LVDCs from consumers. Converting existing lines in substations, where most power equipment is alternating current centric, to direct current lines will reduce transmission losses and ensure greater current capacity. The process bus of a digital substation is a communication network consisting of communication equipment such as Ethernet switches that connect installed devices between bay level and process level. For MVDC linkage to existing digital substations, the process level was divided into two buses: AC and DC, and a system that can be comprehensively managed in conjunction with diagnostic IEDs as well as surveillance and control was proposed.