P. P. Fathimathul Rajeena^1,*, R. Sivakumar²

Intelligent Automation & Soft Computing, Vol.35, No.3, pp. 2837-2855, 2023, DOI:10.32604/iasc.2023.030144

Abstract An accurate and early diagnosis of brain tumors based on medical imaging modalities is of great interest because brain tumors are a harmful threat to a person’s health worldwide. Several medical imaging techniques have been used to analyze brain tumors, including computed tomography (CT) and magnetic resonance imaging (MRI). CT provides information about dense tissues, whereas MRI gives information about soft tissues. However, the fusion of CT and MRI images has little effect on enhancing the accuracy of the diagnosis of brain tumors. Therefore, machine learning methods have been adopted to diagnose brain tumors in recent years. This paper intends… More >

Junyu Chen¹, Yunwen Feng^1,*, Cheng Lu^1,2, Chengwei Fei²

CMES-Computer Modeling in Engineering & Sciences, Vol.129, No.2, pp. 1013-1027, 2021, DOI:10.32604/cmes.2021.016980

Abstract As the key component in aeroengine rotor systems, the health status of rolling bearings directly influences the reliability and safety of aeroengine rotor systems. In order to monitor rolling bearing conditions, a fusion fault diagnosis method, namely empirical mode decomposition (EMD)-Mahalanobis distance (E2MD) and improved wavelet threshold (IWT) (E2MD-IWT) for vibrational signals and acoustic emission (AE) signals is developed to improve the diagnostic accuracy of rolling bearings. The IWT method is proposed with a hard wavelet threshold and a soft wavelet threshold. Moreover, it is shown to be effective through numerical simulation. EMD is utilized to process the original AE… More >