• Title/Summary/Keyword: Feasibility assessment

Search Result 655, Processing Time 0.026 seconds

Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels

  • Pyeong Hwa Kim;Hee Mang Yoon;Jeong Rye Kim;Jae-Yeon Hwang;Jin-Ho Choi;Jisun Hwang;Jaewon Lee;Jinkyeong Sung;Kyu-Hwan Jung;Byeonguk Bae;Ah Young Jung;Young Ah Cho;Woo Hyun Shim;Boram Bak;Jin Seong Lee
    • Korean Journal of Radiology
    • /
    • v.24 no.11
    • /
    • pp.1151-1163
    • /
    • 2023
  • Objective: To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model. Materials and Methods: A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model). Results: Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2. Conclusion: The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

Exploring automatic scoring of mathematical descriptive assessment using prompt engineering with the GPT-4 model: Focused on permutations and combinations (프롬프트 엔지니어링을 통한 GPT-4 모델의 수학 서술형 평가 자동 채점 탐색: 순열과 조합을 중심으로)

  • Byoungchul Shin;Junsu Lee;Yunjoo Yoo
    • The Mathematical Education
    • /
    • v.63 no.2
    • /
    • pp.187-207
    • /
    • 2024
  • In this study, we explored the feasibility of automatically scoring descriptive assessment items using GPT-4 based ChatGPT by comparing and analyzing the scoring results between teachers and GPT-4 based ChatGPT. For this purpose, three descriptive items from the permutation and combination unit for first-year high school students were selected from the KICE (Korea Institute for Curriculum and Evaluation) website. Items 1 and 2 had only one problem-solving strategy, while Item 3 had more than two strategies. Two teachers, each with over eight years of educational experience, graded answers from 204 students and compared these with the results from GPT-4 based ChatGPT. Various techniques such as Few-Shot-CoT, SC, structured, and Iteratively prompts were utilized to construct prompts for scoring, which were then inputted into GPT-4 based ChatGPT for scoring. The scoring results for Items 1 and 2 showed a strong correlation between the teachers' and GPT-4's scoring. For Item 3, which involved multiple problem-solving strategies, the student answers were first classified according to their strategies using prompts inputted into GPT-4 based ChatGPT. Following this classification, scoring prompts tailored to each type were applied and inputted into GPT-4 based ChatGPT for scoring, and these results also showed a strong correlation with the teachers' scoring. Through this, the potential for GPT-4 models utilizing prompt engineering to assist in teachers' scoring was confirmed, and the limitations of this study and directions for future research were presented.

An assessment on feasibility of flotation as a secondary clarifier of an activated sludge process (생물반응공정에 대한 고액분리조로서 부상공정의 적용성 평가)

  • Chung, Chong Min;Kim, Yun Jung;Cho, Kang Woo;Lee, Sang Hyup;Hong, Seok Won;Chung, Tai Hak
    • Journal of Korean Society of Water and Wastewater
    • /
    • v.22 no.5
    • /
    • pp.551-559
    • /
    • 2008
  • An experimental study was carried out to evaluate the potential of flotation process for the secondary clarifier of an activated sludge process. Flotation techniques, applied in this study, include electrofloation (EF) which generated fine bubbles smaller than $35{\mu}m$ in average and diffuser flotation (DF) which generated fine bubbles smaller than $55{\mu}m$ in average. The batch experiments were done with activated sludge displaying various characteristics. It was shown that the efficiency of solids/liquid separation was reduced as the diluted sludge volume index ($DSVI_{30}$) of activated sludge increased. The dependency, however, gradually decreased as the gas to solids (G/S) ratio increased. Thickening efficiency of EF was more than 2~10 times and DF process was more than 1.5~5 times as compared with gravity sedimentation (GS). Stable sludge blanket was maintained regardless of sludge settleability when the G/S ratio was 0.019 in the EF. On the other hand, Serious deterioration in the sludge blanket was observed in the DF depends on G/S ratio and sludge settleability. And For EF and DF, the suspended solids concentration of effluent was not nearly influenced on settleability of activated sludge and more clear than GS. A biological nutrient removal (BNR) process, combined with EF as a secondary clarifier was operated for three months. The mean MLSS (mixed liquid suspended solids) concentration in the reactor and mean solids concentration of return sludge were estimated to be 5,340 mg/L and 16,770 mg/L, respectively. The water quality of effluent was considerably stable and low value was accomplished, that was, standard suspended solids concentration $0.07{\pm}0.51mg/L$ and standard turbidity $1.44{\pm}0.56NTU$. The EF could be applicable for enhancement of efficiency of activated sludge system as well as improvement of the water quality of effluent.

