The Bayes-Optimal Feature Extraction Procedure for Pattern Recognition Using Genetic Algorithm

The wavelet packet decomposition can be used to extract the frequency band containing bearing fault feature, because the fault signal can be decomposed into different frequency bands by using the wavelet packet decomposition, that is to say the optimal wavelet packet decomposition node needs to be found. A method applying the average Euclidean distance to find the optimal wavelet packet decomposition node was presented. First of all, the bearing fault signals were decomposed into three layers wavelet coefficients by which the bearing fault signals were reconstructed. The peak values extracted from the reconstructing signal spectrum constructed a feature space. Then, the minimum average Euclidean distance calculated from the feature space indicated the optimal wavelet packet node. The optimal feature space could be constructed by the feature points extracted from the signals reconstructed by the optimal wavelet packet nodes. Finally, the optimal feature space was used for the K-means clustering. The feature extraction and pattern recognition test of the four kinds of bearing conditions under four kinds of rotation speeds was detailed. The test results show this method, which can extract the bearing fault feature efficiently and make the fault feature space have the lowest within-class scatter, wons a high pattern recognition accuracy.

Download Full-text

Acceleration Feature Extraction of Human Body Based on Wearable Devices

Energies ◽

10.3390/en14040924 ◽

2021 ◽

Vol 14 (4) ◽

pp. 924

Author(s):

Zhenzhen Huang ◽

Qiang Niu ◽

Ilsun You ◽

Giovanni Pau

Keyword(s):

Genetic Algorithm ◽

Feature Extraction ◽

Kalman Filter ◽

Human Body ◽

Wearable Devices ◽

Human Motion ◽

Data Set ◽

Feature Extraction Method ◽

Motion Data ◽

Kalman Filter Algorithm

Wearable devices used for human body monitoring has broad applications in smart home, sports, security and other fields. Wearable devices provide an extremely convenient way to collect a large amount of human motion data. In this paper, the human body acceleration feature extraction method based on wearable devices is studied. Firstly, Butterworth filter is used to filter the data. Then, in order to ensure the extracted feature value more accurately, it is necessary to remove the abnormal data in the source. This paper combines Kalman filter algorithm with a genetic algorithm and use the genetic algorithm to code the parameters of the Kalman filter algorithm. We use Standard Deviation (SD), Interval of Peaks (IoP) and Difference between Adjacent Peaks and Troughs (DAPT) to analyze seven kinds of acceleration. At last, SisFall data set, which is a globally available data set for study and experiments, is used for experiments to verify the effectiveness of our method. Based on simulation results, we can conclude that our method can distinguish different activity clearly.

Download Full-text

A Genetic Algorithm Optimized RNN-LSTM Model for Remaining Useful Life Prediction of Turbofan Engine

Electronics ◽

10.3390/electronics10030285 ◽

2021 ◽

Vol 10 (3) ◽

pp. 285

Author(s):

Kwok Tai Chui ◽

Brij B. Gupta ◽

Pandian Vasant

Keyword(s):

Genetic Algorithm ◽

Feature Extraction ◽

Prediction Model ◽

Prediction Models ◽

Remaining Useful Life ◽

Prediction Algorithm ◽

Short Term ◽

Turbofan Engine ◽

Term Prediction ◽

Useful Life

Understanding the remaining useful life (RUL) of equipment is crucial for optimal predictive maintenance (PdM). This addresses the issues of equipment downtime and unnecessary maintenance checks in run-to-failure maintenance and preventive maintenance. Both feature extraction and prediction algorithm have played crucial roles on the performance of RUL prediction models. A benchmark dataset, namely Turbofan Engine Degradation Simulation Dataset, was selected for performance analysis and evaluation. The proposal of the combination of complete ensemble empirical mode decomposition and wavelet packet transform for feature extraction could reduce the average root-mean-square error (RMSE) by 5.14–27.15% compared with six approaches. When it comes to the prediction algorithm, the results of the RUL prediction model could be that the equipment needs to be repaired or replaced within a shorter or a longer period of time. Incorporating this characteristic could enhance the performance of the RUL prediction model. In this paper, we have proposed the RUL prediction algorithm in combination with recurrent neural network (RNN) and long short-term memory (LSTM). The former takes the advantages of short-term prediction whereas the latter manages better in long-term prediction. The weights to combine RNN and LSTM were designed by non-dominated sorting genetic algorithm II (NSGA-II). It achieved average RMSE of 17.2. It improved the RMSE by 6.07–14.72% compared with baseline models, stand-alone RNN, and stand-alone LSTM. Compared with existing works, the RMSE improvement by proposed work is 12.95–39.32%.

