Surface EMG Pattern Recognition Using Long Short-Term Memory Combined with Multilayer Perceptron

2018 ◽  
Author(s):  
Yunan He ◽  
Osamu Fukuda ◽  
Nan Bu ◽  
Hiroshi Okumura ◽  
Nobuhiko Yamaguchi
Keyword(s):  
Pattern Recognition ◽  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Surface Emg ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Emg Pattern Recognition

scholarly journals Long Short-Term Memory Networks for Pattern Recognition of Synthetical Complete Earthquake Catalog

2021 ◽  
Vol 13 (9) ◽  
pp. 4905
Author(s):  
Chen Cao ◽  
Xiangbin Wu ◽  
Lizhi Yang ◽  
Qian Zhang ◽  
Xianying Wang ◽  
...  
Keyword(s):  
Pattern Recognition ◽  
Short Term Memory ◽  
Three Dimensional ◽  
Earthquake Risk ◽  
Earthquake Activity ◽  
Earthquake Catalog ◽  
Short Term ◽  
Term Memory ◽  
Earthquake Migration ◽  
Long Short Term Memory

Exploring the spatiotemporal distribution of earthquake activity, especially earthquake migration of fault systems, can greatly to understand the basic mechanics of earthquakes and the assessment of earthquake risk. By establishing a three-dimensional strike-slip fault model, to derive the stress response and fault slip along the fault under regional stress conditions. Our study helps to create a long-term, complete earthquake catalog. We modelled Long-Short Term Memory (LSTM) networks for pattern recognition of the synthetical earthquake catalog. The performance of the models was compared using the mean-square error (MSE). Our results showed clearly the application of LSTM showed a meaningful result of 0.08% in the MSE values. Our best model can predict the time and magnitude of the earthquakes with a magnitude greater than Mw = 6.5 with a similar clustering period. These results showed conclusively that applying LSTM in a spatiotemporal series prediction provides a potential application in the study of earthquake mechanics and forecasting of major earthquake events.

scholarly journals A Two-Stage Short-Term Load Forecasting Method Using Long Short-Term Memory and Multilayer Perceptron

Energies ◽  
2021 ◽  
Vol 14 (18) ◽  
pp. 5873
Author(s):  
Yuhong Xie ◽  
Yuzuru Ueda ◽  
Masakazu Sugiyama
Keyword(s):  
Neural Networks ◽  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Historical Data ◽  
Load Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Proposed Model ◽  
Short Term Load Forecasting ◽  
Long Short Term Memory

Load forecasting is an essential task in the operation management of a power system. Electric power companies utilize short-term load forecasting (STLF) technology to make reasonable power generation plans. A forecasting model with low prediction errors helps reduce operating costs and risks for the operators. In recent years, machine learning has become one of the most popular technologies for load forecasting. In this paper, a two-stage STLF model based on long short-term memory (LSTM) and multilayer perceptron (MLP), which improves the forecasting accuracy over the entire time horizon, is proposed. In the first stage, a sequence-to-sequence (seq2seq) architecture, which can handle a multi-sequence of input to extract more features of historical data than that of single sequence, is used to make multistep predictions. In the second stage, the MLP is used for residual modification by perceiving other information that the LSTM cannot. To construct the model, we collected the electrical load, calendar, and meteorological records of Kanto region in Japan for four years. Unlike other LSTM-based hybrid architectures, the proposed model uses two independent neural networks instead of making the neural network deeper by concatenating a series of LSTM cells and convolutional neural networks (CNNs). Therefore, the proposed model is easy to be trained and more interpretable. The seq2seq module performs well in the first few hours of the predictions. The MLP inherits the advantage of the seq2seq module and improves the results by feeding artificially selected features both from historical data and information of the target day. Compared to the LSTM-AM model and single MLP model, the mean absolute percentage error (MAPE) of the proposed model decreases from 2.82% and 2.65% to 2%, respectively. The results demonstrate that the MLP helps improve the prediction accuracy of seq2seq module and the proposed model achieves better performance than other popular models. In addition, this paper also reveals the reason why the MLP achieves the improvement.

scholarly journals GIS Partial Discharge Pattern Recognition Based on a Novel Convolutional Neural Networks and Long Short-Term Memory

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 774
Author(s):  
Tingliang Liu ◽  
Jing Yan ◽  
Yanxin Wang ◽  
Yifan Xu ◽  
Yiming Zhao
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Short Term Memory ◽  
Partial Discharge ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Analysis Methods ◽  
Voltage Signal ◽  
Long Short Term Memory

Distinguishing the types of partial discharge (PD) caused by different insulation defects in gas-insulated switchgear (GIS) is a great challenge in the power industry, and improving the recognition accuracy of the relevant models is one of the key problems. In this paper, a convolutional neural network and long short-term memory (CNN-LSTM) model is proposed, which can effectively extract and utilize the spatiotemporal characteristics of PD input signals. First, the spatial characteristics of higher-level PD signals can be obtained through the CNN network, but because CNN is a deep feedforward neural network, it does not have the ability to process time-series data. The PD voltage signal is related to the time dimension, so LSTM saves and analyzes the previous voltage signal information, realizes the modeling of the time dependence of the data, and improves the accuracy of the PD signal pattern recognition. Finally, the pattern recognition results based on CNN-LSTM are given and compared with those based on other traditional analysis methods. The results show that the pattern recognition rate of this method is the highest, with an average of 97.9%, and its overall accuracy is better than that of other traditional analysis methods. The CNN-LSTM model provides a reliable reference for GIS PD diagnosis.

scholarly journals Software Effort Estimation Using Multilayer Perceptron and Long Short Term Memory

2019 ◽  
Vol 23 (2/2019) ◽  
pp. 76-87
Author(s):  
Eduard-Florin PREDESCU ◽  
Alexandru STEFAN ◽  
Alexis-Valentin ZAHARIA
Keyword(s):  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Effort Estimation ◽  
Software Effort Estimation ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Prediksi Harga Beras Menggunakan Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM)

2020 ◽  
Vol 12 (1) ◽  
pp. 35-41
Author(s):  
Steven Sen ◽  
Dedy Sugiarto ◽  
Abdul Rochman
Keyword(s):  
Deep Learning ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Multilayer Perceptron ◽  
Short Term Memory ◽  
Mean Square ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Hidden Layer

Beras adalah salah satu komoditas utama di masyarakat Indonesia. Masalah utama dengan beras secara nasional adalah inflasi harga beras. Oleh karena itu, penelitian ini memprediksi harga beras menggunakan arsitektur jaringan saraf tiruan Multilayer Perceptron (MLP) dan deep learning : Long Short Term Memory (LSTM) untuk mengantisipasi masalah ini. Data yang digunakan dalam penelitian ini adalah data riil harga beras selama 2016 - 2019 yang diperoleh dari PT. Food Station. Total dataset adalah 1307 dengan distribusi 1123 sebagai data train dan 184 sebagai data uji. Hasil akhir yang diperoleh dalam penelitian ini adalah LSTM lebih unggul dari MLP, dengan nilai Root Mean Square Error (RMSE) data train : 0,49, dan nilai loss RMSE dari data tes adalah 0,27. Model LSTM paling optimal dari 3 tes dilakukan, yaitu jumlah hidden layer = 16 dan epochs = 150 kali.

Sign in / Sign up

Export Citation Format

Share Document