Grzegorz Dudek- Professor
- Professor (Full) at Częstochowa University of Technology
Grzegorz Dudek
- Professor
- Professor (Full) at Częstochowa University of Technology
machine learning, neural networks, artificial intelligence, time series forecasting
About
131
Publications
74,814
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,493
Citations
Introduction
I am a Professor at the Department of Electrical Engineering, Czestochowa University of Technology, Poland. My research interests include pattern recognition, machine learning, artificial intelligence, and their application in classification, regression and optimization problems.
Current institution
Publications
Publications (131)
This paper introduces the Hierarchical Kolmogorov-Arnold Network (HKAN), a novel network architecture that offers a competitive alternative to the recently proposed Kolmogorov-Arnold Network (KAN). Unlike KAN, which relies on backpropagation, HKAN adopts a randomized learning approach, where the parameters of its basis functions are fixed, and line...
This paper presents an enhanced N-BEATS model, N-BEATS*, for improved mid-term electricity load forecasting (MTLF). Building on the strengths of the original N-BEATS architecture, which excels in handling complex time series data without requiring preprocessing or domain-specific knowledge, N-BEATS* introduces two key modifications. (1) A novel los...
In this study, we delve into the realm of meta-learning to combine point base forecasts for probabilistic short-term electricity demand forecasting. Our approach encompasses the utilization of quantile linear regression, quantile regression forest, and post-processing techniques involving residual simulation to generate quantile forecasts. Furtherm...
Machine learning (ML) algorithms can handle complex genomic data and identify predictive patterns that may not be apparent through traditional statistical methods. They become popular tools for medical applications including prediction, diagnosis or treatment of complex diseases like rheumatoid arthritis (RA). RA is an autoimmune disease in which g...
Rheumatoid arthritis (RA) is an autoimmune disease characterized by chronic inflammation affecting up to 2.0% of adults around the world. The molecular background of RA has not yet been fully elucidated, but RA is classified as a disease in which the genetic background is one of the most significant risk factors. One hallmark of RA is impaired DNA...
In this study, we explore meta-learning for combining forecasts derived from individual base models for both deterministic and probabilistic short-term load forecasting. Unlike conventional approaches that rely on straightforward averaging, we harness the power of machine learning to implement more advanced methods for combining forecasts through m...
Forecasting cryptocurrency volatility can help investors make better-informed investment decisions in order to minimize risks and maximize potential profits. Accurate forecasting of cryptocurrency price fluctuations is crucial for effective portfolio management and contributes to the stability of the financial system by identifying potential threat...
This paper compares recurrent neural networks (RNNs) with different types of gated cells for forecasting time series with multiple seasonality. The cells we compare include classical long short-term memory (LSTM), gated recurrent unit (GRU), modified LSTM with dilation, and two new cells we proposed recently, which are equipped with dilation and at...
The decomposition of a time series is an essential task that helps to understand its very nature. It facilitates the analysis and forecasting of complex time series expressing various hidden components such as the trend, seasonal components, cyclic components and irregular fluctuations. Therefore, it is crucial in many fields for forecasting and de...
This paper proposes a novel ensemble forecasting method that combines randomized neural networks (RandNNs) and seasonal-trend-dispersion decomposition (STD) in four different ways to construct ensembles for time series with multiple seasonal patterns. We evaluate the performance of the proposed ensemble methods on short-term load forecasting proble...
The realm of machine learning (ML) is one of the most dynamic and compellingdomains within the computing landscape today [...]
Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This article proposes a novel hybrid hierarchical deep-learning (DL) model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoot...
In this paper, we propose a method for combining forecasts generated by different models based on long short-term memory (LSTM) ensemble learning. While typical approaches for combining forecasts involve simple averaging or linear combinations of individual forecasts, machine learning techniques enable more sophisticated methods of combining foreca...
In this paper, we introduce a new approach to multivariate forecasting cryptocurrency prices using a hybrid contextual model combining exponential smoothing (ES) and recurrent neural network (RNN). The model consists of two tracks: the context track and the main track. The context track provides additional information to the main track, extracted f...
