Autor: Sajit, Ahmed S. - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: Breast cancer cad system by using transfer learning and enhanced ROI
Autorzy:: Al-Huseiny, Muayed S
Sajit, Ahmed S
Powiązania:: https://bibliotekanauki.pl/articles/2097433.pdf
Data publikacji:: 2022
Wydawca:: Polskie Towarzystwo Promocji Wiedzy
Tematy:: mammography
transfer learning
computer vision
image processing
Opis:: Computer systems are being employed in specialized professions such as medical diagnosis to alleviate some of the costs and to improve dependability and scalability. This paper implements a computer aided breast cancer diagnosis system. It utilizes the publicly available mini MIAS mammography image dataset. Images are preprocessed to clean isolate breast tissue region. Extracted regions are used to adjust and verify a pretrained convolutional deep neural network, the GoogLeNet. The implemented model shows good performance results compared to other published works with accuracy of 86.6%, sensitivity of 75% and specificity of 88.9%.
Źródło:: Applied Computer Science; 2022, 18, 1; 99--111
1895-3735
Pojawia się w:: Applied Computer Science
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 2.

Tytuł:: Detection of epileptic seizures in EEG by using machine learning techniques
Autorzy:: AL-Huseiny, Muayed S.
Sajit, Ahmed S.
Powiązania:: https://bibliotekanauki.pl/articles/2174474.pdf
Data publikacji:: 2023
Wydawca:: Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
Tematy:: epileptic seizure
EEG
machine learning
CADe
biomedical engineering
napad padaczkowy
uczenie maszynowe
inżynieria biomedyczna
Opis:: In this research a public dataset of recordings of EEG signals of healthy subjects and epileptic patients was used to build three simple classifiers with low time complexity, these are decision tree, random forest and AdaBoost algorithm. The data was initially preprocessed to extract short waves of electrical signals representing brain activity. The signals are then used for the selected models. Experimental results showed that random forest achieved the best accuracy of detection of the presence/absence of epileptic seizure in the EEG signals at 97.23% followed by decision tree with accuracy of 96.93%. The least performing algorithm was the AdaBoost scoring accuracy of 87.23%. Further, the AUC scores were 99% for decision tree, 99.9% for random forest and 95.6% for AdaBoost. These results are comparable to state-of-the-art classifiers which have higher time complexity.
Źródło:: Diagnostyka; 2023, 24, 1; art. no. 2023108
1641-6414
2449-5220
Pojawia się w:: Diagnostyka
Dostawca treści:: Biblioteka Nauki

Artykuł

Informacja