• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1439-1448
• /
• 2022

Background: We investigated the feasibility of in vitro radiosensitivity prediction with gene expression using deep learning. Methods: A microarray gene expression of the National Cancer Institute-60 (NCI-60) panel was acquired from the Gene Expression Omnibus. The clonogenic surviving fractions at an absorbed dose of 2 Gy (SF2) from previous publications were used to measure in vitro radiosensitivity. The radiosensitivity prediction model was based on the convolutional neural network. The 6-fold cross-validation (CV) was applied to train and validate the model. Then, the leave-one-out cross-validation (LOOCV) was applied by using the large-errored samples as a validation set, to determine whether the error was from the high bias of the folded CV. The criteria for correct prediction were defined as an absolute error<0.01 or a relative error<10%. Results: Of the 174 triplicated samples of NCI-60, 171 samples were correctly predicted with the folded CV. Through an additional LOOCV, one more sample was correctly predicted, representing a prediction accuracy of 98.85% (172 out of 174 samples). The average relative error and absolute errors of 172 correctly predicted samples were 1.351±1.875% and 0.00596±0.00638, respectively. Conclusion: We demonstrated the feasibility of a deep learning-based in vitro radiosensitivity prediction using gene expression.

• International conference on construction engineering and project management
• /
• 2007.03a
• /
• pp.820-829
• /
• 2007

This paper presents an evaluation of feasibility studies conducted to justify investments in infrastructure projects. An analysis of a previous feasibility study for a highway construction project is presented in this paper with an emphasis on the estimates and forecasts presented in that study in order to weigh expected benefits from the project against expected costs. The forecasted numbers are compared with actual data collected during the operation phase about the usage of the facility. The comparison reveals a huge difference between estimated numbers and actual numbers. Based on the lessons learned from the analyzed case study, recommendations are presented to improve feasibility studies for infrastructure projects including: peer review of feasibility studies; before-and-after feasibility studies; and defined scope and methodology for feasibility studies. Decision makers are advised to take outcomes of feasibility studies for infrastructure projects with extreme caution as some studies may provide erroneous and misleading input to their decisions regarding investment in infrastructure projects.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.8
• /
• pp.873-879
• /
• 2012

Metamodels have been developed with a variety of design optimization techniques in the field of structural engineering over the last decade because they are efficient, show excellent prediction performance, and provide easy interconnections into design frameworks. To construct a metamodel, a sequential procedure involving steps such as the design of experiments, metamodeling techniques, and validation techniques is performed. Because validation techniques can measure the accuracy of the metamodel, the number of presampled points for an accurate kriging metamodel is decided by the validation technique in the sequential kriging metamodel. Because the interpolation model such as the kriging metamodel based on computer experiments passes through responses at presampled points, additional analyses or reconstructions of the metamodels are required to measure the accuracy of the metamodel if existing validation techniques are applied. In this study, we suggest a sensitivity validation that does not require additional analyses or reconstructions of the metamodels. Fourteen two-dimensional mathematical problems and an engineering problem are illustrated to show the feasibility of the suggested method.

• Korean Journal of Community Nutrition
• /
• v.27 no.2
• /
• pp.146-157
• /
• 2022

Objectives: This study aimed to develop and assess the content validity and internal consistency of a questionnaire on the feasibility of mobile dietary self-monitoring applications. Methods: We developed a feasibility questionnaire to assess the overall usage, convenience, usefulness, and satisfaction of mobile dietary applications. The initial draft of the questionnaire contained 17 items with yes/no, multiple-choice, and open-ended questions and 52 items on 5-point Likert scales. To validate the content, ten experts evaluated the relevance of the items for each subscale using a 5-point scale. We calculated the item-level content validity index (I-CVI) and scale-level content validity index (S-CVI). A total of 102 adults answered the questionnaires which reflected the experts' reviews. We conducted an exploratory factor analysis to determine the underlying structure of responses and categorized convenience, usefulness, and satisfaction. We also calculated Cronbach's alpha coefficient to examine the internal consistency of items in each subscale. Results: The S-CVI score of the items was 0.86, and we removed items with an I-CVI score of < 0.80. We combined, revised, or separated some remaining items and added one item as per the experts' comments. As a result, we included 16 items about overall usage and 42 sub-questions. Based on the responses of the 102 adults, we performed exploratory factor analysis using the principal axis method. We retained items with a factor loading of > 0.40, resulting in a final set of 35 questions (convenience: 15, usefulness: 12, satisfaction: 8 items). The Cronbach's alpha values of the three scales were 0.93, 0.91, and 0.91 for 1) usefulness, 2) convenience, and 3) satisfaction, respectively. Conclusions: We developed a feasibility questionnaire for mobile dietary self-monitoring applications and examined its content validity and internal consistency. Our questionnaire has the potential to measure the feasibility of mobile dietary self-monitoring applications.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.5
• /
• pp.481-486
• /
• 2007

Wireless Sensor Network(WSNs) consists of small sensor nodes with sensing, computation, and wireless communication capabilities. The large number of sensor nodes in a WSN means that there will often be some nodes which give erroneous sensor data owing to several reasons such as power shortage and transmission error. Generally, these sensor data are gathered by a sink node to monitor and diagnose the current environment. Therefore, this can make it difficult to get an effective monitoring and diagnosis. In this paper, to overcome the aforementioned problems, intelligent sensor data validation method based on PCA(Principle Component Analysis) is utilized. Furthermore, a practical implementation using embedded system is given to show the feasibility of the proposed scheme.

