• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.3
• /
• pp.140-151
• /
• 2020

It is important to identify the location of ship hull blocks with exact block identification number when scheduling the shipbuilding process. The wrong information on the location and identification number of some hull block can cause low productivity by spending time to find where the exact hull block is. In order to solve this problem, it is necessary to equip the system to track the location of the blocks and to identify the identification numbers of the blocks automatically. There were a lot of researches of location tracking system for the hull blocks on the stockyard. However there has been no research to identify the hull blocks on the stockyard. This study compares the performance of 5 Convolutional Neural Network (CNN) models with multi-view image set on the classification of the hull blocks to identify the blocks on the stockyard. The CNN models are open algorithms of ImageNet Large-Scale Visual Recognition Competition (ILSVRC). Four scaled hull block models are used to acquire the images of ship hull blocks. Learning and transfer learning of the CNN models with original training data and augmented data of the original training data were done. 20 tests and predictions in consideration of five CNN models and four cases of training conditions are performed. In order to compare the classification performance of the CNN models, accuracy and average F1-Score from confusion matrix are adopted as the performance measures. As a result of the comparison, Resnet-152v2 model shows the highest accuracy and average F1-Score with full block prediction image set and with cropped block prediction image set.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1403-1408
• /
• 2021

Recently, FPGA-based AI processors are being studied actively. Deep convolutional neural networks (CNN) are basic computational structures performed by AI processors and require a very large amount of multiplication. Considering that the multiplication coefficients used in CNN inference operation are all constants and that an FPGA is easy to design a multiplier tailored to a specific coefficient, this paper proposes a methodology to optimize the multiplier. The method utilizes 2's complement and distributive law to minimize the number of bits with a value of 1 in a multiplication coefficient, and thereby reduces the number of required stacked adders. As a result of applying this method to the actual example of implementing CNN in FPGA, the logic usage is reduced by up to 30.2% and the propagation delay is also reduced by up to 22%. Even when implemented with an ASIC chip, the hardware area is reduced by up to 35% and the delay is reduced by up to 19.2%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.73-78
• /
• 2020

Musculoskeletal disease is often caused by sitting down for long period's time or by bad posture habits. In order to prevent musculoskeletal disease in daily life, it is the most important to correct the bad sitting posture to the right one through real-time monitoring. In this study, to detect the sitting information of user's without any constraints, we propose posture measurement system based on multi-channel pressure sensor and CNN model for classifying sitting posture types. The proposed CNN model can analyze 5 types of sitting postures based on sitting posture information. For the performance assessment of posture classification CNN model through field test, the accuracy, recall, precision, and F1 of the classification results were checked with 10 subjects. As the experiment results, 99.84% of accuracy, 99.6% of recall, 99.6% of precision, and 99.6% of F1 were verified.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.1-10
• /
• 2021

The ability to recognize human emotions by computer vision is a very important task, with many potential applications. Therefore the demand for emotion recognition using not only RGB images but also thermal images is increasing. Compared to RGB images, thermal images has the advantage of being less affected by lighting conditions but require a more sophisticated recognition method with low-resolution sources. In this paper, we propose a Divide and Conquer-based CNN training strategy to improve the performance of facial thermal image-based emotion recognition. The proposed method first trains to classify difficult-to-classify similar emotion classes into the same class group by confusion matrix analysis and then divides and solves the problem so that the emotion group classified into the same class group is recognized again as actual emotions. In experiments, the proposed method has improved accuracy in all the tests than when recognizing all the presented emotions with a single CNN model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.35-45
• /
• 2024

In this paper, we propose an intra prediction method for depth picture using CNN and Attention mechanism. The proposed method allows each pixel in a block to predict to select pixels among reference area. Spatial features in the vertical and horizontal directions for reference pixels are extracted from the top and left areas adjacent to the block, respectively, through a CNN layer. The two spatial features are merged into the feature direction and the spatial direction to predict features for the prediction block and reference pixels, respectively. the correlation between the prediction block and the reference pixel is predicted through attention mechanism. The predicted correlations are restored to the pixel domain through CNN layers to predict the pixels in the block. The average prediction error of intra prediction is reduced by 5.8% when the proposed method is added to VVC intra modes.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1475-1490
• /
• 2021

