Abstract
A biological signal has the multi-scale and signals complexity properties. Many studies have used the signal complexity calculation methods and multi-scale analysis to analyze the biological signal, such as lung sound. Signal complexity methods used in the biological signal analysis include entropy, fractal analysis, and Hjorth descriptor. Meanwhile, the commonly used multi-scale methods include wavelet analysis, coarse-grained procedure, and empirical mode decomposition (EMD). One of the multi-scale methods in the biological signal analysis is the multi-distance signal level difference (MSLD), which calculates a difference between two signal samples at a specific distance. In previous studies, MSLD was combined with Hjorth descriptor for lung sound classification. MSLD has the potential to be developed by modifying the fundamental equation of MSLD. This study presents the comparison of MSLD and its variations combined with Hjorth descriptor for lung sound classification. The results showed that MSLD and its variations had the highest accuracy of 98.99% for five lung sound data classes. The results of this study provided several alternatives for multi-scale signal complexity analysis method for biological signals.
Highlights
Multi-scale analysis for biological signals is essential in the biological signal analysis [1] as it is believed that the multi-scale analysis can extract information in the signal
We proposed several multi-distance signal level difference (MSLD) variations combined with Hjorth descriptor for lung sound classification
The output signal of multistep signal level difference (MStepLD) was different from MSLD-A because the input signal for the process in MStepLD is the output signal in the previous step
Summary
Multi-scale analysis for biological signals is essential in the biological signal analysis [1] as it is believed that the multi-scale analysis can extract information in the signal. A biological signal is generated from a complex biological system with various inputs and outputs where the inputs-outputs relation has not been thoroughly explained [4]. The complex system generates a complex signal, which is a signal with no proper mathematical explanation. Various complexity signal calculation methods have been developed to quantify the properties of the complex signals. Several approaches have been developed to calculate signal complexity. Land and Damian explained three approaches to calculate signal complexity in the time domain; namely information theory, chaos theory, and Kolmogorov estimation [5]. Hjorth used statistical analysis to calculate the characteristics of biological signals [6] with the parameters of Activity, Mobility, and Complexity. Hjorth descriptor was used to analyze electroencephalogram (EEG) signals. The Hjorth descriptor was used to analyze the electrocardiogram (ECG) signal [7] and lung sound [8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
