• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.237-246
• /
• 2019

In order to improve the accuracy of the rating prediction of the recommendation model, not only user-item rating data are used but also consider auxiliary information of item such as comments, tags, or descriptions. The traditional approaches use a word-level model of the bag-of-words for the auxiliary information. This model, however, cannot utilize the auxiliary information effectively, which leads to shallow understanding of auxiliary information. Convolution neural network (CNN) can capture and extract feature vector from auxiliary information effectively. Thus, this paper proposes character-level deep-Convolution Neural Network based matrix factorization (Char-DCNN-MF) that integrates deep CNN into matrix factorization for a novel recommendation model. Char-DCNN-MF can deeper understand auxiliary information and further enhance recommendation performance. Experiments are performed on three different real data sets, and the results show that Char-DCNN-MF performs significantly better than other comparative models.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.29-37
• /
• 2021

In this paper, we propose a deep learning-based retinal vessel segmentation model for handling multi-scale information of fundus images. we integrate the selective kernel convolution into U-Net-based convolutional neural network. The proposed model extracts and segment features information with various shapes and sizes of retinal blood vessels, which is important information for diagnosing eye-related diseases from fundus images. The proposed model consists of standard convolutions and selective kernel convolutions. While the standard convolutional layer extracts information through the same size kernel size, The selective kernel convolution extracts information from branches with various kernel sizes and combines them by adaptively adjusting them through split-attention. To evaluate the performance of the proposed model, we used the DRIVE and CHASE DB1 datasets and the proposed model showed F1 score of 82.91% and 81.71% on both datasets respectively, confirming that the proposed model is effective in segmenting retinal blood vessels.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.3
• /
• pp.123-128
• /
• 2019

This paper proposes the stock price prediction based on the artificial intelligence, where the model with recurrent convolution neural network (RCNN) layers is adopted. In the motivation of this prediction, long short-term memory model (LSTM)-based neural network can make the output of the time series prediction. On the other hand, the convolution neural network provides the data filtering, averaging, and augmentation. By combining the advantages mentioned above, the proposed technique predicts the estimated stock price of next day. In addition, in order to emphasize the recent time series, a custom weighted loss function is adopted. Moreover, stock data related to the stock price index are adopted to consider the market trends. In the experiments, the proposed stock price prediction reduces the test error by 3.19%, which is over other techniques by about 19%.

• Journal of the Korean Statistical Society
• /
• v.28 no.1
• /
• pp.35-44
• /
• 1999

We derive a new upper bound of convolution type for the median-unbiased estimators with respect to an arbitrary unimodal utility functions. We also obtain the necessary and sufficient condition for the attainability of the information bound. Applications to general MLR(Monotone Likelihood Ratio) model and censored survival data re discussed as examples.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.

• Nuclear Engineering and Technology
• /
• v.54 no.5
• /
• pp.1769-1780
• /
• 2022

A new method of dose calculation algorithm, called GPU-accelerated Monte Carlo and collapsed cone Convolution (GMCC) was developed to improve the calculation speed of BNCT treatment planning system. The GPU-accelerated Monte Carlo routine in GMCC is used to simulate the neutron transport over whole energy range and the Collapsed Cone Convolution method is to calculate the gamma dose. Other dose components due to alpha particles and protons, are calculated using the calculated neutron flux and reaction data. The mathematical principle and the algorithm architecture are introduced. The accuracy and performance of the GMCC were verified by comparing with the FLUKA results. A water phantom and a head CT voxel model were simulated. The neutron flux and the absorbed dose obtained by the GMCC were consistent well with the FLUKA results. In the case of head CT voxel model, the mean absolute percentage error for the neutron flux and the absorbed dose were 3.98% and 3.91%, respectively. The calculation speed of the absorbed dose by the GMCC was 56 times faster than the FLUKA code. It was verified that the GMCC could be a good candidate tool instead of the Monte Carlo method in the BNCT dose calculations.

• Journal of Environmental Science International
• /
• v.23 no.4
• /
• pp.625-635
• /
• 2014

Temporal variation of groundwater levels in Jeju Island reveals time-delaying and dispersive process of recharge, mainly caused by the hydrogeological feature that thickness of the unsaturated zone is highly variable. Most groundwater flow models have limitations on delineating temporal variation of recharge, although it is a major component of the groundwater flow system. A new mathematical model was developed to generate time series of recharge from precipitation data. The model uses a convolution technique to simulate the time-delaying and dispersive process of recharge. The vertical velocity and the dispersivity are two parameters determining the time series of recharge for a given thickness of the unsaturated zone. The model determines two parameters by correlating the generated recharge time series with measured groundwater levels. The model was applied to observation wells of Jeju Island, and revealed distinctive variations of recharge depending on location of wells. The suggested model demonstrated capability of the convolution method in dealing with recharge undergoing the time-delaying and dispersive process. Therefore, it can be used in many groundwater flow models for generating a time series of recharge.

• Journal of Environmental Science International
• /
• v.8 no.3
• /
• pp.309-318
• /
• 1999

In order to fast predict the wind-driven current in a small bay, a convolution method in which the wind-driven current can be generated only wih the local wind is developed and applied in the Sachon Bay. The root mean square(rms) ratio defined as the ratio of the rms error to the rms speed is 0.37. The rms ratio is generally less than 0.2, except for all the mouths of Junju Bay and Namhae-do and in the region between Saryang Island and Sachon. The spatial average of the recover rate of kinetic energy(rrke) is 87%. Thus, the predicted wind-driven current by the convolution model is in a good agreement with the computed one by the numerical model. The raio of the difference between observed residual current (Vr) and predicted wind-driven current (Vc) to a residual current, that is, (Vr-Vc)/Vr shows 56%, 62% at 2 moorings in the Sachon Bay.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.46-54
• /
• 2023

To improve the railway transportation capacity and maximize the benefits of railway transportation, a method for layout optimization of railway transportation route based on deep convolution neural network is proposed in this study. Considering the transportation cost of railway transportation and other factors, the layout model of railway transportation route is constructed. Based on improved ant colony algorithm, the layout model of railway transportation route was optimized, and multiple candidate railway transportation routes were output. Taking into account external information such as regional information, weather conditions and actual information of railway transportation routes, optimization of the candidate railway transportation routes obtained by the improved ant colony algorithm was performed based on deep convolution neural network, and the optimal railway transportation routes were output, and finally layout optimization of railway transportation routes was realized. The experimental results show that the proposed method can obtain the optimal railway transportation route, the shortest transportation length, and the least transportation time, maximizing the interests of railway transportation enterprises.