Jaya Spider Monkey Optimization-driven Deep Convolutional LSTM for the prediction of COVID’19

2020 ◽  
Vol 16 (4) ◽  
Author(s):  
Satish Chander ◽  
Vijaya Padmanabha ◽  
Joseph Mani
Keyword(s):  
Time Series ◽  
Mean Square Error ◽  
Time Series Data ◽  
Moving Average ◽  
Spider Monkey ◽  
World Health ◽  
Series Data ◽  
Mean Square ◽  
The World ◽  
Spider Monkey Optimization

AbstractCOVID’19 is an emerging disease and the precise epidemiological profile does not exist in the world. Hence, the COVID’19 outbreak is treated as a Public Health Emergency of the International Concern by the World Health Organization (WHO). Hence, an effective and optimal prediction of COVID’19 mechanism, named Jaya Spider Monkey Optimization-based Deep Convolutional long short-term classifier (JayaSMO-based Deep ConvLSTM) is proposed in this research to predict the rate of confirmed, death, and recovered cases from the time series data. The proposed COVID’19 prediction method uses the COVID’19 data, which is the trending domain of research at the current era of fighting the COVID’19 attacks thereby, to reduce the death toll. However, the proposed JayaSMO algorithm is designed by integrating the Spider Monkey Optimization (SMO) with the Jaya algorithm, respectively. The Deep ConvLSTM classifier facilitates to predict the COVID’19 from the time series data based on the fitness function. Besides, the technical indicators, such as Relative Strength Index (RSI), Rate of Change (ROCR), Exponential Moving Average (EMA), Williams %R, Double Exponential Moving Average (DEMA), and Stochastic %K, are extracted effectively for further processing. Thus, the resulted output of the proposed JayaSMO-based Deep ConvLSTM is employed for COVID’19 prediction. Moreover, the developed model obtained the better performance using the metrics, like Mean Square Error (MSE), and Root Mean Square Error (RMSE) by considering confirmed, death, and the recovered cases of COVID’19 for China and Oman. Thus, the proposed JayaSMO-based Deep ConvLSTM showed improved results with a minimal MSE of 1.791, and the minimal RMSE of 1.338 based on confirmed cases in Oman. In addition, the developed model achieved the death cases with the values of 1.609, and 1.268 for MSE and RMSE, whereas the MSE and the RMSE value of 1.945, and 1.394 is achieved by the developed model using recovered cases in China.

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.

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).

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 COVID 19: Real-time Forecasts of confirmed cases, active cases, and health infrastructure requirements for India and its states using the ARIMA model

2020 ◽  
Author(s):  
Rishabh Tyagi ◽  
Mahadev Bramhankar ◽  
Mohit Pandey ◽  
M Kishore
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Moving Average ◽  
Arima Model ◽  
Public Health Care ◽  
World Health ◽  
Series Data ◽  
Health Infrastructure ◽  
Future Demands ◽  
Health Organization

AbstractBackgroundCOVID-19 is an emerging infectious disease which has been declared a Pandemic by the World Health Organization (WHO) on 11th March 2020. The Indian public health care system is already overstretched, and this pandemic is making things even worse. That is why forecasting cases for India is necessary to meet the future demands of the health infrastructure caused due to COVID-19.ObjectiveOur study forecasts the confirmed and active cases for COVID-19 until July mid, using time series Autoregressive Integrated Moving Average (ARIMA) model. Additionally, we estimated the number of isolation beds, Intensive Care Unit (ICU) beds and ventilators required for the growing number of COVID-19 patients.MethodsWe used ARIMA model for forecasting confirmed and active cases till the 15th July. We used time-series data of COVID-19 cases in India from 14th March to 22nd May. We estimated the requirements for ICU beds as 10%, ventilators as 5% and isolation beds as 85% of the active cases forecasted using the ARIMA model.ResultsOur forecasts indicate that India will have an estimated 7,47,772 confirmed cases (95% CI: 493943, 1001601) and 296,472 active cases (95% CI:196820, 396125) by 15th July. While Maharashtra will be the most affected state, having the highest number of active and confirmed cases, Punjab is expected to have an estimated 115 active cases by 15th July. India needs to prepare 2,52,001 isolation beds (95% CI: 167297, 336706), 29,647 ICU beds (95% CI: 19682, 39612), and 14,824 ventilator beds (95% CI: 9841, 19806).ConclusionOur forecasts show an alarming situation for India, and Maharashtra in particular. The actual numbers can go higher than our estimated numbers as India has a limited testing facility and coverage.

