• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.1
• /
• pp.42.1-42.1
• /
• 2021

In this study, we present a visual explanation of a deep learning solar flare forecast model and its relationship to physical parameters of solar active regions (ARs). For this, we use full-disk magnetograms at 00:00 UT from the Solar and Heliospheric Observatory/Michelson Doppler Imager and the Solar Dynamics Observatory/Helioseismic and Magnetic Imager, physical parameters from the Space-weather HMI Active Region Patch (SHARP), and Geostationary Operational Environmental Satellite X-ray flare data. Our deep learning flare forecast model based on the Convolutional Neural Network (CNN) predicts "Yes" or "No" for the daily occurrence of C-, M-, and X-class flares. We interpret the model using two CNN attribution methods (guided backpropagation and Gradient-weighted Class Activation Mapping [Grad-CAM]) that provide quantitative information on explaining the model. We find that our deep learning flare forecasting model is intimately related to AR physical properties that have also been distinguished in previous studies as holding significant predictive ability. Major results of this study are as follows. First, we successfully apply our deep learning models to the forecast of daily solar flare occurrence with TSS = 0.65, without any preprocessing to extract features from data. Second, using the attribution methods, we find that the polarity inversion line is an important feature for the deep learning flare forecasting model. Third, the ARs with high Grad-CAM values produce more flares than those with low Grad-CAM values. Fourth, nine SHARP parameters such as total unsigned vertical current, total unsigned current helicity, total unsigned flux, and total photospheric magnetic free energy density are well correlated with Grad-CAM values.

• Journal of Korean Dental Science
• /
• v.16 no.2
• /
• pp.218-226
• /
• 2023

Treatment of multiple gingival recession defects is usually more challenging than that of single gingival recession. Various techniques for the treatment of multiple gingival recession have been established. Recently, vestibular incision subperiosteal tunnel access (VISTA) technique has been considered to exhibit high predictive ability. Connective tissue graft (CTG) has also been considered a gold standard technique owing to its high predictability of root coverage. However, this technique requires a suitable donor site and has clinical disadvantages, such as additional pain. Thus, in this case presentation, platelet-rich fibrin (PRF) was used as an alternative material for CTG along with VISTA. We herein report cases of two patients with Miller's class I and III multiple gingival recession defects, respectively. These patients underwent VISTA along with the use of a PRF membrane. They were followed up for 12 months postoperatively, and their clinical parameters, including probing depth, depth of gingival recession, clinical attachment level, and width of attached gingiva at baseline and at 2, 6, and 12 months postoperatively, were assessed. The patient with class 1 recession defects exhibited a significant amount of root coverage, which remained stable during the follow-up period. Whereas the patient with class 3 recession defects had lesser amount of coverage compared to class 1 patient. The partial coverage observed may be attributed to not only anatomical factors but also the technique-sensitive nature of the procedure. Considering these results, the use of VISTA along with PRF is a viable option for treating gingival recession, as it does not cause discomfort to patients. However, various factors need to be considered during the surgical procedure.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.6
• /
• pp.851-863
• /
• 2023

The mandatory use of BIM(Building Information Model) in larger Korean public construction projects necessitates participants to have a comprehensive understanding of the relevant procedures and technologies, especially during the bidding stage. However, most small and medium-sized construction and engineering companies possess limited BIM proficiency and understanding. This hampers their ability to recognize bidding requirements and make informed decisions. To address this challenge, our study introduces a method to gauge the complexity of BIM requirements in bidding documents. This is achieved by integrating a morphological analyzer, which encompasses BIM bidding terminology, with a deep learning model. We investigated the effects of the parameters in our proposed deep learning model and examined its predictive validity. The results revealed an F1-score of 0.83 for the test data, indicating that the model's predictions align closely with the actual BIM performance challenges.

• Structural Engineering and Mechanics
• /
• v.90 no.1
• /
• pp.19-26
• /
• 2024

In recent years, an increasing number of experimental studies have shown that the practical application of mature active control systems requires consideration of robustness criteria in the design process, including the reduction of tracking errors, operational resistance to external disturbances, and measurement noise, as well as robustness and stability. Good uncertainty prediction is thus proposed to solve problems caused by poor parameter selection and to remove the effects of dynamic coupling between degrees of freedom (DOF) in nonlinear systems. To overcome the stability problem, this study develops an advanced adaptive predictive fuzzy controller, which not only solves the programming problem of determining system stability but also uses the law of linear matrix inequality (LMI) to modify the fuzzy problem. The following parameters are used to manipulate the fuzzy controller of the robotic system to improve its control performance. The simulations for system uncertainty in the controller design emphasized the use of acceleration feedback for practical reasons. The simulation results also show that the proposed H∞ controller has excellent performance and reliability, and the effectiveness of the LMI-based method is also recognized. Therefore, this dynamic control method is suitable for seismic protection of civil buildings. The objectives of this document are access to adequate, safe, and affordable housing and basic services, promotion of inclusive and sustainable urbanization, implementation of sustainable disaster-resilient construction, sustainable planning, and sustainable management of human settlements. Simulation results of linear and non-linear structures demonstrate the ability of this method to identify structures and their changes due to damage. Therefore, with the continuous development of artificial intelligence and fuzzy theory, it seems that this goal will be achieved in the near future.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• Geomechanics and Engineering
• /
• v.36 no.5
• /
• pp.465-474
• /
• 2024

