scholarly journals Approach to COVID-19 time series data using deep learning and spectral analysis methods

2021 ◽  
Vol 9 (1) ◽  
pp. 1-21
Author(s):  
Kayode Oshinubi ◽  
◽  
Augustina Amakor ◽  
Olumuyiwa James Peter ◽  
Mustapha Rachdi ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Spectral Analysis ◽  
Deep Learning ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Time Series Data ◽  
Series Data ◽  
Mean Square

<abstract> <p>This article focuses on the application of deep learning and spectral analysis to epidemiology time series data, which has recently piqued the interest of some researchers. The COVID-19 virus is still mutating, particularly the delta and omicron variants, which are known for their high level of contagiousness, but policymakers and governments are resolute in combating the pandemic's spread through a recent massive vaccination campaign of their population. We used extreme machine learning (ELM), multilayer perceptron (MLP), long short-term neural network (LSTM), gated recurrent unit (GRU), convolution neural network (CNN) and deep neural network (DNN) methods on time series data from the start of the pandemic in France, Russia, Turkey, India, United states of America (USA), Brazil and United Kingdom (UK) until September 3, 2021 to predict the daily new cases and daily deaths at different waves of the pandemic in countries considered while using root mean square error (RMSE) and relative root mean square error (rRMSE) to measure the performance of these methods. We used the spectral analysis method to convert time (days) to frequency in order to analyze the peaks of frequency and periodicity of the time series data. We also forecasted the future pandemic evolution by using ELM, MLP, and spectral analysis. Moreover, MLP achieved best performance for both daily new cases and deaths based on the evaluation metrics used. Furthermore, we discovered that errors for daily deaths are much lower than those for daily new cases. While the performance of models varies, prediction and forecasting during the period of vaccination and recent cases confirm the pandemic's prevalence level in the countries under consideration. Finally, some of the peaks observed in the time series data correspond with the proven pattern of weekly peaks that is unique to the COVID-19 time series data.</p> </abstract>

scholarly journals Prediksi Kedatangan Turis Asing ke Indonesia Menggunakan Backpropagation Neural Networks

2016 ◽  
Vol 4 (4) ◽  
pp. 485
Author(s):  
Haviluddin Haviluddin ◽  
Zainal Arifin ◽  
Awang Harsa Kridalaksana ◽  
Dedy Cahyadi
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Mean Square Error ◽  
Time Series Data ◽  
Alternative Methods ◽  
Series Data ◽  
Mean Square ◽  
Backpropagation Neural Network ◽  
Forecasting Accuracy ◽  
The Mean

In this paper, a backpropagation neural network (BPNN) method with time series data have been explored. The BPNN method to predict the foreign tourist’s arrival to Indonesia datasets have been implemented. The foreign tourist’s arrival datasets were taken from the center agency on statistics (BPS) Indonesia. The experimental results showed that the BPNN method with two hidden layers were able to forecast foreign tourist’s arrival to Indonesia. Where, the mean square error (MSE) as forecasting accuracy has been indicated. In this study, the BPNN method is able and recommended to be alternative methods for predicting time series datasets. Also, the BPNN method showed that effective and easy to use. In other words, BPNN method is capable to producing good value of forecasting.Keywords - BPNN; foreign tourists; BPS; MSEPemanfaatan backpropagation neural network (BPNN) dengan data deret waktu telah digunakan dalam paper ini. Metode BPNN telah digunakan untuk memprediksi data kedatangan turis asing ke Indonesia, dimana data turis tersebut diambil dari badan pusat statistik Indonesia (BPS). Hasil pengujian menunjukkan bahwa metode BPNN dengan dua lapisan tersembunyi mampu memodelkan dan meramalkan data kedatangan turis asing ke Indonesia yang diindikasikan dengan nilai mean square error (MSE). Penelitian ini merekomendasikan bahwa metode BPNN mampu menjadi alternative metode dalam memprediksi data yang berjenis deret waktu karena metode BPNN efektif dan lebih mudah digunakan serta mampu menghasilkan akurasi nilai peramalan yang baik.

