Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals.
Özal YildirimMuhammed TaloBetül Ay KarakusUlas Baran BalogluGalip AydinU. Rajendra AcharyaPublished in: Comput. Biol. Medicine (2019)
Keyphrases
- heart rate
- pre trained
- automated detection
- frequency spectrum
- input image
- bandpass
- edge detection
- probabilistic model
- fourier transform
- random fields
- blood pressure
- image analysis
- spectral features
- transfer function
- lung cancer
- image processing
- illumination conditions
- training examples
- bit rate
- image registration
- control signals