본 연구의 목적은 유해 해양생물의 고밀도 출현을 조기에 탐지하기 위한 시스템 구축이다. 수중영상 기반 객체탐지 모델의 정 확도와 이미지 처리속도를 고려하여 실시간 적용에 적합한 YOLOv8m을 선정하였다. 영상 데이터를 해양생물 탐지 알고리즘에 적용한 결 과 다수의 어류 및 간헐적인 해파리 출현을 탐지하였다. 학습 모델의 검증 데이터에 대한 평균 정밀도는 0.931, 재현율은 0.881, mAP는 0.948로 산출되었다. 또한, 각 클래스별 mAP는 어류 0.970, 해파리 0.970, 살파 0.910로 모든 클래스에서 0.9(90%) 이상으로 산출되어 우수한 성능을 확인하였다. 과학어탐 시스템을 통해 객체의 탐지 범위와 시간에 따른 수중 객체탐지 결과를 확인할 수 있었으며 에코적분 격자 평균을 적용하여 시공간축으로 스무딩 처리된 결과를 얻을 수 있었다. 또한, 평균체적후방산란강도 값이 분석 도메인 내 객체탐지 여부에 따른 변동성을 반영하는 것을 확인할 수 있었다. 수중영상 기반 객체(해양생물)탐지 알고리즘, 환경조건(야간 포함)에 따른 수중영상 보정 기법, 과학어탐 시스템 기반의 정량화된 탐지결과를 제시하고 향후 다양한 사용처에서의 활용 가능성을 토의하였다.

In 2012, POSIVA selected a bentonite-based (montmorillonite) block/pellet as the backfilling solution for the deposition tunnel in the application for a construction license for the deep geological repository of high-level radioactive waste in Finland. However, in the license application (i.e. SC-OLA) for the operation submitted to the Finnish Government in 2021, the design for backfilling was changed to a granular mixture consisting of bentonite (smectite) pellets crushed to various sizes, based on NAGRA’s buffer solution. In this study, as part of the preliminary design of the deep geological repository system in Korea, we reviewed history and its rationale for the design change of Finland’s deposition tunnel backfilling solution. After the construction license was granted by the Finnish Government in 2015, POSIVA conducted various lab- and full-scale in-situ tests to evaluate the producibility and performance of two design alternatives (i.e. block/pellet type and granular type) for backfilling. Principal demonstration tests and their results are summarized as follows: (a) Manufacturing of blocks using three types of materials (Friedland, IBeco RWC, and MX-80): Cracking and jointing under higher pressing loads were found. Despite adjusting the pressing process, similar phenomena were observed. (b) 1:6 scale experiment: Confirmation of density difference inhomogeneity due to the swelling of block/pellet backfill and void filling due to swelling behavior into the mass loss area of block/pellet. (c) FISST (Full-Scale In situ system Test): Identification of technical unfeasibility due to the inefficient (too manual) installation process of blocks/pellets and development of an efficient granular in-situ backfilling solution to resolve the disadvantage. (d) LUCOEX-FE (Large Underground Concept Experiments – Full-scale Emplacement) experiment: Confirmation of dense/homogeneous constructability and performance of granular backfilling solution. In conclusion, the simplified granular backfill system is more feasible compared to the block/ pellet system from the perspective of handling, production, installation, performance, and quality control. It is presumed that various experimental and engineering researches should be preceded reflecting specific disposal conditions even though these results are expected to be applied as key data and/or insights for selecting the backfilling solution in the domestic deep geological repository.

Consumers' online reviews have become more powerful in the Internet market. Consumers share reviews, post comments and constantly evaluate products online. In previous studies, the analysis of online reviews mainly focused on purchasing products based on consumers' own use experience, but in innovative products, it was difficult to find an analysis of product acceptor's response to product user reviews. In particular, there is no online review study of VR covered in this study. This study not only quantitatively analyzed online reviews of consumers who purchased VR products on Amazon, an online distribution site, but also qualitatively analyzed them through crawling. This study used Amazon's VR product user review, where purchases were confirmed, to select algorithms that are more likely to be matched by predicting a helpful review and presenting a predictive model. In addition, the online review extracted deep text associated with Helpful and conducted topical modeling. As a result, topics related to 1) experience in use, 2) post-product evaluation, 3) product composition and peripherals, 4) immersion, and 5) comfort were highly acceptable to potential inmates. To enhance the acceptability of innovative products through online reviews, it is not just highlighting the product advantages of VR, but also suggests that the link between smartphones and applications can bring in more potential users. Also, interworking with other peripheral devices (speakers or screens) can be predicted as a way to increase the acceptability of VR products. From a marketing perspective, this study has found targeted topics that help consumers in pioneering the VR market, which will help potential customers create the services they want.