scholarly journals Demonstration of an open source platform for reproducible comparison of predictive models

2016 ◽  
Author(s):  
Neeraj Bokde ◽  
Kishore Kulat
Keyword(s):  
Moving Average ◽  
Time Series Prediction ◽  
Prediction Method ◽  
R Package ◽  
Autoregressive Integrated Moving Average ◽  
Imputation Methods ◽  
Time Consumption ◽  
Error Metrics ◽  
Pattern Sequence ◽  
State Of Art

This paper discusses about a tool PredictTestbench, which is an R package which provides a testbench to do comparison of prediction methods. This package compares a proposed time series prediction method with other default methods like Autoregressive integrated moving average (ARIMA) and Pattern Sequence based Forecasting (PSF). The testbench is not limited to these methods. It allows user to add or remove multiple numbers of methods in the existing methods in the study. By default, testbench compares different imputation methods considering different error metrics RMSE, MAE or MAPE. Along with this, it facilitates user to add new error metrics as per requirements. The simplicity of the package usage and significant reduction in efforts and time consumption in state of art procedure, adds valuable advantage to it. The aim of the testbench is reduce the efforts for coding, experiments on output visualization and time for different steps involved in such study. This paper explains the use of all functions in PredictTestbench package with the demonstration of examples.

scholarly journals Demonstration of an open source platform for reproducible comparison of predictive models

2016 ◽  
Author(s):  
Neeraj Bokde ◽  
Kishore Kulat
Keyword(s):  
Moving Average ◽  
Time Series Prediction ◽  
Prediction Method ◽  
R Package ◽  
Autoregressive Integrated Moving Average ◽  
Imputation Methods ◽  
Time Consumption ◽  
Error Metrics ◽  
Pattern Sequence ◽  
State Of Art

This paper discusses about a tool PredictTestbench, which is an R package which provides a testbench to do comparison of prediction methods. This package compares a proposed time series prediction method with other default methods like Autoregressive integrated moving average (ARIMA) and Pattern Sequence based Forecasting (PSF). The testbench is not limited to these methods. It allows user to add or remove multiple numbers of methods in the existing methods in the study. By default, testbench compares different imputation methods considering different error metrics RMSE, MAE or MAPE. Along with this, it facilitates user to add new error metrics as per requirements. The simplicity of the package usage and significant reduction in efforts and time consumption in state of art procedure, adds valuable advantage to it. The aim of the testbench is reduce the efforts for coding, experiments on output visualization and time for different steps involved in such study. This paper explains the use of all functions in PredictTestbench package with the demonstration of examples.

scholarly journals A Time Series Sustainability Assessment of a Partial Energy Portfolio Transition

Energies ◽  
2020 ◽  
Vol 14 (1) ◽  
pp. 141
Author(s):  
Jacob Hale ◽  
Suzanna Long
Keyword(s):  
Time Series ◽  
Electricity Generation ◽  
Sustainability Assessment ◽  
Moving Average ◽  
Time Series Prediction ◽  
State Level ◽  
Autoregressive Integrated Moving Average ◽  
Energy Transitions ◽  
Univariate Time Series ◽  
Partial Energy

Energy portfolios are overwhelmingly dependent on fossil fuel resources that perpetuate the consequences associated with climate change. Therefore, it is imperative to transition to more renewable alternatives to limit further harm to the environment. This study presents a univariate time series prediction model that evaluates sustainability outcomes of partial energy transitions. Future electricity generation at the state-level is predicted using exponential smoothing and autoregressive integrated moving average (ARIMA). The best prediction results are then used as an input for a sustainability assessment of a proposed transition by calculating carbon, water, land, and cost footprints. Missouri, USA was selected as a model testbed due to its dependence on coal. Of the time series methods, ARIMA exhibited the best performance and was used to predict annual electricity generation over a 10-year period. The proposed transition consisted of a one-percent annual decrease of coal’s portfolio share to be replaced with an equal share of solar and wind supply. The sustainability outcomes of the transition demonstrate decreases in carbon and water footprints but increases in land and cost footprints. Decision makers can use the results presented here to better inform strategic provisioning of critical resources in the context of proposed energy transitions.

scholarly journals Real-Time Forecasting of COVID-19 prevalence in India using ARIMA Model

