• 정보과학회 논문지
• /
• 제44권6호
• /
• pp.607-612
• /
• 2017

도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한 Recurrent Neural Networks (RNNs)을 활용하여 강의 수위 관측 데이터를 학습하고 침수 가능성을 예측하였다. 예측 정확도 검증을 위해 사용한 데이터는 미국의 트리니티강의 데이터로, 학습을 위해 2013 년부터 2015 년까지 데이터를 사용하였고 평가 데이터로는 2016 년 데이터를 사용하였다. 입력은 16개의 레코드로 구성된 15분단위의 시계열 데이터를 사용하였고, 출력으로는 30분과 60분 후의 강의 수위 예측 정보이다. 실험에 사용한 딥러닝 모델들은 표준 RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)을 사용했는데, 그 중 LSTM의 NE(Nash Efficiency)가 0.98을 넘는 정확도로 기존 연구에 비해 매우 높은 성능 향상을 보였고, 표준 RNN과 RNN-BPTT에 비해서도 좋은 성능을 보였다.

• 한국음향학회지
• /
• 제39권6호
• /
• pp.505-514
• /
• 2020

심층 신경망(Deep Neural Network, DNN) 모델을 대량의 학습 데이터로 학습시키기 위해서는 많은 시간이 소요되기 때문에 병렬 학습 방법이 필요하다. DNN의 학습에는 일반적으로 Stochastic Gradient Descent(SGD) 방법이 사용되는데, SGD는 근본적으로 순차적인 처리가 필요하므로 병렬화하기 위해서는 다양한 근사(approximation) 방법을 적용하게 된다. 본 논문에서는 기존의 DNN 병렬 학습 알고리즘들을 소개하고 연산량, 통신량, 근사 방법 등을 분석한다.

• International Journal of Computer Science & Network Security
• /
• 제23권1호
• /
• pp.41-46
• /
• 2023

Because of the significant role that harakat plays in Arabic text, this paper used deep learning to extract Arabic text with its harakat from an image. Convolutional neural networks and recurrent neural network algorithms were applied to the dataset, which contained 110 images, each representing one word. The results showed the ability to extract some letters with harakat.

• 문화기술의 융합
• /
• 제8권5호
• /
• pp.613-618
• /
• 2022

SNN(Spiking Neural Networks) 기반의 인공지능 연구는 현재 유행하는 DNN(Deep Neural Networks) 기반의 인공지능의 한계를 극복할 수 있는 차세대 인공지능으로서 주목받고 있다. 본 논문에서는 SNN 형태의 입력을 뉴로모픽 컴퓨팅 시스템에서 구동시킬 수 있는 시스템 SW인 SNN 컴파일러의 구조에 대하여 설명한다. 또한 컴파일러 구현을 위하여 사용된 알고리즘을 소개하고 매핑 알고리즘의 동작 형태에 따라 뉴로모픽 컴퓨팅 시스템에서 수행시간이 어떻게 달라지는지에 대한 실험결과를 제시한다. 본문에서 제안한 매핑 알고리즘은 랜덤 매핑에 비해 최대 3.96배의 수행속도 향상이 있었다. 해당 연구 결과를 통해 SNN들을 다양한 뉴로모픽 하드웨어에서 적용할 수 있을 것이다.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.150-161
• /
• 2018

We propose a novel deep neural network model for detecting human activities in untrimmed videos. The process of human activity detection in a video involves two steps: a step to extract features that are effective in recognizing human activities in a long untrimmed video, followed by a step to detect human activities from those extracted features. To extract the rich features from video segments that could express unique patterns for each activity, we employ two different convolutional neural network models, C3D and I-ResNet. For detecting human activities from the sequence of extracted feature vectors, we use BLSTM, a bi-directional recurrent neural network model. By conducting experiments with ActivityNet 200, a large-scale benchmark dataset, we show the high performance of the proposed DeepAct model.

• 말소리와 음성과학
• /
• 제7권4호
• /
• pp.27-33
• /
• 2015

This paper proposes an audio event classification method using Deep Neural Networks (DNN). The proposed method applies Feed Forward Neural Network (FFNN) to generate event probabilities of ten audio events (dog barks, engine idling, and so on) for each frame. For each frame, mel scale filter bank features of its consecutive frames are used as the input vector of the FFNN. These event probabilities are accumulated for the events and the classification result is determined as the event with the highest accumulated probability. For the same dataset, the best accuracy of previous studies was reported as about 70% when the Support Vector Machine (SVM) was applied. The best accuracy of the proposed method achieves as 79.23% for the UrbanSound8K dataset when 80 mel scale filter bank features each from 7 consecutive frames (in total 560) were implemented as the input vector for the FFNN with two hidden layers and 2,000 neurons per hidden layer. In this configuration, the rectified linear unit was suggested as its activation function.

• ETRI Journal
• /
• 제42권5호
• /
• pp.658-668
• /
• 2020

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to end-device service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

• Nuclear Engineering and Technology
• /
• 제51권3호
• /
• pp.723-730
• /
• 2019

Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.136-141
• /
• 2022

A very complex task in deep learning such as image classification must be solved with the help of neural networks and activation functions. The backpropagation algorithm advances backward from the output layer towards the input layer, the gradients often get smaller and smaller and approach zero which eventually leaves the weights of the initial or lower layers nearly unchanged, as a result, the gradient descent never converges to the optimum. We propose a two-factor non-saturating activation functions known as Bea-Mish for machine learning applications in deep neural networks. Our method uses two factors, beta (𝛽) and alpha (𝛼), to normalize the area below the boundary in the Mish activation function and we regard these elements as Bea. Bea-Mish provide a clear understanding of the behaviors and conditions governing this regularization term can lead to a more principled approach for constructing better performing activation functions. We evaluate Bea-Mish results against Mish and Swish activation functions in various models and data sets. Empirical results show that our approach (Bea-Mish) outperforms native Mish using SqueezeNet backbone with an average precision (AP50val) of 2.51% in CIFAR-10 and top-1accuracy in ResNet-50 on ImageNet-1k. shows an improvement of 1.20%.

• 한국정보통신학회논문지
• /
• 제26권1호
• /
• pp.49-57
• /
• 2022

최근 인공지능의 다양한 활용은 기계학습의 딥 인공신경망 구조를 통해 가능해졌으며 인간과 같은 능력을 보여주고 있다. 불행하게도 딥 구조의 인공신경망은 아직 정확한 해석이 이루어지고 있지 못하고 있다. 이러한 부분은 인공지능에 대한 불안감과 거부감으로 작용하고 있다. 우리는 이러한 문제 중에서 인공신경망의 능력 부분을 해결한다. 인공신경망 구조의 크기를 계산하고, 그 인공신경망이 처리할 수 있는 데이터의 크기를 계산해 본다. 계산의 방법은 수학에서 쓰이는 군의 방법을 사용하여 데이터와 인공신경망의 크기를 군의 구조와 크기를 알 수 있는 Order를 이용하여 계산한다. 이를 통하여 인공신경망의 능력을 알 수 있으며, 인공지능에 대한 불안감을 해소할 수 있다. 수치적 실험을 통하여 데이터의 크기와 딥 인공신경망을 계산하고 이를 검증한다.