Artificial Olfactory System Technology on Chicken Freshness Detection

2013 ◽  
Vol 461 ◽  
pp. 801-808 ◽  
Author(s):  
Dong Hui Chen ◽  
Shao Bo Ye ◽  
Xiao Hui Weng ◽  
Jin Tong ◽  
Zhi Yong Chang
Keyword(s):  
Neural Network ◽  
Gas Sensors ◽  
Olfactory System ◽  
Sensor Array ◽  
Rbf Neural Network ◽  
Pattern Recognition Method ◽  
System Technology ◽  
Recognition Method ◽  
Sensitive Sensor ◽  
Non Destructive

To detect the freshness of chicken quickly and accurately with non-destructive, in this paper, the gas-sensitive sensor array has been optimized according to the odor of chicken and the sensor experiment. gas sensors combinations of TGS2600 TGS2610 TGS2611 TGS2620 and TGS2442 were selected and combined to establish new sensor array,The outcome of biological olfactory research has been used to design a bionic gas collection chamber. We have also adopted RBF neural network as a pattern recognition method. The fact that the accuracy of chicken freshness detection using the system is physically and chemically proved to be 96% demonstrates the feasibility of making use of artificial olfactory system to detect chicken freshness.

Research on fault diagnosis of automobile engines based on the deep learning 1D-CNN method

2022 ◽  
Author(s):  
Canyi Du ◽  
Rui Zhong ◽  
Yishen Zhuo ◽  
Xinyu Zhang ◽  
Feifei Yu ◽  
...  
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Pattern Recognition Method ◽  
Recognition Method ◽  
Vibration Signals ◽  
One Dimensional ◽  
Sample Set

Abstract Traditional engine fault diagnosis methods usually need to extract the features manually before classifying them by the pattern recognition method, which makes it difficult to solve the end-to-end fault diagnosis problem. In recent years, deep learning has been applied in different fields, bringing considerable convenience to technological change, and its application in the automotive field also has many applications, such as image recognition, language processing, and assisted driving. In this paper, a one-dimensional convolutional neural network (1D-CNN) in deep learning is used to process vibration signals to achieve fault diagnosis and classification. By collecting the vibration signal data of different engine working conditions, the collected data are organized into several sets of data in a working cycle, which are divided into a training sample set and a test sample set. Then, a one-dimensional convolutional neural network model is built in Python to allow the feature filter (convolution kernel) to learn the data from the training set and these convolution checks process the input data of the test set. Convolution and pooling extract features to output to a new space, which is characterized by learning features directly from the original vibration signals and completing fault diagnosis. The experimental results show that the pattern recognition method based on a one-dimensional convolutional neural network can be effectively applied to engine fault diagnosis and has higher diagnostic accuracy than traditional methods.

Nano Sensor Using One Dimensional Porous Indium Oxide and Pattern Recognition Method of Its Electronic Information

2021 ◽  
Vol 16 (2) ◽  
pp. 255-263
Author(s):  
Qinghong Wu ◽  
Wanying Zhang
Keyword(s):  
Pattern Recognition ◽  
Indium Oxide ◽  
Electronic Nose ◽  
Sensor Array ◽  
Dimensional Space ◽  
Ordinary Least Squares ◽  
Acquisition Time ◽  
Pattern Recognition Method ◽  
Recognition Method ◽  
Linear Discriminant

Due to its high sensitivity, low price and fast response speed, gas sensors based on metal oxide nanomate-rials have attracted many researchers to modify and explore the materials. First, pure indium oxide (In2O3) nanotubes (NTs)/porous NTs (PNTs) and Ho doped In2O3 NTs/PNTs are prepared by electrospinning and calcination. Then, based on the prepared nanomaterials, the 6-channel sensor array is obtained and used in the electronic nose sensing system for wine product identification. The system obtains the frequency signals of different liquor products by means of 6-channel sensor array, analyzes the extracted electronic signal characteristic information by means of ordinary least squares, and introduces the pattern recognition method of moving average and linear discriminant to identify liquor products. In the experiment, compared with pure In2O3 NTs sensor, pure In2O3 PNTs sensor has higher sensitivity to 100 ppm ethanol gas, and the sensitivity is further improved after mixing Ho. Among them, 6 mol% Ho + In2O3 PNTs have the highest sensitivity and the shortest response time; based on the electronic nose system composed of prepared nanomaterial sensor array, frequency signals of different Wu Liang Ye wines are collected. With the extension of acquisition time, the corresponding frequency first decreases and then becomes stable; the extracted liquor characteristic signal is projected into two-dimensional space and three-dimensional space. The results show that the pattern recognition system based on this method can extract the characteristic signals of liquor products and distinguish them.

scholarly journals Deep Learning-Based Classification of Weld Surface Defects

2019 ◽  
Vol 9 (16) ◽  
pp. 3312 ◽  
Author(s):  
Zhu ◽  
Ge ◽  
Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Surface Defects ◽  
Recognition Method ◽  
High Level ◽  
Intelligent Recognition ◽  
Non Destructive

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Sign in / Sign up

Export Citation Format

Share Document