scholarly journals Analyzing and Forecasting HIV Data Using Hybrid Time Series Models

2019 ◽  
pp. 1-12
Author(s):  
Liming Xie
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Hybrid Methods ◽  
Moving Average ◽  
Series Data ◽  
People Living With Hiv ◽  
The World ◽  
Linear And Nonlinear ◽  
Original Time ◽  
And Control

In real work, we often confront complete linear and nonlinear time series data. But some time series are not pure linear and nonlinear, or complicated one, we need apply two or more models to analyze and predict them. It is necessary to explore and find some novel time series hybrid methods to solve it. Human Immunodeficiency and Virus (HIV) is one of intractable and trouble diseases in the world. Thus, the author of this article wants to analyze and probe into some novel time series methods to get breaking breach in the epidemiology that find some rules in the incidence, distribution, pathogen, and control of HIV in a population.  In this article, to find the best model, auto.arima function is applied to the original time series data to determine autoregressive integrated moving average, ARIMA(0,0,0); ARIMA and generalized autoregressive conditional heteroskedasticity (GARCH), that is, ARIMA-GARCH (1,1) model is used to analyze numbers of people living with HIV for the data of HIV in the world such some important parameters as mu, ar1, ar2, omega, alpha 1, or beta 1 and some specific tests, for example, Jarque-Bera Test, Shapiro-Wilk Test, Ljung-Box Test, etc. Using ARIMA (0, 0, 0) and SARIMA (0,2), seasonal ARIMA, to predict the future values and trends after 2015. Both suggest identical results.

scholarly journals A Comparison of Time-Series Predictions for Healthcare Emergency Department Indicators and the Impact of COVID-19

2021 ◽  
Vol 11 (8) ◽  
pp. 3561
Author(s):  
Diego Duarte ◽  
Chris Walshaw ◽  
Nadarajah Ramesh
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Moving Average ◽  
General Regression Neural Network ◽  
Series Data ◽  
Machine Learning Model ◽  
Hospital Patients ◽  
Major Incidents ◽  
General Regression ◽  
The Impact

Across the world, healthcare systems are under stress and this has been hugely exacerbated by the COVID pandemic. Key Performance Indicators (KPIs), usually in the form of time-series data, are used to help manage that stress. Making reliable predictions of these indicators, particularly for emergency departments (ED), can facilitate acute unit planning, enhance quality of care and optimise resources. This motivates models that can forecast relevant KPIs and this paper addresses that need by comparing the Autoregressive Integrated Moving Average (ARIMA) method, a purely statistical model, to Prophet, a decomposable forecasting model based on trend, seasonality and holidays variables, and to the General Regression Neural Network (GRNN), a machine learning model. The dataset analysed is formed of four hourly valued indicators from a UK hospital: Patients in Department; Number of Attendances; Unallocated Patients with a DTA (Decision to Admit); Medically Fit for Discharge. Typically, the data exhibit regular patterns and seasonal trends and can be impacted by external factors such as the weather or major incidents. The COVID pandemic is an extreme instance of the latter and the behaviour of sample data changed dramatically. The capacity to quickly adapt to these changes is crucial and is a factor that shows better results for GRNN in both accuracy and reliability.

scholarly journals The CSS and The Two-Staged Methods for Parameter Estimation in SARFIMA Models

2011 ◽  
Vol 2011 ◽  
pp. 1-11 ◽  
Author(s):  
Erol Egrioglu ◽  
Cagdas Hakan Aladag ◽  
Cem Kadilar
Keyword(s):  
Time Series ◽  
Parameter Estimation ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Simulation Study ◽  
Long Memory ◽  
Moving Average ◽  
Mean Square ◽  
Sample Sizes ◽  
Advantages And Disadvantages

Seasonal Autoregressive Fractionally Integrated Moving Average (SARFIMA) models are used in the analysis of seasonal long memory-dependent time series. Two methods, which are conditional sum of squares (CSS) and two-staged methods introduced by Hosking (1984), are proposed to estimate the parameters of SARFIMA models. However, no simulation study has been conducted in the literature. Therefore, it is not known how these methods behave under different parameter settings and sample sizes in SARFIMA models. The aim of this study is to show the behavior of these methods by a simulation study. According to results of the simulation, advantages and disadvantages of both methods under different parameter settings and sample sizes are discussed by comparing the root mean square error (RMSE) obtained by the CSS and two-staged methods. As a result of the comparison, it is seen that CSS method produces better results than those obtained from the two-staged method.

