A Neural Net Based Scheme for Narrowband Signal Extraction

1994 ◽  
Vol 40 (2-3) ◽  
pp. 113-118
Author(s):  
P K Dash ◽  
P K Nanda ◽  
A K Swain ◽  
H P Khincha
Keyword(s):  
Signal Extraction ◽  
Neural Net ◽  
Narrowband Signal

A new method of fluxgate signal extraction

2017 ◽  
Vol 2017 (45) ◽  
pp. 83-89
Author(s):  
A.A. Marusenkov ◽  
Keyword(s):  
High Frequency ◽  
Second Harmonic ◽  
Excitation Frequency ◽  
Low Noise ◽  
Measuring System ◽  
Signal Extraction ◽  
Fluxgate Magnetometer ◽  
New Approach ◽  
Average Value ◽  
The Time Domain

Using dedicated high-frequency measuring system the distribution of the Barkhausen jumps intensity along a reversal magnetization cycle was investigated for low noise fluxgate sensors of various core shapes. It is shown that Barkhausen (reversal magnetization) noise intensity is strongly inhomogeneous during an excitation cycle. In the traditional second harmonic fluxgate magnetometers the signals are extracted in the frequency domain, as a result, some average value of reversal magnetization noises is contributed to the output signals. In order to fit better the noise shape and minimize its transfer to the magnetometer output the new approach for demodulating signals of these sensors is proposed. The new demodulating method is based on information extraction in the time domain taking into account the statistical properties of cyclic reversal magnetization noises. This approach yields considerable reduction of the fluxgate magnetometer noise in comparison with demodulation of the signal filtered at the second harmonic of the excitation frequency.

Using artificial neural network condensation to facilitate adaption of machine learning in medical settings by reducing computational burden (Preprint)

2020 ◽  
Author(s):  
Dianbo Liu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Third World ◽  
Mortality Prediction ◽  
Neural Net ◽  
Medical Settings ◽  
Hidden Layer ◽  
Applications Of Machine Learning ◽  
Computational Resources ◽  
Developed Nations

BACKGROUND Applications of machine learning (ML) on health care can have a great impact on people’s lives. At the same time, medical data is usually big, requiring a significant amount of computational resources. Although it might not be a problem for wide-adoption of ML tools in developed nations, availability of computational resource can very well be limited in third-world nations and on mobile devices. This can prevent many people from benefiting of the advancement in ML applications for healthcare. OBJECTIVE In this paper we explored three methods to increase computational efficiency of either recurrent neural net-work(RNN) or feedforward (deep) neural network (DNN) while not compromising its accuracy. We used in-patient mortality prediction as our case analysis upon intensive care dataset. METHODS We reduced the size of RNN and DNN by applying pruning of “unused” neurons. Additionally, we modified the RNN structure by adding a hidden-layer to the RNN cell but reduce the total number of recurrent layers to accomplish a reduction of total parameters in the network. Finally, we implemented quantization on DNN—forcing the weights to be 8-bits instead of 32-bits. RESULTS We found that all methods increased implementation efficiency–including training speed, memory size and inference speed–without reducing the accuracy of mortality prediction. CONCLUSIONS This improvements allow the implementation of sophisticated NN algorithms on devices with lower computational resources.

scholarly journals Circulant Singular Spectrum Analysis to Monitor the State of the Economy in Real Time

Mathematics ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1169
Author(s):  
Juan Bógalo ◽  
Pilar Poncela ◽  
Eva Senra
Keyword(s):  
Business Cycles ◽  
Real Time ◽  
Parametric Method ◽  
Singular Spectrum Analysis ◽  
The State ◽  
Signal Extraction ◽  
Alternative Procedure ◽  
State Of The Economy ◽  
Regular Patterns ◽  
Non Parametric

Real-time monitoring of the economy is based on activity indicators that show regular patterns such as trends, seasonality and business cycles. However, parametric and non-parametric methods for signal extraction produce revisions at the end of the sample, and the arrival of new data makes it difficult to assess the state of the economy. In this paper, we compare two signal extraction procedures: Circulant Singular Spectral Analysis, CiSSA, a non-parametric technique in which we can extract components associated with desired frequencies, and a parametric method based on ARIMA modelling. Through a set of simulations, we show that the magnitude of the revisions produced by CiSSA converges to zero quicker, and it is smaller than that of the alternative procedure.

Sign in / Sign up

Export Citation Format

Share Document