This paper presents a comprehensive study of statistical and machine learning methods for predicting daily and weekly volatility of the following four cryptocurrencies: Bitcoin, Ethereum, Litecoin, and Monero. Several methods, i.e., HAR, ARFIMA, GARCH, LASSO, ridge regression, SVR, MLP, fuzzy neighbourhood model, random forest, and LSTM, are compar...
A modern power system is a complex network of interconnected components, such as generators, transmission lines, and distribution subsystems, that are designed to provide electricity to consumers in an efficient and reliable manner [...]
In this paper, we propose a new short-term load forecasting (STLF) model based on contextually enhanced hybrid and hierarchical architecture combining exponential smoothing (ES) and a recurrent neural network (RNN). The model is composed of two simultaneously trained tracks: the context track and the main track. The context track introduces additio...
Skuteczne prognozowanie procesów ekonomicznych i finansowych ma fundamentalne znaczenie dla uczestników i analityków życia gospodarczego. Jednocześnie jednak można wskazać wiele obszarów, gdzie wciąż brakuje narzędzi prognostycznych, dających wyniki o zadowalającej trafności. Z tego względu trwają nieustanne prace nad nowymi koncepcjami metodologic...
Random forest (RF) is one of the most popular machine learning (ML) models used for both classification and regression problems. As an ensemble model, it demonstrates high predictive accuracy and low variance, while being easy to learn and optimize. In this study, we use RF for short-term load forecasting (STLF), focusing on data representation and...
The decomposition of a time series is an essential task that helps to understand its very nature. It facilitates the analysis and forecasting of complex time series expressing various hidden components such as the trend, seasonal components, cyclic components and irregular fluctuations. Therefore, it is crucial in many fields for forecasting and de...
This paper compares recurrent neural networks (RNNs) with different types of gated cells for forecasting time series with multiple seasonality. The cells we compare include classical long short term memory (LSTM), gated recurrent unit (GRU), modified LSTM with dilation, and two new cells we proposed recently, which are equipped with dilation and at...
Time series forecasting is a challenging problem particularly when a time series expresses multiple seasonality, nonlinear trend and varying variance. In this work, to forecast complex time series, we propose ensemble learning which is based on randomized neural networks, and boosted in three ways. These comprise ensemble learning based on residual...
Short-term load forecasting (STLF) is a challenging problem due to the complex nature of the time series expressing multiple seasonality and varying variance. This paper proposes an extension of a hybrid forecasting model combining exponential smoothing and dilated recurrent neural network (ES-dRNN) with a mechanism for dynamic attention. We propos...
Machine learning (ML) is one of the most exciting fields of computing today [...]
Time series forecasting is a challenging problem particularly when a time series expresses multiple seasonality, nonlinear trend and varying variance. In this work, to forecast complex time series, we propose ensemble learning which is based on randomized neural networks, and boosted in three ways. These comprise ensemble learning based on residual...
In this work, we propose an ensemble forecasting approach based on randomized neural networks. Improved randomized learning streamlines the fitting abilities of individual learners by generating network parameters adjusted to the target function complexity. A pattern-based time series representation makes the ensemble model suitable for forecasting...
Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This paper proposes a novel hybrid hierarchical deep learning model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (E...
This work contributes to the development of a new data-driven method (D-DM) of feedforward neural networks (FNNs) learning. This method was proposed recently as a way of improving randomized learning of FNNs by adjusting the network parameters to the target function fluctuations. The method employs logistic sigmoid activation functions for hidden n...
This work contributes to the development of neural forecasting models with novel randomization-based learning methods. These methods improve the fitting abilities of the neural model, in comparison to the standard method, by generating network parameters in accordance with the data and target function features. A pattern-based representation of tim...
There is an issue with the way in which feedforward neural networks with random hidden nodes generate random parameters in order to obtain a good projection space. Typically, random weights and biases are both drawn from the same interval, which is misguided as they have different functions. Recently, more sophisticated methods of random parameters...