Download Full-text

Image Pattern Recognition Algorithm Based on Improved Genetic Algorithm

Journal of Physics Conference Series ◽

10.1088/1742-6596/1852/3/032038 ◽

2021 ◽

Vol 1852 (3) ◽

pp. 032038

Author(s):

Qing Kuang

Keyword(s):

Genetic Algorithm ◽

Pattern Recognition ◽

Recognition Algorithm ◽

Improved Genetic Algorithm ◽

Pattern Recognition Algorithm ◽

Image Pattern

Download Full-text

Instrumental Odour Monitoring System Classification Performance Optimization by Analysis of Different Pattern-Recognition and Feature Extraction Techniques

Sensors ◽

10.3390/s21010114 ◽

2020 ◽

Vol 21 (1) ◽

pp. 114

Author(s):

Tiziano Zarra ◽

Mark Gino K. Galang ◽

Florencio C. Ballesteros ◽

Vincenzo Belgiorno ◽

Vincenzo Naddeo

Keyword(s):

Pattern Recognition ◽

Feature Extraction ◽

Performance Optimization ◽

Industrial Plant ◽

Mathematical Treatment ◽

Extraction Techniques ◽

Peak Period ◽

Linear Discriminant ◽

Artificial Neural

Instrumental odour monitoring systems (IOMS) are intelligent electronic sensing tools for which the primary application is the generation of odour metrics that are indicators of odour as perceived by human observers. The quality of the odour sensor signal, the mathematical treatment of the acquired data, and the validation of the correlation of the odour metric are key topics to control in order to ensure a robust and reliable measurement. The research presents and discusses the use of different pattern recognition and feature extraction techniques in the elaboration and effectiveness of the odour classification monitoring model (OCMM). The effect of the rise, intermediate, and peak period from the original response curve, in collaboration with Linear Discriminant Analysis (LDA) and Artificial Neural Networks (ANN) as a pattern recognition algorithm, were investigated. Laboratory analyses were performed with real odour samples collected in a complex industrial plant, using an advanced smart IOMS. The results demonstrate the influence of the choice of method on the quality of the OCMM produced. The peak period in combination with the Artificial Neural Network (ANN) highlighted the best combination on the basis of high classification rates. The paper provides information to develop a solution to optimize the performance of IOMS.

Download Full-text

Pattern recognition using multilayer neural-genetic algorithm

Neurocomputing ◽

10.1016/s0925-2312(02)00619-7 ◽

2003 ◽

Vol 51 ◽

pp. 237-247 ◽

Cited By ~ 26

Author(s):

Yas Abbas Alsultanny ◽

Musbah M. Aqel

Keyword(s):

Genetic Algorithm ◽

Pattern Recognition

Download Full-text

Research on Modulation Recognition Algorithm of Digital Communication Signal Based on Wavelet Denoising

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.608-609.459 ◽

2014 ◽

Vol 608-609 ◽

pp. 459-467 ◽

Cited By ~ 1

Author(s):

Xiao Yu Gu

Keyword(s):

Pattern Recognition ◽

Feature Extraction ◽

Decision Theory ◽

Recognition Rate ◽

Recognition Algorithm ◽

Modulation Recognition ◽

The Core ◽

Feature Parameters ◽

Communication Signal ◽

Modulation Signal

The paper researches a recognition algorithm of modulation signal and modulation modes. The modulation modes to be recognized include 2ASK, 2FSK, 2PSK, 4ASK, 4FSK and 4PSK modulation. There are two methods recognizing modulation modes of digital signal, method based on decision theory and pattern-recognition method based on feature extraction. The method based on decision theory is not suitable for recognition with multiple modulation modes. The core of pattern recognition based on feature extraction is selection of feature parameters. So the paper uses the feature parameters with simple calculation, easy to be implemented and high recognition rate as the core. The extraction of feature parameters is based on instant feature of modulation signal after Hilbert transformation.

Download Full-text