• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.3-10
• /
• 2018

Depth map has been utilized in a varity of fields. Recently research on generating depth map by artificial neural network (ANN) has gained much interest. This paper validates the feasibility of implementing the ready-made depth map generation by convolutional neural network (CNN). First, for a given image, a depth map is generated by the weighted average of a saliency map as well as a motion history image. Then CNN network is trained by test images and depth maps. The objective and subjective experiments are performed on the CNN and showed that the CNN can replace the ready-made depth generation method.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.309-316
• /
• 2020

We predict the mortality of the elderly patients visiting the emergency department who are over 65 years old using Feed Forward Neural Network (FFNN) and Convolutional Neural Network (CNN) respectively. Medical data consist of 99 features including basic information such as sex, age, temperature, and heart rate as well as past history, various blood tests and culture tests, and etc. Among these, we used random forest to select features by measuring the importance of features in the prediction of mortality. As a result, using the top 80 features with high importance is best in the mortality prediction. The performance of the FFNN and CNN is compared by using the selected features for training each neural network. To train CNN with images, we convert medical data to fixed size images. We acquire better results with CNN than with FFNN. With CNN for mortality prediction, F1 score and the AUC for test data are 56.9 and 92.1 respectively.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.139-155
• /
• 2024

This study performed a multi-classification task to classify mesial temporal lobe epilepsy with left hippocampal sclerosis patients (left mTLE), mesial temporal lobe epilepsy with right hippocampal sclerosis (right mTLE), and healthy controls (HC) using magnetoencephalography (MEG) data. We applied various artificial neural networks and compared the results. As a result of modeling with convolutional neural networks (CNN), recurrent neural networks (RNN), and graph neural networks (GNN), the average k-fold accuracy was excellent in the order of CNN-based model, GNN-based model, and RNN-based model. The wall time was excellent in the order of RNN-based model, GNN-based model, and CNN-based model. The graph neural network, which shows good figures in accuracy, performance, and time, and has excellent scalability of network data, is the most suitable model for brain research in the future.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.238-244
• /
• 2019

In this study, we compared and analyzed the performance of each Convolution Neural Network (CNN) by implementing the CNN that reflected the characteristics of the cerebral structure, in order to analyze the CNN that was used for the prediction of cybersickness, and provided the performance varying depending on characteristics of the brain. Dizziness has many causes, but the most severe symptoms are considered attributable to vestibular dysfunction associated with the brain. Brain waves serve as indicators showing the state of brain activities, and tend to exhibit differences depending on external stimulation and cerebral activities. Changes in brain waves being caused by external stimuli and cerebral activities have been proved by many studies and experiments, including the thesis of Martijn E. Wokke, Tony Ro, published in 2019. Based on such correlation, we analyzed brain wave data collected from dizziness-inducing environments and implemented the dizziness predictive artificial neural network reflecting characteristics of the cerebral structure. The results of this study are expected to provide a basis for achieving optimal performance of the CNN used in the prediction of dizziness, and for predicting and preventing the occurrence of dizziness under various virtual reality (VR) environments.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.6
• /
• pp.38-44
• /
• 2019

A Convolution Neural Network(CNN) model was utilized to detect surface cracks in asphalt concrete pavements. The CNN used for this study consists of five layers with 3×3 convolution filter and 2×2 pooling kernel. Pavement surface crack images collected by automated road surveying equipment was used for the training and testing of the CNN. The performance of the CNN was evaluated using the accuracy, precision, recall, missing rate, and over rate of the surface crack detection. The CNN trained with the largest amount of data shows more than 96.6% of the accuracy, precision, and recall as well as less than 3.4% of the missing rate and the over rate.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.44-45
• /
• 2019