PERAMALAN TINGKAT PENGANGGURAN DI INDONESIA MENGGUNAKAN METODE TIME SERIES DENGAN MODEL ARIMA DAN HOLT-WINTERS

2021 ◽  
Vol 26 (1) ◽  
pp. 13-28
Author(s):  
Agus Sulaiman ◽  
Asep Juarna
Keyword(s):  
Time Series ◽  
Mean Square Error ◽  
Moving Average ◽  
Exponential Smoothing ◽  
Mean Square ◽  
Autoregressive Integrated Moving Average ◽  
Model Time Series

Beberapa penyebab terjadinya pengangguran di Indonesia ialah, tingkat urbanisasi, tingkat industrialisasi, proporsi angkatan kerja SLTA dan upah minimum provinsi. Faktor-faktor tersebut turut serta mempengaruhi persentase data terkait tingkat pengangguran menjadi sedikit fluktuatif. Berdasarkan pergerakan persentase data tersebut, diperlukan sebuah prediksi untuk mengetahui persentase tingkat pengangguran di masa depan dengan menggunakan konsep peramalan. Pada penelitian ini, peneliti melakukan analisis peramalan time series menggunakan metode Box-Jenkins dengan model Autoregressive Integrated Moving Average (ARIMA) dan metode Exponential Smoothing dengan model Holt-Winters. Pada penelitian ini, peramalan dilakukan dengan menggunakan dataset tingkat pengangguran dari tahun 2005 hingga 2019 per 6 bulan antara Februari hingga Agustus. Peneliti akan melihat evaluasi Range Mean Square Error (RMSE) dan Mean Square Error (MSE) terkecil dari setiap model time series. Berdasarkan hasil penelitian, ARIMA(0,1,12) menjadi model yang terbaik untuk metode Box-Jenkins sedangkan Holt-Winters dengan alpha(mean) = 0.3 dan beta(trend) = 0.4 menjadi yang terbaik pada metode Exponential Smoothing. Pemilihan model terbaik dilanjutkan dengan perbandingan nilai akurasi RMSE dan MSE. Pada model ARIMA(0,1,12) nilai RMSE = 1.01 dan MSE = 1.0201, sedangkan model Holt-Winters menghasilkan nilai RMSE = 0.45 dan MSE = 0.2025. Berdasarkan data tersebut terpilih model Holt-Winters sebagai model terbaik untuk peramalan data tingkat pengangguran di Indonesia.

scholarly journals FAKTOR – FAKTOR YANG MEMPENGARUHI KONSUMSI GAS DI INDONESIA

2021 ◽  
Vol 3 (2) ◽  
pp. 69
Author(s):  
Rohim Rohim ◽  
Mike Triani
Keyword(s):  
Time Series ◽  
World Bank ◽  
Time Series Data ◽  
Secondary Data ◽  
Series Data ◽  
Industrial Growth ◽  
A Value ◽  
The World Bank ◽  
The World ◽  
Gas Consumption

The purpose of this research is to determine (1) the effect of income on gas consumption in Indonesia (2) the effect of population on gas consumption in Indonesia (3) the effect of industrial growth on gas consumption in Indonesia. This type of research is descriptive and associative. The data used in this research is secondary data from Indonesia in the form of time series data from 1970 to 2019 and this data was obtained from official institutions of the World Bank and BP Statistic World. The data were processed using multiple linear regression. The results showed that the income had a negative and significant effect on gas consumption with a probability value of 0.0005 <0.05, the population had a positive and significant effect on gas consumption with a value of prob t-count of 0.0010 <0.05 and industrial growth had a positive and significant effect on gas consumption.  The significant to gas consumption in Indonesia with a value of prob t-count value of 0.5219 <0.05 and suggestions for further researchers to be able to analyze other factors that affecting gas consumption in Indonesia.  Because from the gas sectors, there are still many factors that affected gas consumption until the research results will be better

Sign in / Sign up

Export Citation Format

Share Document