scholarly journals Forecasting Electricity Load With Hybrid Scalable Model Based on Stacked Non Linear Residual Approach

2021 ◽  
Vol 9 ◽  
Author(s):  
Ayush Sinha ◽  
Raghav Tayal ◽  
Aamod Vyas ◽  
Pankaj Pandey ◽  
O. P. Vyas
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Mean Square Error ◽  
Performance Metrics ◽  
Time Series Data ◽  
Hybrid Approach ◽  
Series Data ◽  
Mean Square ◽  
Power Load ◽  
Non Linear

Power has totally different attributes than other material commodities as electrical energy stockpiling is a costly phenomenon. Since it should be generated when demanded, it is necessary to forecast its demand accurately and efficiently. As electrical load data is represented through time series pattern having linear and non-linear characteristics, it needs a model that may handle this behavior well in advance. This paper presents a scalable and hybrid approach for forecasting the power load based on Vector Auto Regression (VAR) and hybrid deep learning techniques like Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). CNN and LSTM models are well known for handling time series data. The VAR model separates the linear pattern in time series data, and CNN-LSTM is utilized to model non-linear patterns in data. CNN-LSTM works as CNN can extract complex features from electricity data, and LSTM can model temporal information in data. This approach can derive temporal and spatial features of electricity data. The experiment established that the proposed VAR-CNN-LSTM(VACL) hybrid approach forecasts better than more recent deep learning methods like Multilayer Perceptron (MLP), CNN, LSTM, MV-KWNN, MV-ANN, Hybrid CNN-LSTM and statistical techniques like VAR, and Auto Regressive Integrated Moving Average (ARIMAX). Performance metrics such as Mean Square Error, Root Mean Square Error, and Mean Absolute Error have been used to evaluate the performance of the discussed approaches. Finally, the efficacy of the proposed model is established through comparative studies with state-of-the-art models on Household Power Consumption Dataset (UCI machine learning repository) and Ontario Electricity Demand dataset (Canada).

Predicting Rice Production using Autoregressive Integrated Moving Average Model

2019 ◽  
Vol 6 (04) ◽  
Author(s):  
R C BHARATI ◽  
ANIL KUMAR SINGH
Keyword(s):  
Time Series ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Time Series Data ◽  
Moving Average ◽  
Information Criterion ◽  
Rice Production ◽  
Series Data ◽  
Mean Square ◽  
Autoregressive Integrated Moving Average

A study was conducted on time-series data on rice production in India. Box-Jenkins Autoregressive Integrated Moving Average (ARIMA) time-series process was considered for predicting country's rice production using the time series data from 1950–51 to 2017–18. Data from 1950–51 to 2014–15 were used for model development and three years data from 2015–16 and 2017–18 were kept for validation The augmented Dicky Fuller test was applied to test stationarity in data set. Root mean square error. Based on ACF and PACF, the model was defined and tested for its suitability. Akaike information criterion and Bayesian information criterion were used to judge the suitability of the model to be fitted. The performance of the fitted model was examined using mean absolute error, mean percent forecast error, root mean square error and Theil's inequality coefficients. IMA (0, 1, 1) model performed well for forecasting purposes. The percent prediction error for the last three years i.e. from 2015–16 and 2017–18, was below 3%. The predicted values along with their standard errors up to the year 2099, were also obtained using the model.

