• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• Proceedings of the KIEE Conference
• /
• 1986.07a
• /
• pp.97-109
• /
• 1986

The ultimate goal of an industrial robot is to make full use of its real ability to communicate with any given intelligent device, and to do so independently of hardware, architecture and languages. This paper describes the necessary functions of a robot used in an integrated manufacturing system, and the basic philosophy of organization as applied to the robot controller. An example of a machine vision system called MYVIS is reviewed in relation to MAP and LAN in a practical cell application.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.53-57
• /
• 2004

In this paper, we will present the Aspheric Surface Program for optical element. X-ray optical element designed to give a high resolution and reflectively in order to observe the living cell in the range of the water window. According to optical design, we developed the Aspheric Surface Program using the visual basic. Using the Aspheric Surface Program, we directly machined the electroless nickel bulk.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.518-523
• /
• 2004

PLGA was suggested. Under various conditions, their diameters and porosity as well as mechanical strength were evaluated. In addition to those, cell(chondrocyte) proliferation and formation of extracelluar matrices were also investigated along with the conventional membrane type PLGA scaffolds for the potential use in tissue engineering. As conclusions, this type of scaffold showed a potential of application to tissue engineering in view of mechanical stability as well as cellular responses.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1997.04a
• /
• pp.26-29
• /
• 1997

Computer Integrated Manufacturing (CIM) is undoubtedly one of the most influential concepts to have been introduced into the manufacturing world in recent times. The successful CIM application is greatly depended on the way of the approach to given manufacturing environments. This paper suggests a new approach in building CIM systems and also discusses roles of a open cell controller for this purpose.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.589-594
• /
• 1989

In this paper, a programming system for robot-based manufacturing cell which can control and simulate manufacturing devices as well as robots in workcell is proposed and developed. The system is based on world model, and modem textual and object-level robot programming language and interactive graphic world modeler are used to construct and exploit world model. Graphic simulation is used as an efficient and easy to use debugging or verifying tool for user written robot programs. Machine dependency is minimized by adopting the hierarchical control structure and by assuming all the workcell components as virtual ones.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.04a
• /
• pp.137-142
• /
• 2003

An analysis of the turbo-blower shaft attached to fuel cell using 3-D FEA (Finite Element Analysis) is proposed by Lanczos algorithm. The modal analysis was peformed in order to investigate natural frequencies for 10 times. It is found that the first mode of natural frequency is 111.243 and the maximum displacement is 0.16mm Consequently, It is found that the dynamic design of turbo-blower shows a good responses transiently.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.370-375
• /
• 1992

This paper deals with the scheduling and simulation for FMC(Flexible Manufacturing Cells). In order to achieve CIM, there is a critical need to link factory level and machine level. The primary functions performed by this link for all jobs issued to the shop floor and cell include short-term scheduling and dynamic operational scheduling. Here, hierarchical control structure is introduced to define these functions. And Intelligent scheduling through expert module is adopted for efficiency of FMC operation. Computer simulation reveals that expert scheduling method is better than heuristics in various performance index.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 1998.10a
• /
• pp.150-156
• /
• 1998

다품종 소량생산 체제는 혼란의 비경제로 인하여 생산관리의 효율을 향상시키는데 어려움이 많고 제품 표준화에 의한 대량생산에 비하여 효율과 경제성이 떨어진다. 이러한 비효율성을 극복하기 위한 방안 중 하나가 셀 생산방식이며, 이의 적용을 위해서는 부품군 (part family)과 기계셀(machine cell)을 구성하는 제조셀 형성이 이루어져야 한다. 제조셀 형성을 위한 연구가 활발히 이루어지고 있는 가운데 최근에는 신경망을 이용한 제조셀 형성 기법이 소개되고 있다. 본 연구에서는 기존에 연구된 신경망 기법 중 가장 제조셀 형성에 적합하다는 ART1 신경망 기법을 GLVQ 신경망 기법과 비교하여 제조셀 형성의 효율성을 분석하였다.

• Journal of Korean Society for Quality Management
• /
• v.12 no.1
• /
• pp.17-30
• /
• 1984

A computer method is developed for group technology layout and its simulation analysis. The method is composed of three phases: Phase I sorts the parts by its similar production routes and forms part families. Phase II plots the layout by machine cell and evaluates the group layout alternatives by the total process time analysis and the part travel distance evaluation analysis. Phase III also evaluates the alternatives by simulation analysis using SIMAN simulation software. All the computer programs are developed with BASIC except SIMAN simulation.