• 한국음향학회지
• /
• 제38권1호
• /
• pp.106-113
• /
• 2019

본 논문은 능동소나 시스템이 비협동으로 운용될 경우 수신된 직접파로 부터 이를 탐지하여 식별하는 일련의 알고리즘을 제안하였다. 제안하는 알고리즘은 최근 다양한 분야에서 우수한 성능을 보여주고 있는 콘볼루션 신경회로망을 사용하였으며, 입력 데이터로 수신신호를 단시간 퓨리에 변환을 수행한 시간 주파수 분석 데이터를 사용하였다. 본 논문에서 사용한 콘볼루션 신경회로망의 구조는 두 개의 콘볼루션 계층과 풀링 계층을 사용하였으며, 출력층에 따라 데이터베이스 기반의 신경회로망과 펄스 특징인자 기반의 신경회로망을 설계하였다. 알고리즘의 성능을 검증하기 위해 실제 해상에서 수신한 3110개의 CW(Continuous Wave)펄스와 LFM(Linear Frequency Modulated) 펄스의 데이터를 가공하여 학습 데이터와 테스트 데이터를 구성하였다. 시뮬레이션을 수행한 결과 데이터베이스 기반의 신경회로망은 99.9 %의 정확도를 보였으며, 특징인자 기반의 신경회로망은 두 픽셀의 오차를 허용할 경우 약 96 %의 정확도를 보였다.

• 한국음향학회지
• /
• 제38권5호
• /
• pp.568-573
• /
• 2019

폐질환 진단에서 청진은 다른 진단 방식에 비해 단순하고, 폐음을 이용하여 폐질환 환자식별뿐 아니라 폐음과 관련된 질병을 예측할 수 있다. 따라서 본 논문에서는 다양한 합성곱 신경방 방식을 기반으로 폐음을 이용하여 폐질환 환자를 식별하고, 소리특성에 따른 폐음을 분류하여 각 신경망 방식의 분류 성능을 비교한다. 먼저 폐질환 소견을 갖는 흉부 영역에서 단채널 폐음 녹음기기를 이용하여 폐음 데이터를 수집하고, 수집된 시간축 신호를 스펙트럼 형태의 특징값으로 추출하여 각 분류 신경망 방식에 적용한다. 폐 사운드 분류 방식으로는 일반적인 합성곱 신경망, 병렬 구조, 잔류학습이 적용된 구조의 합성곱 신경망을 사용하고 실험을 통해 각 신경망 모델의 폐음 분류 성능을 비교한다.

• 한국정보전자통신기술학회논문지
• /
• 제14권4호
• /
• pp.314-322
• /
• 2021

Skeleton-based action recognition has attracted considerable attention in human action recognition. Recent methods for skeleton-based action recognition employ spatiotemporal graph convolutional networks (GCNs) and have remarkable performance. However, most of them have heavy computational complexity for robust action recognition. To solve this problem, we propose a shuffle graph convolutional network (SGCN) which is a lightweight graph convolutional network using pointwise group convolution rather than pointwise convolution to reduce computational cost. Our SGCN is composed of spatial and temporal GCN. The spatial shuffle GCN contains pointwise group convolution and part shuffle module which enhances local and global information between correlated joints. In addition, the temporal shuffle GCN contains depthwise convolution to maintain a large receptive field. Our model achieves comparable performance with lowest computational cost and exceeds the performance of baseline at 0.3% and 1.2% on NTU RGB+D and NTU RGB+D 120 datasets, respectively.

• 한국음향학회지
• /
• 제40권2호
• /
• pp.130-138
• /
• 2021

본 논문에서는 지진 이벤트 분류를 위한 다양한 정규화 기법 분석 및 효과적인 합성곱 신경망(Convolutional Neural Network, CNN)기반의 네트워크 구조를 제안하였다. 정규화 기법은 신경망의 학습 속도를 개선할 뿐만 아니라 잡음에 강인한 모습을 보여 준다. 본 논문에서는 지진 이벤트 분류를 위한 딥러닝 모델에서 입력 정규화 및 은닉 레이어 정규화가 모델에 미치는 영향을 분석하였다. 또한, 적용 은닉 레이어의 구조에 따른 다양한 실험을 통해 효과적인 모델을 도출하였다. 다양한 모의실험 결과 입력 데이터 정규화 및 제1 은닉 레이어에 가중치 정규화를 적용한 모델이 가장 안정적인 성능 향상을 보여 주었다.

• Journal of Web Engineering
• /
• 제21권2호
• /
• pp.497-522
• /
• 2021

Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.177-182
• /
• 2003

Conventional multilayer feedforward artificial neural networks are very effective in dealing with spatial problems. To deal with problems with time dependency, some kinds of memory have to be built in the processing algorithm. In this paper we show how the newly proposed Serial Input Neuron (SIN) convolutional decoders can be derived. As an example, we derive the SIN decoder for rate code with constraint length 3. The SIN is tested in Gaussian channel and the results are compared to the results of the optimal Viterbi decoder. A SIN approach to decode convolutional codes is presented. No supervision is required. The decoder lends itself to pleasing implementations in hardware and processing codes with high speed in a time. However, the speed of the current circuits may set limits to the codes used. With increasing speeds of the circuits in the future, the proposed technique may become a tempting choice for decoding convolutional coding with long constraint lengths.

• 한국정보기술학회 영문논문지
• /
• 제10권1호
• /
• pp.111-120
• /
• 2020

Generative adversarial networks (GANs) achieved impressive performance on image generation and visual classification applications. However, adversarial networks meet difficulties in combining the generative model and unstable training process. To overcome the problem, we combined the deep residual network with upsampling convolutional layers to construct the generative network. Moreover, the study shows that image generation and classification performance become more prominent when the residual layers include on the generator. The proposed network empirically shows that the ability to generate images with higher visual accuracy provided certain amounts of additional complexity using proper regularization techniques. Experimental evaluation shows that the proposed method is superior to image generation and classification tasks.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 추계학술대회
• /
• pp.11-14
• /
• 2018

The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.