Outlier Detection Using Convolutional Neural Network for Wireless Sensor Network

2021 ◽  
Vol 17 (2) ◽  
pp. 0-0
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
Wireless Sensor Network ◽  
Convolutional Neural Network ◽  
Sensor Network ◽  
Time Series Data ◽  
Wireless Sensor ◽  
Series Data ◽  
Detection Accuracy

Over the recent years, the term deep learning has been considered as one of the primary choice for handling huge amount of data. Having deeper hidden layers, it surpasses classical methods for detection of outlier in wireless sensor network. The Convolutional Neural Network (CNN) is a biologically inspired computational model which is one of the most popular deep learning approaches. It comprises neurons that self-optimize through learning. EEG generally known as Electroencephalography is a tool used for investigation of brain function and EEG signal gives time-series data as output. In this paper, we propose a state-of-the-art technique designed by processing the time-series data generated by the sensor nodes stored in a large dataset into discrete one-second frames and these frames are projected onto a 2D map images. A convolutional neural network (CNN) is then trained to classify these frames. The result improves detection accuracy and encouraging.

scholarly journals Forecasting hourly emergency department arrival using time series analysis

2020 ◽  
Vol 26 (1) ◽  
pp. 34-43
Author(s):  
Avishek Choudhury ◽  
Estefania Urena
Keyword(s):  
Emergency Department ◽  
Time Series ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Moving Average ◽  
Time Series Forecasting ◽  
Mean Square ◽  
Mean Error ◽  
Auto Regressive

Background/aims The stochastic arrival of patients at hospital emergency departments complicates their management. More than 50% of a hospital's emergency department tends to operate beyond its normal capacity and eventually fails to deliver high-quality care. To address this concern, much research has been carried out using yearly, monthly and weekly time-series forecasting. This article discusses the use of hourly time-series forecasting to help improve emergency department management by predicting the arrival of future patients. Methods Emergency department admission data from January 2014 to August 2017 was retrieved from a hospital in Iowa. The auto-regressive integrated moving average (ARIMA), Holt–Winters, TBATS, and neural network methods were implemented and compared as forecasters of hourly patient arrivals. Results The auto-regressive integrated moving average (3,0,0) (2,1,0) was selected as the best fit model, with minimum Akaike information criterion and Schwartz Bayesian criterion. The model was stationary and qualified under the Box–Ljung correlation test and the Jarque–Bera test for normality. The mean error and root mean square error were selected as performance measures. A mean error of 1.001 and a root mean square error of 1.55 were obtained. Conclusions The auto-regressive integrated moving average can be used to provide hourly forecasts for emergency department arrivals and can be implemented as a decision support system to aid staff when scheduling and adjusting emergency department arrivals.

scholarly journals Flood Detection and Susceptibility Mapping Using Sentinel-1 Time Series, Alternating Decision Trees, and Bag-ADTree Models

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-21 ◽  
Author(s):  
Ayub Mohammadi ◽  
Khalil Valizadeh Kamran ◽  
Sadra Karimzadeh ◽  
Himan Shahabi ◽  
Nadhir Al-Ansari
Keyword(s):  
Time Series ◽  
Root Mean Square Error ◽  
Decision Trees ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Susceptibility Mapping ◽  
Mean Square ◽  
Topographic Wetness Index ◽  
Flood Detection ◽  
Flooded Areas

Flooding is one of the most damaging natural hazards globally. During the past three years, floods have claimed hundreds of lives and millions of dollars of damage in Iran. In this study, we detected flood locations and mapped areas susceptible to floods using time series satellite data analysis as well as a new model of bagging ensemble-based alternating decision trees, namely, bag-ADTree. We used Sentinel-1 data for flood detection and time series analysis. We employed twelve conditioning parameters of elevation, normalized difference’s vegetation index, slope, topographic wetness index, aspect, curvature, stream power index, lithology, drainage density, proximities to river, soil type, and rainfall for mapping areas susceptible to floods. ADTree and bag-ADTree models were used for flood susceptibility mapping. We used software of Sentinel application platform, Waikato Environment for Knowledge Analysis, ArcGIS, and Statistical Package for the Social Sciences for preprocessing, processing, and postprocessing of the data. We extracted 199 locations as flooded areas, which were tested using a global positioning system to ensure that flooded areas were detected correctly. Root mean square error, accuracy, and the area under the ROC curve were used to validate the models. Findings showed that root mean square error was 0.31 and 0.3 for ADTree and bag-ADTree techniques, respectively. More findings illustrated that accuracy was obtained as 86.61 for bag-ADTree model, while it was 85.44 for ADTree method. Based on AUC, success and prediction rates were 0.736 and 0.786 for bag-ADTree algorithm, in order, while these proportions were 0.714 and 0.784 for ADTree. This study can be a good source of information for crisis management in the study area.