Uniaxial compressive strength (UCS) is a critical geomechanical parameter that plays a significant role in the evaluation of rocks. The practice of indirectly estimating said characteristics is widespread due to the challenges associated with obtaining high-quality core samples. The primary aim of this study is to investigate the feasibility of utilizing the gene expression programming (GEP) technique for the purpose of forecasting the UCS for various rock categories, including Schist, Granite, Claystone, Travertine, Sandstone, Slate, Limestone, Marl, and Dolomite, which were sourced from a wide range of quarry sites. The present study utilized a total of 170 datasets, comprising Schmidt hammer (SH), porosity (n), point load index (Is(50)), and P-wave velocity (Vp), as the effective parameters in the model to determine their impact on the UCS. The UCS parameter was computed through the utilization of the GEP model, resulting in the generation of an equation. Subsequently, the efficacy of the GEP model and the resultant equation were assessed using various statistical evaluation metrics to determine their predictive capabilities. The outcomes indicate the prospective capacity of the GEP model and the resultant equation in forecasting the unconfined compressive strength (UCS). The significance of this study lies in its ability to enable geotechnical engineers to make estimations of the UCS of rocks, without the requirement of conducting expensive and time-consuming experimental tests. In particular, a user-friendly program was developed based on the GEP model to enable rapid and very accurate calculation of rock's UCS, doing away with the necessity for costly and time-consuming laboratory experiments.

• Information Systems Review
• /
• v.20 no.4
• /
• pp.25-41
• /
• 2018

Applying predictive analytics to enterprise processes is an effective way to reduce operation costs and enhance productivity. Accordingly, the ability to predict business processes and performance indicators are regarded as a core capability. Recently, several works have predicted processes using deep learning in the form of recurrent neural networks (RNN). In particular, the approach of predicting the next step of activity using static or dynamic RNN has excellent results. However, few studies have given attention to applying deep learning in the form of dynamic RNN to predictions of process performance indicators. To fill this knowledge gap, the study developed an approach to using process mining and dynamic RNN. By utilizing actual data from a large domestic company, it has applied the suggested approach in estimating timely stocking in purchasing process, which is an important indicator of the process. The analytic methods and results of this study were presented and some implications and limitations are also discussed.

• Journal of Microbiology and Biotechnology
• /
• v.34 no.4
• /
• pp.958-968
• /
• 2024

In recent years, there has been a growing recognition of the important role that long non-coding RNAs (lncRNAs) play in the immunological process of hepatocellular carcinoma (LIHC). An increasing number of studies have shown that certain lncRNAs hold great potential as viable options for diagnosis and treatment in clinical practice. The primary objective of our investigation was to devise an immune lncRNA profile to explore the significance of immune-associated lncRNAs in the accurate diagnosis and prognosis of LIHC. Gene expression profiles of LIHC samples obtained from TCGA database were screened for immune-related genes. The optimal immune-related lncRNA signature was built via correlational analysis, univariate and multivariate Cox analysis. Then, the Kaplan-Meier plot, ROC curve, clinical analysis, gene set enrichment analysis, and principal component analysis were performed to evaluate the capability of the immune lncRNA signature as a prognostic indicator. Six long non-coding RNAs were identified via correlation analysis and Cox regression analysis considering their interactions with immune genes. Subsequently, tumor samples were categorized into two distinct risk groups based on different clinical outcomes. Stratification analysis indicated that the prognostic ability of this signature acted as an independent factor. The Kaplan-Meier method was employed to conduct survival analysis, results showed a significant difference between the two risk groups. The predictive performance of this signature was validated by principal component analysis (PCA). Additionally, data obtained from gene set enrichment analysis (GSEA) revealed several potential biological processes in which these biomarkers may be involved. To summarize, this study demonstrated that this six-lncRNA signature could be identified as a potential factor that can independently predict the prognosis of LIHC patients.

• Journal of Music and Human Behavior
• /
• v.13 no.1
• /
• pp.1-18
• /
• 2016

This study examined the correlation between the rhythm reproduction performance and cognitive function of school-aged children. A total of 59 third grade elementary students participated in this study. An iPad-based rhythm reproduction task, the Digit Span Test (DST), the Children's Color Trails Test (CCTT), and a self-paced tapping task via a MIDI keyboard were conducted for each participant. The results demonstrated that scores at each stage of the iPad-based rhythm reproduction test showed different patterns of correlation with cognitive function test scores. This result suggests that accuracy of a simple rhythm task is correlated to speed of self-paced tapping (second). Also cognitive function may affect rhythm grouping ability. Results of this analysis for each of 20 rhythm items showed that there was a common rhythm characteristics that correlated with executive function, working memory or self-paced tapping speed. These results indicate that rhythm ability is related to, and predictive of, the level of cognitive functioning in elementary school students and can be used as an useful parameter when examining cognitive function of school-aged children in multifaceted dimensions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.173-178
• /
• 2014

In this study, we introduce ASM-based face recognition classifier and its design methodology with the aid of 2-dimensional 2-directional hybird preprocessing algorithm. Since the image of face recognition is easily affected by external environments, ASM(active shape model) as image preprocessing algorithm is used to resolve such problem. In particular, ASM is used widely for the purpose of feature extraction for human face. After extracting face image area by using ASM, the dimensionality of the extracted face image data is reduced by using $(2D)^2$hybrid preprocessing algorithm based on LDA and PCA. Face image data through preprocessing algorithm is used as input data for the design of the proposed polynomials based radial basis function neural network. Unlike as the case in existing neural networks, the proposed pattern classifier has the characteristics of a robust neural network and it is also superior from the view point of predictive ability as well as ability to resolve the problem of multi-dimensionality. The essential design parameters (the number of row eigenvectors, column eigenvectors, and clusters, and fuzzification coefficient) of the classifier are optimized by means of ABC(artificial bee colony) algorithm. The performance of the proposed classifier is quantified through yale and AT&T dataset widely used in the face recognition.