• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.9 no.3
• /
• pp.191-197
• /
• 2009

Up to now, a number of models have been proposed and discussed to describe a wide range of inelastic behaviors of materials. The fatal problem of using such models is however the existence of model errors, and the problem remains inevitably as far as a material model is written explicitly. In this paper, the authors define the implicit constitutive model and propose an implicit viscoplastic constitutive model using neural networks. In their modeling, inelastic material behaviors are generalized in a state space representation and the state space form is constructed by a neural network using input-output data sets. A technique to extract the input-output data from experimental data is also described. The proposed model was first generated from pseudo-experimental data created by one of the widely used constitutive models and was found to replace the model well. Then, having been tested with the actual experimental data, the proposed model resulted in a negligible amount of model errors indicating its superiority to all the existing explicit models in accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.251-256
• /
• 2005

Up to now, a number of models have been proposed and discussed to describe a wide range of inelastic behaviors of materials. The fetal problem of using such models is however the existence of model errors, and the problem remains inevitably as far as a material model is written explicitly. In this paper, the authors define the implicit constitutive model and propose an implicit viscoplastic constitutive model using neural networks. In their modeling, inelastic material behaviors are generalized in a state space representation and the state space form is constructed by a neural network using input output data sets. A technique to extract the input-output data from experimental data is also described. The proposed model was first generated from pseudo-experimental data created by one of the widely used constitutive models and was found to replace the model well. Then, having been tested with the actual experimental data, the proposed model resulted in a negligible amount of model errors indicating its superiority to all the existing explicit models in accuracy.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.23-26
• /
• 2024

본 논문에서는 그래프 구조의 데이터에서 각 노드의 신호를 예측하는 연구를 진행하였다. 이를 위해 분석하고자 하는 그래프에 대해 연결 관계를 기반으로 각 노드에 비-유클리드 공간 상에서의 좌표를 부여하여 그래프의 공간적 임베딩을 얻은 뒤, 각 노드의 공간적 임베딩을 입력으로 받고 해당 노드의 신호를 예측하는 그래프 암시적 신경 표현 모델을 제안 하였다. 제안된 모델의 검증을 위해 네트워크형 데이터와 3차원 메시 데이터 두 종류의 그래프 데이터에 대하여 신호 학습, 신호 예측 및 메시 데이터의 초해상도 과정 실험들을 진행하였다. 전반적으로 기존의 그래프 암시적 신경 표현 모델과 비교하였을 때 비슷하거나 더 우수한 성능을 보였으며, 특히 네트워크형 그래프 데이터 신호 예측 실험에서 큰 성능 향상을 보였다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.267-275
• /
• 2022

Using a nonconforming mesh in enrichment methods results in several numerical issues induced by discontinuities and singularities found within the solution spaces, including the computational overhead during integration. In this study, we present a novel enrichment technique based on the selective expansion technique of moment fitting (Düster and Allix, 2020). In particular, two modifications are proposed to address the inefficiency during the integration process. First, a feedforward artificial neural network is introduced to correlate the implicit functions and integration moments. Through numerical examples, it is shown that the efficiency of the method is greatly improved when compared with existing expansion techniques, whereas the solution accuracy is maintained. Additionally, the finite element and domain representation grids are separated, which in turn improves the solution accuracy even for coarse mesh conditions.