• Title/Summary/Keyword: LSTM 신경망

Search Result 229, Processing Time 0.031 seconds

A study on recognition improvement of velopharyngeal insufficiency patient's speech using various types of deep neural network (심층신경망 구조에 따른 구개인두부전증 환자 음성 인식 향상 연구)

  • Kim, Min-seok;Jung, Jae-hee;Jung, Bo-kyung;Yoon, Ki-mu;Bae, Ara;Kim, Wooil
    • The Journal of the Acoustical Society of Korea
    • /
    • v.38 no.6
    • /
    • pp.703-709
    • /
    • 2019
  • This paper proposes speech recognition systems employing Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) structures combined with Hidden Markov Moldel (HMM) to effectively recognize the speech of VeloPharyngeal Insufficiency (VPI) patients, and compares the recognition performance of the systems to the Gaussian Mixture Model (GMM-HMM) and fully-connected Deep Neural Network (DNNHMM) based speech recognition systems. In this paper, the initial model is trained using normal speakers' speech and simulated VPI speech is used for generating a prior model for speaker adaptation. For VPI speaker adaptation, selected layers are trained in the CNN-HMM based model, and dropout regulatory technique is applied in the LSTM-HMM based model, showing 3.68 % improvement in recognition accuracy. The experimental results demonstrate that the proposed LSTM-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM and fully-connected DNN-HMM system.

Performance Analysis of Deep Learning-based Normalization According to Input-output Structure and Neural Network Model (입출력구조와 신경망 모델에 따른 딥러닝 기반 정규화 기법의 성능 분석)

  • Changsoo Ryu;Geunhwan Kim
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.29 no.4
    • /
    • pp.13-24
    • /
    • 2024
  • In this paper, we analyzed the performance of normalization according to various neural network models and input-output structures. For the analysis, a simulation-based dataset for noise environments with homogeneous and up to three interfering signals was used. As a result, the end-to-end structure that directly outputs noise variance showed superior performance when using a 1-D convolutional neural network and BiLSTM model, and was analyzed to be particularly robust against interference signals. This is because the 1-D convolutional neural network and bidirectional long short-term memory models have stronger inductive bias than the multilayer perceptron and transformer models. The analysis of this paper are expected to be used as a useful reference for future research on deep learning-based normalization.

Application of Informer for time-series NO2 prediction

  • Hye Yeon Sin;Minchul Kang;Joonsung Kang
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.7
    • /
    • pp.11-18
    • /
    • 2023
  • In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained. Consequently, Informer has improved prediction accuracy compared with other methods.

A study on activation functions of Artificial Neural Network model suitable for prediction of the groundwater level in the mid-mountainous area of eastern Jeju island (제주도 동부 중산간지역 지하수위 예측에 적합한 인공신경망 모델의 활성화함수 연구)

  • Mun-Ju Shin;Jeong-Hun Kim;Su-Yeon Kang;Jeong-Han Lee;Kyung Goo Kang
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2023.05a
    • /
    • pp.520-520
    • /
    • 2023
  • 제주도 동부 중산간 지역은 화산암으로 구성된 지하지질로 인해 지하수위의 변동폭이 크고 변동양상이 복잡하여 인공신경망(Artificial Neural Network, ANN) 모델 등을 활용한 지하수위의 예측이 어렵다. ANN에 적용되는 활성화함수에 따라 지하수의 예측성능은 달라질 수 있으므로 활성화함수의 비교분석 후 적절한 활성화함수의 사용이 반드시 필요하다. 본 연구에서는 5개 활성화함수(sigmoid, hyperbolic tangent(tanh), Rectified Linear Unit(ReLU), Leaky Rectified Linear Unit(Leaky ReLU), Exponential Linear Unit(ELU))를 제주도 동부 중산간지역에 위치한 2개 지하수 관정에 대해 비교분석하여 최적 활성화함수 도출을 목표로 한다. 또한 최적 활성화함수를 활용한 ANN의 적용성을 평가하기 위해 최근 널리 사용되고 있는 순환신경망 모델인 Long Short-Term Memory(LSTM) 모델과 비교분석 하였다. 그 결과, 2개 관정 중 지하수위 변동폭이 상대적으로 큰 관정은 ELU 함수, 상대적으로 작은 관정은 Leaky ReLU 함수가 지하수위 예측에 적절하였다. 예측성능이 가장 낮은 활성화함수는 sigmoid 함수로 나타나 첨두 및 최저 지하수위 예측 시 사용을 지양해야 할 것으로 판단된다. 도출된 최적 활성화함수를 사용한 ANN-ELU 모델 및 ANN-Leaky ReLU 모델을 LSTM 모델과 비교분석한 결과 대등한 지하수위 예측성능을 나타내었다. 이것은 feed-forward 방식인 ANN 모델을 사용하더라도 적절한 활성화함수를 사용하면 최신 순환신경망과 대등한 결과를 도출하여 활용 가능성이 충분히 있다는 것을 의미한다. 마지막으로 LSTM 모델은 가장 적절한 예측성능을 나타내어 다양한 인공지능 모델의 예측성능 비교를 위한 기준이 되는 참고모델로 활용 가능하다. 본 연구에서 제시한 방법은 지하수위 예측과 더불어 하천수위 예측 등 다양한 시계열예측 및 분석연구에 유용하게 사용될 수 있다.