In this work, we propose an ensemble forecasting approach based on randomized neural networks. Improved randomized learning streamlines the fitting abilities of individual learners by generating network parameters in accordance with the data and target function features. A pattern-based representation of time series makes the proposed approach suit...
This work contributes to the development of a new data-driven method (D-DM) of feedforward neural networks (FNNs) learning. This method was proposed recently as a way of improving randomized learning of FNNs by adjusting the network parameters to the target function fluctuations. The method employs logistic sigmoid activation functions for hidden n...
Feedforward neural networks are widely used as universal predictive models to fit data distribution. Common gradient-based learning, however, suffers from many drawbacks making the training process ineffective and time-consuming. Alternative randomized learning does not use gradients but selects hidden node parameters randomly. This makes the train...
This work contributes to the development of neural forecasting models with novel randomization-based learning methods. These methods improve the fitting abilities of the neural model, in comparison to the standard method, by generating network parameters in accordance with the data and target function features. A pattern-based representation of tim...
This paper addresses the mid-term electricity load forecasting problem. Solving this problem is necessary for power system operation and planning as well as for negotiating forward contracts in deregulated energy markets. We show that our proposed deep neural network modeling approach based on the deep neural architecture is effective at solving th...
Forecasting time series with multiple seasonal cycles such as short-term load forecasting is a challenging problem due to the complicated relationship between input and output data. In this work, we use a pattern representation of the time series to simplify this relationship. A neural network trained on patterns is an easier task to solve. Thus, i...
Pattern similarity-based frameworks are widely used for classification and regression problems. Repeated, similar-shaped cycles observed in seasonal time series encourage the use of such frameworks for forecasting. In this paper, we use pattern similarity-based models for mid-term load forecasting. An integral part of these models is the use of pat...
This work presents a hybrid and hierarchical deep learning model for midterm load forecasting. The model combines exponential smoothing (ETS), advanced long short-term memory (LSTM), and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multilayer LSTM is equ...
This work presents an extended hybrid and hierarchical deep learning model for electrical energy consumption forecasting. The model combines initial time series (TS) decomposition, exponential smoothing (ETS) for forecasting trend and dispersion components, ETS for deseasonalization, advanced long short-term memory (LSTM), and ensembling. Multi-lay...
The standard method of generating random weights and biases in feedforward neural networks with random hidden nodes selects them both from the uniform distribution over the same fixed interval. In this work, we show the drawbacks of this approach and propose new methods of generating random parameters. These methods ensure the most nonlinear fragme...
This work presents ensemble forecasting of monthly electricity demand using pattern similarity-based forecasting methods (PSFMs). PSFMs applied in this study include k-nearest neighbor model, fuzzy neighborhood model, kernel regression model, and general regression neural network. An integral part of PSFMs is a time series representation using patt...
A random vector functional link network (RVFL) is widely used as a universal approximator for classification and regression problems. The big advantage of RVFL is fast training without backpropagation. This is because the weights and biases of hidden nodes are selected randomly and stay untrained. Recently, alternative architectures with randomized...
We address the mid-term electricity load forecasting (MTLF) problem. This problem is relevant and challenging. On the one hand, MTLF supports high-level (e.g. country level) decision-making at distant planning horizons (e.g. month, quarter, year). Therefore, financial impact of associated decisions may be significant and it is desirable that they b...
This work presents a Long Short-Term Memory (LSTM) network for forecasting a monthly electricity demand time series with a one-year horizon. The novelty of this work is the use of pattern representation of the seasonal time series as an alternative to decomposition. Pattern representation simplifies the complex nonlinear and nonstationary time seri...
Many forecasting models are built on neural networks. The key issues in these models, which strongly translate into the accuracy of forecasts, are data representation and the decomposition of the forecasting problem. In this work, we consider both of these problems using short-term electricity load demand forecasting as an example. A load time seri...
