Abstract
Mobile healthcare is an emerging approach which can be realized by using cloud-connected biomedical implants. In this context, a level-crossing sampling and adaptive-rate processing based innovative method is suggested for an effective and automated epileptic seizures diagnosis. The suggested solution can achieve a significant real-time compression in computational complexity and transmission activity reduction. The proposed method acquires the electroencephalogram (EEG) signal by using the level-crossing analog-to-digital converter (LCADC) and selects its active segments by using the activity selection algorithm (ASA). This effectively pilots the post adaptive-rate modules such as denoising, wavelet based sub-bands decomposition, and dimension reduction. The University of Bonn and Hauz Khas epilepsy-detection databases are used to evaluate the proposed approach. Experiments show that the proposed system achieves a 4.1-fold and 3.7-fold decline, respectively, for University of Bonn and Hauz Khas datasets, in the number of samples obtained as opposed to traditional counterparts. This results in a reduction of the computational complexity of the proposed adaptive-rate processing approach by more than 14-fold. It promises a noticeable reduction in transmitter power, the use of bandwidth, and cloud-based classifier computational load. The overall accuracy of the method is also quantified in terms of the epilepsy classification performance. The proposed system achieves100% classification accuracy for most of the studied cases.
Original language | English |
---|---|
Article number | 106034 |
Number of pages | 13 |
Journal | Computer Methods and Programs in Biomedicine |
Volume | 203 |
Early online date | 10 Mar 2021 |
DOIs | |
Publication status | Published - May 2021 |
Keywords
- Adaptive-Rate Processing
- Computational complexity
- Compression
- Classification
- Electroencephalogram (EEG)
- Level-Crossing Sampling
- Information Gain
- Statistical features extraction
- Dimension reduction
- Machine learning
- Mobile healthcare
- Wavelet transform