Loading [MathJax]/extensions/MathZoom.js
Bogdan M. Wilamowski - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Bogdan M. Wilamowski

Also published under: Bogdan Wilamowski, B. M. Wilamowski, B. Wilamowski, Bodgan M. Wilamowski, B. A. Wilamowski

Publications
178
Citations
3,970
Publications by Year
19772022
Co-Authors:
Show All Co-Authors (132)
Image of author Bogdan M. Wilamowski

Bogdan M. Wilamowski

Also published under: Bogdan Wilamowski, B. M. Wilamowski, B. Wilamowski, Bodgan M. Wilamowski, B. A. Wilamowski

Affiliation

Department of Electrical and Computer Engineering
Auburn University
Auburn, AL, USA
University of Information Technology and Management, Rzeszow, Poland

Publication Topics

Biography

Bogdan M. Wilamowski (Life Fellow, IEEE) received the M.S. degree in computer engineering, the Ph.D. degree in neural computing, and the Habilitation degree in integrated circuit design from the Gdansk University of Technology, Gdansk, Poland, in 1966, 1970, and 1977, respectively. He was the Director of the Alabama Micro/Nano Science and Technology Center, Auburn University, Auburn, AL, USA, from 2003 to 2016, where he is currently a Professor Emeritus with the Department of Electrical and Computer Engineering. He is also with The University of Information Technology and Management, Rzeszow, Poland. He was the Editor-in-Chief of the IEEE Transactions on Industrial Electronics from 2007 to 2010 and the IEEE Transactions on Industrial Inform...
Publications
178
Citations
3,970
Publications by Year
19772022
Co-Authors:
Show All Co-Authors (132)
Author's Published Works

Showing 1-25 of 178 results

  • Sort

Filter Results

Show

Sort By

Results

Pre-Trained Models for Non-Intrusive Appliance Load Monitoring

Lingxiao Wang;Shiwen Mao;Bogdan M. Wilamowski;Robert M. Nelms

IEEE Transactions on Green Communications and Networking
Year: 2022 | Volume: 6, Issue: 1 | Journal Article |
Cited by: Papers (31)
Non-intrusive load monitoring (NILM) is to estimate individual appliance’s power consumption from aggregated smart meter data, which is useful for optimized energy management and provisioning of customized services. While deep learning (DL) has achieved state-of-the-art NILM performance, it is still constrained by the dependency on large amounts of data and intensive computations on training. In t...Show More

Pre-Trained Models for Non-Intrusive Appliance Load Monitoring

Lingxiao Wang;Shiwen Mao;Bogdan M. Wilamowski;Robert M. Nelms

Year: 2022 | Volume: 6, Issue: 1 | Journal Article |

Ensemble Learning for Load Forecasting

Lingxiao Wang;Shiwen Mao;Bogdan M. Wilamowski;R. M. Nelms

IEEE Transactions on Green Communications and Networking
Year: 2020 | Volume: 4, Issue: 2 | Journal Article |
Cited by: Papers (52)
In this paper, an ensemble learning approach is proposed for load forecasting in urban power systems. The proposed framework consists of two levels of learners that integrate clustering, Long Short-Term Memory (LSTM), and a Fully Connected Cascade (FCC) neural network. Historical load data is first partitioned by a clustering algorithm to train multiple LSTM models in the level-one learner, and th...Show More

Ensemble Learning for Load Forecasting

Lingxiao Wang;Shiwen Mao;Bogdan M. Wilamowski;R. M. Nelms

Year: 2020 | Volume: 4, Issue: 2 | Journal Article |

Approximation-based Estimation of Learning Rate for Error Back Propagation Algorithm

Pawel Rozycki;Janusz Kolbusz;Grzegorz Krzos;Bogdan M. Wilamowski

2019 IEEE 23rd International Conference on Intelligent Engineering Systems (INES)
Year: 2019 | Conference Paper |
Cited by: Papers (1)
The paper presents a new method for improvement of the Error Back Propagation, one of the most popular algorithms for training artificial neural networks, that is based on the estimation of the learning rate by the approximation of the error of the output error. Experimental studies confirming the effectiveness of the applied method of improving the network learning effectiveness have been present...Show More

Approximation-based Estimation of Learning Rate for Error Back Propagation Algorithm