Detecting oil spill area using statistical characteristics of SAR images has limitations in that classification algorithm is complicated and is greatly affected by outliers. To overcome these limitations, studies using neural networks to classify oil spills are recently investigated. However, the studies to evaluate whether the performance of model shows a consistent detection performance for various oil spill cases were insufficient. Therefore, in this study, two CNNs (Convolutional Neural Networks) with basic structures(Simple CNN and U-net) were used to discover whether there is a difference in detection performance according to the structure of CNN and distribution characteristics of oil spill. As a result, through the method proposed in this study, the Simple CNN with contracting path only detected oil spill with an F1 score of 86.24% and U-net, which has both contracting and expansive path showed an F1 score of 91.44%. Both models successfully detected oil spills, but detection performance of the U-net was higher than Simple CNN. Additionally, in order to compare the accuracy of models according to various oil spill cases, the cases were classified into four different categories according to the spatial distribution characteristics of the oil spill (presence of land near the oil spill area) and the clarity of border between oil and seawater. The Simple CNN had F1 score values of 85.71%, 87.43%, 86.50%, and 85.86% for each category, showing the maximum difference of 1.71%. In the case of U-net, the values for each category were 89.77%, 92.27%, 92.59%, and 92.66%, with the maximum difference of 2.90%. Such results indicate that neither model showed significant differences in detection performance by the characteristics of oil spill distribution. However, the difference in detection tendency was caused by the difference in the model structure and the oil spill distribution characteristics. In all four oil spill categories, the Simple CNN showed a tendency to overestimate the oil spill area and the U-net showed a tendency to underestimate it. These tendencies were emphasized when the border between oil and seawater was unclear.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.41-45
• /
• 2017

본 논문에서는 컨볼루션 신경망 네트워크(CNN:Convolution Neural Network)을 기반으로 단어의 의미와 순서를 고려하는 문서 색인 방법을 이용하여 한글 문서 분류 방법을 제안한다. 먼저 문서를 형태소 분석하여 어절 단위로 분리 한 후, 불용어를 처리 하고, 문서의 단어 의미를 고려하는 문서 표현하고, 문서의 단어 순서까지 고려하여 CNN의 입력으로 사용하였다. 실험결과 CNN 분류기를 기반으로 본 논문에서 제안하는 문서 색인 방법은 TF-IDF를 이용하는 방법보다 4.2%, Word2vec만 단독으로 사용하는 것보다 1.4%의 성능 상승을 이루었다. 이러한 결과를 통해 본 논문에서 제안하는 방법이 문서범주화 데이터 셋에서 문서 분류 성능향상에 영향을 미친다는 것을 확인하였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.271-272
• /
• 2016

본 논문에서는 딥러닝 기술 중의 하나인 CNN(Convolutional Neural Network) 기반의 얼굴 표정 인식 기법을 제안한다. 다섯 가지 주요 표정의 얼굴 영상을 CNN 구조에 스스로 학습시켜 각각의 표정 패턴에 적합한 특징 지도(feature map)를 형성하고 이 특징 지도를 통해 들어오는 입력 영상을 적합한 표정으로 분류한다. 기존의 CNN 구조를 본 논문에서 이용한 데이터 셋에 알맞게 convolutional layer 및 node의 수를 변경하여 특징 지도를 형성하고 학습 및 인식에 필요한 파라미터수를 대폭 감소시켰다. 실험 결과 제안하는 기법이 높은 얼굴 표정 분류 성능을 보여준다는 것을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.141-146
• /
• 2016

대화 시스템에서 사용자가 나타내는 발화에 내재된 감정을 분류하는 것은, 시스템이 적절한 응답과 서비스를 제공하는데 있어 매우 중요하다. 본 연구에서는 대화 내 감정 분류를 하는데 있어 직접적, 간접적으로 드러나는 감정 자질을 자동으로 학습하고 감정이 지속되는 대화 문맥을 효과적으로 반영하기 위해 CNN-LSTM 방식의 딥 뉴럴 네트워크 구조를 제안한다. 그리고 대량의 구어체 코퍼스를 이용한 사전 학습으로 데이터 부족 문제를 완화하였다. 실험 결과 제안하는 방법이 기존의 SVM이나, 단순한 RNN, CNN 네트워크 구조에 비해 전반전인 성능 향상을 보였고, 특히 감정이 있는 경우 더 잘 분류하는 것을 확인할 수 있었다.