  • PDF

Sentiment Analysis of Korean Sentences using a Neural Network Model (신경망 모델을 활용한 한국어 감성분석)

  • Kim, Dong-Hyeon;Kim, Tae-Yeong;Kim, Hyo-Jeong;Moon, Yoo-Jin
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2022.01a
    • /
    • pp.7-8
    • /
    • 2022
  • 본 연구에서는 한국어 SNS 대화에서 나타나는 문장들의 감성을 분석하고자 신경망 모델을 활용하여 시스템을 구축하였다. 현재 해외 SNS 감성분석에 대한 연구는 많이 진행된 상황이지만, 한국어 범용 대화에 대해 적절한 모델이 무엇인지는 연구가 부족한 실정이었다. 따라서 한국어 대화에 적합한 모델을 채택해 보다 정확한 감성분석을 수행하였다. 이를 위해 한국어 SNS 대화 데이터에 대해 신경망 모델을 적용하여, 82% 성공률로 기존 모델 72% 성공률보다 훨씬 더 우수한 성능을 보였다. 또한 본 연구의 결과는 악플 추적 등 실용적인 분야에도 기여할 수 있다고 사료된다.

  • PDF

A Study on the Forecasting of Bunker Price Using Recurrent Neural Network

  • Kim, Kyung-Hwan
    • Journal of the Korea Society of Computer and Information
    • /
    • v.26 no.10
    • /
    • pp.179-184
    • /
    • 2021
  • In this paper, we propose the deep learning-based neural network model to predict bunker price. In the shipping industry, since fuel oil accounts for the largest portion of ship operation costs and its price is highly volatile, so companies can secure market competitiveness by making fuel oil purchasing decisions based on rational and scientific method. In this paper, short-term predictive analysis of HSFO 380CST in Singapore is conducted by using three recurrent neural network models like RNN, LSTM, and GRU. As a result, first, the forecasting performance of RNN models is better than LSTM and GRUs using long-term memory, and thus the predictive contribution of long-term information is low. Second, since the predictive performance of recurrent neural network models is superior to the previous studies using econometric models, it is confirmed that the recurrent neural network models should consider nonlinear properties of bunker price. The result of this paper will be helpful to improve the decision quality of bunker purchasing.

CNN-LSTM based Autonomous Driving Technology (CNN-LSTM 기반의 자율주행 기술)

  • Ga-Eun Park;Chi Un Hwang;Lim Se Ryung;Han Seung Jang
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.18 no.6
    • /
    • pp.1259-1268
    • /
    • 2023
  • This study proposes a throttle and steering control technology using visual sensors based on deep learning's convolutional and recurrent neural networks. It collects camera image and control value data while driving a training track in clockwise and counterclockwise directions, and generates a model to predict throttle and steering through data sampling and preprocessing for efficient learning. Afterward, the model was validated on a test track in a different environment that was not used for training to find the optimal model and compare it with a CNN (Convolutional Neural Network). As a result, we found that the proposed deep learning model has excellent performance.

Learning and Transferring Deep Neural Network Models for Image Caption Generation (이미지 캡션 생성을 위한 심층 신경망 모델 학습과 전이)

  • Kim, Dong-Ha;Kim, Incheol
    • Annual Conference of KIPS
    • /
    • 2016.10a
    • /
    • pp.617-620
    • /
    • 2016
  • 본 논문에서는 이미지 캡션 생성과 모델 전이에 효과적인 심층 신경망 모델을 제시한다. 본 모델은 멀티 모달 순환 신경망 모델의 하나로서, 이미지로부터 시각 정보를 추출하는 컨볼루션 신경망 층, 각 단어를 저차원의 특징으로 변환하는 임베딩 층, 캡션 문장 구조를 학습하는 순환 신경망 층, 시각 정보와 언어 정보를 결합하는 멀티 모달 층 등 총 5 개의 계층들로 구성된다. 특히 본 모델에서는 시퀀스 패턴 학습과 모델 전이에 우수한 LSTM 유닛을 이용하여 순환 신경망 층을 구성하고, 컨볼루션 신경망 층의 출력을 임베딩 층뿐만 아니라 멀티 모달 층에도 연결함으로써, 캡션 문장 생성을 위한 매 단계마다 이미지의 시각 정보를 이용할 수 있는 연결 구조를 가진다. Flickr8k, Flickr30k, MSCOCO 등의 공개 데이터 집합들을 이용한 다양한 비교 실험을 통해, 캡션의 정확도와 모델 전이의 효과 면에서 본 논문에서 제시한 멀티 모달 순환 신경망 모델의 우수성을 입증하였다.

Study on the Prediction of Motion Response of Fishing Vessels using Recurrent Neural Networks (순환 신경망 모델을 이용한 소형어선의 운동응답 예측 연구)

  • Janghoon Seo;Dong-Woo Park;Dong Nam
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.29 no.5
    • /
    • pp.505-511
    • /
    • 2023
  • In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

Derivation of Flow Duration Curve and Sensitivity analysis using LSTM deep learning prediction technique and SWAT (LSTM 딥러닝 예측기법과 SWAT을 이용한 유량지속곡선 도출 및 민감도 분석)

  • An, Sung Wook;Choi, Jung Ryel;Kim, Byung Sik
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.354-354
    • /
    • 2022
  • 딥러닝(Deep Learning)은 일반적으로 인공신경망(Artificial Neural Network) 를 의미하는데, 이에 따른 결과는 데이터의 양, 변수, 학습모델의 학습횟수, 은닉층(Hidden Layer)의 개수 등 여러 요소로 인해 결정된다. 본 연구에서는 물리적 장기유출 모형인 SWAT의 결과를 참값으로 LSTM모형의 매개변수인 은닉층 갯수와 학습횟수등의 시나리오를 바탕으로 검보정을 수행하였으며, 최적의 목적함수를 갖는 매개변수를 도출하였다. 이를 이용하여 유량지속곡선을 도출한결과를 SWAT의 결과와 비교해본 결과 매우 높은 상관성을 도출하였으며 이를 통해 수자원분야에서 인공신경망의 활용 가능성을 확인하였다.

  • PDF