A random vector functional link network (RVFL) is widely used as a universal approximator for classification and regression problems. The big advantage of RVFL is fast training without backpropagation. This is because the weights and biases of hidden nodes are selected randomly and stay untrained. Recently, alternative architectures with randomized...
This work presents a hybrid and hierarchical deep learning model for mid-term load forecasting. The model combines exponential smoothing (ETS), advanced Long Short-Term Memory (LSTM) and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multi-layer LSTM is eq...
This work presents ensemble forecasting of monthly electricity demand using pattern similarity-based forecasting methods (PSFMs). PSFMs applied in this study include $k$-nearest neighbor model, fuzzy neighborhood model, kernel regression model, and general regression neural network. An integral part of PSFMs is a time series representation using pa...
Pattern similarity-based methods are widely used in classification and regression problems. Repeated, similar-shaped cycles observed in seasonal time series encourage to apply these methods for forecasting. In this paper we use the pattern similarity-based methods for forecasting monthly electricity demand expressing annual seasonality. An integral...
https://wydawnictwo.umk.pl/pl/products/5432/uczenie-maszynowe-w-podejmowaniu-decyzji-prognostycznych
Feedforward neural networks with random hidden nodes suffer from a problem with the generation of random weights and biases as these are difficult to set optimally to obtain a good projection space. Typically, random parameters are drawn from an interval which is fixed before or adapted during the learning process. Due to the different functions of...
The standard method of generating random weights and biases in feedforward neural networks with random hidden nodes, selects them both from the uniform distribution over the same fixed interval. In this work, we show the drawbacks of this approach and propose a new method of generating random parameters. This method ensures the most nonlinear fragm...
In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions from an interval adjusted to the target function, then randomly rotates the activation functions, and finally...
Randomized methods of neural network learning suffer from a problem with the generation of random parameters as they are difficult to set optimally to obtain a good projection space. The standard method draws the parameters from a fixed interval which is independent of the data scope and activation function type. This does not lead to good results...
Randomized algorithms for learning feedforward neural networks are increasingly used in practice. They offer very speed training because the only parameters that are learned are the output weights. Parameters of hidden neurons are generated randomly once and need not to be adjusted. The key issue in randomized learning algorithms is to generate par...
Medium-term electric energy demand forecasting is coming a key tool for energy management, power system operation and maintenance scheduling. This paper offers a solution to forecasting monthly electricity demand based on multilayer perceptron model which approximates a relationship between historical and future demand patterns. Energy demand time...
In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions from an interval adjusted to the target function, then randomly rotates the activation functions, and finally...
Improving reliability of a power network is an issue of great importance for power distribution companies. The aim stated by the President of Energy Regulatory Office to improve the reliability of the distribution network includes steps towards improving the monitoring and control of the network managed by distribution companies. Ensuring continuit...
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping are set randomly and are not le...
Medium-term electric energy demand forecasting is becoming an essential tool for energy management, maintenance scheduling, power system planning and operation. In this work we propose Generalized Regression Neural Network as a model for monthly electricity demand forecasting. This is a memory-based, fast learned and easy tuned type of neural netwo...
The Theta method attracted the attention of researchers and practitioners in recent years due to its simplicity and superior forecasting accuracy. Its performance has been confirmed by many empirical studies as well as forecasting competitions. In this article the Theta method is tested in short-term load forecasting problem. The load time series e...
Improving reliability of a power network is an issue of great importance for power distribution companies. The aim stated by the President of Energy Regulatory Office to improve the reliability of the distribution network includes steps towards improving the monitoring and control of the network managed by distribution companies. Ensuring continuit...
Active thermography is a highly efficient and powerful technique that enables us to detect the subsurface defects by heating the investigated material sample and recording the thermal response using an infrared camera. In this work a simple variant of the time-resolved infrared radiometry method was used. The study was conducted for a sample made o...
Medium-term electric energy demand forecasting plays an important role in power system planning and operation as well as for negotiation forward contracts. This paper proposes a solution to medium-term energy demand forecasting that covers definition of input and output variables and the forecasting model based on a neuro-fuzzy system. As predictor...
