• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1643-1652
• /
• 2022

Deposited Marine Debris(DMD) can negatively affect marine ecosystems, fishery resources, and maritime safety and is mainly detected by sonar sensors, lifting frames, and divers. Considering the limitation of cost and time, recent efforts are being made by integrating underwater images and artificial intelligence (AI). We conducted a comparative study of You Only Look Once Version 5 (YOLOv5) and You Only Look Once Version 7 (YOLOv7) models to detect DMD from underwater images for more accurate and efficient management of DMD. For the detection of the DMD objects such as glass, metal, fish traps, tires, wood, and plastic, the two models showed a performance of over 0.85 in terms of Mean Average Precision (mAP@0.5). A more objective evaluation and an improvement of the models are expected with the construction of an extensive image database.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.274-282
• /
• 2022

In order to secure pedestrians' right to walk, we have up-cycled second hand mobile phones to overcome limitations of the existing survey methods, analysis methods, and diagnosis to reduce pedestrian traffic accidents. Second hand mobile phones were up-cycled to produce mobile CCTVs and installed in areas where pedestrian deaths rate is high to secure image data sets for the period of more than 24 hours. It was analyzed by applying image visualization technology and clouding reporting technology, and more precise and accurate results were derived through modeling based on artificial intelligence learning and GIS-based diagnostic guidance. As a result, it was possible to analyze the risk factors and number of pedestrian safety, and even factors that were not known in the existing method could be derived. In addition, the traffic accident risk index was derived by converting data into one year to verify whether second hand mobile phone up-cycling mobile CCTV will be an objective tool for finding pedestrian risk factors. Up-cycling mobile CCTV of second hand mobile phones newly applied through research can be used as a new tool to find pedestrian risk factors, and it can be used as a service to protect the safety of the traffic vulnerable other than pedestrians.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.913-924
• /
• 2022

In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1627-1634
• /
• 2021

This paper introduces a low-power compact ADC circuit for analog Convolutional filter for low-power neural network accelerator SOC. While convolutional neural network accelerators can speed up the learning and inference process, they have drawback of consuming excessive power and occupying large chip area due to large number of multiply-and-accumulate operators when implemented in complex digital circuits. To overcome these drawbacks, we implemented an analog convolutional filter that consists of an analog multiply-and-accumulate arithmetic circuit along with an ADC. This paper is focused on the design optimization of a low-power 8bit SAR ADC for the analog convolutional filter accelerator We demonstrate how to minimize the capacitor-array DAC, an important component of SAR ADC, which is three times smaller than the conventional circuit. The proposed ADC has been fabricated in CMOS 65nm process. It achieves an overall size of 1355.7㎛², power consumption of 2.6㎼ at a frequency of 100MHz, SNDR of 44.19 dB, and ENOB of 7.04bit.

• Journal of Christian Education in Korea
• /
• v.70
• /
• pp.141-173
• /
• 2022

The purpose of this study is to illuminate depersonalization in the flow of technological revolution and to present a Christian SARAMDAUM education that aims for a new human image. It represents the Christian SARAMDAUM education that adapts to, mediates, and offers alternatives to the technological and human evolutionary flow of the machine age. The purpose of education for this purpose is to aim for 'Homo Creators', creative human beings presented as a new human image in the age of technological revolution. The educational goal is to nurture creative human beings through creative interpretation, creative integration between disciplines, and personal dialogue in the post-mechanical/ post-conventional paradigm. The content of the education is a conversation with the SARAMDAUM that consiliences the characteristics of post-machine and post-convention. The educational method utilizes Edu-Tech and AIED(Artificial Intelligence in Education) to realize systemic thinking and SARAMDAUM dialogue of technology. In addition, the composition of teachers and learners, educational environment and educational evaluation is presented. The significance of this study is that from the point of view of Christian education, the identity of human beings in the era of the technological revolution has been identified, and research on the creative image of the human being is newly attempted, and the direction of Christian SARAMDAUM education aimed at this is presented. This can be said to be a Christian education that emphasizes the essential characteristics of human beings while accommodating the era of technological revolution.