A study on the foreign investment law and permission procedure of forestation business in Laos (라오스의 외국인투자법제 및 조림사업 허가 절차에 관한 고찰)

  • Bang, Hong-Seok;Kweon, Hyeong-Keun;Choi, Sung-Min;Lee, Joon-Woo;Kong, Young-Ho
    • Korean Journal of Agricultural Science
    • /
    • v.39 no.1
    • /
    • pp.17-21
    • /
    • 2012
  • The purpose of this study is to review the laws on foreign investment and the changed licensing procedures in Laos and to provide the data for basic understanding of foreign forestation investment in Laos. The conclusions are as follows. The Laos government has been consistently trying to promote foreign investment. In particular, in 2004, the "Law on the Promotion of Foreign Investment" was legislated. In 2009, the Foreign Investment Promotion Act and the Domestic Investment Promotion Act to incorporate the principles of the "Law on Investment Promotion" were enacted. In Laos, the country's land is owned by the nation's community and maintained by the government. Therefore, through the procedures for registration of land, land can be conceded or leased. The ways to invest are joint ventures (where at least 10% of the total capital investment has to be made), foreign sole investment (where the investor must have a minimum capital of $100,000 or more), joint venture agreement and etc. Lastly, the forestation licensing procedures in Laos are carried out in the following order: site selection, business investments feasibility studies, environmental and social impact assessment, forestry permit application.

Assessment of dehydrothermally cross-linked collagen membrane for guided bone regeneration around peri-implant dehiscence defects: a randomized single-blinded clinical trial

  • Lee, Jae-Hong;Lee, Jung-Seok;Baek, Won-Sun;Lim, Hyun-Chang;Cha, Jae-Kook;Choi, Seong-Ho;Jung, Ui-Won
    • Journal of Periodontal and Implant Science
    • /
    • v.45 no.6
    • /
    • pp.229-237
    • /
    • 2015
  • Purpose: The aim of this study was to determine the clinical feasibility of using dehydrothermally cross-linked collagen membrane (DCM) for bone regeneration around peri-implant dehiscence defects, and compare it with non-cross-linked native collagen membrane (NCM). Methods: Dehiscence defects were investigated in twenty-eight patients. Defect width and height were measured by periodontal probe immediately following implant placement (baseline) and 16 weeks afterward. Membrane manipulation and maintenance were clinically assessed by means of the visual analogue scale score at baseline. Changes in horizontal thickness at 1 mm, 2 mm, and 3 mm below the top of the implant platform and the average bone density were assessed by cone-beam computed tomography at 16 weeks. Degradation of membrane was histologically observed in the soft tissue around the implant prior to re-entry surgery. Results: Five defect sites (two sites in the NCM group and three sites in the DCM group) showed soft-tissue dehiscence defects and membrane exposure during the early healing period, but there were no symptoms or signs of severe complications during the experimental postoperative period. Significant clinical and radiological improvements were found in all parameters with both types of collagen membrane. Partially resorbed membrane leaflets were only observed histologically in the DCM group. Conclusions: These findings suggest that, compared with NCM, DCM has a similar clinical expediency and possesses more stable maintenance properties. Therefore, it could be used effectively in guided bone regeneration around dehiscence-type defects.

Probabilistic Assessment of Dynamic Properties of Offshore Wind Turbines Considering Soil-Pile Interaction (지반과 말뚝의 상호작용을 고려한 고정식 해상풍력터빈의 동적 특성에 대한 확률적 평가)

  • Yi, Jin-Hak;Kim, Sun-Bin;Han, Taek Hee;Yoon, Gil-Lim
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.28 no.4
    • /
    • pp.343-350
    • /
    • 2015
  • Extensive discussion on the optimal types of offshore wind turbine(OWT) among monopile, tripod and jacket in the intermediate depth of water has been actively carried out in worldwide wind turbine industry. Selecting the optimal types of OWT among several substructural types, it is required to consider the economic and technical feasibility including dynamically stable design of a wind turbine system. In this study, the effects of loading levels and uncertainties of soil properties on the natural frequency of OWT have been quantitatively investigated. In conclusion, the natural frequency of monopile-type OWTs has a significant level of uncertainty, hence it is very important to minimize the level of uncertainties in soil properties when the monopile is selected as a foundation for an OWT.

Modification of Bearing Capacity Formula Considering Seam Tensile Strength of Geotextile in Soft Ground (연약지반에 포설된 Geotextile 봉합인장강도를 고려한 지지력 수정방정식)

  • Kim, Sun-Hak;Chae, Yu-Mi;Kim, Jae-Hong
    • Journal of the Korean Geotechnical Society
    • /
    • v.35 no.12
    • /
    • pp.59-67
    • /
    • 2019
  • With the increasing use of geotextile mats in dredging and reclaiming work and coastal construction, the assessment of bearing capacity in soft ground has become an important evaluation index for negligent accidents. The review of the allowable bearing capacity of soft ground consisting of inhomogeneous layers by laying geotextile mats and sand mat layers for soft ground improvement is generally compared with the equation of Meyerhof (1974) and Yamanouchi (1985). Mayerhof formula results in economic loss due to underestimation of bearing capacity, and Yamanouchi (1985) formula does not take into account negligent accidents for punching shear failure, so rather high bearing capacity is evaluated. It is considered that economic feasibility and stability will be ensured by proposing a modified formula to calculate the appropriate bearing capacity by applying the seam tensile strength of the geotextile mat to the design standard of soft ground improvement.

