• Smart Media Journal
• /
• v.11 no.10
• /
• pp.89-96
• /
• 2022

An open domain machine reading comprehension is a model that adds a function to search paragraphs as there are no paragraphs related to a given question. Document searches have an issue of lower performance with a lot of documents despite abundant research with word frequency based TF-IDF. Paragraph selections also have an issue of not extracting paragraph contexts, including sentence characteristics accurately despite a lot of research with word-based embedding. Document reading comprehension has an issue of slow learning due to the growing number of parameters despite a lot of research on BERT. Trying to solve these three issues, this study used BM25 which considered even sentence length and InferSent to get sentence contexts, and proposed an open domain machine reading comprehension with ALBERT to reduce the number of parameters. An experiment was conducted with SQuAD1.1 datasets. BM25 recorded a higher performance of document research than TF-IDF by 3.2%. InferSent showed a higher performance in paragraph selection than Transformer by 0.9%. Finally, as the number of paragraphs increased in document comprehension, ALBERT was 0.4% higher in EM and 0.2% higher in F1.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.77-82
• /
• 2023

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.67 no.4
• /
• pp.274-284
• /
• 2022

To use kenaf (Hibiscus cannabinus L.) as a fiber and livestock feed, a high-yielding variety needs to be identified. For this, accurate phenotyping of plant height is required for this breeding purpose due to the strong relationship between plant height and yield. Plant height can be estimated using RGB images from unmanned aerial vehicles (UAV-RGB) and photogrammetry based on Structure from Motion (SfM) algorithms. In kenaf, accurate measurement of height is limited because kenaf stems have high flexibility and its height is easily affected by wind, growing up to 3 ~ 4 m. Therefore, we aimed to identify a method suitable for the accurate estimation of plant height of kenaf and investigate the feasibility of using the UAV-RGB-derived plant height map. Height estimation derived from UAV-RGB was improved using multi-point calibration against the five different wooden structures with known heights (30, 60, 90, 120, and 150 cm). Using the proposed method, we analyzed the variation in temporal height of 23 kenaf cultivars. Our results demontrated that the actual and estimated heights were reliably comparable with the coefficient of determination (R²) of 0.80 and a slope of 0.94. This method enabled the effective identification of cultivars with significantly different heights at each growth stages.

• Journal of Life Science
• /
• v.33 no.2
• /
• pp.199-207
• /
• 2023

To prepare for the threat of a future epidemic in the post-COVID-19 era, research based on the one-health concept (i.e., the health of humans, animals, and the environment as "one") is essential. Cross-species infections are being identified as a result of the high infection rate and viral load of SARS-CoV-2 in humans. The possibility of transmission of SARS-CoV-2 from humans to mink has been determined. In addition, the transmission of SARS-CoV-2 from humans to cats through contact has been considered possible. The data so far show that livestock and poultry are less likely to be infected with SARS-CoV-2. However, if infections are established through a new mutation, the resulting diseases are expected to have enormous ripple effects on various fields, such as human food security, the economy, and trade. In addition, there are concerns about the endemic prospect of SARS-CoV-2 and the high accessibility of companion animals. This is because the evolution of the virus likely occurs in animal hosts. Once SARS-CoV-2 is established in other species, they might serve as intermediate hosts for the re-emergence of the virus in the human population. Thus, it is necessary to ensure a rapid response to future outbreaks by accumulating research data on the animal infection of SARS-CoV-2. These data can have implications for the development of animal models for vaccines and therapeutics against SARS-CoV-2. Therefore, in this study, epidemiological reviews were analyzed, and response strategies against SARS-CoV-2 infection in animals were presented using the One-health approach.

• Journal of the Korean Society of Radiology
• /
• v.17 no.2
• /
• pp.175-184
• /
• 2023

Based on the actual shape of the detector and the data provided by the manufacturer, the shape of the detector was implemented through Penelope simulation and applied to the appropriate four-layer thickness based on the efficiency obtained from the measurements. Efficiency calculations to determine the effect of the simulated number of Full Energy Peak Efficiency(FEPE) channels in the detector and the outside contact layer in the crystal on the Full Energy Peak Efficiency were performed for various four-layer thicknesses of 0.3, 0.5, 0.7, 1.0, 1.2, and 1.4 mm using the Penelope Code. When the thickness of the external contact layer was increased by 5 times, the Full Energy Peak Efficiency decreased by about 36% for 59.50 keV, and the Full Energy Peak Efficiency decreased by 10% for 1836. In addition, as it increased by 10 times, the Full Energy Peak Efficiency decreased by about 20% for 59.54 keV, and 7% for 1836.01 keV. The Penelope simulated Full Energy Peak Efficiency channel decreases exponentially with the increase in the four layers. In addition, it was confirmed that the total effect curve was well matched with a relative difference of less than 3.5% in the 0.3-1.4 mm dead layer thickness region. However, it was found that the inhomogeneous dead layer is still a parameter in the Monte Carlo model.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.3
• /
• pp.163-190
• /
• 2023

