• Journal of Multimedia Information System
• /
• v.3 no.3
• /
• pp.97-102
• /
• 2016

Deep learning enables machines to have perception and can potentially outperform humans in the medical field. It can save a lot of time and reduce human error by detecting certain patterns from medical images without being trained. The main goal of this paper is to build the optimal model for breast mass classification by applying various methods that influence the performance of Convolutional Neural Network (CNN). Google's newly developed software library Tensorflow was used to build CNN and the mammogram dataset used in this study was obtained from 340 breast cancer cases. The best classification performance we achieved was an accuracy of 0.887, sensitivity of 0.903, and specificity of 0.869 for normal tissue versus malignant mass classification with augmented data, more convolutional filters, and ADAM optimizer. A limitation of this method, however, was that it only considered malignant masses which are relatively easier to classify than benign masses. Therefore, further studies are required in order to properly classify any given data for medical uses.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.1
• /
• pp.117-129
• /
• 2006

In this paper, we consider broadband satellite networks using MF-TDMA (Multi-Frequency Time Division Multiple Access) scheme. We analyze the number of expected lost packets in each terminal, and mathematically formulate optimal buffer and timeslot allocation model to minimize the weighted sum of the numbers of expected lost packets. We also suggest optimal buffer and timeslot allocation scheme based on Lagrangean relaxation technique to solve the proposed model in a fast time. Extensive experiments show that the proposed scheme provides encouraging results.

• Clinical Endoscopy
• /
• v.56 no.2
• /
• pp.229-238
• /
• 2023

Background/Aims: Shear wave elastography (SWE) is used for liver fibrosis staging based on stiffness measurements. It can be performed using endoscopic ultrasound (EUS) or a transabdominal approach. Transabdominal accuracy can be limited in patients with obesity because of the thick abdomen. Theoretically, EUS-SWE overcomes this limitation by internally assessing the liver. We aimed to define the optimal technique for EUS-SWE for future research and clinical use and compare its accuracy with that of transabdominal SWE. Methods: Benchtop study: A standardized phantom model was used. The compared variables included the region of interest (ROI) size, depth, and orientation and transducer pressure. Porcine study: Phantom models with varying stiffness values were surgically implanted between the hepatic lobes. Results: For EUS-SWE, a larger ROI size of 1.5 cm and a smaller ROI depth of 1 cm demonstrated a significantly higher accuracy. For transabdominal SWE, the ROI size was nonadjustable, and the optimal ROI depth ranged from 2 to 4 cm. The transducer pressure and ROI orientation did not significantly affect the accuracy. There were no significant differences in the accuracy between transabdominal SWE and EUS-SWE in the animal model. The variability among the operators was more pronounced for the higher stiffness values. Small lesion measurements were accurate only when the ROI was entirely situated within the lesion. Conclusions: We defined the optimal viewing windows for EUS-SWE and transabdominal SWE. The accuracy was comparable in the non-obese porcine model. EUS-SWE may have a higher utility for evaluating small lesions than transabdominal SWE.

• Journal of Environmental Impact Assessment
• /
• v.29 no.6
• /
• pp.403-413
• /
• 2020

A mathematical model comprised with eight simultaneous quasi-linear partial differential equations was suggested to provide optimal chlorination strategy. Upstream weighted finite element method was employed to construct multidimensional numerical code. The code was verified against measured concentrations in three type of reactors. Boundary conditions and reaction rate were calibrated for the sixteen cases of experimental results to regenerate the measured values. Eight reaction rate coefficients were estimated from the modeling result. The reaction rate coefficients were expressed in terms of pH and temperature. Automatic optimal algorithm was invented to estimate the reaction rate coefficients by minimizing the sum of squares of the numerical errors and combined with the model. In order to minimize the concentration of chlorine and pollutants at the final usage sites, a real-time predictive control system is imperative which can predict the water quality variables from the chlorine disinfection process at the water purification plant to the customer by means of a model and operate the disinfection process according to the influent water quality. This model can be used to build such a system in water treatment plants.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.10 no.6
• /
• pp.661-669
• /
• 2018