• YAKHAK HOEJI
• /
• v.46 no.5
• /
• pp.331-336
• /
• 2002

The purpose of this study is to develop a non-invasive blood glucose measurement method by a portable near infrared (NIR) system which was newly integrated by our lab. The portable NIR system includes a tungsten halogen lamp, a specialized reflectance fiber optic probe and a photo diode array type InGaAs detector; which was developed by a microchip technology based on the lithography. Reflectance NIR spectra of different parts of human body (finger tip, earlobe, and inner lip) were recorded by using a fiber optic probe. The spectra were collected over the spectral range 1100 ∼ 1740 nm. Partial least squares regression (PLSR) was applied for the calibration and validation for the determination of blood glucose. The calibration model from earlobe spectra presented better results, showing good correlation with a glucose oxidase method which is a mostly used standard method. This model predicted the glucose concentration for validation set with a SEP of 33 mg/dL. This study indicated the feasibility for non-invasive monitoring of blood glucose by a portable near infrared system.

• Journal of Wind Energy
• /
• v.4 no.2
• /
• pp.34-39
• /
• 2013

The wind resource assessment for measured wind data over 1 year by using the meteorological mast should be a prerequisite for business feasibility of the wind farm development. Even though the direction of boom mounting the wind vane and anemometer is carefully engineered to escape the interference of wakes generated from the met-mast structures, the shadow effect is not completely avoided due to seasonal winds in the Korean Peninsula. The shadow effect should be properly calibrated because it is able to distort the wind resources. In this study a calibration method is introduced for the measured wind data at Julpo in Jeonbuk Province. Each sectoral terrain conditions along the selected wind direction nearby the met-mast is investigated, and the distorted wind data due to shadow effects can be calibrated effectively. The correction factor is adopted for quantitative calibration by carrying out the WindSim analysis.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.34 no.3
• /
• pp.214-218
• /
• 2014

This study was conducted to assess the feasibility of near-infrared reflectance spectroscopy (NIRS) as a rapid and reliable method for the estimation of crude protein (CP) fractions in forage legume mixtures (sudangrass and pea mixture, and kidney bean and potato mixture). A total of 178 samples were collected and their spectral reflectance obtained in the range of 400~2,500 nm. Of these, 50 samples were selected for calibration and validation, and 35 samples were used for calibration of the data set, and the modified partial least square regression (MPLSR) analysis was performed. The correlation coefficient ($r^2$) and the standard error of cross-validation (SECV) of the calibration models in the CP fractions, A, B1, B2, B3, and C, were 0.94 (1.05), 0.92 (0.74), 0.96 (0.95), 0.91 (0.42), and 0.83 (0.38), respectively. Fifteen samples were used for equation validation, and the $r^2$ and the standard error of prediction (SEP) were 0.87 (1.45), 0.91 (0.49), 0.94 (1.13), 0.36 (0.96), and 0.74 (0.67), respectively. This study showed that NIRS could be an effective tool for the rapid and precise estimation of CP fractions in forage legume mixtures.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.4 no.2
• /
• pp.197-207
• /
• 2006

The engineering performance of a high level waste repository is significantly dependent upon the T-H-M behavior in the engineered barrier system. An engineering-scale test facility (KENTEX) was set up to validate the T-H-M behaviors in the buffer of a reference disposal system developed in the 2002. The validation tests started on May 31, 2005 and is now in progress. The KENTEX facility and validation test programme are introduced, and pre-operation calculations are also presented to give information on the sensitive location of sensors and operational conditions. This test will provide information (e.g., large-scale apparatus, sensors, monitoring system etc.) needed for 'in-situ' tests, make the validation of a T-H-M model for the T-H-M performance assessment of the reference disposal system, and demonstrate the engineering feasibility of fabricating and emplacing the buffer of a repository.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.2
• /
• pp.108-113
• /
• 2019

Due to the special structure of the car seat, the heating and cooling module must be installed in a limited area resulting in difficulty in regards to achieving optimal cooling and heating efficiency. In order to solve these problems, this paper establishes a new structure for heating and cooling modules, verifies the structural feasibility of the thermoelectric module for cooling and heating the seat through fluid simulations, and verifies the proper design of the mechanical components of the thermoelectric module.