• Structural Engineering and Mechanics
• /
• v.70 no.3
• /
• pp.339-350
• /
• 2019

This research focuses on finite element model updating and damage assessment of structures at element level based on global nondestructive test results. For this purpose, an optimization system is generated to minimize the structural dynamic parameters discrepancies between numerical and experimental models. Objective functions are selected based on the square of Euclidean norm error of vibration frequencies and modal assurance criterion of mode shapes. In order to update the finite element model and detect local damages within the structural members, modern optimization techniques is implemented according to the evolutionary algorithms to meet the global optimized solution. Using a simulated numerical example, application of genetic algorithm (GA), particle swarm (PSO) and artificial bee colony (ABC) algorithms are investigated in FE model updating and damage detection problems to consider their accuracy and convergence characteristics. Then, a hybrid multi stage optimization method is presented merging advantages of PSO and ABC methods in finding damage location and extent. The efficiency of the methods have been examined using two simulated numerical examples, a laboratory dynamic test and a high-rise building field ambient vibration test results. The implemented evolutionary updating methods show successful results in accuracy and speed considering the incomplete and noisy experimental measured data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.247-252
• /
• 2019

The diffraction properties of optical signals by multi-layered periodic structures is formulated in two-dimensional space by using Fourier expansions associated with basic grating profile. The fields in each layer are then expressed in terms of characteristic modes, and the complete solution is found rigorously by using a modal transmission-line theory(MTLT) to address the pertinent boundary-value problems. Such an approach can treat periodic arbitrary gratings containing arbitrarily shaped dielectric components, which may generally have optical properties along directions that are parallel or perpendicular to the multi-layers. This paper illustrates the present approach by comparing our numerical results with data reported in the past for simple periodic circular 2D structures. In addition, this proposed theory can apply easily for more complex configurations, which include multiple periodic regions with several possible canonic shapes and high dielectric constants.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.38 no.4
• /
• pp.110-124
• /
• 1996

This study was conducted to simulate long seres of synthetic monthly flows by multi-season first order Markov model with selection of best fitting frequency distribution, harmonic synthetic and harmonic regression models and to make a comparison of statistical parameters between observes and synthetic flows of five watersheds in Geum river system. The results obtained through this study can be summarized as follow. 1. Both gamma and two parameter lognormal distributions were found to be suitable ones for monthly flows in all watersheds by Kolmogorov-Smirnov test. 2. It was found that arithmetic mean values of synthetic monthly flows simulated by multi-season first order Markov model with gamma distribution are much closer to the results of the observed data in comparison with those of the other models in the applied watersheds. 3. The coefficients of variation, index of fluctuation for monthly flows simulated by multi-season first order Markov model with gamma distribution are appeared closer to those of the observed data in comparison with those of the other models in Geum river system. 4. Synthetic monthly flows were simulated over 100 years by multi-season first order Markov model with gamma distribution which is acknowledged as a suitable simulation modal in this study.

• Journal of KSNVE
• /
• v.8 no.4
• /
• pp.690-699
• /
• 1998

This paper discusses the techniques, procedures and the results of the ground vibration test(GVT) performed on the development aircraft and the simple procedure of FE model updating technique from the GVT results. The GVT was carried out using random excitation technique with MIMO(Multi-Input-Multi-Output) data acquistion method, and taking full advantage of poly-reference global parameter estimation technique to identify the vibration modes. In dynamic FE modeling, the aircraft was represented by beam elements and all dynamic analysis was performed using MSC/NASTRAN for this model. In updating procedure, the stiffness of the beam model was adjusted iteratively so as to get the natural frequencies and mode shapes close to the GVT results.

• Journal of Korea Game Society
• /
• v.16 no.2
• /
• pp.7-16
• /
• 2016

In this paper, we propose a method for effectively detecting specific behavior. The proposed method detects outlying behavior based on the game players' characteristics. These characteristics are captured non-invasively in a general game environment and add keystroke based on repeated pattern. In this paper, cameras were used to analyze observed data such as facial expressions and player movements. Moreover, multimodal data from the game players was used to analyze high-dimensional game-player data for a detection effect of repeated behaviour pattern. A support vector machine was used to efficiently detect outlying behaviors. We verified the effectiveness of the proposed method using games from several genres. The recall rate of the outlying behavior pre-identified by industry experts was approximately 70%. In addition, Repeated behaviour pattern can be analysed possible. The proposed method can also be used for feedback and quantification about analysis of various interactive content provided in PC environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.2
• /
• pp.1-9
• /
• 2008