Pawel Rozycki;Janusz Kolbusz;Grzegorz Krzos;Bogdan M. Wilamowski

Year: 2019 | Conference Paper |

The Impact of Architecture on the Deep Neural Networks Training

Pawel Rozycki;Janusz Kolbusz;Aleksander Malinowski;Bogdan Wilamowski

2019 12th International Conference on Human System Interaction (HSI)
Year: 2019 | Conference Paper |
Deep neural networks are able to solve much more complex and nonlinear problems than very popular but shallow technologies such as ELM, SVR or SLP. Despite of their power deep neural networks are difficult to apply due to problems with effective and successful training caused by `vanishing' problem. The paper shows that these problems can be reduced by using appropriate network architecture. The p...Show More

The Impact of Architecture on the Deep Neural Networks Training

Pawel Rozycki;Janusz Kolbusz;Aleksander Malinowski;Bogdan Wilamowski

Year: 2019 | Conference Paper |

Effective Training of RBF Networks

Pawel Rozycki;Janusz Kolbusz;Aleksander Malinowski;Bogdan M. Wilamowski

2019 12th International Conference on Human System Interaction (HSI)
Year: 2019 | Conference Paper |
RBF networks seem to be an interesting and efficient alternative for traditional sigmoid-based neural networks. More sophisticated activation function makes a network more powerful but requires developing of new training methods. The paper presents a new more efficient training algorithm based on the second-order constructive ErrCor (Error Correction) algorithm. The effectiveness of the proposed a...Show More

Effective Training of RBF Networks

Pawel Rozycki;Janusz Kolbusz;Aleksander Malinowski;Bogdan M. Wilamowski

Year: 2019 | Conference Paper |

Short-Term Load Forecasting with LSTM Based Ensemble Learning

Lingxiao Wang;Shiwen Mao;Bogdan Wilamowski

2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
Year: 2019 | Conference Paper |
Cited by: Papers (12)
In this paper, a short-term load forecasting framework with long short-term memory (LSTM)-based ensemble learning is proposed. To fully exploit the correlation in data for accurate load forecasting, the data is first clustered and each cluster is used to train an LSTM model. Then a Fully Connected Cascade (FCC) Neural Network is incorporated for ensemble learning, which is solved by an enhanced Le...Show More

Short-Term Load Forecasting with LSTM Based Ensemble Learning

Lingxiao Wang;Shiwen Mao;Bogdan Wilamowski

Year: 2019 | Conference Paper |

Error Back Propagation Algorithm with Adaptive Learning Rate

Janusz Kolbusz;Pawel Rozycki;Oleksandr Lysenko;Bogdan M. Wilamowski

2019 International Conference on Information and Digital Technologies (IDT)
Year: 2019 | Conference Paper |
Cited by: Papers (4)
Error Back Propagation algorithm is one of the most popular method for training artificial neural networks. Unfortunately, this is also one of the slowest due to constant and small learning rate parameter used to update weights of neurons. There are therefore many methods for dynamic change this parameter in the adaptive manner. In this paper has been presented new method based on estimation of le...Show More

Error Back Propagation Algorithm with Adaptive Learning Rate

Janusz Kolbusz;Pawel Rozycki;Oleksandr Lysenko;Bogdan M. Wilamowski

Year: 2019 | Conference Paper |

Neural Network Training With Levenberg–Marquardt and Adaptable Weight Compression

James S. Smith;Bo Wu;Bogdan M. Wilamowski

IEEE Transactions on Neural Networks and Learning Systems
Year: 2019 | Volume: 30, Issue: 2 | Journal Article |
Cited by: Papers (71)
Difficult experiments in training neural networks often fail to converge due to what is known as the flat-spot problem, where the gradient of hidden neurons in the network diminishes in value, rending the weight update process ineffective. Whereas a first-order algorithm can address this issue by learning parameters to normalize neuron activations, the second-order algorithms cannot afford additio...Show More

Neural Network Training With Levenberg–Marquardt and Adaptable Weight Compression

James S. Smith;Bo Wu;Bogdan M. Wilamowski

Year: 2019 | Volume: 30, Issue: 2 | Journal Article |

Implementation of Deep Neural Networks for Industry Applications

Pawel Rozycki;Janusz Kolbusz;Grzegorz Krzos;Bogdan M. Wilamowski

IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society
Year: 2018 | Conference Paper |
Cited by: Papers (5)
Deep learning become a popular trend in current research and applications. Deep neural networks are important part of this trend. The paper shows the effect of neural network architecture on its power and capacity for solving complex, nonlinear problems. The problem has been analyzed using trigonometric, polynomial and digital approaches. Presented analysis show that the network capacity increases...Show More

