1. Enhancement detection of COVID-19 based on fuzzy
logic techniques and Independent component analysis
By
Mohanad Sarem Abdullah
Supervisor
Asst. prof. Dr. Ahmed Albakri Prof. Dr. Faris Mohammed Ali
2. Presentation Content
What is (Fuzzy Logic) ? Why we use it in this work ?
What kind of model should be used in this work ?
What we accomplished for this work?
What is the final research idea?
3. What is (Fuzzy Logic) ? Why we use it in this work ?
Fuzzy Logic :Resembles the human decision-making methodology shown in figure (1).
Figure 1: Fuzzy explain
4. What is (Fuzzy Logic) ? Why we use it in this work ?
Following are some reasons to use fuzzy logic in neural networks :
Fuzzy logic is largely used to define the weights, from fuzzy sets, in neural networks.
When crisp values are not possible to apply, then fuzzy values are used.
We have already studied that training and learning help neural networks perform better in
unexpected situations. At that time fuzzy values would be more applicable than crisp values.
When we use fuzzy logic in neural networks then the values must not be crisp and the
processing can be done in parallel.
5. What kind of model should be used in this work ?
Two image type use for classification:
A- Chest X-Ray Images
B- Ct Scans
** We use Chest X-Ray Images**
dataset input
shown in figure (2).
Figure 2: general model
7. Model
Explain Suggested
generate the decision scores to be fused by the proposed transfer learning-based on
convolutional neural network models are used: VGG16, ResNet152V2, InceptionV3
and EfficientNetB3. The framework has been tested on two publicly available chest x-
ray datasets, with state-of-the-art results, proving the model's reliability shown in
figure (3).
8. What have we accomplished for this work?
Image dimensions: (256, 256)
Maximum pixel value : 1.0 ; Minimum pixel value:0.0
Mean value of the pixels : 0.5 ; Standard deviation : 0.4
Figure 4: Image with fuzzy
12. What is the final research idea?
Figure 6: Figure 5: Hardware implementation for the proposed model
13.
Reference :
E. Kerre and M. Nachtegael, Eds., Fuzzy Techniques in Image[1] E. Kerre and M. Nachtegael, Eds.,
Fuzzy Techniques in Image Processing. New York: Springer-Verlag, 2000, vol. 52, Studies in
Fuzziness and Soft Computing.
[2] D. Van De Ville, W. Philips, and I. Lemahieu, Fuzzy Techniques in Image Processing. New York:
Springer-Verlag, 2000, vol. 52, Studies in Fuzziness and Soft Computing, ch. Fuzzy-based motion
detection and its application to de-interlacing, pp. 337–369.
[3] M. Nachtegael and E. E.Kerre, “Connections between binary, gray-scale and fuzzy mathematical
morphologies,” Fuzzy Sets Syst., to be published.