As the security requirements of mobile phones have been increasing, there have been extensive researches using one biometric feature (e.g., an iris, a fingerprint, or a face image) for authentication. Due to the limitation of uni-modal biometrics, we propose a method that combines face and iris images in order to improve accuracy in mobile environments. This paper presents four advantages and contributions over previous research. First, in order to capture both face and iris image at fast speed and simultaneously, we use a built-in conventional mega pixel camera in mobile phone, which is revised to capture the NIR (Near-InfraRed) face and iris image. Second, in order to increase the authentication accuracy of face and iris, we propose a score level fusion method based on SVM (Support Vector Machine). Third, to reduce the classification complexities of SVM and intra-variation of face and iris data, we normalize the input face and iris data, respectively. For face, a NIR illuminator and NIR passing filter on camera are used to reduce the illumination variance caused by environmental visible lighting and the consequent saturated region in face by the NIR illuminator is normalized by low processing logarithmic algorithm considering mobile phone. For iris, image transform into polar coordinate and iris code shifting are used for obtaining robust identification accuracy irrespective of image capturing condition. Fourth, to increase the processing speed on mobile phone, we use integer based face and iris authentication algorithms. Experimental results were tested with face and iris images by mega-pixel camera of mobile phone. It showed that the authentication accuracy using SVM was better than those of uni-modal (face or iris), SUM, MAX, NIN and weighted SUM rules.

• Structural Engineering and Mechanics
• /
• v.46 no.3
• /
• pp.433-445
• /
• 2013

Vibration-based structural identification has become an important tool for structural health monitoring and safety evaluation. However, various kinds of uncertainties (e.g., observation noise) involved in the field test data obstruct automation system identification for accurate and fast structural safety evaluation. A practical way including a data preprocessing procedure and a vector backward auto-regressive (VBAR) method has been investigated for practical bridge identification. The data preprocessing procedure serves to improve the data quality, which consists of multi-level uncertainty mitigation techniques. The VBAR method provides a determinative way to automatically distinguish structural modes from extraneous modes arising from uncertainty. Ambient test data of a cantilever beam is investigated to demonstrate how the proposed method automatically interprets vibration data for structural modal estimation. Especially, structural identification of a truss bridge using field test data is also performed to study the effectiveness of the proposed method for real bridge identification.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.9-15
• /
• 2024

Tree-based algorithms have been the dominant methods used build a prediction model for tabular data. This also includes personal credit data. However, they are limited to compatibility with categorical and numerical data only, and also do not capture information of the relationship between other features. In this work, we proposed an ensemble model using the Transformer architecture that includes text features and harness the self-attention mechanism to tackle the feature relationships limitation. We describe a text formatter module, that converts the original tabular data into sentence data that is fed into FinBERT along with other text features. Furthermore, we employed FT-Transformer that train with the original tabular data. We evaluate this multi-modal approach with two popular tree-based algorithms known as, Random Forest and Extreme Gradient Boosting, XGBoost and TabTransformer. Our proposed method shows superior Default Recall, F1 score and AUC results across two public data sets. Our results are significant for financial institutions to reduce the risk of financial loss regarding defaulters.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.11 no.4
• /
• pp.5-12
• /
• 2001

This paper presents the simulation methodology of the interior noise of vehicle using the frequency response function based hybrid modeling of the system which consists of multi-subsystem models obtained by the test or analysis. The complex systems such as a trimmed body of high modal density and a powertrain were modeled by using experimental data, and a sub-frame of a vehicle of low modal density was modeled by finite element data. Modeling of the whole system was executed and validated in the two stages. The first stave is combining the trimmed body and the sub-frame, and the second stage is attaching the powertrain, which is a exciting source, to the combined model of the first stage. The input force to the system was modeled as an equivalent force in the virtual space, which was obtained from impedance method using the FRFs of the powertrain and the responses. The interior noise predicted by the proposed method was very close to the direct measurement, which showed feasibility of the proposed modeling procedure. Since the methodology is easily applied to both the transfer path analysis of structure-borne noise and the analysis of noise contribution of a sub-system, it is expected to be a strong tool for design change of a vehicle in the earlier stare.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.