Implementation of Deep Neural Networks for Industry Applications

Pawel Rozycki;Janusz Kolbusz;Grzegorz Krzos;Bogdan M. Wilamowski

Year: 2018 | Conference Paper |

Nonlinear System Modeling Using RBF Networks for Industrial Application

Xi Meng;Pawel Rozycki;Jun-Fei Qiao;Bogdan M. Wilamowski

IEEE Transactions on Industrial Informatics
Year: 2018 | Volume: 14, Issue: 3 | Journal Article |
Cited by: Papers (78)
Radial basis function (RBF) networks, because of their universal approximation ability, have been widely applied to industrial process modeling. In this study, an Improved ErrCor (IErrCor) algorithm-an extension of error correction (ErrCor) algorithm-is proposed, in which compact structure and satisfactory generalization ability can be obtained with only one learning try. First, a second-order-bas...Show More

Nonlinear System Modeling Using RBF Networks for Industrial Application

Xi Meng;Pawel Rozycki;Jun-Fei Qiao;Bogdan M. Wilamowski

Year: 2018 | Volume: 14, Issue: 3 | Journal Article |

A Fast Density and Grid Based Clustering Method for Data With Arbitrary Shapes and Noise

Bo Wu;Bogdan M. Wilamowski

IEEE Transactions on Industrial Informatics
Year: 2017 | Volume: 13, Issue: 4 | Journal Article |
Cited by: Papers (79)
This paper presents a density- and grid- based (DGB) clustering method for categorizing data with arbitrary shapes and noise. As most of the conventional clustering approaches work only with round-shaped clusters, other methods are needed to be explored to proceed classification of clusters with arbitrary shapes. Clustering approach by fast search and find of density peaks and density-based spatia...Show More

A Fast Density and Grid Based Clustering Method for Data With Arbitrary Shapes and Noise

Bo Wu;Bogdan M. Wilamowski

Year: 2017 | Volume: 13, Issue: 4 | Journal Article |

An efficient grid-based clustering method by finding density peaks

Bo Wu;B. M. Wilamowski

IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society
Year: 2016 | Conference Paper |
Clustering or categorizing an unprocessed data set is essential and critical in many areas. Much success has been published, which first needs to calculate the mutual distances between data points. It suffers from considerable computational costs, preventing the state-of-the-art methods such as the clustering method by fast search and find of density peaks (FSFDP, published in Science, 2014) from ...Show More

An efficient grid-based clustering method by finding density peaks

Bo Wu;B. M. Wilamowski

Year: 2016 | Conference Paper |

Big data and deep learning

B. M. Wilamowski;Bo Wu;Janusz Korniak

2016 IEEE 20th Jubilee International Conference on Intelligent Engineering Systems (INES)
Year: 2016 | Conference Paper |
Cited by: Papers (7)
Traditional data processing algorithms are usually not capable to process big data. As matter of fact, usually big data is being defined as such which cannot be processed with traditional techniques. At the same time a progress of technology makes that humans are now overwhelm by big data. One way of processing big data is to use deep neural networks, which are difficult to train so often a combin...Show More

Big data and deep learning

B. M. Wilamowski;Bo Wu;Janusz Korniak

Year: 2016 | Conference Paper |

Estimation of deep neural networks capabilities based on a trigonometric approach

P. Rózycki;J. Kolbusz;B.M. Wilamowski

2016 IEEE 20th Jubilee International Conference on Intelligent Engineering Systems (INES)
Year: 2016 | Conference Paper |
Cited by: Papers (5)
The rapid development of computing machines led to renewed interest in deep neural networks. For years it is known that they have a great possibilities, but to use them new training algorithms are required. The paper shows benefits for deep neural networks usage by analysis of the Fourier series approximation of the activation function for shallow and deep neural network architectures. The propose...Show More

Estimation of deep neural networks capabilities based on a trigonometric approach

P. Rózycki;J. Kolbusz;B.M. Wilamowski

Year: 2016 | Conference Paper |

Performance Enhancement in Bipolar Junction Transistors Using Uniaxial Stress on (100) Silicon

P. Gnanachchelvi;R. C. Jaeger;B. M. Wilamowski;G. Niu;S. Hussain;J. C. Suhling;M. C. Hamilton

IEEE Transactions on Electron Devices
Year: 2016 | Volume: 63, Issue: 7 | Journal Article |
Cited by: Papers (4)
This paper demonstrates that collector current ( $I_{C}$ ), dc current gain ( $\beta $ ), cutoff frequency ( $f_{T}$ ), and maximum oscillation frequency ( $f_{\max }$ ) of bipolar transistors (BJTs) can be improved by uniaxial stress. A unified modeling approach that includes a piezoresistive model for changes in mobility and a deformation potential model for changes in intrinsic carrier concentr...Show More

