• Imaging Science in Dentistry
• /
• v.52 no.2
• /
• pp.219-224
• /
• 2022

Purpose: This study aimed to evaluate the performance of transfer learning in a deep convolutional neural network for classifying implant fixtures. Materials and Methods: Periapical radiographs of implant fixtures obtained using the Superline (Dentium Co. Ltd., Seoul, Korea), TS III(Osstem Implant Co. Ltd., Seoul, Korea), and Bone Level Implant(Institut Straumann AG, Basel, Switzerland) systems were selected from patients who underwent dental implant treatment. All 355 implant fixtures comprised the total dataset and were annotated with the name of the system. The total dataset was split into a training dataset and a test dataset at a ratio of 8 to 2, respectively. YOLOv3 (You Only Look Once version 3, available at https://pjreddie.com/darknet/yolo/), a deep convolutional neural network that has been pretrained with a large image dataset of objects, was used to train the model to classify fixtures in periapical images, in a process called transfer learning. This network was trained with the training dataset for 100, 200, and 300 epochs. Using the test dataset, the performance of the network was evaluated in terms of sensitivity, specificity, and accuracy. Results: When YOLOv3 was trained for 200 epochs, the sensitivity, specificity, accuracy, and confidence score were the highest for all systems, with overall results of 94.4%, 97.9%, 96.7%, and 0.75, respectively. The network showed the best performance in classifying Bone Level Implant fixtures, with 100.0% sensitivity, specificity, and accuracy. Conclusion: Through transfer learning, high performance could be achieved with YOLOv3, even using a small amount of data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.29-38
• /
• 2022

This paper proposes a system for classifying gait types using an ensemble deep learning network for gait data measured by a smart insole equipped with multi-sensors. The gait type classification system consists of a part for normalizing the data measured by the insole, a part for extracting gait features using a deep learning network, and a part for classifying the gait type by inputting the extracted features. Two kinds of gait feature maps were extracted by independently learning networks based on CNNs and LSTMs with different characteristics. The final ensemble network classification results were obtained by combining the classification results. For the seven types of gait for adults in their 20s and 30s: walking, running, fast walking, going up and down stairs, and going up and down hills, multi-sensor data was classified into a proposed ensemble network. As a result, it was confirmed that the classification rate was higher than 90%.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1491-1495
• /
• 2023

This study utilized automated machine learning (AutoML) to calculate Arctic ice surface temperature (IST). AutoML-derived IST exhibited a strong correlation coefficient (R) of 0.97 and a root mean squared error (RMSE) of 2.51K. Comparative analysis with deep neural network (DNN) models revealed that AutoML IST demonstrated good accuracy, particularly when compared to Moderate Resolution Imaging Spectroradiometer (MODIS) IST and ice mass balance (IMB) buoy IST. These findings underscore the effectiveness of AutoML in enhancing IST estimation accuracy under challenging polar conditions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.1-8
• /
• 2024

On-device AI technology, which can operate AI models at the edge devices to support real-time processing and privacy enhancement, is attracting attention. As intelligent IoT is applied to various industries, services utilizing the on-device AI technology are increasing significantly. However, general deep learning models require a lot of computational resources for inference and learning. Therefore, various lightweighting methods such as quantization and pruning have been suggested to operate deep learning models in embedded edge devices. Among the lightweighting methods, we analyze how to lightweight and apply deep learning models to edge computing devices, focusing on pruning technology in this paper. In particular, we utilize dynamic and static pruning techniques to evaluate the inference speed, accuracy, and memory usage of a lightweight AI vision model. The content analyzed in this paper can be used for intelligent video control systems or video security systems in autonomous vehicles, where real-time processing are highly required. In addition, it is expected that the content can be used more effectively in various IoT services and industries.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.4
• /
• pp.183-191
• /
• 2024

Accurate seismic vulnerability assessment requires high quality and large amounts of ground motion data. Ground motion data generated from time series contains not only the seismic waves but also the background noise. Therefore, it is crucial to determine the high-pass cut-off frequency to reduce the background noise. Traditional methods for determining the high-pass filter frequency are based on human inspection, such as comparing the noise and the signal Fourier Amplitude Spectrum (FAS), f² trend line fitting, and inspection of the displacement curve after filtering. However, these methods are subject to human error and unsuitable for automating the process. This study used a deep learning approach to determine the high-pass filter frequency. We used the Mel-spectrogram for feature extraction and mixup technique to overcome the lack of data. We selected convolutional neural network (CNN) models such as ResNet, DenseNet, and EfficientNet for transfer learning. Additionally, we chose ViT and DeiT for transformer-based models. The results showed that ResNet had the highest performance with R² (the coefficient of determination) at 0.977 and the lowest mean absolute error (MAE) and RMSE (root mean square error) at 0.006 and 0.074, respectively. When applied to a seismic event and compared to the traditional methods, the determination of the high-pass filter frequency through the deep learning method showed a difference of 0.1 Hz, which demonstrates that it can be used as a replacement for traditional methods. We anticipate that this study will pave the way for automating ground motion processing, which could be applied to the system to handle large amounts of data efficiently.

• International Journal of Computer Science & Network Security
• /
• v.24 no.9
• /
• pp.63-76
• /
• 2024

Weather forecasting has become a very popular topic nowadays among researchers because of its various effects on global lives. It is a technique to predict the future, what is going to happen in the atmosphere by analyzing various available datasets such as rain, snow, cloud cover, temperature, moisture in the air, and wind speed with the help of our gained scientific knowledge i.e., several approaches and set of rules or we can say them as algorithms that are being used to analyze and predict the weather. Weather analysis and prediction are required to prevent nature from natural losses before it happens by using a Deep Learning Approach. This analysis and prediction are the most challenging task because of having multidimensional and nonlinear data. Several Deep Learning Approaches are available: Numerical Weather Prediction (NWP), needs a highly calculative mathematical equation to gain the present condition of the weather. Quantitative precipitation nowcasting (QPN), is also used for weather prediction. In this article, we have implemented and analyzed the various distinct techniques that are being used in data mining for weather prediction.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.373-380
• /
• 2022

This paper presents a deep learning based group synchronization that supports networked immersive interactions between remote users. The goal of group synchronization is to enable all participants to synchronously interact with others for increasing user presence Most previous methods focus on NTP-based clock synchronization to enhance time accuracy. Moving average filters are used to control media playout time on the synchronization server. As an example, the exponentially weighted moving average(EWMA) would be able to track and estimate accurate playout time if the changes in input data are not significant. However it needs more time to be stable for any given change over time due to codec and system loads or fluctuations in network status. To tackle this problem, this work proposes the Deep Group Synchronization(DeepGroupSync), a group synchronization based on deep learning that models important features from the data. This model consists of two Gated Recurrent Unit(GRU) layers and one fully-connected layer, which predicts an optimal playout time by utilizing the sequential playout delays. The experiments are conducted with an existing method that uses the EWMA and the proposed method that uses the DeepGroupSync. The results show that the proposed method are more robust against unpredictable or rapid network condition changes than the existing method.