• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1387-1395
• /
• 2018

Core algorithm of deep learning Convolutional Neural Network(CNN) shows better performance than other machine learning algorithms. However, if there is not sufficient data, CNN can not achieve satisfactory performance even if the classifier is excellent. In this situation, it has been proven that the use of transfer learning can have a great effect. In this paper, we apply two transition learning methods(freezing, retraining) to three CNN models(ResNet-50, Inception-V3, DenseNet-121) and compare and analyze how the classification performance of CNN changes according to the methods. As a result of statistical significance test using various evaluation indicators, ResNet-50, Inception-V3, and DenseNet-121 differed by 1.18 times, 1.09 times, and 1.17 times, respectively. Based on this, we concluded that the retraining method may be more effective than the freezing method in case of transition learning in image classification problem.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.344-346
• /
• 2019

In this paper, we propose a distance estimation method using the convolutional neural network in Ultra-Wideband (UWB) systems. The training data set used to learn the deep learning model using the convolutional neural network is generated by the MATLAB program and utilizes the IEEE 802.15.4a standard. The performance of the proposed distance estimation method is verified by comparing the threshold based distance estimation technique and the performance comparison used in the conventional distance estimation.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2019

In this paper, we propose deep convolutional neural network(CNN) with bottleneck structure which improves the performance of earthquake classification. In order to address all possible forms of earthquakes including micro-earthquakes and artificial-earthquakes as well as large earthquakes, we need a representation and classifier that can effectively discriminate seismic waveforms in adverse conditions. In particular, to robustly classify seismic waveforms even in low snr, a deep CNN with 1x1 convolution bottleneck structure is proposed in raw seismic waveforms. The representative experimental results show that the proposed method is effective for noisy seismic waveforms and outperforms the previous state-of-the art methods on domestic earthquake database.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.24 no.4
• /
• pp.363-374
• /
• 2020

Fingerprint authentication identifies a user based on the individual's unique fingerprint features. Fingerprint authentication methods are used in various real-life devices because they are convenient and safe and there is no risk of leakage, loss, or oblivion. However, fingerprint authentication methods are often ineffective when there is contamination of the given image through wet, dirty, dry, or wounded fingers. In this paper, a method is proposed to remove noise from fingerprint images using a convolutional neural network. The proposed model was verified using the dataset from the ChaLearn LAP Inpainting Competition Track 3-Fingerprint Denoising and Inpainting, ECCV 2018. It was demonstrated that the model proposed in this paper obtains better results with respect to the methods that achieved high performances in the competition.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.25 no.2
• /
• pp.26-38
• /
• 2021

Image coloration refers to adding plausible colors to a grayscale image or video. Image coloration has been used in many modern fields, including restoring old photographs, as well as reducing the time spent painting cartoons. In this paper, a method is proposed for colorizing grayscale images using a convolutional neural network. We propose an encoder-decoder model, adapting FusionNet to our purpose. A proper loss function is defined instead of the MSE loss function to suit the purpose of coloring. The proposed model was verified using the ImageNet dataset. We quantitatively compared several colorization models with ours, using the peak signal-to-noise ratio (PSNR) metric. In addition, to qualitatively evaluate the results, our model was applied to images in the test dataset and compared to images applied to various other models. Finally, we applied our model to a selection of old black and white photographs.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.2
• /
• pp.125-133
• /
• 2022

This paper proposes a fault detection method for a Unmanned Surface Vehicle (USV) with overactuated system. Current status information for fault detection is expressed as a scalogram image. The scalogram image is obtained by wavelet-transforming the USV's control input and sensor information. The fault detection scheme is based on Convolutional Neural Network (CNN) algorithm. The previously generated scalogram data was transferred learning to GoogLeNet algorithm. The data are generated as scalogram images in real time, and fault is detected through a learning model. The result of fault detection is very robust and highly accurate.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.118-121
• /
• 2023

Recently, green energy support policies have been announced around the world in accordance with environmental regulations, and asthe market grows rapidly, demand for batteries is also increasing. Therefore, various methodologies for battery diagnosis and recycling methods are being discussed, but current accurate life prediction of batteries has limitations due to the nonlinear form according to the internal structure or chemical change of the battery. In this paper, CS2 lithium-ion battery measurement data measured at the A. James Clark School of Engineering, University of Marylan was used to predict battery performance with high accuracy using a convolutional neural network (CNN) model among deep learning-based models. As a result, the battery performance was predicted with high accuracy. A data structure with a matrix of total data 3,931 ☓ 19 was designed as test data for the CS2 battery and checking the result values, the MAE was 0.8451, the RMSE was 1.3448, and the accuracy was 0.984, confirming excellent performance.

• Geomechanics and Engineering
• /
• v.36 no.1
• /
• pp.1-8
• /
• 2024

We propose a new method for detecting voids behind tunnel concrete linings using the impact-echo method that is based on continuous wavelet transform (CWT) and a convolutional neural network (CNN). We first collect experimental data using the impact-echo method and then convert them into time-frequency images via CWT. We provide a CNN model trained using the converted images and experimentally confirm that our proposed model is robust. Moreover, it exhibits outstanding performance in detecting backfill voids and their status.

• Geomechanics and Engineering
• /
• v.37 no.5
• /
• pp.467-474
• /
• 2024

Monitoring and managing the condition of underground utilities is crucial for ground stability. This study aims to determine whether images obtained using ground penetrating radar (GPR) accurately reflect the characteristics of buried pipelines through image analysis. The investigation focuses on pipelines made from different materials, namely concrete and steel, with concrete pipes tested under various diameters to assess detectability under differing conditions. A total of 400 images are acquired at locations with pipelines, and for comparison, an additional 100 data points are collected from areas without pipelines. The study employs GPR at frequencies of 200 MHz and 600 MHz, and image analysis is performed using machine learning-based convolutional neural network (CNN) techniques. The analysis results demonstrate high classification reliability based on the training data, especially in distinguishing between pipes of the same material but of different diameters. The findings suggest that the integration of GPR and CNN algorithms can offer satisfactory performance in exploring the ground's interior characteristics.