Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Computation, Validation and Optimization in Machine Learning for Time Series...
share announcement

Computation, Validation and Optimization in Machine Learning for Time Series Forecasting

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Mathematics and Computer Science".

Deadline for manuscript submissions: closed (30 March 2023) | Viewed by 12434

Special Issue Editors

Prof. Dr. Panagiotis Pintelas

E-Mail Website
Guest Editor
Department of Mathematics, University of Patras, GR 265-00 Patras, Greece
Interests: software engineering; AI in education; intelligent systems; decision support systems; machine learning; data mining; knowledge discovery
Prof. Dr. Stavros Stavroyiannis

E-Mail Website
Guest Editor
Department of Accounting & Finance, University of Peloponnese, GR 241-00 Antikalamos, Greece
Interests: financial econometrics; financial engineering and risk management; fractals and multifractals in finance; chaotic systems; computational mathematics and nonlinear algorithms
Dr. Ioannis E. Livieris

E-Mail Website1 Website2
Co-Guest Editor
Department of Mathematics, University of Patras, GR 265-00 Patras, Greece
Interests: artificial intelligence; machine learning; neural networks; deep learning; optimization algorithms
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Time-series forecasting has been generally recognized as a significant and challenging area of research with respect to the demand for handling the increasing availability of new data of time series. Over the last two decades, the advancements in digital technology and the vigorous development of the Internet have led to the development of large repositories of time-series data, resulting in a wide range of research applications. Many fields of study, ranging from healthcare, finance, and signal processing to cyber security, require time-series analysis and forecasting. However, time-series forecasting and analysis are considered significantly complex and challenging tasks. Therefore, more sophisticated and revolutionary approaches, such as deep learning, have recently been adopted for learning spatiotemporal time-series data and addressing real-world forecasting time-series problems.

The main aim of this Special Issue is to gather a collection of articles reflecting the latest advances related to all time-series forecasting methodologies and investigate the impact of their application on an array of real-world problems.

Prof. Dr. Panagiotis Pintelas
Prof. Dr. Stavros Stavroyiannis
Dr. Ioannis E. Livieris
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 submissions that pass pre-check are 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. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). 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

  • time-series forecasting and analysis
  • univariate and multivariate time series
  • time-series modeling
  • data analytics
  • big data
  • deep learning
  • advanced machine learning
  • interpretability for reliability and trust in time-series forecasting
  • clustering algorithms for time-series data
  • clustering analysis
  • autoencoders

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 3035 KiB  
Article
Variational Bayesian Network with Information Interpretability Filtering for Air Quality Forecasting
by Xue-Bo Jin, Zhong-Yao Wang, Wen-Tao Gong, Jian-Lei Kong, Yu-Ting Bai, Ting-Li Su, Hui-Jun Ma and Prasun Chakrabarti
Mathematics 2023, 11(4), 837; https://0-doi-org.brum.beds.ac.uk/10.3390/math11040837 - 07 Feb 2023
Cited by 32 | Viewed by 2213
Abstract
Air quality plays a vital role in people’s health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal [...] Read more.
Air quality plays a vital role in people’s health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal and spatial dimensions. Deep models, with their ability to model strong nonlinearities, have become the primary methods for air quality forecasting. However, because of the lack of mechanism-based analysis, uninterpretability forecasting makes decisions risky, especially when the government makes decisions. This paper proposes an interpretable variational Bayesian deep learning model with information self-screening for PM2.5 forecasting. Firstly, based on factors related to PM2.5 concentration, e.g., temperature, humidity, wind speed, spatial distribution, etc., an interpretable multivariate data screening structure for PM2.5 forecasting was established to catch as much helpful information as possible. Secondly, the self-screening layer was implanted in the deep learning network to optimize the selection of input variables. Further, following implantation of the screening layer, a variational Bayesian gated recurrent unit (GRU) network was constructed to overcome the complex distribution of PM2.5 and achieve accurate multi-step forecasting. The high accuracy of the proposed method is verified by PM2.5 data in Beijing, China, which provides an effective way, with multiple factors for PM2.5 forecasting determined using deep learning technology. Full article
(This article belongs to the Special Issue Computation, Validation and Optimization in Machine Learning for Time Series Forecasting)
►▼ Show Figures

Figure 1

23 pages, 3903 KiB  
Article
A Comparative Study of Forecasting Electricity Consumption Using Machine Learning Models
by Madeline Hui Li Lee, Yee Chee Ser, Ganeshsree Selvachandran, Pham Huy Thong, Le Cuong, Le Hoang Son, Nguyen Trung Tuan and Vassilis C. Gerogiannis
Mathematics 2022, 10(8), 1329; https://0-doi-org.brum.beds.ac.uk/10.3390/math10081329 - 17 Apr 2022
Cited by 19 | Viewed by 4339
Abstract
Production of electricity from the burning of fossil fuels has caused an increase in the emission of greenhouse gases. In the long run, greenhouse gases cause harm to the environment. To reduce these gases, it is important to accurately forecast electricity production, supply [...] Read more.
Production of electricity from the burning of fossil fuels has caused an increase in the emission of greenhouse gases. In the long run, greenhouse gases cause harm to the environment. To reduce these gases, it is important to accurately forecast electricity production, supply and consumption. Forecasting of electricity consumption is, in particular, useful for minimizing problems of overproduction and oversupply of electricity. This research study focuses on forecasting electricity consumption based on time series data using different artificial intelligence and metaheuristic methods. The aim of the study is to determine which model among the artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), least squares support vector machines (LSSVMs) and fuzzy time series (FTS) produces the highest level of accuracy in forecasting electricity consumption. The variables considered in this research include the monthly electricity consumption over the years for different countries. The monthly electricity consumption data for seven countries, namely, Norway, Switzerland, Malaysia, Egypt, Algeria, Bulgaria and Kenya, for 10 years were used in this research. The performance of all of the models was evaluated and compared using error metrics such as the root mean squared error (RMSE), average forecasting error (AFE) and performance parameter (PP). The differences in the results obtained via the different methods are analyzed and discussed, and it is shown that the different models performed better for different countries in different forecasting periods. Overall, it was found that the FTS model performed the best for most of the countries studied compared to the other three models. The research results can allow electricity management companies to have better strategic planning when deciding on the optimal levels of electricity production and supply, with the overall aim of preventing surpluses or shortages in the electricity supply. Full article
(This article belongs to the Special Issue Computation, Validation and Optimization in Machine Learning for Time Series Forecasting)
►▼ Show Figures

