• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.2
• /
• pp.113-120
• /
• 2024

The population sparseness index(PSI) is being utilized to describe the functioning of internal layers in artificial neural networks from the perspective of neurons, shedding light on the black-box nature of the network's internal operations. There is research indicating a positive correlation between the PSI and performance in each layer of convolutional neural network models for image classification. In this study, we observed the internal operations of a convolutional neural network when adversarial examples were applied. The results of the experiments revealed a similar pattern of positive correlation for adversarial examples, which were modified to maintain 5% accuracy compared to applying benign data. Thus, while there may be differences in each adversarial attack, the observed PSI for adversarial examples demonstrated consistent positive correlations with benign data across layers.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.721-732
• /
• 2024

Species identification of zooplankton is the most basic process in understanding the marine ecosystem and studying global warming. In this study, we propose an convolutional neural network model that can classify females and males of three zooplankton at the species level. First, training data including morphological features is constructed based on microscopic images acquired by researchers. In constructing training data, a data argumentation method that preserves morphological feature information of the target species is applied. Next, we propose a convolutional neural network model in which features can be learned from the constructed learning data. The proposed model minimized the information loss of training image in consideration of high resolution and minimized the number of learning parameters by using the global average polling layer instead of the fully connected layer. In addition, in order to present the generality of the proposed model, the performance was presented based on newly acquired data. Finally, through the visualization of the features extracted from the model, the key features of the classification model were presented.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.105-110
• /
• 2022

Traffic sign recognition plays an important role in solving traffic-related problems. Traffic sign recognition and classification systems are key components for traffic safety, traffic monitoring, autonomous driving services, and autonomous vehicles. A lightweight model, applicable to portable devices, is an essential aspect of the design agenda. We suggest a lightweight convolutional neural network model with residual blocks for traffic sign recognition systems. The proposed model shows very competitive results on publicly available benchmark data.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.35-42
• /
• 2018

Deep learning is known as a method of high accuracy among several methods for image classification. In this paper, we propose a method of enhancing the accuracy of image classification using CNN with a batch normalization method for classification of images using deep CNN (Convolutional Neural Network). In this paper, we propose a method to add a batch normalization layer to existing neural networks to enhance the accuracy of image classification. Batch normalization is a method to calculate and move the average and variance of each batch for reducing the deflection in each layer. In order to prove the superiority of the proposed method, Accuracy and mAP are measured by image classification experiments using five image data sets SHREC13, MNIST, SVHN, CIFAR-10, and CIFAR-100. Experimental results showed that the CNN with batch normalization is better classification accuracy and mAP rather than using the conventional CNN.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.686-689
• /
• 2018

3D 손 포즈 추정(Hand Pose Estimation, HPE)은 스마트 인간 컴퓨터 인터페이스를 위해서 중요한 기술이다. 이 연구에서는 딥러닝 방법을 기반으로 하여 단일 RGB-Depth 카메라로 촬영한 양손의 3D 손 자세를 실시간으로 인식하는 손 포즈 추정 시스템을 제시한다. 손 포즈 추정 시스템은 4단계로 구성된다. 첫째, Skin Detection 및 Depth cutting 알고리즘을 사용하여 양손을 RGB와 깊이 영상에서 감지하고 추출한다. 둘째, Convolutional Neural Network(CNN) Classifier는 오른손과 왼손을 구별하는데 사용된다. CNN Classifier 는 3개의 convolution layer와 2개의 Fully-Connected Layer로 구성되어 있으며, 추출된 깊이 영상을 입력으로 사용한다. 셋째, 학습된 CNN regressor는 추출된 왼쪽 및 오른쪽 손의 깊이 영상에서 손 관절을 추정하기 위해 다수의 Convolutional Layers, Pooling Layers, Fully Connected Layers로 구성된다. CNN classifier와 regressor는 22,000개 깊이 영상 데이터셋으로 학습된다. 마지막으로, 각 손의 3D 손 자세는 추정된 손 관절 정보로부터 재구성된다. 테스트 결과, CNN classifier는 오른쪽 손과 왼쪽 손을 96.9%의 정확도로 구별할 수 있으며, CNN regressor는 형균 8.48mm의 오차 범위로 3D 손 관절 정보를 추정할 수 있다. 본 연구에서 제안하는 손 포즈 추정 시스템은 가상 현실(virtual reality, VR), 증강 현실(Augmented Reality, AR) 및 융합 현실 (Mixed Reality, MR) 응용 프로그램을 포함한 다양한 응용 분야에서 사용할 수 있다.

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.490-501
• /
• 2023

Laboratory column tests were conducted to analyze infiltration and water redistribution processes on the basis of rainfall. To efficiently measure moisture content within soil layers, this research developed a predictive model grounded in a convolutional neural network (CNN), a deep learning technique. The digital images obtained during the column tests were incorporated into the established CNN. The moisture content of each soil layer over time was effectively measured. The measured values were also in relatively good agreement with the moisture content determined using the moisture sensors installed for each soil layer. The use of CNN enabled a comprehensive understanding of continuous moisture distribution within the soil layers, as well as the infiltration process according to soil texture and initial moisture content conditions.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3571-3584
• /
• 2024

Reactor core transient calculation is very important for the reactor safety analysis, in which the kernel is neutron kinetics calculation by simulating the variation of neutron density or thermal power over time. Compared with the point kinetics method, the time-space neutron kinetics calculation can provide accurate variation of neutron density in both space and time domain. But it consumes a lot of resources. It is necessary to develop a surrogate model that can quickly obtain the temporal and spatial variation information of neutron density or power with acceptable calculation accuracy. This paper uses the time-varying characteristics of power to construct a time function, parameterizes the time-varying characteristics which contains the information about the spatial change of power. Thereby, the amount of targets to predict in the space domain is compressed. A surrogate method using the machine learning is proposed in this paper. In the construction of a neural network, the input is processed by a convolutional layer, followed by a fully connected layer or a deconvolution layer. For the problem of time sequence disturbance, a structure combining convolutional neural network and recurrent neural network is used. It is verified in the tests of a series of 1D, 2D and 3D reactor models. The predicted values obtained using the constructed neural network models in these tests are in good agreement with the reference values, showing the powerful potential of the surrogate models.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.203-226
• /
• 2021

Purpose The purpose of this study is to enhance the accuracy score of personal credit scoring using the convolutional neural networks and secure the transparency of the deep learning model using eXplainalbe Artifical Inteligence(XAI) technique. Design/methodology/approach This study built a classification model by using the convolutional neural networks(CNN) and applied a methodology that is transformation of numerical data to imaged data to apply CNN on personal credit data. Then layer-wise relevance propagation(LRP) was applied to model we constructed to find what variables are more influenced to the output value. Findings According to the empirical analysis result, this study confirmed that accuracy score by model using CNN is highest among other models using logistic regression, neural networks, and support vector machines. In addition, With the LRP that is one of the technique of XAI, variables that have a great influence on calculating the output value for each observation could be found.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.522-531
• /
• 2021

We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.'s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.