Special Issue "Applications of Forecasting by Hybrid Artificial Intelligent Technologies"

A special issue of Forecasting (ISSN 2571-9394).

Deadline for manuscript submissions: 31 December 2018

Special Issue Editors

Guest Editor
Prof. Dr. Wei-Chiang Hong

Department of Information Management, Oriental Institute of Technology, No. 58, Sec. 2, Sichuan Rd., Panchiao, Taipei, 220, Taiwan
Website | E-Mail
Interests: computational intelligence (neural networks; evolutionary computation); application of forecasting technology (ARIMA; support vector regression; chaos theory)
Guest Editor
Assoc. Prof. Dr. Ming-Wei Li

College of Shipbuilding Engineering, Harbin Engineering University, Harbin, 150001, P. R. China
Website | E-Mail
Guest Editor
Dr. Yi Liang

School of Economics and Management, North China Electric Power University, Beijing 102206, P. R. China
E-Mail
Guest Editor
Dr. Guo-Feng Fan

College of Mathematics & Statistics, Pingdingshan University, Henan, 467000, P. R. China
E-Mail

Special Issue Information

Dear Colleagues,

Applications of hybridizing artificial intelligent technologies have been widely explored to address the complicated and nonlinear relationships among forecasting targets and other relevant factors. More accurate, or more precise, forecasts are required for decisions making in competitive environments. The development of hybrid artificial intelligent technologies would strongly support experts in any forecasting field to improve accuracy. In addition, this is of special relevance in the big data era, these data usually have dynamic, nonlinear complicate characteristics. Therefore, the forecasting models have often resulted in over-reliance on the use of informal judgments and higher expenses if lacking the ability to determine the data pattern. The novel applications of hybrid artificially intelligent technologies can provide more satisfactory performances.

This Special Issue aims to attract both academic researchers and practitioners from a wide range of forecasting fields, from engineering, operations research, economic, and also management. The so-called hybrid model means that some process of the former model is integrated into the process of the later one, for example, hybrid A and B implies some processes of A are controlled by A, some by B. Based on the definition of hybrid model, specifically, we are interested in contributions towards the development of all artificial intelligent technologies hybridizing with each other (as shown in the second keyword), or hybridizing novel intelligent tools with existing algorithms or existing models to improve or overcome the embedded drawbacks (as shown in the fourth keyword), or hybridizing with other novel methods, such as chaos theory, fuzzy theory, cloud theory, quantum behavior, and so on (as shown in the fifth and eighth keywords) to significantly improve forecasting accuracy.

All submissions should be based on the applications of the mentioned approaches and the developed models should also be presented with a corresponding theoretical sound framework, lacking such a scientific approach is discouraged. Validation support of existing/presented approaches is encouraged to be done using real practical applications.

Prof. Dr. Wei-Chiang Hong
Assoc. Prof. Dr. Ming-Wei Li
Dr. Yi Liang
Dr. Guo-Feng Fan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Forecasting is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) is waived for well-prepared manuscripts submitted to this issue. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  1. Statistical forecasting models (ARIMA; SARIMA; ARMAX; multi-variate regression; Kalman filter; exponential smoothing; and so on);
  2. Hybrid evolutionary algorithms (including genetic algorithm, simulated annealing algorithm, particle swarm optimization, ant colony optimization, immune algorithm, artificial bee colony algorithm, etc.) in forecasting applications;
  3. Theoretical comparison and empirical comparison of hybrid evolutionary algorithms and original evolutionary algorithms in forecasting applications;
  4. Hybridizing chaotic mapping functions (including logistic mapping, cat mapping, Tent mapping, and An mapping, etc.) with evolutionary algorithms or forecasting models in forecasting applications;
  5. Hybridizing fuzzy theory and fuzzy inference systems with evolutionary algorithms or forecasting models in forecasting applications;
  6. Hybridizing artificial neural networks with evolutionary algorithms or forecasting models in forecasting applications;
  7. Hybridizing knowledge-based expert systems with evolutionary algorithms or forecasting models in forecasting applications;
  8. Hybridizing novel intelligent technologies (including wavelet transform, chaos theory, cloud theory, quantum theory) with evolutionary algorithms or forecasting models in forecasting applications.

Published Papers (2 papers)

View options order results:
result details:
Displaying articles 1-2
Export citation of selected articles as:

Research

Open AccessArticle Fast Univariate Time Series Prediction of Solar Power for Real-Time Control of Energy Storage System
Forecasting 2018, 1(1), 107-120; https://doi.org/10.3390/forecast1010008
Received: 17 July 2018 / Revised: 13 September 2018 / Accepted: 13 September 2018 / Published: 17 September 2018
PDF Full-text (1747 KB) | HTML Full-text | XML Full-text
Abstract
In this paper, super-short-term prediction of solar power generation for applications in dynamic control of energy system has been investigated. In order to follow and satisfy the dynamics of the controller, the deployed prediction method should have a fast response time. To this
[...] Read more.
In this paper, super-short-term prediction of solar power generation for applications in dynamic control of energy system has been investigated. In order to follow and satisfy the dynamics of the controller, the deployed prediction method should have a fast response time. To this end, this paper proposes fast prediction methods to provide the control system with one step ahead of solar power generation. The proposed methods are based on univariate time series prediction. That is, instead of using external data such as the weather forecast as the input of prediction algorithms, they solely rely on past values of solar power data, hence lowering the volume and acquisition time of input data. In addition, the selected algorithms are able to generate the forecast output in less than a second. The proposed methods in this paper are grounded on four well-known prediction algorithms including Autoregressive Integrated Moving Average (ARIMA), K-Nearest Neighbors (kNN), Support Vector Regression (SVR), and Random Forest (RF). The speed and accuracy of the proposed algorithms have been compared based on two different error measures, Mean Absolute Error (MAE) and Symmetric Mean Absolute Percentage Error (SMAPE). Real world data collected from the PV installation at the University of California, Riverside (UCR) are used for prediction purposes. The results show that kNN and RF have better predicting performance with respect to SMAPE and MAE criteria. Full article
Figures

Figure 1

Open AccessArticle Forecasting International Tourism Demand Using a Non-Linear Autoregressive Neural Network and Genetic Programming
Forecasting 2018, 1(1), 90-106; https://doi.org/10.3390/forecast1010007
Received: 17 August 2018 / Revised: 10 September 2018 / Accepted: 10 September 2018 / Published: 13 September 2018
PDF Full-text (1398 KB) | HTML Full-text | XML Full-text
Abstract
This study explores the forecasting ability of two powerful non-linear computational methods: artificial neural networks and genetic programming. We use as a case of study the monthly international tourism demand in Spain, approximated by the number of tourist arrivals and of overnight stays.
[...] Read more.
This study explores the forecasting ability of two powerful non-linear computational methods: artificial neural networks and genetic programming. We use as a case of study the monthly international tourism demand in Spain, approximated by the number of tourist arrivals and of overnight stays. The forecasting results reveal that non-linear methods achieve slightly better predictions than those obtained by a traditional forecasting technique, the seasonal autoregressive integrated moving average (SARIMA) approach. This slight forecasting improvement was close to being statistically significant. Forecasters must judge whether the high cost of implementing these computational methods is worthwhile. Full article
Figures

Figure 1

Back to Top