Figure 1

14 pages, 2326 KiB  
Article
Fuzzy Algebraic Modeling of Spatiotemporal Timeseries’ Paradoxes in Cosmic Scale Kinematics
by Lazaros Iliadis
Mathematics 2022, 10(4), 622; https://0-doi-org.brum.beds.ac.uk/10.3390/math10040622 - 17 Feb 2022
Cited by 3 | Viewed by 1255
Abstract
This paper introduces the prototype of a generic fuzzy algebraic framework, that aims to serve as a holistic modeling approach of kinematics. Moreover, it detects paradoxes and uncertainties when the involved features of the timeseries have “unconventional” values. All well accepted models are [...] Read more.
This paper introduces the prototype of a generic fuzzy algebraic framework, that aims to serve as a holistic modeling approach of kinematics. Moreover, it detects paradoxes and uncertainties when the involved features of the timeseries have “unconventional” values. All well accepted models are perfectly capturing and clearly describing the spatiotemporal characteristics of a moving object’s (MO) status, when its actual distance from the observer is conventional, i.e., “insignificant compared to the magnitude of light years”. Let us consider the concept that emerges by the following Boolean expression1 (BE1): “Velocity is significant compared to the speed of light (SIV_cSL) AND distance between observer and moving body is significant compared to light years (SID_cLY)”. The only restriction in the above BE1 Boolean expression is that velocity would always be less than C. So far, BE1 is not considered to be true in the models that are employed to build our scientific physics studies. This modeling effort performs mining of kinematics phenomena for which BE1 is true. This approach is quite innovative, in the sense that it reveals paradoxes and uncertainties, and it reaches the following conclusions: When a particle is moving inside hypersurfaces characterized by any type of BE1′s negation, our existing kinematics’ models can survive. In the opposite case, we are gradually led to paradoxes and uncertainties. The gradual and smooth transition from the one state to the other as well as the importance of the aforementioned limitations, can be inferred-modeled by employing fuzzy logic. Full article
(This article belongs to the Special Issue Computation, Validation and Optimization in Machine Learning for Time Series Forecasting)
►▼ Show Figures

Figure 1

22 pages, 14157 KiB  
Article
CL-Net: ConvLSTM-Based Hybrid Architecture for Batteries’ State of Health and Power Consumption Forecasting
by Noman Khan, Ijaz Ul Haq, Fath U Min Ullah, Samee Ullah Khan and Mi Young Lee
Mathematics 2021, 9(24), 3326; https://0-doi-org.brum.beds.ac.uk/10.3390/math9243326 - 20 Dec 2021
Cited by 22 | Viewed by 3526
Abstract
Traditional power generating technologies rely on fossil fuels, which contribute to worldwide environmental issues such as global warming and climate change. As a result, renewable energy sources (RESs) are used for power generation where battery energy storage systems (BESSs) are widely used to [...] Read more.
Traditional power generating technologies rely on fossil fuels, which contribute to worldwide environmental issues such as global warming and climate change. As a result, renewable energy sources (RESs) are used for power generation where battery energy storage systems (BESSs) are widely used to store electrical energy for backup, match power consumption and generation during peak hours, and promote energy efficiency in a pollution-free environment. Accurate battery state of health (SOH) prediction is critical because it plays a key role in ensuring battery safety, lowering maintenance costs, and reducing BESS inconsistencies. The precise power consumption forecasting is critical for preventing power shortage and oversupply, and the complicated physicochemical features of batteries dilapidation cannot be directly acquired. Therefore, in this paper, a novel hybrid architecture called ‘CL-Net’ based on convolutional long short-term memory (ConvLSTM) and long short-term memory (LSTM) is proposed for multi-step SOH and power consumption forecasting. First, battery SOH and power consumption-related raw data are collected and passed through a preprocessing step for data cleansing. Second, the processed data are fed into ConvLSTM layers, which extract spatiotemporal features and form their encoded maps. Third, LSTM layers are used to decode the encoded features and pass them to fully connected layers for final multi-step forecasting. Finally, a comprehensive ablation study is conducted on several combinations of sequential learning models using three different time series datasets, i.e., national aeronautics and space administration (NASA) battery, individual household electric power consumption (IHEPC), and domestic energy management system (DEMS). The proposed CL-Net architecture reduces root mean squared error (RMSE) up to 0.13 and 0.0052 on the NASA battery and IHEPC datasets, respectively, compared to the state-of-the-arts. These experimental results show that the proposed architecture can provide robust and accurate SOH and power consumption forecasting compared to the state-of-the-art. Full article
(This article belongs to the Special Issue Computation, Validation and Optimization in Machine Learning for Time Series Forecasting)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop