Research on Intelligent Classification System of Ceramic Tiles Based on Machine Vision

2011 ◽  
Vol 101-102 ◽  
pp. 648-651
Author(s):  
Shi Long Li ◽  
Yao Chen
Keyword(s):  
Neural Network ◽  
Information Fusion ◽  
Bp Neural Network ◽  
Classification System ◽  
Shape Features ◽  
Ceramic Tiles ◽  
Color Features ◽  
The Neural Network ◽  
Sensor Information

An intelligent classification system of ceramic tiles is introduced in the light of the theory about multi-sensor information fusion. The system includes image acquisition, image processing and intelligent classification of ceramic tiles. The color features and shape features of tile image are synthetically processed using BP neural network. The topological structure of the neural network based on “681” structure is proposed in the system. The numerical calculation and simulation about classification of ceramic tiles is carried out based on MATLAB software. The results show this algorithm is fast and accurate, which can effectively accomplish the classification of comprehensive detection of ceramic tiles.

Research of Orange Quality Classification Technology Based on BP Neural Network Algorithm

2015 ◽  
Vol 713-715 ◽  
pp. 1821-1824
Author(s):  
Chun Hua Qian ◽  
He Qun Qiang ◽  
Sheng Rong Gong
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Classification Accuracy ◽  
Bp Algorithm ◽  
Shape Features ◽  
Accuracy Rate ◽  
Network Algorithm ◽  
Quality Classification ◽  
Neural Network Algorithm

BP algorithm is a classical neural network algorithm. We analyzed the deficiency of traditional BP neural network algorithm, designed new S function and momentum method strategy, optimized the algorithm parameters. We use the new algorithm in the classification of orange images, take color and shape features as input value, the experimental results proved that our algorithm is faster and the classification accuracy rate reaches to 90%

scholarly journals Estimation for Runway Friction Coefficient Based on Multi-Sensor Information Fusion and Model Correlation

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3886
Author(s):  
Yadong Niu ◽  
Sixiang Zhang ◽  
Guangjun Tian ◽  
Huabo Zhu ◽  
Wei Zhou
Keyword(s):  
Neural Network ◽  
Friction Coefficient ◽  
Information Fusion ◽  
Optical Sensors ◽  
Sensor System ◽  
Correlation Model ◽  
The Neural Network ◽  
Physical Sensors ◽  
Sensor Information ◽  
Fusion Scheme

Friction is a crucial factor affecting air accident occurrence on landing or taking off. Tire–runway friction directly contributes to aircraft stability on land. Therefore, an accurate friction estimation is a rising issue for all stakeholders. This paper summarizes the existing measurement methods, and a multi-sensor information fusion scheme is proposed to estimate the friction coefficient between the tire and the runway. Acoustic sensors, optical sensors, tread sensors, and other physical sensors form a sensor system that is used to measure friction-related parameters and fuse them through a neural network. So far, many attempts have been made to link the ground friction coefficient with the aircraft braking friction coefficient. The models that have been developed include the International Runway Friction Index (IRFI), Canada Runway Friction Index (CRFI), and other fitting models. Additionally, this paper attempts to correlate the output of the neural network (estimated friction coefficient) with the correlation model to predict the friction coefficient between the tire and the runway when the aircraft brakes. The sensor system proposed in this paper can be regarded as a mobile weather–runway–tire system, which can estimate the friction coefficient by integrating the runway surface conditions and the tire conditions, and fully consider their common effects. The role of the correlation model is to convert the ground friction coefficient to the grade of the aircraft braking friction coefficient and the information is finally reported to the pilots so that they can make better decisions.

The Automatic Classification of ECG Based on BP Neural Network

2010 ◽  
Vol 121-122 ◽  
pp. 111-116 ◽  
Author(s):  
Lan Lan Yu ◽  
Bo Xue Tan ◽  
Tian Xing Meng
Keyword(s):  
Neural Network ◽  
Clinical Application ◽  
Bp Neural Network ◽  
Heart Diseases ◽  
Automatic Classification ◽  
Learning Ability ◽  
The Neural Network ◽  
Heart Beating ◽  
Recognition Level

The classification and recognition of ECG are helpful to distinguish and diagnose heart diseases, which also have very important clinical application value for the automatic diagnoses of ECG. The traditional recognition methods need people to extract determinant rules and have no learning ability so that they are unable to simulate the intuition and fuzzy diagnoses function used by doctor very well. The neural network technology has strongpoint of self-organization, self-learning and strong tolerance for error. It provides a new method for the automatic classification of ECG. In this paper, we use BP neural network to do automatic classification for five kinds of ECG which are natural stylebook, paced heart beating, left branch block, right branch block and ventricular tachycardia. The average recognition level is 98.1%. Experiment results show that the neural networ k technology can greatly improve the recognition level of ECG. It has good clinical application value.

scholarly journals Fault Diagnosis for Methane Sensors using Generalized Regression Neural Network