2020 ◽  
Vol 4 (10) ◽  
pp. 78-83
Keyword(s):  
Time Series ◽  
Virus Disease ◽  
Moving Average ◽  
Time Series Prediction ◽  
Arima Model ◽  
Autoregressive Integrated Moving Average ◽  
Daily Data ◽  
The World ◽  
Increasing Trend ◽  
Short Term Prediction

Corona virus disease (COVID -19) has changed the world completely due to unavailability of its exact treatment. It has affected 215 countries in the world in which India is no exception where COVID patients are increasing exponentially since 15th of Feb. The objective of paper is to develop a model which can predict daily new cases in India. The autoregressive integrated moving average (ARIMA) models have been used for time series prediction. The daily data of new COVID-19 cases act as an exogenous variable in this framework. The daily data cover the sample period of 15th February, 2020 to 24th May, 2020. The time variable under study is a non-stationary series as 𝒚𝒕 is regressed with 𝒚𝒕−𝟏 and the coefficient is 1. The time series have clearly increasing trend. Results obtained revealed that the ARIMA model has a strong potential for short-term prediction. In PACF graph. Lag 1 and Lag 13 is significant. Regressed values implies Lag 1 and Lag 13 is significant in predicting the current values. The model predicted maximum COVID-19 cases in India at around 8000 during 5thJune to 20th June period. As per the model, the number of new cases shall start decreasing after 20th June in India only. The results will help governments to make necessary arrangements as per the estimated cases. The limitation of this model is that it is unable to predict jerks on either lower or upper side of daily new cases. So, in case of jerks re-estimation will be required.

Joint Network Traffic Forecast with ARIMA Models and Chaotic Models Based on Wavelet Analysis

2011 ◽  
Vol 55-57 ◽  
pp. 743-746 ◽  
Author(s):  
Ming Ke Dong ◽  
Chen Chen ◽  
Min Hua Huang ◽  
Ye Jin
Keyword(s):  
Network Traffic ◽  
Moving Average ◽  
Prediction Method ◽  
Arima Models ◽  
Self Similarity ◽  
Short Term ◽  
Autoregressive Integrated Moving Average ◽  
Linear Behavior ◽  
Forecast Result ◽  
Wavelet Multiresolution Analysis

In the recent study of network traffic, it is shown that the traffic flow presents both periodic and self-similar characteristics. Due to these two features, the short-term forecast of network traffic cannot be accurately fit in either autoregressive integrated moving average (ARIMA) models which is suitable for linear behavior, or chaotic models which is corresponding to self-similarity characteristic. In this paper, our methodology suggests that by using wavelet multiresolution analysis, we can obtain a joint short-term network traffic prediction method and get a more precise forecast result as compared to using either ARIMA models or chaotic models. We also run simulations to show the improvement of prediction accuracy of our proposed approach.

scholarly journals COVID-19 Infection Forecasting based on Deep Learning in Iran

2020 ◽  
Author(s):  
Mehdi Azarafza ◽  
Mohammad Azarafza ◽  
Jafar Tanha
Keyword(s):  
Short Term Memory ◽  
Mean Squared Error ◽  
Moving Average ◽  
National Level ◽  
Absolute Error ◽  
Percentage Error ◽  
Autoregressive Integrated Moving Average ◽  
Error Metrics ◽  
Squared Error ◽  
Better Than

Since December 2019 coronavirus disease (COVID-19) is outbreak from China and infected more than 4,666,000 people and caused thousands of deaths. Unfortunately, the infection numbers and deaths are still increasing rapidly which has put the world on the catastrophic abyss edge. Application of artificial intelligence and spatiotemporal distribution techniques can play a key role to infection forecasting in national and province levels in many countries. As methodology, the presented study employs long short-term memory-based deep for time series forecasting, the confirmed cases in both national and province levels, in Iran. The data were collected from February 19, to March 22, 2020 in provincial level and from February 19, to May 13, 2020 in national level by nationally recognised sources. For justification, we use the recurrent neural network, seasonal autoregressive integrated moving average, Holt winter's exponential smoothing, and moving averages approaches. Furthermore, the mean absolute error, mean squared error, and mean absolute percentage error metrics are used as evaluation factors with associate the trend analysis. The results of our experiments show that the LSTM model is performed better than the other methods on the collected COVID-19 dataset in Iran

