Eggshell Crack Detection and Egg Classification Using Resonance and Support Vector Machine Methods

2019 ◽  
Vol 35 (1) ◽  
pp. 23-30
Author(s):  
Ching-Wei Cheng ◽  
Pei-Hsuan Feng ◽  
Jun-Hong Xie ◽  
Yu-Kai Weng
Keyword(s):  
Support Vector Machine ◽  
Characteristic Frequency ◽  
Crack Detection ◽  
Detection Method ◽  
Maximum Amplitude ◽  
Identification Accuracy ◽  
Support Vector ◽  
Training Set ◽  
Processed Products ◽  
Resonance Detection

Abstract. Cracks in eggshells not only affect the egg preservation time but also reduce the success rate for the end-processed products. This study was based on the theory of resonant inspection (RI). The use of the support vector machine (SVM) method as a means of more accurate eggshell crack detection was evaluated. The results revealed that comparing the resonant frequency and amplitude by using a microphone as a sensor allowed non-cracked eggs to be distinguished from cracked eggs. The characteristic frequency of a non-cracked egg was between 4130 and 5500 Hz, and its amplitude was between 0.16 and 0.20 V. The spectrum of a cracked egg was fuzzy, with no obvious characteristic frequency, and the maximum amplitude was approximately 0.06 V. The identification accuracy was 99% and 98% for the SVM training set and testing set, respectively. These results prove that the resonance detection method is effective for identifying eggs with cracked shells. Keywords: Eggshells, Resonant inspection, Fast Fourier transform, Support vector machine.

scholarly journals Leveraging Electronic Dental Record Data to Classify Patients Based on Their Smoking Intensity

2018 ◽  
Vol 57 (05/06) ◽  
pp. 253-260 ◽  
Author(s):  
J. Patel ◽  
Z. Siddiqui ◽  
A. Krishnan ◽  
T. Thyvalikakath
Keyword(s):  
Support Vector Machine ◽  
Smoking Status ◽  
Smoking History ◽  
Support Vector ◽  
Oral Diseases ◽  
Training Set ◽  
Valuable Source ◽  
Smoking Intensity ◽  
Established Risk Factor ◽  
Record Data

Background Smoking is an established risk factor for oral diseases and, therefore, dental clinicians routinely assess and record their patients' detailed smoking status. Researchers have successfully extracted smoking history from electronic health records (EHRs) using text mining methods. However, they could not retrieve patients' smoking intensity due to its limited availability in the EHR. The presence of detailed smoking information in the electronic dental record (EDR) often under a separate section allows retrieving this information with less preprocessing. Objective To determine patients' detailed smoking status based on smoking intensity from the EDR. Methods First, the authors created a reference standard of 3,296 unique patients’ smoking histories from the EDR that classified patients based on their smoking intensity. Next, they trained three machine learning classifiers (support vector machine, random forest, and naïve Bayes) using the training set (2,176) and evaluated performances on test set (1,120) using precision (P), recall (R), and F-measure (F). Finally, they applied the best classifier to classify smoking status from an additional 3,114 patients’ smoking histories. Results Support vector machine performed best to classify patients into smokers, nonsmokers, and unknowns (P, R, F: 98%); intermittent smoker (P: 95%, R: 98%, F: 96%); past smoker (P, R, F: 89%); light smoker (P, R, F: 87%); smokers with unknown intensity (P: 76%, R: 86%, F: 81%), and intermediate smoker (P: 90%, R: 88%, F: 89%). It performed moderately to differentiate heavy smokers (P: 90%, R: 44%, F: 60%). EDR could be a valuable source for obtaining patients’ detailed smoking information. Conclusion EDR data could serve as a valuable source for obtaining patients' detailed smoking information based on their smoking intensity that may not be readily available in the EHR.

scholarly journals Eggshell crack detection based on acoustic impulse response and supervised pattern recognition

2009 ◽  
Vol 27 (No. 6) ◽  
pp. 393-402 ◽  
Author(s):  
H. Lin ◽  
J. Zhao ◽  
Q. Chen ◽  
J. Cai ◽  
P. Zhou
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Crack Detection ◽  
Support Vector Machine Model ◽  
Acoustic Resonance ◽  
Support Vector ◽  
Machine Model ◽  
Nearest Neighbours

A system based on acoustic resonance was developed for eggshell crack detection. It was achieved by the analysis of the measured frequency response of eggshell excited with a light mechanism. The response signal was processed by recursive least squares adaptive filter, which resulted in the signal-to-noise ratio of the acoustic impulse response reing remarkably enhanced. Five features variables were exacted from the response frequency signals. To develop a robust discrimination model, three pattern recognition algorithms (i.e. K-nearest neighbours, artificial neural network, and support vector machine) were examined comparatively in this work. Some parameters of the model were optimised by cross-validation in the building model. The experimental results showed that the performance of the support vector machine model is the best in comparison to k-nearest neighbours and artificial neural network models. The optimal support vector machine model was obtained with the identification rates of 95.1% in the calibration set, and 97.1% in the prediction set, respectively. Based on the results, it was concluded that the acoustic resonance system combined with the supervised pattern recognition has a significant potential for the cracked eggs detection.

Sign in / Sign up

Export Citation Format

Share Document