• 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.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1403-1412
• /
• 2013

In the maritime ships or airplanes, users should utilize the satellite channel in orer to use web service. However, the satellite channel is costly and does not give users satisfied response time. In the ship, the users may receive plenty of extra data when they obtain internet news. The extra data may be unnecessary image and advertise. Therefore, they should pay unnecessary data usage charges as well. In this paper, we suggest a proxy model that solves the problem of cost and speed. The proposed proxy reduces the of data through the satellite link by image and advertising blocking, caching, image re-requesting functions. It's performance was tested by a real satellite communication.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.901-908
• /
• 2010

A geometrical description method is proposed to represent the process of the forward selection and backward elimination methods among many variable selection methods for multiple regression models. This graphical method shows the process of the forward selection and backward elimination on the first and second quadrants, respectively, of half circle with a unit radius. At each step, the SSR is represented by the norm of vector and the extra SSR or partial determinant coefficient is represented by the angle between two vectors. Some lines are dotted when the partial F test results are statistically significant, so that statistical analysis could be explored. This geometrical description can be obtained the final regression models based on the forward selection and backward elimination methods. And the goodness-of-fit for the model could be explored.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.3
• /
• pp.590-598
• /
• 1988

Viscous flows through a screen normal to an uniform flow are numerically simulated. A .kappa.-.epsilon. model is adopted for evaluation of the Reynolds stresses. The existence of a screen is regarded as extra sources in the momentum equations. The amount of extra sources is related to the resistance coefficient and the refraction coefficient of the screen. Flows are numerically simulated for various resistance coefficients and heights of the screen and Reynolds numbers. The present method has been verified to reasonably simulate viscous wakes and shear layers of the screen, for which the inviscid theory is quite limitted. As the fluids approach the screen, the velocity is reduced and the pressure is raised to satisfy the Bernoulli equation. After passing the screen, the velocity shows its minimum value at the down-stream, but static pressure is slowly recovered. A detached separation-bubble from the screen appears as the resistance coefficient is increased to a certain level. Such results are qualitatively in agreement with limitted experimental data available. The turbulent kinetic energy shows its maximum value at further down stream and decrease thereafter.

• International Journal of Aeronautical and Space Sciences
• /
• v.16 no.3
• /
• pp.463-474
• /
• 2015

Future Ground Control Stations (GCSs) for Unmanned Aerial Vehicles (UAVs) teleoperation targets better situational awareness by providing extra motion cues to stimulate the vestibular system. This paper proposes a new virtual environment for long range Unmanned Aerial Vehicle (UAV) control via Non-Line-of-Sight (NLoS) communications, which is based on motion platforms. It generates motion cues for the teleoperator for extra sensory stimulation to enhance the guidance performance. The proposed environment employs the distributed component simulation over GSM network as a simulation platform. GSM communications are utilized as a multi-hop communication network, which is similar to global satellite communications. It considers a UAV mathematical model and wind turbulence effects to simulate a realistic UAV dynamics. Moreover, the proposed virtual environment simulates a Multiple Axis Rotating Device (MARD) as Human Machine Interface (HMI) device to provide a complete delay analysis. The demonstrated measurements cover Graphical User Interface (GUI) capabilities, NLoS GSM communications delay, MARD performance, and different software workload. The proposed virtual environment succeeded to provide visual and vestibular feedbacks for teleoperators via GSM networks. The overall system performance is acceptable relative to other Line-of-Sight (LoS) systems, which promises a good potential for future long range, medium altitude UAV teleoperation researches.

• Journal of Power Electronics
• /
• v.11 no.3
• /
• pp.311-318
• /
• 2011

LCL filters installed at converter outputs offer a higher harmonic attenuation than L filters. However, as a three order resonant circuit, it is difficult to stabilize and has a risk of oscillating with the power grid. Therefore, careful design is required to damp LCL resonance. Compared to a passive damping method, an active damping method is a more attractive solution for this problem, since it avoids extra power losses. In this paper, the damping capabilities of capacitor current, capacitor voltage, and grid-side current feedback methods, are analyzed under the discrete-time state-space model. Theoretical analysis shows that the grid-side current feedback method is more suitable for use in active power filters, because it can damp LCL resonance more effectively than the other two methods when the ratio of the resonance and the control frequency is between 0.225 and 0.325. Furthermore, since there is no need for extra sensors for additional states measurements, this method provides a cost-efficient solution. To support the theoretical analysis, the proposed method is tested on a 7-kVA single-phase shunt active power filter.

• Ocean Systems Engineering
• /
• v.10 no.4
• /
• pp.359-371
• /
• 2020

The performance of a multi-level overtopping wave energy converter (OWEC) has been numerically and experimentally investigated in a two-dimensional wave tank in order to study the effects of opening width of additional reservoirs. The device is a fixed OWEC consisting of an inclined ramp together with several reservoirs at different levels. A particle-based numerical simulation utilizing the Lattice Boltzmann Method (LBM) is used to simulate the flow behavior around the OWEC. Additionally, an experimental model is also built and tested in a small wave flume in order to validate the numerical results. A comparison in energy captured performance between single-level and multi-level devices has been proposed using the hydraulic efficiency. The enhancement of power capture performance is accomplished by increasing an overtopping flow rate captured by the extra reservoirs. However, a noticeably large opening of the extra reservoirs can result in a reduction in the power efficiency. The overtopping flow behavior into the reservoirs is also presented and discussed. Moreover, the results of hydrodynamic performance are compared with a similar study, of which a similar tendency is achieved. Nevertheless, the LBM simulations consume less computational time in both pre-processing and calculating phases.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.350-358
• /
• 2021

In modern years, the performance of the students is analysed with lot of difficulties, which is a very important problem in all the academic institutions. The main idea of this paper is to analyze and evaluate the academic performance of the college students with bipolar disorder by applying data mining classification algorithms using Jupiter Notebook, python tool. This tool has been generally used as a decision-making tool in terms of academic performance of the students. The various classifiers could be logistic regression, random forest classifier gini, random forest classifier entropy, decision tree classifier, K-Neighbours classifier, Ada Boost classifier, Extra Tree Classifier, GaussianNB, BernoulliNB are used. The results of such classification model deals with 13 measures like Accuracy, Precision, Recall, F1 Measure, Sensitivity, Specificity, R Squared, Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, TPR, TNR, FPR and FNR. Therefore, conclusion could be reached that the Decision Tree Classifier is better than that of different algorithms.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.92-100
• /
• 2023

Wireless communication technology is becoming increasingly prevalent in smart factories, but the rise in the number of wireless devices can lead to interference in the ISM band and obstacles like metal blocks within the factory can weaken communication signals, creating radio shadow areas that impede information exchange. Consequently, accurately determining the radio communication coverage range is crucial. To address this issue, a Radio Environment Map (REM) can be used to provide information about the radio environment in a specific area. In this paper, a technique for estimating an indoor REM usinga mobile robot and machine learning methods is introduced. The mobile robot first collects and processes data, including the Received Signal Strength Indicator (RSSI) and location estimation. This data is then used to implement the REM through machine learning regression algorithms such as Extra Tree Regressor, Random Forest Regressor, and Decision Tree Regressor. Furthermore, the numerical and visual performance of REM for each model can be assessed in terms of R2 and Root Mean Square Error (RMSE).

• ETRI Journal
• /
• v.45 no.3
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.