Feature Extraction (Pattern Detection) Methods in Pattern Recognition

Deterioration of structures due to aging, cumulative crack growth or excessive response significantly affects the performance and safety of structures during their service life. Recently, signal-based methods have received many attentions for structural health monitoring and damage detection. These methods examine changes in the features derived directly from the measured time histories or their corresponding spectra through proper signal processing methods and algorithms to detect damage. Based on different signal processing techniques for feature extraction, these methods are classified into time-domain methods, frequency-domain methods, and time-frequency (or time-scale)-domain methods. As an enhancement for feature extraction, selection and classification, pattern recognition techniques are deeply integrated into signal-based damage detection. This paper provided an overview of these methods based on two aspects: (1) feature extraction and selection, and (2) pattern recognition. Signal-based methods are particularly more effective for structures with complicated nonlinear behavior and the incomplete, incoherent, and noise-contaminated measurements of structural response.

Download Full-text

Quantization-Based Novel Extraction Method Of EEG Signal For Classification

JELIKU (Jurnal Elektronik Ilmu Komputer Udayana) ◽

10.24843/jlk.2020.v09.i02.p02 ◽

2020 ◽

Vol 9 (2) ◽

pp. 169

Author(s):

Ni Putu Dewi Angreni ◽

Agus Muliantara ◽

Yuriko Christian

Keyword(s):

Pattern Recognition ◽

Feature Extraction ◽

Extraction Process ◽

Point Of View ◽

Eeg Signal ◽

Signal Quantization ◽

Analysis Process ◽

Signal Features ◽

Artificial Neural Network Classifier ◽

Extraction Pattern

In the pattern recognition field, features or object’s characteristics are one of the key points to recognizing them. The feature extraction process will see that objects have different features, where the features are obtained through the analysis process from the extractor, such as for data statistics, energy, power spectral, and so on. This study aims to enrich the point of view of EEG signal features by quantifying the signal. It will be analyzed whether the features obtained by quantization represent the EEG signal object from different viewpoints. This research uses the DEAP dataset, with the result being a feature vector that will be included in the artificial neural network classifier using the Keras library. The experiment carried out is to try to enter quantized and Non-quantized feature vectors into the classifier. As a result, the accuracy of the classification process with the quantization vector was 75%, and the accuracy in the Non-quantized vector classification process was only 58%. These results indicate the EEG signal quantization feature can represent the EEG signal object. Keywords: EEG signal, quantization, DEAP, feature extraction, pattern recognition

Download Full-text

A review on the pattern detection methods for epilepsy seizure detection from EEG signals

Biomedical Engineering / Biomedizinische Technik ◽

10.1515/bmt-2017-0233 ◽

2019 ◽

Vol 64 (5) ◽

pp. 507-517 ◽

Cited By ~ 4

Author(s):

Ashok Sharmila ◽

Purusothaman Geethanjali

Keyword(s):

Pattern Recognition ◽

Epileptic Seizures ◽

Seizure Detection ◽

Pattern Detection ◽

Detection Methods ◽

Eeg Signals ◽

Research Papers ◽

Eeg Data ◽

Different Characteristics ◽

Electroencephalogram Eeg

Abstract Over several years, research had been conducted for the detection of epileptic seizures to support an automatic diagnosis system to comfort the clinicians’ encumbrance. In this regard, a number of research papers have been published for the identification of epileptic seizures. A thorough review of all these papers is required. So, an attempt has been made to review on the pattern detection methods for epilepsy seizure detection from EEG signals. More than 150 research papers have been discussed to determine the techniques for detecting epileptic seizures. Further, the literature review confirms that the pattern recognition techniques required to detect epileptic seizures varies across the electroencephalogram (EEG) datasets of different conditions. This is mostly owing to the fact that EEG detected under different conditions have different characteristics. This consecutively necessitates the identification of the pattern recognition technique to efficiently differentiate EEG epileptic data from the EEG data of various conditions.

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

Deep Recurrent Neural Networks for Automatic Detection of Sleep Apnea from Single Channel Respiration Signals

Sensors ◽

10.3390/s20185037 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5037

Author(s):

Hisham ElMoaqet ◽

Mohammad Eid ◽

Martin Glos ◽

Mutaz Ryalat ◽

Thomas Penzel

Keyword(s):

Feature Extraction ◽

Sleep Apnea ◽

Short Term Memory ◽

Single Channel ◽

Automated Detection ◽

Detection Methods ◽

Short Term ◽

Term Memory ◽

Deep Recurrent Neural Network ◽

Long Short Term Memory

Sleep apnea is a common sleep disorder that causes repeated breathing interruption during sleep. The performance of automated apnea detection methods based on respiratory signals depend on the signals considered and feature extraction methods. Moreover, feature engineering techniques are highly dependent on the experts’ experience and their prior knowledge about different physiological signals and conditions of the subjects. To overcome these problems, a novel deep recurrent neural network (RNN) framework is developed for automated feature extraction and detection of apnea events from single respiratory channel inputs. Long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) are investigated to develop the proposed deep RNN model. The proposed framework is evaluated over three respiration signals: Oronasal thermal airflow (FlowTh), nasal pressure (NPRE), and abdominal respiratory inductance plethysmography (ABD). To demonstrate our results, we use polysomnography (PSG) data of 17 patients with obstructive, central, and mixed apnea events. Our results indicate the effectiveness of the proposed framework in automatic extraction for temporal features and automated detection of apneic events over the different respiratory signals considered in this study. Using a deep BiLSTM-based detection model, the NPRE signal achieved the highest overall detection results with true positive rate (sensitivity) = 90.3%, true negative rate (specificity) = 83.7%, and area under receiver operator characteristic curve = 92.4%. The present results contribute a new deep learning approach for automated detection of sleep apnea events from single channel respiration signals that can potentially serve as a helpful and alternative tool for the traditional PSG method.

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