Multi-features fusion diagnosis of tremor based on artificial neural network and D–S evidence theory

Ai, Lingmei; Wang, Jue; Wang, Xuelian

doi:10.1016/j.sigpro.2008.06.018

Cited by 37 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, with ȣ in the same frame of discernment, the combining results of n basic probability assignment values ଵ ǡ ଶ ǡ ‫ڮ‬ ǡ ୬ are as follows [11,12]:…”

Section: Multi-sensors Data Fusion Based On D-s Evidence Theorymentioning

confidence: 99%

Feature extraction and multi-sensor data fusion in monitoring and pre-warning system for security of pipeline based on multi-seismic sensors

Sun

Jin-quan²,

Wang³

2012

2012 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

In recent years, aiming at the increasingly serious pipeline damages because of the artificial factors, we investigate the characteristic of seismic signals and develop a monitoring and pre-warning system for security of pipelines based on multi-seismic sensors. There are many sensors and processing modules to acquire the seismic signals generated by the ground targets. If these modules all transmit the original data to host machine, it will jam the information channel. So in this system, the seismic signals are processed and extracted the features in respective modules. The non-stationary signal analysis method based on empirical mode decomposition is used to process the seismic signals and acquire some intrinsic mode functions. The target feature vectors were composed of the normalized kurtosis extracted from the decomposition results. The single sensor's judgment was made by the main normalized kurtosis values in the important decomposed frequency bands. Then the features vectors are transmitted to the host machine which will finish the pattern recognition, multi-sensor data fusion and target classification analysis. It will greatly reduce the dimension of feature vectors, the data amount and complexity. This paper will mainly introduce the feature extraction and multi-sensor data fusion. This D-S evidence reasoning was to fuse the recognition results for improving the target recognition accuracy. Then the last judgment was made. The processing methods above were proved effective by the experiment data analysis.

show abstract

“…In general, with ȣ in the same frame of discernment, the combining results of n basic probability assignment values ଵ ǡ ଶ ǡ ‫ڮ‬ ǡ ୬ are as follows [11,12]:…”

Section: Multi-sensors Data Fusion Based On D-s Evidence Theorymentioning

confidence: 99%

Feature extraction and multi-sensor data fusion in monitoring and pre-warning system for security of pipeline based on multi-seismic sensors

Sun

Jin-quan²,

Wang³

2012

2012 IEEE International Conference on Mechatronics and Automation

View full text Add to dashboard Cite

show abstract

“…Reference [20] presented a tremor detection method that combined artificial net works and D-S evidence theory, which first used three independent Back-propagation neural networks (BPNNs) to process the tremor hand accelerator signals, the output results of the BPNNs were fused by D-S evidence theory. It was shown from the experimental result that the accuracy of the proposed method was 3.37%~13.37% higher than that of BPNN.…”

Section: Fusion Algorithmmentioning

confidence: 99%

System Detection Technology Based on Multi-sensor Information Fusion

Cixiong

2011

2011 Third International Conference on Measuring Technology and Mechatronics Automation

View full text Add to dashboard Cite

System detection technology based on multi-sensor information fusion makes full use of redundant and complementary information between sensors, which overcomes the shortcomings of single sensor and improves the detection accuracy. In this paper, the detection technology is briefly introduced, which contains the basic model and detection process of a detection system. According to the different abstract degree of information, the system detection process is divided into three different forms i.e., data level fusion, feature level fusion and decision level fusion. The key technologies about the multi-sensor detection system are analyzed, which include the sensory technology, communication technology and fusion algorithm. Finally, the developing trends of the proposed detection technology are discussed with applications.

show abstract

“…HHT is a powerful tool for analyzing data from nonlinear and nonstationary processes 15 and has yielded many successful applications, such as fusion diagnose of tremor, 16 speech pitch determination, 17 moving target indication, 18 etc. HHT is developed by Huang et al 15 based on the Hilbert transform and the assumption that every data set consists of different simple IMFs.…”

Section: A the Hilbert-huang Transformmentioning

confidence: 99%

Multiscale dynamic analysis of blast furnace system based on intensive signal processing

Chu

Gao

Liu

2010

Chaos: An Interdisciplinary Journal of Nonlinear Science

View full text Add to dashboard Cite

In this paper, the Hilbert-Huang transform method and time delay embedding method are applied to multiscale dynamic analysis on the time series of silicon content in hot metal collected from a medium-sized blast furnace with the inner volume of 2500 m3. The results provide clear evidence of multiscale features in blast furnace ironmaking process. Ten intrinsic mode functions (IMFs) are decomposed from the silicon content time series; the presence of noninteger fractal dimension, positive finite Kolmogorov entropy, and positive finite maximum Lyapunov exponent are found in some IMF components. In addition, the coupling of subscale structures of blast furnace system is studied using the dimension of interaction dynamics and a robust algorithm for detecting interdependence. It is found that IMF(3) is the main driver in the coupling system IMF(2) and IMF(3) while for the coupling system IMF(3) and IMF(4) neither subsystem can act as the driver. All these provide a guideline for studying blast furnace ironmaking process with multiscale theory and methods, and may open way for more candidate tools to model and control blast furnace system in the future.

show abstract

Multi-features fusion diagnosis of tremor based on artificial neural network and D–S evidence theory

Cited by 37 publications

References 14 publications

Feature extraction and multi-sensor data fusion in monitoring and pre-warning system for security of pipeline based on multi-seismic sensors

Feature extraction and multi-sensor data fusion in monitoring and pre-warning system for security of pipeline based on multi-seismic sensors

System Detection Technology Based on Multi-sensor Information Fusion

Multiscale dynamic analysis of blast furnace system based on intensive signal processing

Contact Info

Product

Resources

About