Multivariate regression tree methodology is used for forecasting time series with multiple seasonal cycles. Unlike typical regression trees, which generate only one output, multivariate approach generates many outputs in the same time, which represent the forecasts for subsequent time-points. In the proposed approach a time series is represented by...
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping are set randomly and are not le...
Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping are set randomly and are not le...
This paper presents stochastic optimization algorithms for learning Generalized Regression Neural Network which is used as a patternbased short-term load forecasting model. For adjustment of the model parameters four types of stochastic optimization methods are used: evolution strategies, differential evolution, particle swarm optimization and tour...
Electricity demand forecasting is of important role in power system planning and operation. In this work, fuzzy nearest neighbour regression has been utilised to estimate monthly electricity demands. The forecasting model was based on the pre-processed energy consumption time series, where input and output variables were defined as patterns represe...
In this work several univariate approaches for short-term load forecasting based on neural networks are proposed and compared. They include: multilayer perceptron, radial basis function neural network, generalized regression neural network, fuzzy counterpropagation neural networks, and self-organizing maps. A common feature of these methods is lear...
Energy and load demand forecasting in short-horizons, over an interval ranging from one hour to one week, is crucial for on-line scheduling and security functions of power system. Many load forecasting methods have been developed in recent years which are usually complex solutions with many adjustable parameters. Best-matching models and their rele...
In this work multi-model ensembles are proposed for short-term electricity demand forecasting. The ensembles are composed of ten members representing different model classes. The base models are integrated using simple averaging or dynamically weighted averaging, where weights depend on the model performance on the forecasting tasks similar to the...
Extreme learning machine is a new scheme for learning the feedforward neural network, where the input weights and biases determining the nonlinear feature mapping are initiated randomly and are not learned. In this work, we analyze approximation ability of the extreme learning machine depending on the activation function type and ranges from which...
This paper proposes a forecasting approach based on a feedforward neural network for probabilistic electricity price forecasting for GEFCom2014. The approach does not require any special data preprocessing, such as detrending, deseasonality or decomposition of the time series. The input variables, zonal and system loads are processed nonlinearly by...
In this paper univariate models for short-term load forecasting based on linear regression and patterns of daily cycles of load time series are proposed. The patterns used as input and output variables simplify the forecasting problem by filtering out the trend and seasonal variations of periods longer than the daily one. The nonstationarity in mea...
In this paper, a new forecasting model based on artificial immune system (AIS) is proposed. The model is used for short-term electrical load forecasting as an example of forecasting time series with multiple seasonal cycles. Artificial immune system learns to recognize antigens (AGs) representing two fragments of the time series: 1) fragment preced...
Load forecasting is an integral problem in the power system operation, planning and maintenance. The article presents the principles of the pattern similarity-based methods for short-term load forecasting. A common feature of these methods is learning from the data and using similarities between patterns of the seasonal cycles of the load time seri...
Load forecasting is an integral problem in the power system operation, planning and maintenance. The article presents the principles of the pattern similarity-based methods for short-term load forecasting. A common feature of these methods is learning from the data and using similarities between patterns of the seasonal cycles of the load time seri...
In this article we present the idea of short-term load cross-forecasting. This approach combines forecasts generated by two models which learn on input data defined in different ways: as daily and weekly patterns. Pattern definitions described in this work simplify the forecasting problem by filtering out the trend and seasonal variations. The nons...
Questions
Questions (6)
Randomized learning of feedforward NNs was proposed as an alternative to gradient-based learning which is known to be time-consuming, sensitive to the initial parameter values and unable to cope with local minima of the loss function. In randomized learning, the parameters of the hidden nodes are selected randomly and stay fixed. Only the output weights are learned. This makes an optimization problem convex and allows us to solve it without tedious gradient descent backpropagation, using a standard linear least-squares method. This leads to very fast training. The main problem in randomized learning is how to select the random parameters to ensure the high performance of NN.
Your opinions, experiences, and solutions?
