A comparative analysis among computational intelligence techniques for dissolved oxygen prediction in Delaware River

Most of the water quality models previously developed and used in dissolved oxygen （DO） prediction are complex. Moreover, reliable data available to develop/calibrate new DO models is scarce. Therefore, there is a need to study and develop models that can handle easily measurable parameters of a particular site, even with short length. In recent decades, computational intelligence techniques, as effective approaches for predicting complicated and significant indicator of the state of aquatic ecosystems such as DO, have created a great change in predictions. In this study, three different AI methods comprising： （1） two types of artificial neural networks （ANN） namely multi linear perceptron （MLP） and radial based function （RBF）; （2） an advancement of genetic programming namely linear genetic programming （LGP）; and （3） a support vector machine （SVM） technique were used for DO prediction in Delaware River located at Trenton, USA. For evaluating the performance of the proposed models, root mean square error （RMSE）, Nash-Sutcliffe efficiency coefficient （NS）, mean absolute relative error （MARE） and, correlation coeffi- cient statistics （R） were used to choose the best predictive model. The comparison of estimation accu- racies of various intelligence models illustrated that the SVM was able to develop the most accurate model in DO estimation in comparison to other models. Also, it was found that the LGP model performs better than the both ANNs models. For example, the determination coefficient was 0.99 for the best SVM model, while it was 0.96, 0.91 and 0.81 for the best LGP, MLP and RBF models, respectively. In general, the results indicated that an SVM model could be employed satisfactorily in DO estimation.

Comparison on Vulnerability of European and Chinese Air Transport Networks under Spatial Hazards

European air transport network(EATN)and Chinese air transport network(CATN),as two important air transport systems in the world,are facing increasingly spatial hazards,such as extreme weathers and natural disasters. In order to reflect and compare impact of spatial hazards on the two networks in a practical way,a new spatial vulnerability model(SVM)is proposed in this paper,which analyzes vulnerability of a network system under spatial hazards from the perspectives of network topology and characteristics of hazards. Before introduction of the SVM,two abstract networks for EATN and CATN are established with a simple topological analysis by traditional vulnerability method. Then,the process to study vulnerability of an air transport network under spatial hazards by SVM is presented. Based on it,a comparative case study on EATN and CATN under two representative spatial hazard scenarios,one with an even spatial distribution,named as spatially uniform hazard,and the other with an uneven spatial distribution that takes rainstorm hazard as an example,is conducted. The simulation results show that both of EATN and CATN are robust to spatially uniform hazard,but vulnerable to rainstorm hazard. In the comparison of the results of the two networks that only stands from the points of network topology and characteristics of hazard without considering certain unequal factors,including airspace openness and flight safety importance in Europe and China,EATN is more vulnerable than CATN under rainstorm hazard. This suggests that when the two networks grow to a similar developed level in future,EATN needs to pay more attention to the impact of rainstorm hazard.

TYRE DYNAMICS MODELLING OF VEHICLE BASED ON SUPPORT VECTOR MACHINES

Various methods of tyre modelling are implemented from pure theoretical to empirical or semi-empirical models based on experimental results. A new way of representing tyre data obtained from measurements is presented via support vector machines （SVMs）. The feasibility of applying SVMs to steady-state tyre modelling is investigated by comparison with three-layer backpropagation （BP） neural network at pure slip and combined slip. The results indicate SVMs outperform the BP neural network in modelling the tyre characteristics with better generalization performance. The SVMsqyre is implemented in 8-DOF vehicle model for vehicle dynamics simulation by means of the PAC 2002 Magic Formula as reference. The SVMs-tyre can be a competitive and accurate method to model a tyre for vehicle dynamics simuLation.

Decoding pilot behavior consciousness of EEG, ECG, eye movements via an SVM machine learning model

To decode the pilot’s behavioral awareness,an experiment is designed to use an aircraft simulator obtaining the pilot’s physiological behavior data.Existing pilot behavior studies such as behavior modeling methods based on domain experts and behavior modeling methods based on knowledge discovery do not proceed from the characteristics of the pilots themselves.The experiment starts directly from the multimodal physiological characteristics to explore pilots’behavior.Electroencephalography,electrocardiogram,and eye movement were recorded simultaneously.Extracted multimodal features of ground missions,air missions,and cruise mission were trained to generate support vector machine behavior model based on supervised learning.The results showed that different behaviors affects different multiple rhythm features,which are power spectra of theθwaves of EEG,standard deviation of normal to normal,root mean square of standard deviation and average gaze duration.The different physiological characteristics of the pilots could also be distinguished using an SVM model.Therefore,the multimodal physiological data can contribute to future research on the behavior activities of pilots.The result can be used to design and improve pilot training programs and automation interfaces.

Non-Destructive Crack Detection of Preserved Eggs Using a Machine Vision and Multivariate Analysis

Pidan or century egg, also known as preserved egg, is one of the most traditional and popular egg products in China. The crack detection of preserved eggshell is very important to guarantee its quality. In this study, we develop an image algorithm for preserved eggshell＇s crack detection by using natural light and polarized image. Four features including crack length, crack state coefficient, maximum projection and angular point are extracted from the natural light image by morphology calculus algorithms. The support vector machines（SVM） model with radial basis kernel function is established using the four features with an accuracy of about 92%. The detection accuracy is improved to 94% by using a new characteristic parameter of crack length on polarization image. The Multi-information fusion analysis indicates the potential for cracks detection by a real-time synthesis imaging system.

Model parameters estimation of aero-engine based on hybrid optimization algorithm

A hybrid optimization algorithm for the time-domain identification of multivariable,state space model for aero-engine was presented in this paper.The optimization procedure runs particle swarm optimization(PSO) and least squares optimization(LSO) "in series".PSO starts from an initial population and searches for the optimum solution by updating generations.However,it can sometimes run into a suboptimal solution.Then LSO can start from the suboptimal solution of PSO,and get an optimum solution by conjugate gradient algorithm.The algorithm is suitable for the high-order multivariable system which has many parameters to be estimated in wide ranges.Hybrid optimization algorithm is applied to estimate the parameters of a 4-input 4-output state variable model(SVM) for aero-engine.The simulation results demonstrate the effectiveness of the proposed algorithm.