• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.324-327
• /
• 2022

Crack inspection of aged structures is mostly conducted by inspectors using surveying tools on site and visually inspecting them. This method greatly depends on professional worker, and consumes a lot of time and money. An artificial intelligence image classification algorithm is used to make reliable and objective judgments. Since 2018, image augmentation techniques have been used in the image pre-processing stage as they lead to high performance improvement. In this study, an analysis algorithm for cracks in concrete structures was developed using image augmentation techniques, in which the accuracy and speed according to the augmentation ratio were compared and measured for optimization. As a result, it was found that 8 times of image augmentation was appropriate when the accuracy was improved and economic feasibility was taken into account.

• 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.

• Journal of Digital Policy
• /
• v.3 no.1
• /
• pp.27-32
• /
• 2024

In this paper, proposes a super resolution method that enhances the quality of results by refining texture features, contrasting each, and utilizing the results as weights. For the improvement of quality, a precise and clear restoration result in details such as boundary areas is crucial in super resolution, along with minimizing unnecessary artifacts like noise. The proposed method constructs a residual block structure with multiple paths and skip-connections for feature estimation in conventional Convolutional Neural Network (CNN)-based super resolution methods to enhance quality. Additional learning is performed for sharpened and blurred image results for further texture analysis. By contrasting each super resolution result and allocating weights through this process, the proposed method achieves improved quality in detailed and smoothed areas of the image. The experimental results of the proposed method, evaluated using the PSNR and SSIM values as quality metrics, show higher results compared to existing algorithms, confirming the enhancement in quality.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.555-556
• /
• 2021

We propose a novel method based on a deep learning model with an optimized dynamic decay learning rate and improved model structure to achieve fast and accurate classification of fashion clothing images.

• The Journal of Korea Robotics Society
• /
• v.15 no.1
• /
• pp.62-69
• /
• 2020

This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.356-361
• /
• 1998

Neural Networks, modeled succinctly from the real nervous system of a living body, can be categorized into two folds; artificial neural network(ANN) and biological neural network(BNN). While the former has been developed to solve practical problems using function approximation capability, pattern classification) clustering algorithm, etc, the latter has been focused on verifying the information processing capability to which brain research gives an impetus, by mimicking real biological systems. However, BNN suffers Iron severe nonlinearities dealt with. A bridge between two neural networks is chaotic neural network(CNN), which simply delineate the real nor-vous system and comprises almost all the ANN structures by selecting parameters. Main research theme of this area is to develop an explanation tool to clarify the information processing mechanism in biological systems and its extension to engineering applications. The CNN has a Gaussian-shaped refractory function with hysteresis effect and the chaotic responses of it have been observed fur a wide range of parameter space. Through the examination of the coupling effects of excitatory and inhibitory connections, the secrets of information processing and memory structure will appear.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.11
• /
• pp.1008-1016
• /
• 2015

This paper proposes a method for detecting the front side of vehicles. The method can find the car side with a license plate even with complicated and cluttered backgrounds. A convolutional neural network (CNN) is used to solve the detection problem as a unified framework combining feature detection, classification, searching, and localization estimation and improve the reliability of the system with simplicity of usage. The proposed CNN structure avoids sliding window search to find the locations of vehicles and reduces the computing time to achieve real-time processing. Multiple responses of the network for vehicle position are further processed by a weighted clustering and probabilistic threshold decision method. Experiments using real images in parking lots show the reliability of the method.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Structural Monitoring and Maintenance
• /
• v.8 no.4
• /
• pp.379-402
• /
• 2021

Traditional approaches for structural health monitoring (SHM) seldom take ambient uncertainty (temperature, humidity, ambient vibration) into consideration, while their impacts on structural responses are substantial, leading to a possibility of raising false alarms. A few predictors model-based approaches deal with these uncertainties through complex numerical models running online, rendering the SHM approach to be compute-intensive, slow, and sometimes not practical. Also, with model-based approaches, the imperative need for a precise understanding of the structure often poses a problem for not so well understood complex systems. The present study employs a data-based approach coupled with Empirical mode decomposition (EMD) to correlate recorded response time histories under varying temperature conditions to corresponding damage scenarios. EMD decomposes the response signal into a finite set of intrinsic mode functions (IMFs). A two-dimensional Convolutional Neural Network (2DCNN) is further trained to associate these IMFs to the respective damage cases. The use of IMFs in place of raw signals helps to reduce the impact of sensor noise while preserving the essential spatio-temporal information less-sensitive to thermal effects and thereby stands as a better damage-sensitive feature than the raw signal itself. The proposed algorithm is numerically tested on a single span bridge under varying temperature conditions for different damage severities. The dynamic strain is recorded as the response since they are frame-invariant and cheaper to install. The proposed algorithm has been observed to be damage sensitive as well as sufficiently robust against measurement noise.