No abstract

No abstract

This paper proposes an automatic reliable two-stage hybrid hierarchical method for ECG heartbeat classification. The heartbeats are segmented dynamically to avoid the consequences of the heart rate variability. Discrete Wavelet Transform (DWT) is utilized to extract morphological features. The extracted features are then reduced by using Principle Component Analysis (PCA). Subsequently, the resulted features along with four RR features are fed into Support Vector Machine (SVM) to classify five categories. Thereafter, the heartbeats are further classified to one of the classes belonging to the assigned category. Two different strategies for classification have been investigated: One versus All and One versus One. The proposed method has been applied on data from lead 1 and lead 2. A new fusion step is introduced, where stacked generalisation algorithm is applied and different types of classifiers have been examined. Experiments have been carried out using a MIT_BIH database. The best overall and average accuracies obtained by the first stage are 98.40% and 97.50% respectively. For the second stage, 94.94% and 93.19% are the best overall and average accuracies obtained respectively. The best results are achieved using SVM with one versus one classification strategy for both stages and decision trees classifier for the fusion step.

No abstract

Computer aided diagnosis (CAD) has a vital role and becomes an urgent demand nowadays. Bone fractures cases are considered from the most frequently occured dieases among individuals. Moreover, the incorrect diagnosis of the bone fractures cases may cause disability for the patient. Hence, CAD system for bone fractures has become a must. This paper proposes a two-stage classifcation method for bone type classification and bone abnormality detection. Xception pre-trained model is considered for all experiments. Two different approaches are utilized for the testing phase: 1) Singl-view and 2) Multi-view approachs. The enhanced images are fed into the first stage to be classified into one of the seven classes: shoulder, humerus, forearm, elbow, wrist, hand and finger. Thereafter, the classified bones are fed into the second stage to detect whether the bone is normal or International Journal of Intelligent Computing and Information Sciences https://ijicis.journals.ekb.eg/ 83 H. El-Saadawy et al. abnormal. MURA dataset has been utilized for all experiments. Moreover, the last layer of the utilized model is replaced by Support Vector Machine (SVM) layer. The results reveal the superiority of the SVM layer.