2016 ◽  
Vol 12 (03) ◽  
pp. 42 ◽  
Author(s):  
Kaifeng Huang ◽  
Zegong Liu ◽  
Dan Huang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Residual Error ◽  
Generalized Regression Neural Network ◽  
Error Signal ◽  
The Neural Network ◽  
Diagnosis Method ◽  
Sensor Information ◽  
Generalized Regression

To identify the hang, collision and drift faults of methane sensors, this paper presents a fault diagnosis method for methane sensors using multi-sensor information fusion. A methane concentration monitoring approximation model with multi-sensor information fusion is established based on generalized regression neural network (GRNN).The output of the neural network is compared with the measured value of the sensor to be diagnosed to obtain the variation curve of the residual error signal. Through the analysis of the variation tendency of the residual error signal, the fault status of a methane sensor could be determined based on a reasonable threshold. Through simulation comparison is applied between the two models of GRNN and BP neural network; verify the GRNN model is much more precise in the approximation of methane concentrations. Fault diagnosis for methane sensors using generalized regression neural network is effective and more efficient.

scholarly journals Corn Classification System based on Computer Vision

Symmetry ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 591 ◽  
Author(s):  
Xiaoming Li ◽  
Baisheng Dai ◽  
Hongmin Sun ◽  
Weina Li
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Maximum Likelihood ◽  
Classification System ◽  
Automated Classification ◽  
Shape Features ◽  
Segmentation Method ◽  
Likelihood Estimator ◽  
Color Features

Automated classification of corn is important for corn sorting in intelligent agriculture. This paper presents a reliable corn classification method based on techniques of computer vision and machine learning. To discriminate different damaged types of corns, a line profile segmentation method is firstly used to segment and separate a group of touching corns. Then, twelve color features and five shape features are extracted for each individual corn object. Finally, a maximum likelihood estimator is trained to classify normal and damaged corns. To evaluate the performance of the proposed method, a private dataset consisting of images of normal corn and six kinds of damage corns, including heat-damaged, germ-damaged, cob-rot-damaged, blue eye mold-damaged, insect-damaged, and surface mold-damaged, were collected in this work. The proposed method achieved an accuracy of 96.67% for the classification between normal corns and the first four common damaged corns, and an accuracy of 74.76% was achieved for the classification between normal corns and six kinds of damaged corns. The experimental results demonstrated the effectiveness of the proposed corn classification system.

Classification of High Quality Carbon Steel Based on BP Neural Network

2013 ◽  
Vol 873 ◽  
pp. 54-59
Author(s):  
Lan Lan Liu ◽  
Tao Hong Zhang ◽  
Yong Hong Xie ◽  
Li Li ◽  
De Zheng Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Carbon Steel ◽  
Bp Neural Network ◽  
Comprehensive Evaluation ◽  
Practical Application ◽  
High Quality ◽  
Standard Data ◽  
The Neural Network ◽  
Neural Network Algorithm

Now carbon steel is used in the engineering aspects and it is the oldest and the largest amount of basic materials. How to determine whether they are high-quality carbon steel? In this paper the standard data of high quality carbon steel by using the classical BP neural network algorithm is researched. Then it is simulated and predicted. The final comprehensive evaluation and analysis show that the neural network model can be used to decide whether it is a high quality carbon steel. Further, it has a good practical application value for utilizing high-quality carbon steel rationally.

scholarly journals Fault Diagnosis of Bearings Based on Multi-Sensor Information Fusion and 2D Convolutional Neural Network

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 23717-23725
Author(s):  
Jiaxing Wang ◽  
Dazhi Wang ◽  
Sihan Wang ◽  
Wenhui Li ◽  
Keling Song
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Information Fusion ◽  
Sensor Information

Building Electronic Commerce Recommendation System Based on Ontology Learning and BP Neural Network

2013 ◽  
Vol 718-720 ◽  
pp. 1961-1966
Author(s):  
Hong Sheng Xu ◽  
Qing Tan
Keyword(s):  
Neural Network ◽  
Electronic Commerce ◽  
Bp Neural Network ◽  
Optimization Problem ◽  
Recommendation System ◽  
High Efficiency ◽  
Ontology Learning ◽  
The Neural Network ◽  
Network Process ◽  
Hidden Layer

Electronic commerce recommendation system can effectively retain user, prevent users from erosion, and improve e-commerce system sales. BP neural network using iterative operation, solving the weights of the neural network and close values to corresponding network process of learning and memory, to join the hidden layer nodes of the optimization problem of adjustable parameters increase. Ontology learning is the use of machine learning and statistical techniques, with automatic or semi-automatic way, from the existing data resources and obtaining desired body. The paper presents building electronic commerce recommendation system based on ontology learning and BP neural network. Experimental results show that the proposed algorithm has high efficiency.

Sign in / Sign up

Export Citation Format

Share Document