• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.6-10
• /
• 2021

Recognition of characters printed or marked on the PCB components from images captured using cameras is an important task in PCB components inspection systems. Previous optical character recognition (OCR) of PCB components typically consists of two stages: character segmentation and classification of each segmented character. However, character segmentation often fails due to corrupted characters, low image contrast, etc. Thus, OCR without character segmentation is desirable and increasingly used via deep neural networks. Typical implementation based on deep neural nets without character segmentation includes convolutional neural network followed by recurrent neural network (RNN). However, one disadvantage of this approach is slow execution due to RNN layers. LPRNet is a segmentation-free character recognition network with excellent accuracy proved in license plate recognition. LPRNet uses a wide convolution instead of RNN, thus enabling fast inference. In this paper, LPRNet was adapted for recognizing characters printed on PCB components with fast execution and high accuracy. Initial training with synthetic images followed by fine-tuning on real text images yielded accurate recognition. This net can be further optimized on Intel CPU using OpenVINO tool kit. The optimized version of the network can be run in real-time faster than even GPU.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.26-30
• /
• 2022

Spiking neural network is a neural network that applies the working principle of real brain neurons. Due to the biological mechanism of neurons, it consumes less power for training and reasoning than conventional neural networks. Recently, as deep learning models become huge and operating costs increase exponentially, the spiking neural network is attracting attention as a third-generation neural network that connects convolution neural networks and recurrent neural networks, and related research is being actively conducted. However, in order to apply the spiking neural network model to the industry, a lot of research still needs to be done, and the problem of model retraining to apply a new model must also be solved. In this paper, we propose a method to minimize the cost of model retraining by extracting the weights of the existing trained deep learning model and converting them into the weights of the spiking neural network model. In addition, it was found that weight conversion worked correctly by comparing the results of inference using the converted weights with the results of the existing model.

• Communications of Mathematical Education
• /
• v.37 no.2
• /
• pp.277-297
• /
• 2023

In mathematics, the concept of convolution is widely used. The convolution operation is required for understanding computer vision and deep learning in artificial intelligence. Therefore, it is vital for this concept to be explained in college mathematics education. In this paper, we present our new teaching and learning materials on convolution available for engineering mathematics. We provide the knowledge and applications on convolution with Python-based code, and introduce Convolutional Neural Network (CNN) used for image classification as an example. These materials can be utilized in class for the teaching of convolution and help students have a good understanding of the related knowledge in artificial intelligence.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.115-126
• /
• 2023

Due to the fluctuating random and periodical nature of renewable energy generation power quality disturbances occurred more frequently in power generation transformation transmission and distribution. Various power quality disturbances may lead to equipment damage or even power outages. Therefore it is essential to detect and classify different power quality disturbances in real time automatically. The traditional PQD identification method consists of three steps: feature extraction feature selection and classification. However, the handcrafted features are imprecise in the feature selection stage, resulting in low classification accuracy. This paper proposes a deep neural architecture based on Convolution Neural Network and Long Short Term Memory combining the time and frequency domain features to recognize 16 types of Power Quality signals. The frequency-domain data were obtained from the Fast Fourier Transform which could efficiently extract the frequency-domain features. The performance in synthetic data and real 6kV power system data indicate that our proposed method generalizes well compared with other deep learning methods.

• International journal of advanced smart convergence
• /
• v.5 no.3
• /
• pp.1-7
• /
• 2016

In existing Convolutional Neural Network (CNNs) for object recognition task, there are only few efforts known to reduce the noises from the images. Both convolution and pooling layers perform the features extraction without considering the noises of the input image, treating all pixels equally important. In computer vision field, there has been a study to weight a pixel importance. Seam carving resizes an image by sacrificing the least important pixels, leaving only the most important ones. We propose a new way to combine seam carving approach with current existing CNN model for object recognition task. We attempt to remove the noises or the "unimportant" pixels in the image before doing convolution and pooling, in order to get better feature representatives. Our model shows promising result with CIFAR-10 dataset.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.311-312
• /
• 2018

This paper proposes an image processing system based on the Convolution Neural Network technique. The image classification was performed using the composite neural network model and the images were classified with accuracy of 84% or more. The proposed system is implemented to operate on various platforms. When the system is used in the classification of images, the efficiency is higher because it is higher than the accuracy of the existing model.

• 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.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1653-1661
• /
• 2022

In this study, the classification of cold water and normal water based on Geo-Kompsat 2A images was performed. Daily mean surface temperature products provided by the National Meteorological Satellite Center (NMSC) were used, and convolution neural network (CNN) deep learning technique was applied as a classification algorithm. From 2019 to 2022, the cold water occurrence data provided by the National Institute of Fisheries Science (NIFS) were used as the cold water class. As a result of learning, the probability of detection was 82.5% and the false alarm ratio was 54.4%. Through misclassification analysis, it was confirmed that cloud area should be considered and accurate learning data should be considered in the future.