• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.533-539
• /
• 2019

This study proposes a malware classification model that can handle arbitrary length input data using the Microsoft Malware Classification Challenge dataset. We are based on imaging existing data from malware. The proposed model generates a lot of images when malware data is large, and generates a small image of small data. The generated image is learned as time series data by Dynamic RNN. The output value of the RNN is classified into malware by using only the highest weighted output by applying the Attention technique, and learning the RNN output value by Residual CNN again. Experiments on the proposed model showed a Micro-average F1 score of 92% in the validation data set. Experimental results show that the performance of a model capable of learning and classifying arbitrary length data can be verified without special feature extraction and dimension reduction.

• ETRI Journal
• /
• v.39 no.3
• /
• pp.398-405
• /
• 2017

In this paper, an artificial stereo extension method that creates stereophonic sound from a mono sound source is proposed. The proposed method first trains deep neural networks (DNNs) that model the nonlinear relationship between the dominant and residual signals of the stereo channel. In the training stage, the band-wise log spectral magnitude and unwrapped phase of both the dominant and residual signals are utilized to model the nonlinearities of each sub-band through deep architecture. From that point, stereo extension is conducted by estimating the residual signal that corresponds to the input mono channel signal with the trained DNN model in a sub-band domain. The performance of the proposed method was evaluated using a log spectral distortion (LSD) measure and multiple stimuli with a hidden reference and anchor (MUSHRA) test. The results showed that the proposed method provided a lower LSD and higher MUSHRA score than conventional methods that use hidden Markov models and DNN with full-band processing.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.89-99
• /
• 2018

Downtime and malfunction of industrial rotor machines represents a crucial cost burden and productivity loss. Fault diagnosis of this equipment has recently been carried out to detect their fault(s) and cause(s) by using fault classification methods. However, these methods are of limited use in detecting rotor faults because of their hypersensitivity to unexpected and different equipment conditions individually. These limitations tend to affect the accuracy of fault classification since fault-related features calculated from vibration signal are moved to other regions or changed. To improve the limited diagnosis accuracy of existing methods, we propose a new approach for fault diagnosis of rotor machines based on the model generated by supervised learning. Our work is based on feature residual values from vibration signals as fault indices. Our diagnostic model is a robust and flexible process that, once learned from historical data only one time, allows it to apply to different target systems without optimization of algorithms. The performance of the proposed method was evaluated by comparing its results with conventional methods for fault diagnosis of rotor machines. The experimental results show that the proposed method can be used to achieve better fault diagnosis, even when applied to systems with different normal-state signals, scales, and structures, without tuning or the use of a complementary algorithm. The effectiveness of the method was assessed by simulation using various rotor machine models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.757-770
• /
• 2022

Palmprint recognition has drawn increasingly attentions in the past decade due to its uniqueness and reliability. Traditional palmprint recognition methods usually use high-resolution images as the identification basis so that they can achieve relatively high precision. However, high-resolution images mean more computation cost in the recognition process, which usually cannot be guaranteed in mobile computing. Therefore, this paper proposes an improved low-resolution palmprint image recognition method based on residual networks. The main contributions include: 1) We introduce a channel attention mechanism to refactor the extracted feature maps, which can pay more attention to the informative feature maps and suppress the useless ones. 2) The ResStage group structure proposed by us divides the original residual block into three stages, and we stabilize the signal characteristics before each stage by means of BN normalization operation to enhance the feature channel. Comparison experiments are conducted on a public dataset provided by the Hong Kong Polytechnic University. Experimental results show that the proposed method achieve a rank-1 accuracy of 98.17% when tested on low-resolution images with the size of 12dpi, which outperforms all the compared methods obviously.

• Journal of the Semiconductor & Display Technology
• /
• v.23 no.2
• /
• pp.129-134
• /
• 2024

This study aims to talk about the necessity of solving the PFC gas emission problem raised by the recent development of the semiconductor industry and the remote plasma source method monitoring system used in the semiconductor industry. The 'monitoring system' means that the researchers applied machine learning to the existing monitoring technology and modeled it. In the process of this study, Residual Gas Analyzer monitoring technology and linear regression model were used. Through this model, the researchers identified emissions of at least 12700mg CO2 to 75800mg CO2 with values ranging from ion current 0.6A to 1.7A, and expect that the 'monitoring system' will contribute to the effective calculation of greenhouse gas emissions in the semiconductor industry in the future.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2006.11a
• /
• pp.213-216
• /
• 2006

During the last decade several different methods have been proposed for the estimation of thermal deformations in the line heating process. These are mainly based on the assumption of residual strains in the heat-affected zone or simulated relations between heating conditions and residual deformations. However these results were restricted in the application from the too simplified heating conditions or the shortage of the data. The purpose of this paper is to develop a simulator of thermal deformation in the line heating using the artificial neural network. Two neural network predicting the maximum temperature and deformations at the heating line are studied. Deformation data from the line heating experiments are used for learning data for the network. It was observed that thermal deformation predicted by the neural network correlate well with the experimental result.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.43-49
• /
• 2020

In this paper, we propose a stage-wise knowledge transfer method that uses block-wise retraining to transfer the useful knowledge of a pre-trained residual network (ResNet) in a teacher-student framework (TSF). First, multiple hint information transfer and block-wise supervised retraining of the information was alternatively performed between teacher and student ResNet models. Next, Softened output information-based knowledge transfer was additionally considered in the TSF. The results experimentally showed that the proposed method using multiple hint-based bottom-up knowledge transfer coupled with incremental block-wise retraining provided the improved student ResNet with higher accuracy than existing KD and hint-based knowledge transfer methods considered in this study.

• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.701-708
• /
• 2021

As one of the most widely used technology in the world right now, Face recognition has already received widespread attention by all the researcher and institutes. It has been used in many fields such as safety protection, surveillance system, crime control and even in our ordinary life such as home security and so on. This technology with today's technology has advantages such as high connectivity and real time transformation. But we still need to improve its recognition rate, reaction time and also reduce impact of different environmental status to the whole system. So in this paper we proposed a face recognition system model with improved CNN which combining the characteristics of flat network and residual network, integrated learning, simplify network structure and enhance portability and also improve the recognition accuracy. We also used AR and ORL database to do the experiment and result shows higher recognition rate, efficiency and robustness for different image conditions.

• Current Optics and Photonics
• /
• v.7 no.5
• /
• pp.511-517
• /
• 2023

Pipelines play an important role in urban water supply and drainage, oil and gas transmission, etc. This paper presents a technique for pattern recognition of fiber optic vibration signals collected by a distributed vibration sensing (DVS) system using a deep learning residual network (ResNet). The optical fiber is laid on the pipeline, and the signal is collected by the DVS system and converted into a 64 × 64 single-channel grayscale image. The grayscale image is input into the ResNet to extract features, and finally the K-nearest-neighbors (KNN) algorithm is used to achieve the classification and recognition of pipeline damage.