• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• Smart Structures and Systems
• /
• v.31 no.5
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• Smart Structures and Systems
• /
• v.31 no.3
• /
• pp.229-245
• /
• 2023

The absence of excitation measurements may pose a big challenge in the application of structural damage identification owing to the fact that substantial effort is needed to reconstruct or identify unknown input force. To address this issue, in this paper, an iterative strategy, a synergy of Tikhonov regularization method for force identification and modified Jaya algorithm (M-Jaya) for stiffness parameter identification, is developed for damage identification with partial output-only responses. On the one hand, the probabilistic clustering learning technique and nonlinear updating equation are introduced to improve the performance of standard Jaya algorithm. On the other hand, to deal with the difficulty of selection the appropriate regularization parameters in traditional Tikhonov regularization, an improved L-curve method based on B-spline interpolation function is presented. The applicability and effectiveness of the iterative strategy for simultaneous identification of structural damages and unknown input excitation is validated by numerical simulation on a 21-bar truss structure subjected to ambient excitation under noise free and contaminated measurements cases, as well as a series of experimental tests on a five-floor steel frame structure excited by sinusoidal force. The results from these numerical and experimental studies demonstrate that the proposed identification strategy can accurately and effectively identify damage locations and extents without the requirement of force measurements. The proposed M-Jaya algorithm provides more satisfactory performance than genetic algorithm, Gaussian bare-bones artificial bee colony and Jaya algorithm.

• The KIPS Transactions:PartB
• /
• v.8B no.6
• /
• pp.651-656
• /
• 2001

In this paper, we propose Improved Self-Organized Graph(Improved SOG：$SOG^*$)thinning method, which maintains the excellent thinning results of Self-organized graph(SOG) built from Self-Organizing features map and improves the performance of modified SOG using a new incremental learning method of Kohonen features map. In the experiments, this method shows the thinning results equal to those of SOG and the time complexity O((logM)3) superior to it. Therefore, the proposed method is useful for the feature extraction from digits and characters in the preprocessing step.

• The Korean Journal of Nuclear Medicine
• /
• v.37 no.2
• /
• pp.73-82
• /
• 2003

Objectives: A new software (Cardiac SPECT Analyzer: CSA) was developed for quantification of volumes and election fraction on gated myocardial SPECT. Volumes and ejection fraction by CSA were validated by comparing with those quantified by Quantitative Gated SPECT (QGS) software. Materials and Methods: Gated myocardial SPECT was peformed in 40 patients with ejection fraction from 15% to 85%. In 26 patients, gated myocardial SPECT was acquired again with the patients in situ. A cylinder model was used to eliminate noise semi-automatically and profile data was extracted using Gaussian fitting after smoothing. The boundary points of endo- and epicardium were found using an iterative learning algorithm. Enddiastolic (EDV) and endsystolic volumes (ESV) and election fraction (EF) were calculated. These values were compared with those calculated by QGS and the same gated SPECT data was repeatedly quantified by CSA and variation of the values on sequential measurements of the same patients on the repeated acquisition. Results: From the 40 patient data, EF, EDV and ESV by CSA were correlated with those by QGS with the correlation coefficients of 0.97, 0.92, 0.96. Two standard deviation (SD) of EF on Bland Altman plot was 10.1%. Repeated measurements of EF, EDV, and ESV by CSA were correlated with each other with the coefficients of 0.96, 0.99, and 0.99 for EF, EDV and ESV respectively. On repeated acquisition, reproducibility was also excellent with correlation coefficients of 0.89, 0.97, 0.98, and coefficient of variation of 8.2%, 5.4mL, 8.5mL and 2SD of 10.6%, 21.2mL, and 16.4mL on Bland Altman plot for EF, EDV and ESV. Conclusion: We developed the software of CSA for quantification of volumes and ejection fraction on gated myocardial SPECT. Volumes and ejection fraction quantified using this software was found valid for its correctness and precision.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.933-948
• /
• 2023

Atmospheric aerosols not only have adverse effects on human health but also exert direct and indirect impacts on the climate system. Consequently, it is imperative to comprehend the characteristics and spatiotemporal distribution of aerosols. Numerous research endeavors have been undertaken to monitor aerosols, predominantly through the retrieval of aerosol optical depth (AOD) via satellite-based observations. Nonetheless, this approach primarily relies on a look-up table-based inversion algorithm, characterized by computationally intensive operations and associated uncertainties. In this study, a novel high-resolution AOD direct retrieval algorithm, leveraging machine learning, was developed using top-of-atmosphere reflectance data derived from the Geostationary Ocean Color Imager-II (GOCI-II), in conjunction with their differences from the past 30-day minimum reflectance, and meteorological variables from numerical models. The Light Gradient Boosting Machine (LGBM) technique was harnessed, and the resultant estimates underwent rigorous validation encompassing random, temporal, and spatial N-fold cross-validation (CV) using ground-based observation data from Aerosol Robotic Network (AERONET) AOD. The three CV results consistently demonstrated robust performance, yielding R²=0.70-0.80, RMSE=0.08-0.09, and within the expected error (EE) of 75.2-85.1%. The Shapley Additive exPlanations(SHAP) analysis confirmed the substantial influence of reflectance-related variables on AOD estimation. A comprehensive examination of the spatiotemporal distribution of AOD in Seoul and Ulsan revealed that the developed LGBM model yielded results that are in close concordance with AERONET AOD over time, thereby confirming its suitability for AOD retrieval at high spatiotemporal resolution (i.e., hourly, 250 m). Furthermore, upon comparing data coverage, it was ascertained that the LGBM model enhanced data retrieval frequency by approximately 8.8% in comparison to the GOCI-II L2 AOD products, ameliorating issues associated with excessive masking over very illuminated surfaces that are often encountered in physics-based AOD retrieval processes.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.207-221
• /
• 2023

This study suggests deep neural network models for estimating air temperature with Level 1B (L1B) datasets of GEO-KOMPSAT-2A (GK-2A). The temperature at 1.5 m above the ground impact not only daily life but also weather warnings such as cold and heat waves. There are many studies to assume the air temperature from the land surface temperature (LST) retrieved from satellites because the air temperature has a strong relationship with the LST. However, an algorithm of the LST, Level 2 output of GK-2A, works only clear sky pixels. To overcome the cloud effects, we apply a deep neural network (DNN) model to assume the air temperature with L1B calibrated for radiometric and geometrics from raw satellite data and compare the model with a linear regression model between LST and air temperature. The root mean square errors (RMSE) of the air temperature for model outputs are used to evaluate the model. The number of 95 in-situ air temperature data was 2,496,634 and the ratio of datasets paired with LST and L1B show 42.1% and 98.4%. The training years are 2020 and 2021 and 2022 is used to validate. The DNN model is designed with an input layer taking 16 channels and four hidden fully connected layers to assume an air temperature. As a result of the model using 16 bands of L1B, the DNN with RMSE 2.22℃ showed great performance than the baseline model with RMSE 3.55℃ on clear sky conditions and the total RMSE including overcast samples was 3.33℃. It is suggested that the DNN is able to overcome cloud effects. However, it showed different characteristics in seasonal and hourly analysis and needed to append solar information as inputs to make a general DNN model because the summer and winter seasons showed a low coefficient of determinations with high standard deviations.