scholarly journals Prediction of Lower Extremity Multi-Joint Angles during Overground Walking by Using a Single IMU with a Low Frequency Based on an LSTM Recurrent Neural Network

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 53
Author(s):  
Joohwan Sung ◽  
Sungmin Han ◽  
Heesu Park ◽  
Hyun-Myung Cho ◽  
Soree Hwang ◽  
...  
Keyword(s):  
Neural Network ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Recurrent Neural Network ◽  
Joint Angle ◽  
Low Frequency ◽  
Measurement Unit ◽  
Mean Square ◽  
Overground Walking

The joint angle during gait is an important indicator, such as injury risk index, rehabilitation status evaluation, etc. To analyze gait, inertial measurement unit (IMU) sensors have been used in studies and continuously developed; however, they are difficult to utilize in daily life because of the inconvenience of having to attach multiple sensors together and the difficulty of long-term use due to the battery consumption required for high data sampling rates. To overcome these problems, this study propose a multi-joint angle estimation method based on a long short-term memory (LSTM) recurrent neural network with a single low-frequency (23 Hz) IMU sensor. IMU sensor data attached to the lateral shank were measured during overground walking at a self-selected speed for 30 healthy young persons. The results show a comparatively good accuracy level, similar to previous studies using high-frequency IMU sensors. Compared to the reference results obtained from the motion capture system, the estimated angle coefficient of determination (R2) is greater than 0.74, and the root mean square error and normalized root mean square error (NRMSE) are less than 7° and 9.87%, respectively. The knee joint showed the best estimation performance in terms of the NRMSE and R2 among the hip, knee, and ankle joints.

scholarly journals ARTIFICIAL NEURAL NETWORK APPLIED IN FORECASTING THE COMPOSITION OF MUNICIPAL SOLID WASTE IN IASI, ROMANIA

2021 ◽  
Vol 29 (3) ◽  
pp. 368-380
Author(s):  
Cristina Ghinea ◽  
Petronela Cozma ◽  
Maria Gavrilescu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Artificial Neural Network ◽  
Root Mean Square Error ◽  
Municipal Solid Waste ◽  
Solid Waste ◽  
Mean Square Error ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Ann Model

Neural network time series (NNTS) tool was used to predict municipal solid waste composition in Iasi, Romania. The nonlinear input output (NIO) time series model and nonlinear autoregressive model with external (exogenous) input (NARX) included in this tool were selected. The coefficient of determination (R2) and root mean square error (RMSE) were chosen for evaluation. By applying NIO, the optimum model is 4-11-6 artificial neural network (ANN, R2 = 0.929) in the case of testing as for the validation, with all 0.849 and 0.885, respectively. Applying NARX, the suitable model became 4-13-6 ANN model, with R2 = 0.999 for training, 0.879 for testing, and 0.931, respectively 0.944 for validation and all. The resulted RMSE is zero for training and 0.0109 for validation in the case of this model which had 4 inputs, 13 neurons and 6 outputs. The four input variables were: number of residents, population aged 15–59 years, urban life expectancy, total municipal solid waste (ton/year). The suitable ANN model revealed the lowest root mean square error and the highest coefficient of determination. Results indicate that NNTS tool is a complex instrument, NARX is more accurate than NIO model, and can be used and applied easily.

