Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network

Hu, Jiaojiao; Wang, Xiaofeng; Ying, Zhang; Zhang, Depeng; Zhang, Meng; Xue, Jianru

doi:10.1007/s11063-020-10319-3

Cited by 60 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) have been used in different studies [33,34] for time-series processing and classification. Long Short-Time Memory (LSTM) and bidirectional LSTM (BiLSTM) belong to the RNN class, usually applied to time-series data processing and prediction [35,36]. CNNs have also been able to extract deep and time-independent features, while being highly noise-resistant models [37].…”

Section: Proposed Modelsmentioning

confidence: 99%

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

Esgalhado

Fernandes²,

Vassilenko

et al. 2021

Computers

View full text Add to dashboard Cite

Photoplethysmography (PPG) is widely used in wearable devices due to its conveniency and cost-effective nature. From this signal, several biomarkers can be collected, such as heart and respiration rate. For the usual acquisition scenarios, PPG is an artefact-ridden signal, which mandates the need for the designated classification algorithms to be able to reduce the noise component effect on the classification. Within the selected classification algorithm, the hyperparameters’ adjustment is of utmost importance. This study aimed to develop a deep learning model for robust PPG wave detection, which includes finding each beat’s temporal limits, from which the peak can be determined. A study database consisting of 1100 records was created from experimental PPG measurements performed in 47 participants. Different deep learning models were implemented to classify the PPG: Long Short-Term Memory (LSTM), Bidirectional LSTM, and Convolutional Neural Network (CNN). The Bidirectional LSTM and the CNN-LSTM were investigated, using the PPG Synchrosqueezed Fourier Transform (SSFT) as the models’ input. Accuracy, precision, recall, and F1-score were evaluated for all models. The CNN-LSTM algorithm, with an SSFT input, was the best performing model with accuracy, precision, and recall of 0.894, 0.923, and 0.914, respectively. This model has shown to be competent in PPG detection and delineation tasks, under noise-corrupted signals, which justifies the use of this innovative approach.

show abstract

Section: Proposed Modelsmentioning

confidence: 99%

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

Esgalhado

Fernandes²,

Vassilenko

et al. 2021

Computers

View full text Add to dashboard Cite

show abstract

“…A ideia original LSTM foi inicialmente proposta em [Hochreiter and Schmidhuber 1997] e desde então diferentes modelos têm sido propostos para melhorar seu desempenho [Cho et al 2014], [Li et al 2019], [Karevan and Suykens 2020], [Hu et al 2020]. As LSTMs utilizam um mecanismo de bloqueio para definir os dados, sua durac ¸ão e tempo de leitura na célula de memória.…”

Section: Predic ¸ãO Em Séries Temporaisunclassified

pmSensing: Uma Rede de Sensoriamento Participativo para Monitoramento Preditivo de Material Particulado

Sachetti

Cussuol

Nogueira³

et al. 2021

Anais Do v Workshop De Computação Urbana (CoUrb 2021)

View full text Add to dashboard Cite

Este trabalho apresenta uma proposta de uma rede de sensores sem fio para sensoriamento participativo, com dispositivos IoT de sensoriamento desenvolvidos especialmente para monitoramento e predição da qualidade do ar, como alternativa a estações meteorológicas de alto custo. O sistema, batizado de pmSensing, objetiva fazer a medição de material particulado. Uma validação é feita comparando os dados coletados pelo protótipo com dados das estações. A comparação mostra que os resultados são próximos, o que pode viabilizar soluções de baixo custo para o problema. O sistema ainda apresenta uma análise preditiva utilizando redes neurais recorrentes, no caso a rede LSTM-RNN, onde as predições apresentaram alta acurácia em relação aos dados reais.

show abstract

“…The original LSTM idea was initially proposed by [Hochreiter and Schmidhuber 1997] and since then different models have been proposed to improve the performance of LSTM [Cho et al 2014], [Li et al 2019], [Karevan and Suykens 2020], [Hu et al 2020]. The LSTM uses a locking mechanism to control the information that must be maintained over time, the duration that must be maintained and the time that can be read through the memory cell.…”

Section: Lstmmentioning

confidence: 99%

Time Series Prediction about Air Quality using LSTM-Based Models: A Systematic Mapping

Sachetti¹,

Mota²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network

Cited by 60 publications

References 14 publications

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

pmSensing: Uma Rede de Sensoriamento Participativo para Monitoramento Preditivo de Material Particulado

Time Series Prediction about Air Quality using LSTM-Based Models: A Systematic Mapping

Contact Info

Product

Resources

About