• Journal of Integrative Natural Science
• /
• v.14 no.4
• /
• pp.183-188
• /
• 2021

Collaborative filtering is one of the commonly used methods in the web recommendation system. Numerous researches on the collaborative filtering proposed the numbers of measures for enhancing the accuracy. This study suggests the movie recommendation system applied with Word2Vec and ensemble convolutional neural networks. First, user sentences and movie sentences are made from the user, movie, and rating information. Then, the user sentences and movie sentences are input into Word2Vec to figure out the user vector and movie vector. The user vector is input on the user convolutional model while the movie vector is input on the movie convolutional model. These user and movie convolutional models are connected to the fully-connected neural network model. Ultimately, the output layer of the fully-connected neural network model outputs the forecasts for user, movie, and rating. The test result showed that the system proposed in this study showed higher accuracy than the conventional cooperative filtering system and Word2Vec and deep neural network-based system suggested in the similar researches. The Word2Vec and deep neural network-based recommendation system is expected to help in enhancing the satisfaction while considering about the characteristics of users.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.8
• /
• pp.2063-2076
• /
• 1996

In this thesis, in order to apply a punctured convolutional codes to the trellis coded modulation(TCM), an efficient punctured trellis coded modulation(PTCM) based on the decomposition of the metric into orthogonal components is presented. Also, a simulation is performed in an additive white Gaussian noise(AWGN) and a rician fading channel modeling the mobile satellite channel. The PTCM combines punctured convolutional coding with MPSK modulation to provide a large coding gain in a power-limited or bandwidth-limited channel. However, in general the use of the punctured convolutional code structure in the decoder results in a performance loss in comparison to trellis codes, due to difficulties in assigning metrics. But, the study shows no loss in performance for punctured trellis coded MPSK in comparison to TCM, and what is more, the punctured convolutional codes results in some savings in the complexity of Viterbi decoders, compared to TCM of the same rate. Also, the results shows that the punctured trellis coded .pi./8 shift 8PSK is an attractive scheme for power-limited and band-limited systems and especially, the Viterbi decoder with first and Lth phase difference metrics improves BER performance by the mobile satellite channel.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

• Structural Engineering and Mechanics
• /
• v.77 no.4
• /
• pp.495-508
• /
• 2021

This study devises a novel approach, namely quadruple 1D convolutional neural network, for detecting connection stiffness reduction in steel truss bridge structure using experimental and numerical modal data. The method is developed based on expertise in two domains: firstly, in Structural Health Monitoring, the mode shapes and its high-order derivatives, including second, third, and fourth derivatives, are accurate indicators in assessing damages. Secondly, in the Machine Learning literature, the deep convolutional neural networks are able to extract relevant features from input data, then perform classification tasks with high accuracy and reduced time complexity. The efficacy and effectiveness of the present method are supported through an extensive case study with the railway Nam O bridge. It delivers highly accurate results in assessing damage localization and damage severity for single as well as multiple damage scenarios. In addition, the robustness of this method is tested with the presence of white noise reflecting unavoidable uncertainties in signal processing and modeling in reality. The proposed approach is able to provide stable results with data corrupted by noise up to 10%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.120-120
• /
• 2020

Spatial precipitation data is one of the essential components in modeling hydrological problems. The estimation of these data has achieved significant achievements own to the recent advances in remote sensing technology. However, there are still gaps between the satellite-derived rainfall data and observed data due to the significant dependence of rainfall on spatial and temporal characteristics. An effective approach based on the Convolutional Neural Network (CNN) model to correct the satellite-derived rainfall data is proposed in this study. The Mekong River basin, one of the largest river system in the world, was selected as a case study. The two gridded precipitation data sets with a spatial resolution of 0.25 degrees used in the CNN model are APHRODITE (Asian Precipitation - Highly-Resolved Observational Data Integration Towards Evaluation) and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks). In particular, PERSIANN-CDR data is exploited as satellite-based precipitation data and APHRODITE data is considered as observed rainfall data. In addition to developing a CNN model to correct the satellite-based rain data, another statistical method based on standard deviations for precipitation bias correction was also mentioned in this study. Estimated results indicate that the CNN model illustrates better performance both in spatial and temporal correlation when compared to the standard deviation method. The finding of this study indicated that the CNN model could produce reliable estimates for the gridded precipitation bias correction problem.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2008.10a
• /
• pp.57-62
• /
• 2008

Finite difference method using not general SSG(standard staggered grid) but RSG(rotated staggered grid) was applied to simulation of elastic wave propagation. Special free surface boundary condition such as imaging method is needed in finite difference method using SSG in elastic wave propagation but free surface boundary condition in finite difference method using RSG is easily solved with adding air layer. Recently PML(Perfectly Matched layer) is widely used to eliminate artificial reflection waves from finite boundary because of its' greate efficiency. Absorbing ability of CPML(convolutional Perfectly Matched Layer) that is more efficient than that of PML was applied to FDM using RSG in this study. The results of CPML eliminated artificial boundary waves very effectively in FDM using RSG in being compared with that of Cerjan's absorbing method.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.573-576
• /
• 2022

본 논문에서는 삼각형 구조로 구성된 3차원 메쉬(Mesh)에서 합성곱 신경망(Convolutional Neural Network, CNN)의 정확도를 개선시킬 수 있는 새로운 학습 표현 기법을 제시한다. 우리는 메쉬를 구성하고 있는 삼각형의 넓이와 그 로컬 특징을 기반으로 학습을 진행한다. 일반적으로 딥러닝은 인공신경망을 수많은 계층 형태로 연결한 기법을 말하며, 주요 처리 대상은 오디오 파일과 이미지이었다. 인공지능에 대한 연구가 지속되면서 3차원 딥러닝이 도입되었지만, 기존의 학습과는 달리 3차원 학습은 데이터의 확보가 쉽지 않다. 혼합현실과 메타버스 시장으로 인해 3차원 모델링 시장이 증가가 하면서 기술의 발전으로 데이터를 획득할 수 있는 방법이 생겼지만, 3차원 데이터를 직접적으로 학습 표현하는 방식으로 적용하는 것은 쉽지 않다. 그렇기 때문에 본 논문에서는 산업 현장에서 사용되는 데이터인 삼각형 메쉬 구조를 바탕으로 기존 방법보다 정확도가 높은 학습 기법을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.425-428
• /
• 2020

본 논문에서는 경계 합성곱 신경망(Convolutional neural network, CNN)기반의 슈퍼 해상도 기법을 이용하여 저해상도 옷감 메쉬를 슈퍼 해상도로 노이즈 없이 안정적으로 표현할 수 있는 기법을 제안한다. 저해상도와 고해상도 메쉬들 간의 쌍은 옷감 시뮬레이션을 통해 얻을 수 있으며, 이렇게 얻어진 데이터를 이용하여 고해상도-저해상도 데이터 쌍을 설정한다. 학습할 때 사용되는 데이터는 옷감 메쉬를 지오메트리 이미지로 변환하여 사용한다. 우리가 제안하는 경계 합성곱 신경망은 저해상도 이미지를 고해상도 이미지로 업스케일링 시키는 이미지 합성기를 학습시키기 위해 사용된다. 테스트 결과로 얻어진 고해상도 이미지가 고해상도 메쉬로 다시 변환되면, 저해상도 메쉬에 비해 주름이 잘 표현되며, 경계 부근에서 나타나는 노이즈 문제가 완화된다. 합성 결과에 대한 성능으로는 전통적인 물리 기반 시뮬레이션보다 약 10배 정도 빠른 성능을 보여준다.