scholarly journals Time Series Segmentation Based on Stationarity Analysis to Improve New Samples Prediction

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7333
Author(s):  
Ricardo Petri Silva ◽  
Bruno Bogaz Zarpelão ◽  
Alberto Cano ◽  
Sylvio Barbon Junior
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Detection Methods ◽  
Sequential Data ◽  
Short Term ◽  
Term Memory ◽  
Wide Range ◽  
Long Short Term Memory ◽  
Adf Test

A wide range of applications based on sequential data, named time series, have become increasingly popular in recent years, mainly those based on the Internet of Things (IoT). Several different machine learning algorithms exploit the patterns extracted from sequential data to support multiple tasks. However, this data can suffer from unreliable readings that can lead to low accuracy models due to the low-quality training sets available. Detecting the change point between high representative segments is an important ally to find and thread biased subsequences. By constructing a framework based on the Augmented Dickey-Fuller (ADF) test for data stationarity, two proposals to automatically segment subsequences in a time series were developed. The former proposal, called Change Detector segmentation, relies on change detection methods of data stream mining. The latter, called ADF-based segmentation, is constructed on a new change detector derived from the ADF test only. Experiments over real-file IoT databases and benchmarks showed the improvement provided by our proposals for prediction tasks with traditional Autoregressive integrated moving average (ARIMA) and Deep Learning (Long short-term memory and Temporal Convolutional Networks) methods. Results obtained by the Long short-term memory predictive model reduced the relative prediction error from 1 to 0.67, compared to time series without segmentation.

scholarly journals Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Haimin Yang ◽  
Zhisong Pan ◽  
Qing Tao
Keyword(s):  
Time Series ◽  
Prediction Error ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Learning Rate ◽  
Stochastic Gradient ◽  
Short Term ◽  
Term Memory ◽  
Wide Range ◽  
Long Short Term Memory

Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam), for long short-term memory (LSTM) to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM.

Prediction of InSAR deformation time-series using a long short-term memory neural network

2021 ◽  
Vol 42 (18) ◽  
pp. 6921-6944
Author(s):  
Yi Chen ◽  
Yi He ◽  
Lifeng Zhang ◽  
Youdong Chen ◽  
Hongyu Pu ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5037
Author(s):  
Hisham ElMoaqet ◽  
Mohammad Eid ◽  
Martin Glos ◽  
Mutaz Ryalat ◽  
Thomas Penzel
Keyword(s):  
Feature Extraction ◽  
Sleep Apnea ◽  
Short Term Memory ◽  
Single Channel ◽  
Automated Detection ◽  
Detection Methods ◽  
Short Term ◽  
Term Memory ◽  
Deep Recurrent Neural Network ◽  
Long Short Term Memory

Sleep apnea is a common sleep disorder that causes repeated breathing interruption during sleep. The performance of automated apnea detection methods based on respiratory signals depend on the signals considered and feature extraction methods. Moreover, feature engineering techniques are highly dependent on the experts’ experience and their prior knowledge about different physiological signals and conditions of the subjects. To overcome these problems, a novel deep recurrent neural network (RNN) framework is developed for automated feature extraction and detection of apnea events from single respiratory channel inputs. Long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) are investigated to develop the proposed deep RNN model. The proposed framework is evaluated over three respiration signals: Oronasal thermal airflow (FlowTh), nasal pressure (NPRE), and abdominal respiratory inductance plethysmography (ABD). To demonstrate our results, we use polysomnography (PSG) data of 17 patients with obstructive, central, and mixed apnea events. Our results indicate the effectiveness of the proposed framework in automatic extraction for temporal features and automated detection of apneic events over the different respiratory signals considered in this study. Using a deep BiLSTM-based detection model, the NPRE signal achieved the highest overall detection results with true positive rate (sensitivity) = 90.3%, true negative rate (specificity) = 83.7%, and area under receiver operator characteristic curve = 92.4%. The present results contribute a new deep learning approach for automated detection of sleep apnea events from single channel respiration signals that can potentially serve as a helpful and alternative tool for the traditional PSG method.

A semiautomatic annotation approach for sentiment analysis

2021 ◽  
pp. 016555152110065
Author(s):  
Rahma Alahmary ◽  
Hmood Al-Dossari
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Short Term ◽  
Term Memory ◽  
Annotation Process ◽  
Learning Classifiers ◽  
Long Short Term Memory

Sentiment analysis (SA) aims to extract users’ opinions automatically from their posts and comments. Almost all prior works have used machine learning algorithms. Recently, SA research has shown promising performance in using the deep learning approach. However, deep learning is greedy and requires large datasets to learn, so it takes more time for data annotation. In this research, we proposed a semiautomatic approach using Naïve Bayes (NB) to annotate a new dataset in order to reduce the human effort and time spent on the annotation process. We created a dataset for the purpose of training and testing the classifier by collecting Saudi dialect tweets. The dataset produced from the semiautomatic model was then used to train and test deep learning classifiers to perform Saudi dialect SA. The accuracy achieved by the NB classifier was 83%. The trained semiautomatic model was used to annotate the new dataset before it was fed into the deep learning classifiers. The three deep learning classifiers tested in this research were convolutional neural network (CNN), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM). Support vector machine (SVM) was used as the baseline for comparison. Overall, the performance of the deep learning classifiers exceeded that of SVM. The results showed that CNN reported the highest performance. On one hand, the performance of Bi-LSTM was higher than that of LSTM and SVM, and, on the other hand, the performance of LSTM was higher than that of SVM. The proposed semiautomatic annotation approach is usable and promising to increase speed and save time and effort in the annotation process.