Performance Enhancement in Bipolar Junction Transistors Using Uniaxial Stress on (100) Silicon

P. Gnanachchelvi;R. C. Jaeger;B. M. Wilamowski;G. Niu;S. Hussain;J. C. Suhling;M. C. Hamilton

Year: 2016 | Volume: 63, Issue: 7 | Journal Article |

Linearization of Bipolar Amplifiers Based on Neural-Network Training Algorithm

Zhan Su;Janusz Kolbusz;Bogdan M. Wilamowski

IEEE Transactions on Industrial Electronics
Year: 2016 | Volume: 63, Issue: 6 | Journal Article |
Cited by: Papers (8)
Traditional bipolar differential amplifiers have only a ±5-mV operational range with nonlinear distortion below 0.1 dB. In this paper, a linearization technique based on neural-network training algorithm is proposed to expand this 0.1-dB linear region to a much wider ±200-mV range. Compared with the traditional and recent state-ofthe-art techniques for linearization, where gain or noise performanc...Show More

Linearization of Bipolar Amplifiers Based on Neural-Network Training Algorithm

Zhan Su;Janusz Kolbusz;Bogdan M. Wilamowski

Year: 2016 | Volume: 63, Issue: 6 | Journal Article |

Nearest-Neighbor Spline Approximation (NNSA) Improvement to TSK Fuzzy Systems

Jordan Richardson;Janusz Korniak;Philip D. Reiner;Bogdan M. Wilamowski

IEEE Transactions on Industrial Informatics
Year: 2016 | Volume: 12, Issue: 1 | Journal Article |
Cited by: Papers (10)
In this paper, we propose two versions of an improved defuzzification technique for Takagi Sugeno Kang (TSK) fuzzy systems (FSs) based on local third-order approximations. The presented nearest-neighbor spline approximation algorithms (NNSA1 and NNSA2) use the concept of a zeroth-order TSK FS and produce smooth surfaces with increased accuracy. The proposed methods are tested on a variety of funct...Show More

Nearest-Neighbor Spline Approximation (NNSA) Improvement to TSK Fuzzy Systems

Jordan Richardson;Janusz Korniak;Philip D. Reiner;Bogdan M. Wilamowski

Year: 2016 | Volume: 12, Issue: 1 | Journal Article |

An algorithm for visualization of big data in a two-dimensional space

Bo Wu;B. M. Wilamowski

IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society
Year: 2015 | Conference Paper |
Cited by: Papers (2)
In this paper, a new algorithm for visualization of high-multidimensional data is described. The algorithm follows several steps. At first, centers representing several categories are selected, and Euclidean distances between these centers are calculated in a high-dimensional space. Then these centers are placed in a 2-dimensional space in such a way that distances in this 2-dimensional space are ...Show More

An algorithm for visualization of big data in a two-dimensional space

Bo Wu;B. M. Wilamowski

Year: 2015 | Conference Paper |

Single-DC-source 7-level CHB inverter with multicarrier level-shifted PWM

Hani Vahedi;Mohammad Sharifzadeh;Kamal Al-Haddad;Bogdan M. Wilamowski

IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society
Year: 2015 | Conference Paper |
Cited by: Papers (27)
This paper presents a 7-level cascaded H-bridge (CHB) multilevel inverter using a single DC source. The second DC bus is a capacitor that its voltage is controlled by switching sequences. The capacitor voltage is regulated at half of the DC source amplitude to have seven voltage levels at the output. Seven voltage levels include each DC bus voltage, their sum and subtraction. Switching pattern is ...Show More

Single-DC-source 7-level CHB inverter with multicarrier level-shifted PWM

Hani Vahedi;Mohammad Sharifzadeh;Kamal Al-Haddad;Bogdan M. Wilamowski

Year: 2015 | Conference Paper |

Characterization of residual stress levels in complementary bipolar junction transistors on (100) silicon

R. C. Jaeger;S. Hussain;G. Niu;P. Gnanachchelvi;J. C. Suhling;B. M. Wilamowski;M. C. Hamilton

2015 IEEE Bipolar/BiCMOS Circuits and Technology Meeting - BCTM
Year: 2015 | Conference Paper |
Cited by: Papers (3)
Residual levels of stress remaining after device fabrication have been characterized in the base and emitter regions of shallow-trench-isolated complementary npn and pnp transistors on (100) silicon utilizing uniaxial stress measurements. A residual biaxial stress of approximately 160 MPa has been found in the active regions of the npn transistors, whereas negligible residual stress is observed in...Show More

