• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.81-90
• /
• 2020

This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 hours and 35 minutes. Various information was manually transcribed such as orthography, pronunciation, dialect, noise, and medical information using Praat. Baseline speech recognition experiments were used to depict problems related to speech recognition in the emergency medical domain. The Korean conversational speech data presented in this paper are first-stage data in the emergency medical domain and are expected to be used as training data for developing conversational systems for emergency medical applications.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.1
• /
• pp.9-18
• /
• 2021

Recently, the rapid proliferation, introduction, and application of the fourth industrial revolution technology has emerged as a trend in the construction market. Building Information Model (BIM) technology is a multidimensional information system that forms the basis of the fourth industrial revolution technology. The river sector utilizing this information-based system is also being actively reviewed, for example, the current measures for maintenance. In recent years, active research and current work should be done to reflect the need for river experts to introduce BIM into the river field. In addition, the development of tools and support software for establishing various information systems is essential for the activation of facility maintenance information systems reflecting advanced technology and to establish and operate management plans. A study on the maintenance of river facilities involves using existing drawings to build a three-dimensional (3D) information model, check the damage utilizing it, and inform it, and utilize it as the data for maintenance reinforcement. This study involved determining a method to build a river facility without the existing information system and using the property maintenance information with 3D modeling to provide a more effective and highly utilized management plan to check maintenance operations and manage damages.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.24 no.5
• /
• pp.95-102
• /
• 2020

For the purpose of developing a PE fiber-reinforced highly ductile cementitious composite having high tensile strain capacity more than 2% under the condition of containing aggregates with large particle size, this study investigated the tensile behavior of composites according to the particle size and distribution of aggregates in the composite. Compared with the mixture containing silica sand of which particle size is less than 0.6 mm, mixtures containing river sand and/or gravel with the maximum particle size of 2.36 mm, 4.75 mm, 5.6 mm, 6.7 mm were considered in the experimental design. The particle size distributions of aggregates were adjusted for the optimized distribution curves obtained from modified A&A model by blending different sizes of aggregates. All the mixtures presented clear strain-hardening behavior in the direct tensile tests. The mixtures with the blended aggregates to meet the optimum curves of aggregate size distributions showed higher tensile strain capacity than the mixture with silica sand. It was also found that the tensile strain capacity was improved as the maximum size of aggregate increased which resulted in wider particle size distribution. The mixtures with the maximum size of 5.6 mm and 6.7 mm presented very high tensile strain capacities of 4.83% and 5.89%, respectively. This study demonstrated that it was possible to use coarse aggregates in manufacturing highly ductile fiber-reinforced cementitous composite by adjusting the particle size distribution.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1277-1290
• /
• 2020

Water resources which is formed of surface and groundwater, are considered as one of the pivotal natural resources worldwide. Since last century, the rapid population growth as well as accelerated industrialization and explosive urbanization lead to boost demand for groundwater for domestic, industrial and agricultural use. In fact, better management of groundwater can play crucial role in sustainable development; therefore, determining accurate location of groundwater based groundwater potential mapping is indispensable. In recent years, integration of machine learning techniques, Geographical Information System (GIS) and Remote Sensing (RS) are popular and effective methods employed for groundwater potential mapping. For determining the status of the integrated approach, a systematic review of 94 directly relevant papers were carried out over the six previous years (2015-2020). According to the literature review, the number of studies published annually increased rapidly over time. The total study area spanned 15 countries, and 85.1% of studies focused on Iran, India, China, South Korea, and Iraq. 20 variables were found to be frequently involved in groundwater potential investigations, of which 9 factors are almost always present namely slope, lithology (geology), land use/land cover (LU/LC), drainage/river density, altitude (elevation), topographic wetness index (TWI), distance from river, rainfall, and aspect. The data integration was carried random forest, support vector machine and boost regression tree among the machine learning techniques. Our study shows that for optimal results, groundwater mapping must be used as a tool to complement field work, rather than a low-cost substitute. Consequently, more study should be conducted to enhance the generalization and precision of groundwater potential map.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• Journal of Wetlands Research
• /
• v.23 no.1
• /
• pp.27-34
• /
• 2021