This study analyzed the effect of technology preparation and technology acceptance factors on the intention of public library librarians to use artificial intelligence-based technology using the technology acceptance model. To this end, a survey was conducted on public library librarians, and a total of 202 survey data were used for statistical analysis. As a result of the hypothesis test, first, optimism has a significant positive (+) effect on perceived usefulness, and discomfort has a significant negative (-) effect. Optimism and innovation on perceived ease of use were found to have a significant positive (+) effect, and discomfort was found to have a significant negative (-) effect. Second, perceived ease of use was found to have a significant positive (+) effect on perceived usefulness, and both perceived usefulness and perceived ease of use had a significant positive (+) effect on the intention to use. Third, optimism was found to have a significant positive (+) effect on the intention to use, and anxiety was found to have a significant negative (-) effect. This study is expected to provide basic data on the use of artificial intelligence technology in the future by empirically analyzing public library librarians' perceptions of artificial intelligence-based technology.

• The Korean Journal of Coaching Psychology
• /
• v.7 no.2
• /
• pp.47-74
• /
• 2023

The purpose of this study was to test the effectiveness of a group coaching program to promote metacognitive learning ability in an academic context for adult learners enrolled at a distance university. The topics and objectives of the group coaching program focused on understanding and applying the elements of 'metacognitive knowledge', and each session was conducted online by integrating 'planing-monitoring-regulating', an element of 'metacognitive regulation', into the REGROW model of coaching. To verify the effectiveness of the program, research participants were recruited from adult university students enrolled in A Cyber University and assigned to the experimental and control groups. The experimental group was given the program, while the control group was given the program after the completion of the study. Metacognitive learning ability level and academic self-efficacy were tested before and after the program for both groups, and a satisfaction survey was conducted for the experimental group. Analyses of the data revealed that the experimental group showed higher scores on both the overall and sub-scales of perceived metacognitive learning ability and academic self-efficacy compared to the control group. Participants in the experimental group also reported high satisfaction with the program, increased knowledge of metacognition, awareness and application of metacognitive strategies, and found the group coaching approach beneficial. Based on these findings, implications, and suggestions for future research are presented.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.3
• /
• pp.85-96
• /
• 2023

This study developed and evaluated a safe route guidance service for electric personal assistive mobility device used mainly by the mobility impaired people to improve their mobility. Thirteen underlying factors affecting the mobility of electric personal assistive mobility device have been derived through a survey with the mobility impaired people and employees in related organizations in Busan Metropolitan City. After assigning safety scores to individual factors and identifying the relevant factors along routes of interest with an object detection AI model, the safe route for electric personal assistive mobility device was provided through an optimal path-finding algorithm. As a result of comparing the general route of T-map and the recommended route of this study for the identical routes, the latter had relatively fewer obstacles and the gentler slope than the former, implicating that the recommended route is safer than the general one. As future works, it is necessary to enhance the function of a route guidance service based on the real-time location of users and to conduct spot investigations to evaluate and verify its social acceptability.

• Journal of the Korea Society for Simulation
• /
• v.32 no.3
• /
• pp.43-53
• /
• 2023

In this detailed and comprehensive study, our primary focus has been placed on accurately gauging the number of visitors and their real-time locations in commercial spaces. Particularly, in a real cafe, using security cameras, we have developed a system that can offer live updates on available seating and predict future congestion levels. By employing YOLO, a real-time object detection and tracking algorithm, the number of visitors and their respective locations in real-time are also monitored. This information is then used to update a cafe's indoor map, thereby enabling users to easily identify available seating. Moreover, we developed a model that predicts the congestion of a cafe in real time. The sophisticated model, designed to learn visitor count and movement patterns over diverse time intervals, is based on Long Short Term Memory (LSTM) to address the vanishing gradient problem and Sequence-to-Sequence (Seq2Seq) for processing data with temporal relationships. This innovative system has the potential to significantly improve cafe management efficiency and customer satisfaction by delivering reliable predictions of cafe congestion to all users. Our groundbreaking research not only demonstrates the effectiveness and utility of indoor location tracking technology implemented through security cameras but also proposes potential applications in other commercial spaces.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.340-344
• /
• 2023

In this paper, we propose a study on the development of deep learning structure to secure visibility of outdoor LED display board according to weather change. The proposed technique secures the visibility of the outdoor LED display board by automatically adjusting the LED luminance according to the weather change using deep learning using an imaging device. In order to automatically adjust the LED luminance according to weather changes, a deep learning model that can classify the weather is created by learning it using a convolutional network after first going through a preprocessing process for the flattened background part image data. The applied deep learning network reduces the difference between the input value and the output value using the Residual learning function, inducing learning while taking the characteristics of the initial input value. Next, by using a controller that recognizes the weather and adjusts the luminance of the outdoor LED display board according to the weather change, the luminance is changed so that the luminance increases when the surrounding environment becomes bright, so that it can be seen clearly. In addition, when the surrounding environment becomes dark, the visibility is reduced due to scattering of light, so the brightness of the electronic display board is lowered so that it can be seen clearly. By applying the method proposed in this paper, the result of the certified measurement test of the luminance measurement according to the weather change of the LED sign board confirmed that the visibility of the outdoor LED sign board was secured according to the weather change.