Assessment and Analysis of Coal Seam Gas Water Management Study for Water Resource Production 2. Prediction of Treatment Technology and Design of Co-treatment System (물 자원 생산을 위한 Coal Seam Gas Water Management Study의 평가 및 분석 2. 처리기술 예측 및 병합 시스템 설계)

  • Shin, Choon-Hwan
    • Journal of Environmental Science International
    • /
    • v.24 no.12
    • /
    • pp.1629-1637
    • /
    • 2015
  • To develop various usable water from coal seam gas (CSG) water that needs to be pumped out from coal seams for methane gas production, a feasibility study was carried out, evaluating and analysing a recent report (Coal Seam Gas Water Management Policy 2012) from Queensland State Government in Australia to suggest potential CSG water treatment options for fit-for-purpose usable water production. As CSG water contains intrinsically high salinity-driven total dissolved solid (TDS), bicarbonate, aliphatic carbon, $Ca^{+2}$, $Mg^{+2}$ and so on, it was found that appropriate treatment technologies are required to reduce the hardness below 60 mg/L as $CaCO_3$ by setting the reduction rates of $Ca^{+2}$, $Mg^{+2}$ and Na+ concentrations, as well as TDS reduction. Also, Along with fiber filtration and membrane separation, an oxidation degradation process was found to be required. Along with salinity reduction, as CSG water contains organic compounds (TOC: 248 mg/L, $C_6-C_9$: <20 mg/L and $C_{10}-C_{36}$: <60 mg/L), compounds with relatively high molecular weights ($C_{10}-C_{36}$) need to be treated first. Therefore, this study suggests a combined system design with filtration (Reverse osmosis) and oxidation reduction (electrolysis) technologies, offering proper operating conditions to produce fit-for-purpose usable water from CSG water.

Assessment of Biomarkers in Acetaminophen-Induced Hepatic Toxicity by siRNA

  • Kang, Jin-Seok;Yum, Young-Na;Kim, Joo-Hwan;Park, Sue-Nie
    • Biomolecules & Therapeutics
    • /
    • v.17 no.4
    • /
    • pp.438-445
    • /
    • 2009
  • We investigated global gene expression from both mouse liver and mouse hepatic cell lines treated with acetaminophen (APAP) in order to compare in vivo and in vitro profiles and to assess the feasibility of the two systems. During our analyses of gene expression profiles, we picked up several down-regulated genes, such as the cytochrome P450 family 51 (Cyp51), sulfotransferase family cytosolic 1C member 2 (Sult1c2), 3-hydroxy-3-methylglutaryl-Coenzyme A synthase 1 (Hmgcs1), and several genes that were up-regulated by APAP, such as growth arrest and DNA-damage-inducible 45 alpha (Gadd45a), transformation related protein 53 inducible nuclear protein 1 (Trp53inp1) and zinc finger protein 688 (Zfp688). For validation of gene function, synthesized short interfering RNAs (siRNAs) for these genes were transfected in a mouse hepatic cell line, BNL CL.2, for investigation of cell viability and mRNA expression level. We found that siRNA transfection of these genes induced down-regulation of respective mRNA expression and decreased cell viability. siRNA transfection for Cyp51 and others induced morphological alterations, such as membrane thickening and nuclear condensation. Taken together, siRNA transfection of these six genes decreased cell viability and induced alteration in cellular morphology, along with effective inhibition of respective mRNA, suggesting that these genes could be associated with APAP-induced toxicity. Furthermore, these genes may be used in the investigation of hepatotoxicity, for better understanding of its mechanism.

Computational Thinking Framework-based Analysis of Afterschool Scratch Team Project Experiences (컴퓨팅 사고 프레임워크 기반 방과후 스크래치 팀프로젝트 경험의 분석)

  • Choi, Hyungshin;Jeong, Inkee;So, Hyojeong
    • Journal of The Korean Association of Information Education
    • /
    • v.18 no.4
    • /
    • pp.549-558
    • /
    • 2014
  • This study aims to provide suggestions for software education in an afterschool program, deriving from the analysis of student experiences of working on Scratch team projects. This study reports on the implementation of the 12 week afterschool software education program in an elementary school, where students worked in pairs to learn Scratch programming from ideation to design and presentation. For an in-depth study of student-generated artifacts, we selected three groups' Scratch projects and conducted artifact-based interviews to unpack student experiences working on Scratch projects as a group. Adopting the computational thinking framework as an overarching analytical lens, we focused on examining student experiences from three dimensions of computational thinking (CT), namely, CT concepts, CT practices, and CT perspectives. The present study provides both theoretical and practical implications. Firstly, we demonstrate the feasibility of applying the CT framework for assessing student-generated artifacts in design-oriented software education. We also believe that this study provides important suggestions to future software education programs adopting CT as an overarching design and assessment framework.