Prognostics and RUL Estimations of SAC305, SAC105 and SnAg Solders Under Temperature and Vibration Using Long Short-Term Memory (LSTM) Deep Learning

2021 ◽  
Author(s):  
Pradeep Lall ◽  
Tony Thomas ◽  
Ken Blecker
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Short Term ◽  
Term Memory ◽  
Rectangular Pattern ◽  
Useful Life ◽  
Long Short Term Memory

Abstract Prognostics and Remaining Useful Life (RUL) estimations of complex systems are essential to operational safety, increased efficiency, and help to schedule maintenance proactively. Modeling the remaining useful life of a system with many complexities is possible with the rapid development in the field of deep learning as a computational technique for failure prediction. Deep learning can adapt to multivariate parameters complex and nonlinear behavior, which is difficult using traditional time-series models for forecasting and prediction purposes. In this paper, a deep learning approach based on Long Short-Term Memory (LSTM) network is used to predict the remaining useful life of the PCB at different conditions of temperature and vibration. This technique can identify the different underlying patterns in the time series that can predict the RUL. This study involves feature vector identification and RUL estimations for SAC305, SAC105, and Tin Lead solder PCBs under different vibration levels and temperature conditions. The acceleration levels of vibration are fixed at 5g and 10g, while the temperature levels are 55°C and 100°C. The test board is a multilayer FR4 configuration with JEDEC standard dimensions consists of twelve packages arranged in a rectangular pattern. Strain signals are acquired from the backside of the PCB at symmetric locations to identify the failure of all the packages during vibration. The strain signals are resistance values that are acquired simultaneously during the experiment until the failure of most of the packages on the board. The feature vectors are identified from statistical analysis on the strain signals frequency and instantaneous frequency components. The principal component analysis is used as a data reduction technique to identify the different patterns produced from the four strain signals with failures of the packages during vibration. LSTM deep learning method is used to model the RUL of the packages at different individual operating conditions of vibration for all three solder materials involved in this study. A combined model for RUL prediction for a material that can take care of the changes in the operating conditions is also modeled for each material.

scholarly journals Prediksi Kunjungan Wisatawan Taman Nasional Gunung Merbabu dengan Time Series Forecasting dan LSTM

2020 ◽  
Vol 11 (2) ◽  
pp. 131
Author(s):  
Josua Manullang ◽  
Albertus Joko Santoso ◽  
Andi Wahju Rahardjo Emanuel
Keyword(s):  
Time Series ◽  
National Park ◽  
Short Term Memory ◽  
Lag Time ◽  
Time Series Forecasting ◽  
Mean Square ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract. Prediction of tourist visits of Mount Merbabu National Park (TNGMb) needs to be done to control the number of visitors and to preserve the national park. The combination of time series forecasting (TSF) and deep learning methods has become a new alternative for prediction. This case study was conducted to implement several methods combination of TSF and Long-Short Term Memory (LSTM) to predict the visits. In this case study, there are 18 modelling scenarios as research objects to determine the best model by utilizing tourist visits data from 2013 to 2018. The results show that the model applying the lag time method can improve the model's ability to capture patterns on time series data. The error value is measured using the root mean square error (RMSE), with the smallest value of 3.7 in the LSTM architecture, using seven lags as a feature and one lag as a label.Keywords: Tourist Visit, Taman Nasional Gunung Merbabu, Prediction, Recurrent Neural Network, Long-Short Term MemoryAbstrak. Prediksi kunjungan wisatawan Taman Nasional Gunung Merbabu (TNGMb) perlu dilakukan untul pengendalian jumlah pengunjung dan menjaga kelestarian taman nasional. Gabungan metode antara time series forecasting (TSF) dan deep learning telah menjadi alternatif baru untuk melakukan prediksi. Studi kasus ini dilakukan untuk mengimplementasi gabungan dari beberapa macam metode antara TSF dan Long-Short Term Memory (LSTM) untuk memprediksi kunjungan pada TNGMb. Pada studi kasus ini, terdapat 18 skenario pemodelan sebagai objek penelitian untuk menentukan model terbaik, dengan memanfaatkan data jumlah kunjungan wisatawan di TNGMb mulai dari tahun 2013 sampai dengan tahun 2018. Hasil prediksi menunjukkan pemodelan dengan menerapkan metode lag time dapat meningkatakan kemampuan model untuk menangkap pola pada data deret waktu. Besar nilai kesalahan diukur menggunakan root mean square error (RMSE), dengan nilai terkecil sebesar 3,7 pada arsitektur LSTM, menggunakan tujuh lag sebagai feature dan satu lag sebagai label. Kata Kunci: Kunjungan Wisatawan, Taman Nasional Gunung Merbabu, Prediksi, Recurrent Neural Network, Long-Short Term Memory

Sign in / Sign up

Export Citation Format

Share Document