• Journal of IKEEE
• /
• v.24 no.2
• /
• pp.523-528
• /
• 2020

With a widespread of sensor-rich mobile devices, the analysis of human activities becomes more general and simpler than ever before. In this paper, we propose two deep neural networks that efficiently and accurately perform human activity recognition (HAR) using tri-axial accelerometers. In combination with powerful modern deep learning techniques like batch normalization and LSTM networks, our model outperforms baseline approaches and establishes state-of-the-art results on WISDM dataset.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.5-7
• /
• 2021

Motion capture data files for pose estimation may have inaccurate data depending on the surrounding environment and the degree of movement, so it is necessary to correct it. In the past, inaccurate data was restored with post-processing by people, but recently various kind of neural networks such as LSTM and R-CNN are used as automated method. However, since neural network-based data restoration methods require a lot of computing resource, this paper proposes a method that reduces computing resource and maintains data restoration rate compared to neural network-based method. The proposed method automatically restores inaccurate motion capture data by using posture measurement data (c3d). As a result of the experiment, data restoration rates ranged from 89% to 99% depending on the degree of inaccuracy of the data.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.4
• /
• pp.203-210
• /
• 2017

In this paper, we propose an effective neural network model for image caption generation and model transfer. This model is a kind of multi-modal recurrent neural network models. It consists of five distinct layers: a convolution neural network layer for extracting visual information from images, an embedding layer for converting each word into a low dimensional feature, a recurrent neural network layer for learning caption sentence structure, and a multi-modal layer for combining visual and language information. In this model, the recurrent neural network layer is constructed by LSTM units, which are well known to be effective for learning and transferring sequence patterns. Moreover, this model has a unique structure in which the output of the convolution neural network layer is linked not only to the input of the initial state of the recurrent neural network layer but also to the input of the multimodal layer, in order to make use of visual information extracted from the image at each recurrent step for generating the corresponding textual caption. Through various comparative experiments using open data sets such as Flickr8k, Flickr30k, and MSCOCO, we demonstrated the proposed multimodal recurrent neural network model has high performance in terms of caption accuracy and model transfer effect.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.943-950
• /
• 2019

Machine learning can greatly improve the efficiency of work by replacing people. In particular, the importance of machine learning is increasing according to the requests of fourth industrial revolution. This paper predicts monthly power transactions using MLP, RNN, LSTM, and ANFIS of neural network algorithms. Also, this paper used monthly electricity transactions for mount and money, final energy consumption, and diesel fuel prices for vehicle provided by the National Statistical Office, from 2001 to 2017. This paper learns each algorithm, and then shows predicted result by using time series. Moreover, this paper proposed most excellent algorithm among them by using RMSE.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.

• Journal of Wind Energy
• /
• v.15 no.2
• /
• pp.10-22
• /
• 2024

This research is a comprehensive analysis of wind power prediction sensitivity using a Long Short-Term Memory (LSTM) deep learning neural network model, accounting for the inherent uncertainties in wind speed estimation. Utilizing a year's worth of operational data from an operational wind farm, the study forecasts the power output of both individual wind turbines and the farm collectively. Predictions were made daily at intervals of 10 minutes and 1 hour over a span of three months. The model's forecast accuracy was evaluated by comparing the root mean square error (RMSE), normalized RMSE (NRMSE), and correlation coefficients with actual power output data. Moreover, the research investigated how inaccuracies in wind speed inputs affect the power prediction sensitivity of the model. By simulating wind speed errors within a normal distribution range of 1% to 15%, the study analyzed their influence on the accuracy of power predictions. This investigation provided insights into the required wind speed prediction error rate to achieve an 8% power prediction error threshold, meeting the incentive standards for forecasting systems in renewable energy generation.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.592-599
• /
• 2020

This paper proposes a Convolutional Recurrent Neural Net (CRNN) structure that can simultaneously reflect both static and dynamic characteristics of seismic waveforms for various earthquake events classification. Addressing various earthquake events, including not only micro-earthquakes and artificial-earthquakes but also macro-earthquakes, requires both effective feature extraction and a classifier that can discriminate seismic waveform under noisy environment. First, we extract the static characteristics of seismic waveform through an attention-based convolution layer. Then, the extracted feature-map is sequentially injected as input to a multi-input single-output Long Short-Term Memory (LSTM) network structure to extract the dynamic characteristic for various seismic event classifications. Subsequently, we perform earthquake events classification through two fully connected layers and softmax function. Representative experimental results using domestic and foreign earthquake database show that the proposed model provides an effective structure for various earthquake events classification.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.4
• /
• pp.267-272
• /
• 2017

In this paper, we propose an effective method of applying multichannel-audio feature values to GRNNs (Gated Recurrent Neural Networks) in polyphonic sound event detection. Real life sounds are often overlapped with each other, so that it is difficult to distinguish them by using a mono-channel audio features. In the proposed method, we tried to improve the performance of polyphonic sound event detection by using multi-channel audio features. In addition, we also tried to improve the performance of polyphonic sound event detection by applying a gated recurrent neural network which is simpler than LSTM (Long Short Term Memory), which shows the highest performance among the current recurrent neural networks. The experimental results show that the proposed method achieves better sound event detection performance than other existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.605-607
• /
• 2018

본 논문에서는 음절 임베딩과 양방향 LSTM-CRF 모델을 이용한 한국어 문장 자동 띄어쓰기 시스템을 제안한다. 문장에 대한 자질 벡터 표현을 위해 문장을 구성하는 음절을 Unigram 및 Bigram으로 나누어 각 음절을 연속적인 벡터 공간에 표현하고, 양방향 LSTM을 이용하여 현재 자질에 양방향 자질들과 의존성을 부여한 새로운 자질 벡터를 생성한다. 이 새로운 자질 벡터는 전방향 신경망과 선형체인(Linear-Chain) CRF를 이용하여 최적의 띄어쓰기 태그 열을 예측하고, 생성된 띄어쓰기 태그를 기반으로 문장 자동 띄어쓰기를 수행하였다. 문장 13,500개와 277,718개 어절로 이루어진 학습 데이터 집합과 문장 1,500개와 31,107개 어절로 이루어진 테스트 집합의 학습 및 평가 결과는 97.337%의 음절 띄어쓰기 태그 분류 정확도를 보였다.