Performance Comparison Between Fast Fourier Transform-Based Segmentation, Feature Selection, and Fault Identification Algorithm and Neural Network for the Condition Monitoring of Centrifugal Equipment

2017 ◽  
Vol 139 (6) ◽  
Author(s):  
Samer Gowid ◽  
Roger Dixon ◽  
Saud Ghani
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Feature Selection ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Condition Monitoring ◽  
Identification Accuracy ◽  
Fault Identification ◽  
Identification Algorithm ◽  
Centrifugal Equipment

This paper compares and evaluates the performance of two major feature selection and fault identification methods utilized for the condition monitoring (CM) of centrifugal equipment, namely fast Fourier transform (FFT)-based segmentation, feature selection, and fault identification (FS2FI) algorithm and neural network (NN). Multilayer perceptron (MLP) is the most commonly used NN model for fault pattern recognition. Feature selection and trending play an important role in pattern recognition and hence affect the performance of CM systems. The technical and developmental challenges of both methods were investigated experimentally on a Paxton industrial centrifugal air blower system with a rotational speed of 15,650 RPMs. Five different machine conditions were experimentally emulated in the laboratory. A low training-to-testing ratio of 50% was utilized to evaluate the performance of both methods. In order to maximize fault identification accuracy and minimize computing time and cost, a near-optimal NN configuration was identified. The results showed that both techniques operated with a fault identification accuracy of 100%. However, the FS2FI algorithm showed a number of advantages over NN. These advantages include the ease of implementation and a reduction of cost and time in development and computing, as it processed the data from the first trial in less than 6.2% of the time taken by the NN.

scholarly journals A Frequency Pattern Mining Model Based on Deep Neural Network for Real-Time Classification of Heart Conditions

Healthcare ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 234 ◽  
Author(s):  
Hyun Yoo ◽  
Soyoung Han ◽  
Kyungyong Chung
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Real Time ◽  
Normal Control ◽  
Input Data ◽  
Deep Neural Network ◽  
Pattern Mining ◽  
F Measure

Recently, a massive amount of big data of bioinformation is collected by sensor-based IoT devices. The collected data are also classified into different types of health big data in various techniques. A personalized analysis technique is a basis for judging the risk factors of personal cardiovascular disorders in real-time. The objective of this paper is to provide the model for the personalized heart condition classification in combination with the fast and effective preprocessing technique and deep neural network in order to process the real-time accumulated biosensor input data. The model can be useful to learn input data and develop an approximation function, and it can help users recognize risk situations. For the analysis of the pulse frequency, a fast Fourier transform is applied in preprocessing work. With the use of the frequency-by-frequency ratio data of the extracted power spectrum, data reduction is performed. To analyze the meanings of preprocessed data, a neural network algorithm is applied. In particular, a deep neural network is used to analyze and evaluate linear data. A deep neural network can make multiple layers and can establish an operation model of nodes with the use of gradient descent. The completed model was trained by classifying the ECG signals collected in advance into normal, control, and noise groups. Thereafter, the ECG signal input in real time through the trained deep neural network system was classified into normal, control, and noise. To evaluate the performance of the proposed model, this study utilized a ratio of data operation cost reduction and F-measure. As a result, with the use of fast Fourier transform and cumulative frequency percentage, the size of ECG reduced to 1:32. According to the analysis on the F-measure of the deep neural network, the model had 83.83% accuracy. Given the results, the modified deep neural network technique can reduce the size of big data in terms of computing work, and it is an effective system to reduce operation time.

An identification algorithm of driver steering characteristics based on backpropagation neural network

2019 ◽  
Vol 233 (9) ◽  
pp. 2333-2342
Author(s):  
Shangyu Zhao ◽  
Guoying Chen ◽  
Min Hua ◽  
Changfu Zong
Keyword(s):  
Neural Network ◽  
Driving Simulator ◽  
Careful Analysis ◽  
Angular Speed ◽  
Identification Accuracy ◽  
Steering Wheel ◽  
Identification Algorithm ◽  
Backpropagation Neural Network ◽  
Feature Parameter ◽  
Steering Characteristics