Deep Learning Stream Temperature Model: Recommendations for Modeling Gauged and Ungauged Basins

2021 ◽  
Author(s):  
Farshid Rahmani ◽  
Kathryn Lawson ◽  
Samantha Oliver ◽  
Alison Appling ◽  
Chaopeng Shen
Keyword(s):  
Deep Learning ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
The United States ◽  
Data Availability ◽  
Efficiency Coefficient ◽  
Mean Square ◽  
Training Set ◽  
The Impact

&lt;p&gt;Stream water temperature (T&lt;sub&gt;s&lt;/sub&gt;) is a variable that plays a pivotal role in managing water resources. We used the long short-term memory (LSTM) deep learning architecture to develop a basin centric single T&lt;sub&gt;s&lt;/sub&gt; model based on general meteorological data and basin meteo-geological attributes. We created a strong tool for long-term Ts projection and subsequently, improved the Ts model using novel approaches. We investigated the impact of both observed and simulated streamflow data on improving the model accuracy. At a national scale, we obtained a median root-mean-square error (RMSE) of 0.69 &lt;sup&gt;o&lt;/sup&gt;C, and Nash-Sutcliffe model efficiency coefficient (NSE) of 0.985, which are marked improvements over previous values reported in previous studies. In order to test the performance of the model on basins ranging from basins with extensive data to unmonitored basins, we used more than 400 basins with different data-availability groups (DAG) across the continent of the United States to explore how to assemble the training dataset for both monitored and unmonitored basins. Best root-mean-square error (RMSE) for sites with extensive (99%), intermediate (60%), scarce (10%) and absent (0%) data for training were 0.75, 0.837, 0.889, and 1.595 &lt;sup&gt;o&lt;/sup&gt;C, respectively. We observed the negative effect of the presence of reservoirs in T&lt;sub&gt;s&lt;/sub&gt; modeling. Our results illustrated that the most suitable training set should be different in modeling basins with different availability of observed data. for predicting T&lt;sub&gt;s&lt;/sub&gt; in a monitored basin, including basins that have at least equal DAG with that particular basin will result in most accurate predictions, however, for T&lt;sub&gt;s&lt;/sub&gt; prediction in ungauged basin, including all basins in training section will generate the best model, showing a more diverse training set. Furthermore, to decrease overfitting produced by attributes for PUB application, we could improve the accuracy of the model using input-selection ensemble method. We got median correlation higher than 0.90 for PUB after seasonality was removed which is still high. While many T&lt;sub&gt;s&lt;/sub&gt; prediction models showed better performance in summer, our model was on the opposite side. We found a strong relationship between general available daily meteorological variables and catchment attributes with the presented T&lt;sub&gt;s&lt;/sub&gt; model. However, our results indicate that combining physics-based criteria to the model can improve the prediction of temperature in river networks.&lt;/p&gt;&lt;p&gt;.&lt;/p&gt;

scholarly journals Study on Apparent Kinetic Prediction Model of the Smelting Reduction Based on the Time-Series

2012 ◽  
Vol 2012 ◽  
pp. 1-15 ◽  
Author(s):  
Guo-feng Fan ◽  
Shan Qing ◽  
Hua Wang ◽  
Zhe Shi ◽  
Wei-Chiang Hong ◽  
...  
Keyword(s):  
Time Series ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Golden Section ◽  
Ar Model ◽  
Mean Square ◽  
Smelting Reduction ◽  
Data Mining Technique ◽  
Promising Alternative

A series of direct smelting reduction experiment has been carried out with high phosphorous iron ore of the different bases by thermogravimetric analyzer. The derivative thermogravimetric (DTG) data have been obtained from the experiments. One-step forward local weighted linear (LWL) method , one of the most suitable ways of predicting chaotic time-series methods which focus on the errors, is used to predict DTG. In the meanwhile, empirical mode decomposition-autoregressive (EMD-AR), a data mining technique in signal processing, is also used to predict DTG. The results show that (1) EMD-AR(4) is the most appropriate and its error is smaller than the former; (2) root mean square error (RMSE) has decreased about two-thirds; (3) standardized root mean square error (NMSE) has decreased in an order of magnitude. Finally in this paper, EMD-AR method has been improved by golden section weighting; its error would be smaller than before. Therefore, the improved EMD-AR model is a promising alternative for apparent reaction rate (DTG). The analytical results have been an important reference in the field of industrial control.

Sign in / Sign up

Export Citation Format

Share Document