In this study, the main influencing factors of the occurrence of cyanobacteria at each of the eight Multifunctional weirs were derived using a random forest, and a categorical prediction model based on a Algal bloom warning system was developed. As a result of examining the importance of variables in the random forest, it was found that the upstream points were directly affected by weir operation during the occurrence of cyanobacteria. This means that cyanobacteria can be managed through efficient security management. DO and E.C were indicated as major influencers in midstream. The midstream section is a section where large-scale industrial complexes such as Gumi and Gimcheon are concentrated as well as the emissions of basic environmental facilities have a great influence. During the period of heatwave and drought, E.C increases along with the discharge of environmental facilities discharged from the basin, which promotes the outbreak of cyanobacteria. Those monitoring sites located in the middle and lower streams are areas that are most affected by heat waves and droughts, and therefore require preemptive management in preparation for the outbreak of cyanobacteria caused by drought in summer. Through this study, the characteristics of cyanobacteria at each point were analyzed. It can provide basic data for policy decision-making for customized cyanobacteria management.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.15 no.6
• /
• pp.81-94
• /
• 2020

Based on innovative technologies and new start-up ideas, startups have been actively researched on the entrepreneurship needed to strengthen the organization's capabilities and generate results in the start-up process. This study studied the entrepreneurial orientation on the performance of startups in the Philippines and the financial and non-financial performance of enterprises. This study carried out not only the entrepreneurial orientation to the performance of Filipino startups but also the role of social capital as parameters in the performance of enterprises. The empirical research was completed for 93 Philippine startups and the suitability of the research model was evaluated with a PLS-based structural equation model. The results of the study first confirmed that the enterprise orientation of Philippine startups has a positive impact on both financial and non-financial performance of the enterprises. Second, the entrepreneurial orientation of Philippine startups has been shown to have a positive effect on both the structural, cognitive and relational dimensions of social capital. Third, it was found that the relevant dimensions of social capital mediated both the corporate orientation and the relationship between the financial and non-financial performance of the entity. Entrepreneurial orientation has been confirmed to be directly or indirectly affecting the performance of startups through social capital. These findings reaffirmed that entrepreneurial orientation is still a valid important factor in developing countries as well as in countries such as Korea and the United States. Based on this study, we have identified the need for research from a more integrated perspective, such as the concept of strategic orientation. Finally, practical implications were presented to reflect the findings analyzed.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.23-30
• /
• 2021

Various customizing services are also being introduced in the fashion industry in line with the diversification of consumer tastes and the demand for small production of multiple varieties. However, barriers to entry are high for consumers who are not customized, and various functions are rather complicated. This study selected the three platforms that provide the most similar services to Marple, the No. 1 fashion platform sales, as comparative models and used them as a basic study for web-based fashion customization platform design through case analysis. As a research method, theoretical examinations were conducted through literature surveys, followed by web analysis based on layout, menu, color, icon, and interaction. The study found that the placement of options, the composition of menu windows, the number of point colors, and the use of icons without functions of metaphores hindered the use of customizing platforms. This work proposes a solution, and aims to contribute to increasing the usability of future customizing web by comprehensively analyzing the visual shaping elements of web platform design.

• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.576-590
• /
• 2021

As a 'Senior Citizen' by applying an active theory based on a role model, elderly volunteers may seek to impart health to the local communities through volunteer activities. In addition, the strategies for promoting the elderly participation volunteering actions may apply with the lifelong education/learning model for citizenship development, which intends to expand the elder volunteer activity participants and the areas of volunteering actions. In this study, we attempted to find out how volunteering fieldworkers experience and perceive volunteer-promoting strategies for senior volunteers drawn from previous literatures and studies on promoting elderly volunteer actions. For the purpose of the study, we conducted in-depth interviews with 12 fieldworkers who worked senior-welfare centers and volunteer centers in Seoul and Kyeong-gi area. We used the directed-content analysis, which categorized 12 themes/categories commonly mentioned from previous literatures and studies. Within these categories, the analysis was made to derive issues and improve promoting strategies specified from the interviewees. The outcomes of the study included the insights regarding what promoting-strategies might be necessary to enrich existing senior volunteer actions. The study highlighted not only reviews volunteer fieldworkers' current experiences with senior volunteers but also barrier and practical suggestions for the continuous advances of senior volunteer programs and strategies.