This paper presents a novel identification method of driver steering characteristics based on backpropagation neural network. First, a driving simulator is built to collect required driving data. After careful analysis, three feature parameters that reflect driver steering characteristics are determined, including the average steering wheel angular speed, the standard deviation of the steering wheel angle, and the average vehicle longitudinal speed. Then, steering feature parameter vectors are extracted from raw data and clustered by the K-means algorithm. According to the clustering result, driver steering characteristics are divided into three types: cautious, average, and aggressive. Subsequently, a backpropagation neural network with two hidden layers is designed and trained to identify the types of feature parameter vectors. Verification results show that the established backpropagation neural network has high identification accuracy and good generalization ability for the identification of driver steering characteristics.

scholarly journals Identifikasi Penyakit Diabetes Mellitus Melalui Nafas Berbasis Sensor Gas Dengan Metode Fast Fourier Transform dan Backpropagation

2018 ◽  
Vol 2 (02) ◽  
pp. 85-91
Author(s):  
Mohammad Hafiz Hersyah ◽  
Andrizal Andrizal ◽  
Revinessia Revinessia
Keyword(s):  
Neural Network ◽  
Diabetes Mellitus ◽  
Fourier Transform ◽  
Hydrogen Sulfide ◽  
Fast Fourier Transform ◽  
Success Rate ◽  
The Neural Network ◽  
Random Samples ◽  
Backpropagation Method ◽  
Bad Breath

The purpose of this research is to detect whether a person has diabetes mellitus or not. In people with diabetes mellitus uncontrolled will result in a decline in the rate of saliva that results in bad breath. The system uses the sensor TGS 2602 and MQ 4. It's function is to detect the levels of Hydrogen Sulfide and Methan in a person’s breath. The decision is made by using the neural network with a backpropagation method. The result for 5 (five) tests of diabetes mellitus samples can be detected with a success rate of 80%, whereas using random samples, the test detected with detected with a success rate of 80% samples that didn’t contain diabetes mellitus. This system could provide a solution for testing if a person is suffering from diabetes mellitus

Fingerprint Recognition in Wavelet Domain

2012 ◽  
Author(s):  
Wan Azizun Wan Adnan ◽  
Tze Siang Lim ◽  
Salasiah Hitam
Keyword(s):  
Image Processing ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Low Cost ◽  
Recognition System ◽  
Fingerprint Recognition ◽  
Fingerprint Identification ◽  
Small Computer ◽  
Identification System ◽  
Identification Algorithm

Teknik cetak ibujari merupakan satu daripada teknologi biometrik yang paling boleh diharapkan. Beberapa pendekatan terhadap pemadanan ibujari secara automatik telah dicadangkan dalam saranan. Dalam pengecaman ibujari, pra–prosesan seperti pelicin, binarization dan thinning diperlukan. Kemudian, ciri–ciri cetak ibujari yang terperinci diambil berdasarkan algoritma pengecaman cetak ibujari (seperti dengan menggunakan Fast Fourier Transform (FFT)) mungkin memerlukan teknik–teknik pengkomputeran yang banyak sehingga menjadikannya tidak praktikal. Algoritma berdasarkan wavelet mungkin merupakan kunci untuk membina sistem pengecaman cetak ibujari kos rendah yang boleh dioperasi dalam sistem komputer bermodul kecil. Di sini, satu sistem pengecaman cetak ibujari yang boleh menjalankan pemadanan cetak ibujari berdasarkan kepada ciri–ciri yang diperolehi daripada domain jelmaan wavelet diperkenalkan. Kajian ini adalah berdasarkan kepada perisian MATLAB dan aplikasinya dalam toolbox seperti Wavelet and Image Processing Toolbox. Kata kunci: Biometrik, wavelet, cetaksekuriti, pengecaman cetak ibujari Fingerprint technique is one of the most reliable biometric technologies. In the fingerprint recognition, pre-processing such as smoothing, binarization, and thinning are needed. Then, fingerprint minutia feature is extracted. Some fingerprint identification algorithm (such as using Fast Fourier Transform, (FFT)) may require so much computation as to be impractical. Wavelet based algorithm may be the key to making a low cost fingerprint identification system that would operate on a small computer. We present a fingerprint recognition system that can match the fingerprint images based on features extracted in the wavelet transform domain. This study is implemented based on MATLAB Software and their toolbox applications, such as Wavelet and Image Processing Toolbox. Key words: Biometrics, wavelet, security, fingerprint recognition

Sign in / Sign up

Export Citation Format

Share Document