• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.15-23
• /
• 2022

Among the learning methods for Continuous Learning environments, "Learning without Forgetting" has fixed regularization strengths, which can lead to poor performance in environments where various data are received. We suggest a way to set weights variable by identifying the features of the data we want to learn. We applied weights adaptively using correlation and complexity. Scenarios with various data are used for evaluation and experiments showed accuracy increases by up to 5% in the new task and up to 11% in the previous task. In addition, it was found that the adaptive weight value obtained by the algorithm proposed in this paper, approached the optimal weight value calculated manually by repeated experiments for each experimental scenario. The correlation coefficient value is 0.739, and overall average task accuracy increased. It can be seen that the method of this paper sets an appropriate lambda value every time a new task is learned, and derives the optimal result value in various scenarios.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.664-671
• /
• 2021

This paper proposes a GPGPU structure that can reduce the number of operations and memory access by effectively applying a data reuse method to a convolutional neural network(CNN). Convolution is a two-dimensional operation using kernel and input data, and the operation is performed by sliding the kernel. In this case, a reuse method using an internal register is proposed instead of loading kernel from a cache memory until the convolution operation is completed. The serial operation method was applied to the convolution to increase the effect of data reuse by using the principle of GPGPU in which instructions are executed by the SIMT method. In this paper, for register-based data reuse, the kernel was fixed at 4×4 and GPGPU was designed considering the warp size and register bank to effectively support it. To verify the performance of the designed GPGPU on the CNN, we implemented it as an FPGA and then ran LeNet and measured the performance on AlexNet by comparison using TensorFlow. As a result of the measurement, 1-iteration learning speed based on AlexNet is 0.468sec and the inference speed is 0.135sec.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.99-104
• /
• 2022

Artificial intelligence is getting a crucial part of our lives with its incredible benefits. Machines outperform humans in recognizing objects in images, particularly in classifying people into correct age and gender groups. In this respect, age and gender classification has been one of the hot topics among computer vision researchers in recent decades. Deployment of deep Convolutional Neural Network(: CNN) models achieved state-of-the-art performance. However, the most of CNN based architectures are very complex with several dozens of training parameters so they require much computation time and resources. For this reason, we propose a new CNN-based classification algorithm with significantly fewer training parameters and training time compared to the existing methods. Despite its less complexity, our model shows better accuracy of age and gender classification on the UTKFace dataset.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.36-48
• /
• 2022

As a valid numerical method to obtain a high-resolution result of a flow field, computational fluid dynamics (CFD) have been widely used to study coolant flow and heat transfer characteristics in fuel rod bundles. However, the time-consuming, iterative calculation of Navier-Stokes equations makes CFD unsuitable for the scenarios that require efficient simulation such as sensitivity analysis and uncertainty quantification. To solve this problem, a reduced-order model (ROM) based on proper orthogonal decomposition (POD) and machine learning (ML) is proposed to simulate the flow field efficiently. Firstly, a validated CFD model to output the flow field data set of the rod bundle is established. Secondly, based on the POD method, the modes and corresponding coefficients of the flow field were extracted. Then, an deep feed-forward neural network, due to its efficiency in approximating arbitrary functions and its ability to handle high-dimensional and strong nonlinear problems, is selected to build a model that maps the non-linear relationship between the mode coefficients and the boundary conditions. A trained surrogate model for modes coefficients prediction is obtained after a certain number of training iterations. Finally, the flow field is reconstructed by combining the product of the POD basis and coefficients. Based on the test dataset, an evaluation of the ROM is carried out. The evaluation results show that the proposed POD-ROM accurately describe the flow status of the fluid field in rod bundles with high resolution in only a few milliseconds.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.62-73
• /
• 2022

