Multiple Sclerosis (MS) is one of the most important diseases of the central nervous system. This disease causes small lesions detectable in Magnetic Resonance Imaging (MRI) images of the patient’s brain. Because of the small size of the lesions, their distribution, and their similarity to some other diseases, the MS diagnosis can be difficult for specialists and may be mistaken. In this paper, we presented a new method based on deep learning for the automatic classification of MRI images. The proposed method is a combinational architecture from transfer learning and wavelet transform (WT). First, WT was applied to the input MRI image, and its four output sub-bands are used as the input of four fine-tuning networks based on EfficientNet-B3. Transfer learning networks perform feature extraction on all four sub-bands. Then, their outputs are combined, and the result is classified by a fully connected neural network. Due to the feature of WT to extract local features, it was possible to highlight the lesions in the images and subsequently classify it with higher accuracy and precision. Various criteria have been used to evaluate the proposed method. The results of the experiments show that the Values of accuracy, precision, sensitivity, and specificity are 98.91%, 99.20%, 99.20%, and 98.33%, respectively. پرونده مقاله

Assessing the seismic vulnerability of existing buildings is one of the major concerns of governments in the world. Reducing the destructive and catastrophic consequences of earthquakes is necessary and inevitable. So far, various techniques have been presented to evaluate the seismic vulnerability of buildings. One of the fast and effective assessment techniques is the Rapid Visual Screening (RVS) technique with fastly identify high-risk buildings for a more accurate assessment. Among the RVS methods, the Hassan-Sozen PI method is the simplest method to evaluate the seismic vulnerability of low-rise RC buildings. The value of the priority index (PI) is determined from the simple geometric features of the building such as the number of stories, floors area, column area, area of concrete walls and infilled in the main directions of the building. In this article, the data collection have been gathered from Elyasi et al.'s reference such as geometrical information (with geometrical features provided by Hassan-Sozen) and earthquake features (peak ground acceleration and earthquake magnitude) for 658 low-rise RC buildings. The number of considered input features includes seven geometric features and two earthquake features (9 features in total) and the predicted output of Hassan-Sozen priority index. The machine learning technique utilized in this article for prediction seismic vulnerability is a probabilities random forest in which a simple Bayesian method is used to create forest trees. This method has had a slight improvement in accuracy criteria and considerable improvement in accuracy and recall criteria compared to other traditional random forest and ML methods.

پرونده مقاله