• ETRI Journal
• /
• 제43권2호
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• Journal of information and communication convergence engineering
• /
• 제22권2호
• /
• pp.139-144
• /
• 2024

In this study, four types of fall detection systems - designed with YOLOPose, principal component analysis (PCA), convolutional neural network (CNN), and long short-term memory (LSTM) architectures - were developed and compared in the detection of everyday falls. The experimental dataset encompassed seven types of activities: walking, lying, jumping, jumping in activities of daily living, falling backward, falling forward, and falling sideways. Keypoints extracted from YOLOPose were entered into the following architectures: RAW-LSTM, PCA-LSTM, RAW-PCA-LSTM, and PCA-CNN-LSTM. For the PCA architectures, the reduced input size stemming from a dimensionality reduction enhanced the operational efficiency in terms of computational time and memory at the cost of decreased accuracy. In contrast, the addition of a CNN resulted in higher complexity and lower accuracy. The RAW-LSTM architecture, which did not include either PCA or CNN, had the least number of parameters, which resulted in the best computational time and memory while also achieving the highest accuracy.

• 한국IT서비스학회지
• /
• 제16권4호
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• 한국음향학회지
• /
• 제41권3호
• /
• pp.312-318
• /
• 2022

본 논문은 딥러닝기법 중 하나인 합성곱 신경망과 순환 신경망 중 하나인 장단기 메모리를 이용하여 사격시 발생하는 소음(이하 사격음)만으로 화기의 종류, 사격음 발생지점에 관한 정보(거리와 방향)을 추정하는 모델을 다루었다. 이를 위해 미국 법무부 산하 연구소의 지원하에 생성된 Gunshot Audio Forensic Dataset을 이용하였으며, 음향신호를 멜 스펙트로그램(Mel-Spectrogram)으로 변환한 후, 4종의 합성곱 신경망과 1종의 장단기 메모리 레이어로 구성된 딥러닝 모델에 학습 및 검증 데이터로 제공하였다. 제안 모델의 성능을 확인하기 위해 합성곱 신경망으로만 구성된 대조 모델과 비교·분석하였으며, 제안 모델의 정확도가 90 % 이상으로 대조모델보다 우수한 성능을 보였다.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1047-1056
• /
• 2022

지구 온난화의 중요한 지시자인 북극의 바다 얼음인 해빙은 기후 시스템, 선박의 항로 안내, 어업 활동 등에서의 중요성으로 인해 다양한 학문 분야에서 관심을 받고 있다. 최근 자동화와 효율적인 미래 예측에 대한 요구가 커지면서 인공지능을 이용한 새로운 해빙 예측 모델들이 전통적인 수치 및 통계 예측 모델을 대체하기 위해 개발되고 있다. 본 연구에서는 북극 해빙의 전역적, 지역적 특징을 학습할 수 있는 two-stream convolutional long- and short-term memory (TS-ConvLSTM) 인공지능 모델의 북극 해빙 면적이 최저를 보이는 9월에 대해 2001년부터 2021년까지 장기적인 성능 검증을 통해 향후 운용 가능한 시스템으로써의 가능성을 살펴보고자 한다. 장기 자료를 통한 검증 결과 TS-ConvLSTM 모델이 훈련자료의 양이 증가하면서 향상된 예측 성능을 보여주고 있지만, 최근 지구 온난화로 인한 단년생 해빙의 감소로 인해 해빙 농도 5-50% 구간에서는 예측력이 저하되고 있음을 보여주었다. 반면 TS-ConvLSTM에 의해 예측된 해빙 면적과 달리 Sea Ice Prediction Network에 제출된 Sea Ice Outlook (SIO)들의 해빙 면적 중간값의 경우 훈련자료가 늘어나더라도 눈에 띄는 향상을 보이지 않았다. 본 연구를 통해 TS-ConvLSTM 모델의 향후 북극 해빙 예측 시스템의 운용 가능 잠재성을 확인하였으나, 향후 연구에서는 예측이 어려운 자연 환경에서 더욱 안정성 있는 예측 시스템 개발을 위해 더 많은 시공간 변화 패턴을 학습할 수 있는 방안을 고려해야 할 것이다.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• 대한원격탐사학회지
• /
• 제39권6_2호
• /
• pp.1577-1589
• /
• 2023

해양의 모니터링을 위해서는 변화를 예측하는 과정이 필요하다는 것은 널리 인정되고 있다. 이 연구에서는 Geostationary Ocean Color Imager (GOCI) 자료를 이용하여 해양의 변화를 지시할 수 있는 반사도의 시계열 예측을 수행하였다. 이를 위해 다중 규모 Convolutional Long-Short-Term-Memory (ConvLSTM) 모델을 제안하였으며, GOCI-I 자료를 이용하여 모델을 학습하였다. 취득 기간이 다른 GOCI-II 자료를 이용하여 모델의 성능을 검증하였으며, 기존의 ConvLSTM 모델과 성능을 비교하였다. 비교 결과, 제안한 모델은 시공간적 특성을 모두 고려하여 반사도의 변화 경향성을 파악하는데 있어 가장 우수한 결과를 보였다. 장기 예측 결과를 통해 모델이 학습한 반사도의 시간적 변화 경향을 확인하였으며, 이를 이용한 주기적 변화 탐지가 가능할 것으로 기대된다.

• ETRI Journal
• /
• 제44권4호
• /
• pp.672-685
• /
• 2022

This article proposes a subject-independent application of brain-computer interfacing (BCI). A 32-channel Electroencephalography (EEG) device is used to measure imagined speech (SI) of four words (sos, stop, medicine, washroom) and one phrase (come-here) across 13 subjects. A deep long short-term memory (LSTM) network has been adopted to recognize the above signals in seven EEG frequency bands individually in nine major regions of the brain. The results show a maximum accuracy of 73.56% and a network prediction time (NPT) of 0.14 s which are superior to other state-of-the-art techniques in the literature. Our analysis reveals that the alpha band can recognize SI better than other EEG frequencies. To reinforce our findings, the above work has been compared by models based on the gated recurrent unit (GRU), convolutional neural network (CNN), and six conventional classifiers. The results show that the LSTM model has 46.86% more average accuracy in the alpha band and 74.54% less average NPT than CNN. The maximum accuracy of GRU was 8.34% less than the LSTM network. Deep networks performed better than traditional classifiers.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.