Characterization of residual stress levels in complementary bipolar junction transistors on (100) silicon

R. C. Jaeger;S. Hussain;G. Niu;P. Gnanachchelvi;J. C. Suhling;B. M. Wilamowski;M. C. Hamilton

Year: 2015 | Conference Paper |

A 0.8–3GHz wideband folded down-converter with noise cancellation in 0.18um SiGe technology

Zhan Su;Fa Foster Dai;B.M. Wilamowski;Michael Hamilton;Wei Zhou;Yudong Wang;Jun Fu

2015 IEEE Bipolar/BiCMOS Circuits and Technology Meeting - BCTM
Year: 2015 | Conference Paper |
Cited by: Papers (2)
This paper proposes a wideband low-noise down converter with operational frequency ranging from 0.8-3GHz in 0.18μm SiGe technology. The down converter is based on a double balanced Gilbert cell configuration with folded structure to lower the supply voltage. The folded structure also allows separate bias for the mixer and the gm stages to optimizing their performances. Bipolar based gm cell with n...Show More

A 0.8–3GHz wideband folded down-converter with noise cancellation in 0.18um SiGe technology

Zhan Su;Fa Foster Dai;B.M. Wilamowski;Michael Hamilton;Wei Zhou;Yudong Wang;Jun Fu

Year: 2015 | Conference Paper |

Dedicated deep neural network architectures and methods for their training

P. Różycki;J. Kolbusz;B.M. Wilamowski

2015 IEEE 19th International Conference on Intelligent Engineering Systems (INES)
Year: 2015 | Conference Paper |
Cited by: Papers (9)
Deep neural networks are currently very popular trend in artificial intelligence. While such networks are very powerful they are difficult in training. The paper discusses capabilities of different neural network architectures and presents the proposition of new multilayer architecture with additional connections across layers, called Bridged MLP, that is much easier to train that traditional MLP ...Show More

Dedicated deep neural network architectures and methods for their training

P. Różycki;J. Kolbusz;B.M. Wilamowski

Year: 2015 | Conference Paper |

Learning architectures with enhanced capabilities and easier training

Bogdan M. Wilamowski;Janusz Korniak

2015 IEEE 19th International Conference on Intelligent Engineering Systems (INES)
Year: 2015 | Conference Paper |
Cited by: Papers (6)
Although discovery of the Error Back Propagation (EBP) learning algorithm was a real breakthrough, this is not only a very slow algorithm, but it also is not capable of training networks with super compact architecture. The most noticeable progress was done with an adaptation of the LM algorithm to neural network training. The LM algorithm is capable of training networks with 100 to 1000 fewer ite...Show More

Learning architectures with enhanced capabilities and easier training

Bogdan M. Wilamowski;Janusz Korniak

Year: 2015 | Conference Paper |

An improved English to Chinese translation of technical text

Xiangyu Zhang;Sihan Tao;Zhitao Gong;Bo Wu;Ruixin Wang;Bogdan M. Wilamowski

2015 IEEE 19th International Conference on Intelligent Engineering Systems (INES)
Year: 2015 | Conference Paper |
The English to Chinese automatic translators cannot always satisfy the requirement of users especially in technical fields. Through research, the main reason is wrong translation of technical terminologies. The researchers summarized common mistakes of technical translation. Then developed an IE (Industrial Electronics) dictionary that is a professional technical dictionary correcting the wrong tr...Show More

An improved English to Chinese translation of technical text

Xiangyu Zhang;Sihan Tao;Zhitao Gong;Bo Wu;Ruixin Wang;Bogdan M. Wilamowski

Year: 2015 | Conference Paper |

Adaptive integratable hardware realization of analog neural networks for nonlinear system

Zhan Su;Bogdan M. Wilamowski;Ruixin Wang;Fa Foster Dai

2015 IEEE 13th International Conference on Industrial Informatics (INDIN)
Year: 2015 | Conference Paper |
Cited by: Papers (2)
This paper presents the adaptive analog hardware implementation of a MLP (multilayer perceptron architecture) ANN (artificial neural networks) for online nonlinear system operation. Neurons are implemented by bipolar differential pairs with tangent hyperbolic activation function. A bipolar current multiplier and a linearized differential amplifier are proposed for storing and adjusting the weights...Show More

Adaptive integratable hardware realization of analog neural networks for nonlinear system

Zhan Su;Bogdan M. Wilamowski;Ruixin Wang;Fa Foster Dai

Year: 2015 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.