Time filter

Source Type

Jia B.,Shanghai JiaoTong University | Yu B.,Shanghai JiaoTong University | Wu Q.,Shanghai JiaoTong University | Yang X.,Middlesex University | And 3 more authors.
Neurocomputing | Year: 2016

Data clustering is a meaningful tool that can, help people classify mixed data automatically. With rapid technological development, data in modern applications become large scale and high dimensional. Some original clustering methods are not suitable for complicated datasets. To improve the performance of the popular kernel fuzzy C-means (KFCM), this study proposed a local density adaptive diffusion maps (LDM) technique to obtain a reliable similarity description and dimensionality reduction. To find the valid cluster centroids of the dataset, this study also proposed an improved cuckoo search (ICS) to optimize the unknown parameters of the KFCM model. The ICS algorithm utilized quaternions to represent individuals who will be optimized. Variable step length of Lévy flights and discovery probability were also proposed, which were adjusted by the evolutional ratio of the cuckoo search process. To verify the availability of the ICS, 5 benchmark functions were tested. Finally, the proposed hybrid ICS and LDM based on KFCM (ICS-LDM-KFCM) was used to identify 4 standard artificial and 6 real world datasets. Compared with other clustering methods, the proposed method obtained more accurate results. This method is verified to be more suitable for complicated datasets with large number of attributes and clusters. © 2016 Elsevier B.V. Source

Wu Q.,Shanghai JiaoTong University | Chen X.,Center for Monitoring Research | Ren H.,Center for Monitoring Research | Wei C.,Institute of Manned Space System Engineering | And 4 more authors.
Aerospace Science and Technology | Year: 2016

The evaluation of the flight performance via multiple physiological signals is an important problem in the field of flight safety. A hybrid prediction model is proposed to dispose multiple physiological signals with high dimension in this paper. Main contribution of our model is that of a novel bacterial foraging algorithm (BF) to optimize Elman neural network, which can perform parallel search and escape local minimum easily, and provide better prediction accuracy of the flight performance. Other bio-inspired algorithms such as genetic algorithm (GA), particle swarm optimization (PSO) and chaotic GA are also used to optimize the unknown parameters of the Elman network. Experimental results indicate that the proposed hybrid model based on BF algorithm and Elman network is well suited for the evaluation and prediction of the flight performance. Compared with the other public algorithms, the BF can easily identify the unknown parameters of the established models and has better optimization capability. © 2016 Elsevier Masson SAS Source

Wu Q.,Shanghai JiaoTong University | Mao J.F.,Nanyang Technological University | Wei C.F.,Institute of Manned Space System Engineering | Fu S.,Shanghai JiaoTong University | And 5 more authors.
Neurocomputing | Year: 2016

In this study, a novel BF-PSO-FSVCM model has been proposed to identify the fatigue status of the electromyography (EMG) signal. To improve the classifier accuracy of fuzzy support vector classification machine (FSVCM), a hybrid Bacterial Foraging (BF) and particle swarm optimization (PSO) is proposed to optimize the unknown parameters of the classifier. In the proposed method, the EMG signals are firstly decomposed by discrete wavelet transform (DWT), Fast Fourier Transformation (FFT) and Ensemble Empirical Mode Decomposition (EEMD)-Hilbert transform (HT), and then a set of combined features were extracted from different types of fatigue or normal EMG signals. The optimal fatigue vectors of static, local and dynamic fatigue are also provided in this study. The obtained results obviously indicate that further significant enhancements in terms of classification accuracy can be achieved by the proposed BF-PSO-FSVCM classification system. BF-PSO-FSVCM is developed as an efficient tool so that various support vector classification machines (SVCMs) can be used conveniently as the core of BF-PSO-FSVCM for diagnosis of fatigue status. © 2015 Elsevier B.V. Source

Du X.,Beihang University | Hou Y.,Institute of Manned Space System Engineering | Sun C.,Beihang University | Zhou Y.,Beihang University
Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica | Year: 2015

Currently high power aero-generators start to adopt variable frequency power output ranging from 360 Hz to 800 Hz, the most distinct influence of which is low starting torque of induction motor at high frequency when the variable frequency power is supplied directy. An analytical method is proposed to optimize the rectangular rotor slot of cage induction motor for starting torque maximization under the premise of invariant steady-state performance. Skin effect coefficient and slot leakage are affected by slot modification and will produce both positive and negative effects on starting torque. Combining the two factors, a dynamic rotor parameter model including slot sizes and frequency is established to revise the traditional torque formula and the starting torque equation regarding rotor slot sizes is obtained, which gains ground for the starting torque optimization. The rotor slot of a 7.5 kW induction motor is optimized with analytical method. Simulation and tests were conducted to verify the starting characteristics of the motor under aero variable frequency power supply, which verified the effectiveness of the optimization method for rectangular rotor slot. ©, 2015, AAAS Press of Chinese Society of Aeronautics and Astronautics. All right reserved. Source

Wu Q.,Shanghai JiaoTong University | Wei C.F.,Institute of Manned Space System Engineering | Cai Z.X.,Shanghai JiaoTong University | Ding L.,Shanghai JiaoTong University | Law R.,Hong Kong Polytechnic University
Optik | Year: 2015

A hybrid dynamic fatigue diagnosis method based on a variation of ensemble empirical mode decomposition (VEEMD) and mean instantaneous frequency (MIF) is presented. This new approach consists of sifting an ensemble of white noise-added signal (data) and treats the mean as the final true result. In the method here proposed, a particular noise is added at each stage of the decomposition and a unique residue is computed to obtain each mode. Our results showed that MIF estimated from each instantaneous frequency of intrinsic mode functions (IMFs) decomposed by the proposed VEEMD is a relevant feature to muscular fatigue diagnosis. We found that MIF reduces when the force level of the muscle contraction increases. Source

Discover hidden collaborations