J
Jiuwen Cao
Researcher at Hangzhou Dianzi University
Publications - 185
Citations - 4340
Jiuwen Cao is an academic researcher from Hangzhou Dianzi University. The author has contributed to research in topics: Extreme learning machine & Computer science. The author has an hindex of 29, co-authored 151 publications receiving 3029 citations. Previous affiliations of Jiuwen Cao include University of Electronic Science and Technology of China & Nanyang Technological University.
Papers
More filters
Journal ArticleDOI
Excavation equipment classification based on improved MFCC features and ELM
TL;DR: An intelligent classification system for four representative excavation equipments and an improved feature extraction approach based on the Mel-Frequency Cepstrual Coefficients (MFCC) which can efficiently describe the dynamics of acoustics wave is developed.
Journal ArticleDOI
Composite Function Wavelet Neural Networks with Differential Evolution and Extreme Learning Machine
TL;DR: A new learning method for composite function wavelet neural networks (CFWNN) is introduced by combining the differential evolution (DE) algorithm with extreme learning machine (ELM), in short, as CWN-E-ELM, which has a much more compact network size and is able to achieve a better generalization performance.
Journal ArticleDOI
BECT Spike Detection Based on Novel EEG Sequence Features and LSTM Algorithms
TL;DR: Wang et al. as mentioned in this paper proposed a novel BECT spike detection algorithm based on time domain EEG sequence features and the long short-term memory (LSTM) neural network, which can obtain an average of 88.54% F1 score, 92.04% sensitivity, and 85.75% precision.
Journal ArticleDOI
An Intelligent Scoring System and Its Application to Cardiac Arrest Prediction
Nan Liu,Zhiping Lin,Jiuwen Cao,Zhi Xiong Koh,Tongtong Zhang,Guang-Bin Huang,Wee Ser,Marcus Eng Hock Ong +7 more
TL;DR: Experimental results reveal that the proposed scoring system not only achieves satisfactory performance on determining the risk of cardiac arrest within 72 h but also has the ability to generate continuous risk scores rather than a simple binary decision by a traditional classifier.
Journal ArticleDOI
An improved feature extraction algorithm for automatic defect identification based on eddy current pulsed thermography
TL;DR: The improved feature extraction algorithm in Eddy Current Pulsed Thermography is developed to realize automatic defect identification and can reduce the time of thermographic sequence processing to improve the detection efficiency.