Software Aging Forecast Using Recurrent SOM with Local Model

2020 ◽  
Vol 13 (1) ◽  
pp. 30-43
Author(s):  
Yongquan Yan
Keyword(s):  
Dimensional Space ◽  
Moving Average ◽  
Web Server ◽  
Prediction Method ◽  
Resource Consumption ◽  
Self Organizing Map ◽  
Autoregressive Integrated Moving Average ◽  
Software Aging ◽  
Space Vectors ◽  
Self Organizing

Studies of software aging problems are important since they are related to QoS. Previous studies have used many methods to guarantee QoS. In this article, a recurrent self-organizing map with multi-layerperceptron is proposed to forecast resource consumption in a web server which suffered from a software aging problem. First, a resource consumption series in a web server is split into p dimensional space vectors. Second, the split series is clustered into local sets by using a recurrent self-organizing map. Last, a local prediction method called multi-layerperceptron is used to predict on each local set. The results indicated that the recurrent self-organizing map with multi-layerperceptron generates a slightly better estimation than multi-layerperceptron and autoregressive integrated moving average in the resource consumption predictions of system and application level of web server.

scholarly journals Wind Wave Prediction by using Autoregressive Integrated Moving Average model : Case Study in Jakarta Bay

2019 ◽  
Vol 4 (2) ◽  
pp. 33 ◽  
Author(s):  
Didit Adytia ◽  
Alif Rizal Yonanta ◽  
Nugrahinggil Subasita
Keyword(s):  
Wind Wave ◽  
Moving Average ◽  
Arima Model ◽  
Prediction Method ◽  
Wave Model ◽  
Offshore Structures ◽  
Model Case ◽  
Autoregressive Integrated Moving Average ◽  
Wave Prediction ◽  
Short Term Prediction

Prediction of wind wave is highly needed to support safe navigation, especially for ship. Besides that, loading and unloading activities in a harbour, as well as for design purpose of coastal and offshore structures, data of prediction of wave height are needed. Based on its nature, the wind wave has random behaviour that is highly depending on behaviour of wind as the main driving force. In this paper, we propose a prediction method for wind wave by using Autoregressive Integrated Moving Average or ARIMA. To obtain historical data of wind wave, we perform  wave simulation by using a phase-averaged wave model SWAN (Simulating Wave Near Shore).  From the simulation, time series of wind wave is obtained. The prediction of wind wave is performed to calculate forecast of 24  hours ahead. Here, we perform wind wave prediction in a location in Jakarta Bay, Indonesia. We perform several combination of ARIMA model to obtain best fit model for wind wave prediction in the location in Jakarta Bay. Results of prediction show that ARIMA model give an accurate prediction especially for short term prediction.

scholarly journals Optimization of ARIMA Forecasting Model using Firefly Algorithm

2019 ◽  
Vol 13 (2) ◽  
pp. 127 ◽  
Author(s):  
Ilham Unggara ◽  
Aina Musdholifah ◽  
Anny Kartika Sari
Keyword(s):  
Time Series ◽  
Firefly Algorithm ◽  
Moving Average ◽  
Time Series Prediction ◽  
Arima Model ◽  
Information Criterion ◽  
Forecasting Model ◽  
Optimal Model ◽  
Autoregressive Integrated Moving Average ◽  
Foreign Tourist

 Time series prediction aims to control or recognize the behavior of the system based on the data in a certain period of time. One of the most widely used method in time series prediction is ARIMA (Autoregressive Integrated Moving Average). However, ARIMA has a weakness in determining the optimal model. firefly algorithm is used to optimize ARIMA model (p, d, q). by finding the smallest AIC (Akaike Information Criterion) value in determining the best ARIMA model. The data used in the study are daily stock data JCI period January 2013 until August 2016 and data of foreign tourist visits to Indonesia period January 1988 to November 2017.Based on testing, for JCI data, obtained predicted results with Box-Jenkins ARIMA model produces RMSE 49.72, whereas the prediction with the ARIMA Optimization model yielded RMSE 49.48. For the data of Foreign Tourist Visits, the predicted results with the Box-Jenkins ARIMA model resulted in RMSE 46088.9, whereas the predicted results with ARIMA optimization resulted in RMSE 44678.4. From these results it can be concluded that the optimization of ARIMA model with Firefly Algorithm produces better forecasting model than ARIMA model without Optimization.

Sign in / Sign up

Export Citation Format

Share Document