• Journal of the Korean Society of Earth Science Education
• /
• v.15 no.2
• /
• pp.263-272
• /
• 2022

The purpose of this study is to investigate the effect of developing and applying a program in the field of astronomy that can improve the spatial perception ability and task commitment of elementary science gifted students. The subjects of this study were 22 students in the advanced course in the elementary science gifted class affiliated with the Gifted and Talented Center of University B. In order to improve spatial perception ability and task attachment to students in elementary school science gifted class, a total of 12 educational learning programs were developed and applied. The results of this study were interpreted as quantitative analysis. The results of this study are as follows. First, the astronomy class had a positive effect on the spatial perception ability improvement of elementary science gifted students. Second, the astronomy class had a positive effect on improving the task commitment of elementary school science gifted students. Third, astronomy class of elementary school science gifted students was more effective in improving spatial perception than improving task commitment. Since elementary school science gifted students are selected with excellent intelligence, creativity, and task commitment, an Individualized Education Program (IEP) is developed and applied to better express their potential giftedness. In addition, in order to express more in-depth giftedness in gifted education, it is necessary to pay attention to the development of programs that can express individual gifted characteristics.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.5
• /
• pp.780-790
• /
• 2022

Quantitative risk levels must be presented by analyzing the causes and consequences of accidents and predicting the occurrence patterns of the accidents. For the analysis of marine accidents related to vessel traffic, research on the traffic such as collision risk analysis and navigational path finding has been mainly conducted. The analysis of the occurrence pattern of marine accidents has been presented according to the traditional statistical analysis. This study intends to present a marine accident prediction model using the statistics on marine accidents related to vessel traffic. Statistical data from 1998 to 2021, which can be accumulated by month and hourly data among the Korean domestic marine accidents, were converted into structured time series data. The predictive model was built using a long short-term memory network, which is a representative artificial intelligence model. As a result of verifying the performance of the proposed model through the validation data, the RMSEs were noted to be 52.5471 and 126.5893 in the initial neural network model, and as a result of the updated model with observed datasets, the RMSEs were improved to 31.3680 and 36.3967, respectively. Based on the proposed model, the occurrence pattern of marine accidents could be predicted by learning the features of various marine accidents. In further research, a quantitative presentation of the risk of marine accidents and the development of region-based hazard maps are required.

• 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.

• 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 Dental Rehabilitation and Applied Science
• /
• v.38 no.4
• /
• pp.196-203
• /
• 2022

Purpose: This study aimed to evaluate the accuracy and clinical usability of an identification model using deep learning for 79 dental implant types. Materials and Methods: A total of 45396 implant fixture images were collected through panoramic radiographs of patients who received implant treatment from 2001 to 2020 at 30 dental clinics. The collected implant images were 79 types from 18 manufacturers. EfficientNet and Meta Pseudo Labels algorithms were used. For EfficientNet, EfficientNet-B0 and EfficientNet-B4 were used as submodels. For Meta Pseudo Labels, two models were applied according to the widen factor. Top 1 accuracy was measured for EfficientNet and top 1 and top 5 accuracy for Meta Pseudo Labels were measured. Results: EfficientNet-B0 and EfficientNet-B4 showed top 1 accuracy of 89.4. Meta Pseudo Labels 1 showed top 1 accuracy of 87.96, and Meta pseudo labels 2 with increased widen factor showed 88.35. In Top5 Accuracy, the score of Meta Pseudo Labels 1 was 97.90, which was 0.11% higher than 97.79 of Meta Pseudo Labels 2. Conclusion: All four deep learning algorithms used for implant identification in this study showed close to 90% accuracy. In order to increase the clinical applicability of deep learning for implant identification, it will be necessary to collect a wider amount of data and develop a fine-tuned algorithm for implant identification.