Researches on the prediction of domestic apartment sales price have been continuously conducted, but it is not easy to accurately predict apartment prices because various characteristics are compounded. Prior to predicting apartment sales price, the analysis of major factors, influencing on sale prices, is of paramount importance to improve the accuracy of sales price. Therefore, this study aims to analyze what are the factors that affect the apartment sales price in Gwangju, which is currently showing a steady increase rate. With 6 years of Gwangju apartment transaction price and various social factor data, several maching learning techniques such as multiple regression analysis, random forest, and deep artificial neural network algorithms are applied to identify major factors in each model. The performances of each model are compared with RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and R² (coefficient of determination). The experiment shows that several factors such as 'contract year', 'applicable area', 'certificate of deposit', 'mortgage rate', 'leading index', 'producer price index', 'coincident composite index' are analyzed as main factors, affecting the sales price.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.483-490
• /
• 2022

Malaria is a disease caused by a parasite and it is prevalent in all over the world. The usual method used to recognize malaria cells is a thick and thin blood smears examination methods, but this method requires a lot of manual calculation, so the efficiency and accuracy are very low as well as the lack of pathologists in impoverished country has led to high malaria mortality rates. In this paper, a malaria cell image recognition model using transfer learning is proposed, which consists in the feature extractor, the residual structure and the fully connected layers. When the pre-training parameters of the VGG-19 model are imported to the proposed model, the parameters of some convolutional layers model are frozen and the fine-tuning method is used to fit the data for the model. Also we implement another malaria cell recognition model without residual structure to compare with the proposed model. The simulation results shows that the model using the residual structure gets better performance than the other model without residual structure and the proposed model has the best accuracy of 97.33% compared to other recent papers.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.521-521
• /
• 2023

지방상수도의 관 파손사고 감지 및 누수관리 방법에는 블록시스템 구축을 통한 소블록별 야간최소유량 감시방법이 가장 대표적이다. 야간최소유량은 새벽 2시와 4시 사이의 인구 활동 비율이 가장 낮은 새벽 시간대에 소블록에 공급된 유량을 의미하며, 대부분 유량 성분은 누수량일 것이라는 가정에서 출발한다. 그러나 아파트 중심의 주거 형태를 보이는 도심지의 경우, 새벽 시간대에도 다량의 물수요가 비정기적으로 발생하고 있어 관망의 이상 여부를 감시하기 위한 관리기준으로서 야간최소유량을 이용하기에는 높은 일간 변동성에 따른 한계가 있다고 할 수 있다. 즉, 야간최소유량은 관 파손사고 발생의 감시보다는 관로 연결 또는 급수전 분기 부위에서 발생하는 미량의 누수가 수개월에 걸쳐 누적되는 장기추세를 분석하여 누수탐사반의 투입 시점을 결정하기 위한 근거를 제시하기 위한 목적으로 사용되며, 아직까지 관 파손사고의 발생은 자체적인 감지보다는 민원에 의해 인지되는 경우가 많다. 최근, 스마트관망 구축사업(SWM) 등을 통해 관 파손 및 누수 감지를 위한 청음식 누수감지센서가 소블록 내 도입되고 있으나, 초기 시설투자에 큰 비용이 수반되며 주변 소음과 배터리 전원방식의 한계로 인하여 새벽 시간대에만 분석이 제한적으로 적용되는 경우가 많아 이 역시도 상시적인 관 파손사고의 감시기술이라 보기는 어렵다. 본 연구에서는 소블록 유입점에서의 유량·압력과 소블록 내에 설치된 대수용가 스마트미터, 그리고 사고감지를 위한 수압계 사이의 평상시 수리적 균형을 학습한 DNN(Deep Neural Network) 모델을 이용하여 관 파손사고를 실시간 감지하는 모델 개발연구를 수행하였다. 모델은 관 파손사고 감지를 위한 수압계의 최적 위치와 대수를 결정하기 위한 모듈과 관 파손사고 감지모듈로 구성되며, 1개 소블록 Test-Bed를 구축하여 모델을 생성하고 PDD 관망해석 모델을 통해 생성된 가상의 사고에 대한 감지 여부로서 개발 모델의 감지성능을 평가하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.