최근 CNN 등 인공신경망은 최근 이미지 분류, 객체 인식, 자연어 처리 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 대부분의 분야에서 보다 더 높은 성능을 얻기 위해 사용한 인공신경망 모델들은 파라미터 수 및 연산량 등이 방대하여, 모바일 및 IoT 디바이스 같은 연산량이나 메모리가 제한된 환경에서 추론하기에는 제한적이다. 따라서 연산량 및 모델 파라미터 수를 압축하기 위한 딥러닝 경량화 알고리즘이 연구되고 있다. 본 논문에서는 임베디트 보드에서의 압축된 CNN 모델의 성능을 검증한다. 인공지능 지원 맞춤형 칩인 QCS605 를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축된 CNN 모델의 분류 성능과 동작속도 비교 분석한다. 본 논문의 실험에서는 CNN 모델로 MobileNetV2, VGG16 을 사용했으며, 주어진 모델에서 가지치기(pruning) 기법, 양자화, 행렬 분해 등의 인공신경망 압축 기술을 적용하였을 때 원래의 모델 대비 추론 시간 및 분류의 정확도 성능을 분석하고 인공신경망 압축 기술의 유용성을 확인하였다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.322-327
• /
• 2017

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long-Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment's result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.464-466
• /
• 2019

CNN 은 합성곱 연산을 사용하는 인공신경망의 한 종류이다. 이러한 인공 신경망에서는 훈련 데이터에 대한 과도한 학습으로 인해 시험 데이터에 제대로 반응하지 못하는 오버피팅이 발생할 우려가 있다. 이를 해결하기 위해 DropOut 과 DropConnect 를 사용할 수 있다. 본 논문에서는 DropOut 과 DropConnect 를 통한 학습 정도를 실험을 통해서 비교해보고, 인공 신경망에서 이 방법의 효과를 살펴본다.

• Asia pacific journal of information systems
• /
• v.5 no.1
• /
• pp.36-51
• /
• 1995

본 논문에서는 비구조적인 의사결정문제를 효과적으로 해결하기 위하여 감독학습 인공신경망 모형과 비감독학습 인공신경망 모형을 결합한 하이브리드 인공신경망 모형인 HYNEN(HYbrid NEural Network) 모형을 제안한다. HYNEN모형은 주어진 자료를 클러스터화 하는 CNN(Clustering Neural Network)과 최종적인 출력을 제공하는 ONN(Output Neural Network)의 2단계로 구성되어 있다. 먼저 CNN에서는 주어진 자료로부터 적정한 퍼지규칙을 찾기 위하여 클러스터를 구성한다. 그리고 이러한 클러스터를 지식베이스로하여 ONN에서 최종적인 의사결정을 한다. CNN에서는 SOFM(Self Organizing Feature Map)과 LVQ(Learning Vector Quantization)를 클러스터를 만든 후 역전파학습 인공신경망 모형으로 이를 학습한다. ONN에서는 역전파학습 인공신경망 모형을 이용하여 각 클러스터의 내용을 학습한다. 제안된 HYNEN 모형을 우리나라 기업의 도산자료에 적용하여 그 결과를 다변량 판별분석법(MDA:Multivariate Discriminant Analysis)과 ACLS(Analog Concept Learning System) 퍼지 ARTMAP 그리고 기존의 역전파학습 인공신경망에 의한 실험결과와 비교하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1290-1297
• /
• 2019

The paper proposes a distance estimation technique for ultra-wideband (UWB) systems using convolutional neural network (CNN). To estimate the distance from the transmitter and the receiver in the proposed method, 1 dimensional vector consisted of the magnitudes of the received samples is reshaped into a 2 dimensional matrix, and by using this matrix, the distance is estimated through the CNN regressor. The received signal for CNN training is generated by the UWB channel model in the IEEE 802.15.4a, and the CNN model is trained. Next, the received signal for CNN test is generated by filed experiments in indoor environments, and the distance estimation performance is verified. The proposed technique is also compared with the existing threshold based method. According to the results, the proposed CNN based technique is superior to the conventional method and specifically, the proposed method shows 0.6 m root mean square error (RMSE) at distance 10 m while the conventional technique shows much worse 1.6 m RMSE.