A heart attack disrupts the normal flow of blood to the heart muscle,potentially causing severe damage or death if not treated promptly.It can lead to long-term health complications,reduce quality of life,and signific...A heart attack disrupts the normal flow of blood to the heart muscle,potentially causing severe damage or death if not treated promptly.It can lead to long-term health complications,reduce quality of life,and significantly impact daily activities and overall well-being.Despite the growing popularity of deep learning,several drawbacks persist,such as complexity and the limitation of single-model learning.In this paper,we introduce a residual learning-based feature fusion technique to achieve high accuracy in differentiating abnormal cardiac rhythms heart sound.Combining MobileNet with DenseNet201 for feature fusion leverages MobileNet lightweight,efficient architecture with DenseNet201,dense connections,resulting in enhanced feature extraction and improved model performance with reduced computational cost.To further enhance the fusion,we employed residual learning to optimize the hierarchical features of heart abnormal sounds during training.The experimental results demonstrate that the proposed fusion method achieved an accuracy of 95.67%on the benchmark PhysioNet-2016 Spectrogram dataset.To further validate the performance,we applied it to the BreakHis dataset with a magnification level of 100X.The results indicate that the model maintains robust performance on the second dataset,achieving an accuracy of 96.55%.it highlights its consistent performance,making it a suitable for various applications.展开更多
Sound Recognition becomes an important tool for intrusion detection or for the monitoring of public premises exposed to personal hostility. It could further identify different sounds. The main idea of the sound recogn...Sound Recognition becomes an important tool for intrusion detection or for the monitoring of public premises exposed to personal hostility. It could further identify different sounds. The main idea of the sound recognition process in a security system is to store samples of different sound signals in the memory of the computer as references,?and?to be analyzed with respect to their frequencies components. In this paper, the sound signal of an unknown source would be analyzed and compared with all the available reference samples,?and?then recognition is made according to the closest sample. The developed security system consists of two main parts: the spectrum analyzer that converts the sound signal to spectrograms. It is designed based on the real-time analyzes, and the recognizer which compares the spectrograms and gives the decision of the recognition by using a special criterion. Experimental results prove that the accuracy of the proposed system can be 98.33% for the selected sample of signals.展开更多
文摘A heart attack disrupts the normal flow of blood to the heart muscle,potentially causing severe damage or death if not treated promptly.It can lead to long-term health complications,reduce quality of life,and significantly impact daily activities and overall well-being.Despite the growing popularity of deep learning,several drawbacks persist,such as complexity and the limitation of single-model learning.In this paper,we introduce a residual learning-based feature fusion technique to achieve high accuracy in differentiating abnormal cardiac rhythms heart sound.Combining MobileNet with DenseNet201 for feature fusion leverages MobileNet lightweight,efficient architecture with DenseNet201,dense connections,resulting in enhanced feature extraction and improved model performance with reduced computational cost.To further enhance the fusion,we employed residual learning to optimize the hierarchical features of heart abnormal sounds during training.The experimental results demonstrate that the proposed fusion method achieved an accuracy of 95.67%on the benchmark PhysioNet-2016 Spectrogram dataset.To further validate the performance,we applied it to the BreakHis dataset with a magnification level of 100X.The results indicate that the model maintains robust performance on the second dataset,achieving an accuracy of 96.55%.it highlights its consistent performance,making it a suitable for various applications.
文摘Sound Recognition becomes an important tool for intrusion detection or for the monitoring of public premises exposed to personal hostility. It could further identify different sounds. The main idea of the sound recognition process in a security system is to store samples of different sound signals in the memory of the computer as references,?and?to be analyzed with respect to their frequencies components. In this paper, the sound signal of an unknown source would be analyzed and compared with all the available reference samples,?and?then recognition is made according to the closest sample. The developed security system consists of two main parts: the spectrum analyzer that converts the sound signal to spectrograms. It is designed based on the real-time analyzes, and the recognizer which compares the spectrograms and gives the decision of the recognition by using a special criterion. Experimental results prove that the accuracy of the proposed system can be 98.33% for the selected sample of signals.
