scholarly journals Multidimensional Features Extraction Methods in Frequency Domain

10.5772/36704 ◽  
2012 ◽  
Author(s):  
Jesus Olivares-Mercado ◽  
Gualberto Aguilar-Torres ◽  
Karina Toscano-Medina ◽  
Gabriel Sanchez-Perez ◽  
Mariko Nakano-Miyatake ◽  
...  
Keyword(s):  
Frequency Domain ◽  
Extraction Methods ◽  
Features Extraction

scholarly journals Evaluation of speech signal features extraction methods

2020 ◽  
Vol 2 (1) ◽  
pp. 69-78
Author(s):  
Ismail Shayeb ◽  
Naseem Asad ◽  
Ziad Alqadi ◽  
Qazem Jaber
Keyword(s):  
Speech Signal ◽  
High Speed ◽  
Research Paper ◽  
Extraction Methods ◽  
Features Extraction ◽  
Experimental Results ◽  
Extraction Time ◽  
Digital Signals ◽  
Human Speech ◽  
Signal Features

Human speech digital signals are famous and important digital types, they are used in many vital applications which require a high speed processing, so creating a speech signal features is a needed issue. In this research paper we will study more widely used methods of features extraction, we will implement them, and the obtained experimental results will be compared, efficiency parameters such as extraction time and throughput will be obtained and a speedup of each method will be calculated. Speech signal histogram will be used to improve some methods efficiency.

scholarly journals A Convolutional Neural Network Based Auto Features Extraction Method for Tea Classification with Electronic Tongue

2019 ◽  
Vol 9 (12) ◽  
pp. 2518 ◽  
Author(s):  
Yuan hong Zhong ◽  
Shun Zhang ◽  
Rongbu He ◽  
Jingyi Zhang ◽  
Zhaokun Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Electronic Tongue ◽  
Extraction Methods ◽  
Features Extraction ◽  
Superior Performance ◽  
Discrete Wavelet ◽  
Features Selection ◽  
Time Frequency ◽  
Value Decomposition

Feature extraction is a key part of the electronic tongue system. Almost all of the existing features extraction methods are “hand-crafted”, which are difficult in features selection and poor in stability. The lack of automatic, efficient and accurate features extraction methods has limited the application and development of electronic tongue systems. In this work, a convolutional neural network-based auto features extraction strategy (CNN-AFE) in an electronic tongue (e-tongue) system for tea classification was proposed. First, the sensor response of the e-tongue was converted to time-frequency maps by short-time Fourier transform (STFT). Second, features were extracted by convolutional neural network (CNN) with time-frequency maps as input. Finally, the features extraction and classification results were carried out under a general shallow CNN architecture. To evaluate the performance of the proposed strategy, experiments were held on a tea database containing 5100 samples for five kinds of tea. Compared with other features extraction methods including features of raw response, peak-inflection point, discrete cosine transform (DCT), discrete wavelet transform (DWT) and singular value decomposition (SVD), the proposed model showed superior performance. Nearly 99.9% classification accuracy was obtained and the proposed method is an approximate end-to-end features extraction and pattern recognition model, which reduces manual operation and improves efficiency.

Comparison of Different Time and Frequency Domain Feature Extraction Methods on Elbow Gesture’s EMG

2016 ◽  
Vol 2 (3) ◽  
pp. 35
Author(s):  
Cemil Altın ◽  
Orhan Er
Keyword(s):  
Feature Extraction ◽  
Frequency Domain ◽  
Nearest Neighbor ◽  
Extraction Methods ◽  
Signal Acquisition ◽  
Wrist Flexion ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Emg Signal ◽  
K Nearest Neighbor Algorithm

Objective:In this study we will get EMG signals from arm for different elbow gestures, than filtering the signal and later classification the signal. The reason for doing is that, EMG signals are used for many rehabilitation and assistive prostheses of paralyzed or injured people. Methods:Filtering a biological signal is the key point for these type studies. Filtering the EMG signals needed and starts with the elimination of the 50 Hz mains supply noise. After filtering the signal, feature extraction will be applied for both wrist flexion and wrist extension cases. There are many feature extraction methods for time and frequency domain. After feature extraction, classification of hand movements will be studied using extracted features. Classification is made using K Nearest Neighbor algorithm. The dataset used in this study is acquired by the EMG signal acquisition tool and belong to us. Results:90 % accuracy performance is obtained by K Nearest Neighbor algorithm purposed signal classification. Conclusion:This system is capable of conducting the classification process with a good performance to biomedical studies. So,this structure can be helpful as machine-learning based decision support system for medical purpose.

Analysis of Brain Tumor Using MR Images: A Brief Survey

2021 ◽  
pp. 2250023
Author(s):  
B. J. Shivaprasad ◽  
M. Ravikumar ◽  
D. S. Guru
Keyword(s):  
Brain Tumor ◽  
Extraction Methods ◽  
Features Extraction ◽  
Tumor Segmentation ◽  
Mr Images ◽  
Brain Tumor Segmentation

In this paper, we have discussed in detail about detection and extraction of brain tumor from MRI technique, where the importance of using MRI is also highlighted. Various features extraction methods and classifiers are explained in brain tumor segmentation. This paper mainly focuses on challenges involved in brain tumor analysis, which is helpful for researchers and those who are interested to carry out their research on this topic.

Speaker identification features extraction methods: A systematic review

2017 ◽  
Vol 90 ◽  
pp. 250-271 ◽  
Author(s):  
Sreenivas Sremath Tirumala ◽  
Seyed Reza Shahamiri ◽  
Abhimanyu Singh Garhwal ◽  
Ruili Wang
Keyword(s):  
Systematic Review ◽  
Speaker Identification ◽  
Extraction Methods ◽  
Features Extraction
Sign in / Sign up

Export Citation Format

Share Document