Engineering system problems consist of multi-objective optimisation and the performance analysis is generally time consuming. To optimise the system concerning its performance, many researchers perform the optimisation using an approximation model. The Response Surface Method (RSM) is usually used to predict the system performance in many research fields, but it shows prediction errors for highly nonlinear problems. To create an appropriate metamodel for marine systems, Lee (2015) compares the prediction accuracy of the approximation model, and multi-objective optimal design framework is proposed based on a confirmed approximation model. The proposed framework is composed of three parts: definition of geometry, generation of approximation model, and optimisation. The major objective of this paper is to confirm the applicability/usability of the proposed optimal design framework and evaluate the prediction accuracy based on sensitivity analysis. We have evaluated the proposed framework applicability in derrick structure optimisation considering its structural performance.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.281-293
• /
• 2023

This study addresses the optimal design methodology for switching between active electronically scanned array (AESA) radar operating modes to easily select the necessary information to reduce pilots' cognitive load and physical workload in situations where diverse and complex information is continuously provided. This study presents a procedure for defining a hidden Markov chain model (HMM) for modeling operating mode changes based on time series data on the operating modes of the AESA radar used by pilots while performing mission scenarios with inherent uncertainty. Furthermore, based on a transition probability matrix (TPM) of the HMM, this study presents a mathematical programming model for proposing the optimal structural design of AESA radar operating modes considering the manipulation method of a hands on throttle-and-stick (HOTAS). Fighter pilots select and activate the menu key for an AESA radar operation mode by manipulating the HOTAS's rotary and toggle controllers. Therefore, this study presents an optimization problem to propose the optimal structural design of the menu keys so that the pilot can easily change the menu keys to suit the operational environment.

• Proceedings of KOSOMES biannual meeting
• /
• 2005.11a
• /
• pp.185-190
• /
• 2005

This study is to determine an optimal reservoir among many alternative proposals in order to obtain the maximized efficiency under the limited budget. There are many alternative proposals which deal with problems to assign reservoir such as water conversion establishment construction, subterranean water, reservoir, submarine pipeline, water bort, and marine water saving base construction. In this paper, the new model to assign the most reasonable alternative is introduced using 0-1 integer programming. This proposed model has not been applied in the optimal reservoir selection problem yet. This paper will contribute to determine the most reasonable alternative to minimize budget under constraints. Also, this proposal model can be applied to other reservoir selection problem in other regions.

• Proceedings of the IEEK Conference
• /
• 2002.06a
• /
• pp.371-374
• /
• 2002

The optimal AP placement for wireless LAN is important factor for improving service quality and reducing cost. Logical area property, which is user's frequently posed place, must be considerated for flexible design. This paper proposes optimal multiple AP placement method based on path loss model which is one of radio prediction tool. The proposed method can got flexibility in multiple AP placement using user's defined parameter and tile optimization design uses Hopfield network algorithm The result of simulation shows that the proposed optimization design of multiple AP placement can improve service quality for wireless LAN.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.209-227
• /
• 2023

The government continues to announce measures to revitalize smart construction technology based on BIM for productivity innovation in the construction industry. In the design phase, the goal is design automation and optimization by converging BIM Data and other advanced technologies. Accordingly, in the basic design of the Namhae Seomyeon-Yeosu Sindeok National Road Construction Project, a domestic undersea tunnel project, BIM-based design was carried out by developing tunnel design automation technology using 3D spatial information according to the tunnel design process. In order to derive the optimal alignment, more than 10,000 alignment cases were generated in 36hr using the generative design technique and a quantitative evaluation of the objective functions defined by the designer was performed. AI-based ground classification and 3D Geo Model were established to evaluate the economic feasibility and stability of the optimal alignment. AI-based ground classification has improved its precision by performing about 30 types of ground classification per borehole, and in the case of the 3D Geo Model, its utilization can be expected in that it can accumulate ground data added during construction. In the case of 3D blasting design, the optimal charge weight was derived in 5 minutes by reviewing all security objects on the project range on Dynamo, and the design result was visualized in 3D space for intuitive and convenient construction management so that it could be used directly during construction.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.4
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.