Spatial interpolation method based on integrated RBF neural networks for estimating heavy metals in soil of a mountain region

A novel spatial interpolation method based on integrated radial basis function artificial neural networks （IRBFANNs） is proposed to provide accurate and stable predictions of heavy metals concentrations in soil at un- sampled sites in a mountain region. The IRBFANNs hybridize the advantages of the artificial neural networks and the neural networks integration approach. Three experimental projects under different sampling densities are carried out to study the performance of the proposed IRBFANNs-based interpolation method. This novel method is compared with six peer spatial interpolation methods based on the root mean square error and visual evaluation of the distribution maps of Mn elements. The experimental results show that the proposed method performs better in accuracy and stability. Moreover, the proposed method can provide more details in the spatial distribution maps than the compared interpolation methods in the cases of sparse sampling density.

Neural Network Method for Colorimetry Calibration of Video Cameras

To transfer the color data from a device (video camera) dependent color space into a device? independent color space, a multilayer feedforward network with the error backpropagation (BP) learning rule, was regarded as a nonlinear transformer realizing the mapping from the RGB color space to CIELAB color space. A variety of mapping accuracy were obtained with different network structures. BP neural networks can provide a satisfactory mapping accuracy in the field of color space transformation for video cameras.

Proactive traffic responsive control based on state-space neural network and extended Kalman filter

The state-space neural network and extended Kalman filter model is used to directly predict the optimal timing plan that corresponds to futuristic traffic conditions in real time with the purposes of avoiding the lagging of the signal timing plans to traffic conditions. Utilizing the traffic conditions in current and former intervals, the network topology of the state-space neural network （SSNN）, which is derived from the geometry of urban arterial routes, is used to predict the optimal timing plan corresponding to the traffic conditions in the next time interval. In order to improve the effectiveness of the SSNN, the extended Kalman filter （EKF） is proposed to train the SSNN instead of conventional approaches. Raw traffic data of the Guangzhou Road, Nanjing and the optimal signal timing plan generated by a multi-objective optimization genetic algorithm are applied to test the performance of the proposed model. The results indicate that compared with the SSNN and the BP neural network, the proposed model can closely match the optimal timing plans in futuristic states with higher efficiency.

Local hierarchical non-negative tensor factorization and its application in machinery fault diagnosis

Aiming at the slow convergence and low accuracy problems of the traditional non-negative tensor factorization, a local hierarchical non-negative tensor factorization method is proposed by applying the local objective function theory to non- negative tensor factorization and combining the three semi-non- negative matrix factorization（NMF） model. The effectiveness of the method is verified by the facial feature extraction experiment. Through the decomposition of a series of an air compressor＇s vibration signals composed in the form of a bispectrum by this new method, the basis images representing the fault features and corresponding weight matrices are obtained. Then the relationships between characteristics and faults are analyzed and the fault types are classified by importing the weight matrices into the BP neural network. Experimental results show that the accuracy of fault diagnosis is improved by this new method compared with other feature extraction methods.

SIMULATION INVESTIGATION OF AEROENGINE FAULT DIAGNOSIS USING NEURAL NETWORKS

Traditional scheduled maintenance systems are costly, labor intensive, and typically provide noncomprehensive detection and diagnosis of engine faults. The engine monitoring system (EMS) on modern aircrafts has the potential to provide maintenance personnel with valuable information for detecting and diagnosing engine faults. In this paper, an RBF neural network approach is applied to aeroengine gas path fault diagnosis. It can detect multiple faults and quantify the amount of deterioration of the various engine components as a function of measured parameters. The results obtained demonstrate that the accuracy of diagnosis is consistent with practical requirements. The approach takes advantage of the nonlinear mapping feature of neural networks to capture the appropriate characteristics of an aeroengine. The methodology is generic and applicable to other similar plants having high complexity.

为了更美好的明天而研究未来——记美国未来学家麦格达

去年十月下旬,在波士顿的一次探讨美国未来发展前景的学术会议上,一位略带苏格兰口音、头发些许灰白的女学者,正在就美国女性未来的地位和作用问题发表演说。当她用“人们必须学会如何成为一个训练有素的人”这句话来结束她的演说时,大厅里响起了经久不息的掌声,她的富有幽默感的演说,不但激起听众的笑声,还促使他们深思:在光怪陆离的美国社会中,什么样的个人的未来才是有价值的?许多人梦寐以求的金钱、汽车、洋房和其他物质享受,

Study on Tri-Stimulus Transformation

To decrease number of samples for the implementation of color space transformation, a method for modeling the chromatic characterization of video cameras was proposed. An additional transformation was required to predict output RGB values for an input color. This additional transformation was based on spectral reflectance relationship. The transformed color coordinates were taken as inputs of a multilayer neural network. Based on network outputs, the RGB values to be predicted were calculated. Experimental results were given to illustrate the performance of the method. Even though much less number of training samples are used, this method can also perform well on this color space transformation.

元旦与圣诞

元旦乃是公历每年的第一天,而"圣诞节"则是基督教徒们纪念耶稣降生的日子,具体日期连《圣经》都没有记载,大多数基督教徒便认定与公历元旦仅相隔5天的12月25日为圣诞的日子。对于我们来说,元旦将至时相互祝贺"新年快乐"本来是很有意义的选择,可现在的情形却实在让人捉摸不透,圣诞节在我们的社会主义生活中竟变得如此引人注目。

A Hybrid Neural Network for Spatiotemporal Pattern Recognition

A hybrid network is presented for spatio-temporal feature detecting, which is called TS-LM-SOFM. Its top layer is a novel single layer temporal sequence recognizer called TS which can transform sparse temporal sequential pattern into abstract spatial feature representations. The bottom layer of TS-LM-SOFM, a modified self-organizing feature map, is used as a spatial feature detector. A learning matrix connects the two layers. Experiments show that the hybrid network can well capture the spatio-temporal features of input signals.

INTELLIGENT FUSION FOR AEROENGINE WEAR FAULT DIAGNOSIS

Four common oil analysis techniques, including the ferrography analysis （FA）, the spectrometric oil analysis （SOA）, the particle count analysis （PCA）, and the oil quality testing （OQT）, are used to implement the military aeroengine wear fault diagnosis during the test drive process. To improve the precision and the reliability of the diagnosis, the aeroengine wear fault fusion diagnosis method based on the neural networks （NN） and the Dempster-Shafter （D-S） evidence theory is proposed. Firstly, according to the standard value of the wear limit, original data are pre-processed into Boolean values. Secondly, sub-NNs are established to perform the single diagnosis, and their training samples are dependent on experiences from experts. After each sub-NN is trained, diagnosis results are obtained. Thirdly, the diagnosis results of each sub-NN are considered as the basic probability allocation value to faults. The improved D-S evidence theory is applied to the fusion diagnosis, and the final fusion results are obtained. Finally, the method is verified by a diagnosis example.

Spatial Interpolation of Soil Nutrients Based on BP Neural Network

With Zengcheng City, Guangdong Province, as the object of study, 200 soil sampling points were col ected for the spatial interpolation prediction of soil properties by using Kriging method and BP neural network method. After comparing the interpolation results with the measured values, the root mean square error of the prediction data was obtained. The results showed that the interpolation accuracy of BP neural network was higher than that of Kriging method under the same cir-cumstances, and there was no smoothness in using BP neural network method when there were few sample points. In addition, with no requirement on the distri-bution of sample data, BP neural network method had stronger generalization ability than traditional interpolation method, which was an alternative interpolation method.

Dissociation, culture and morphologic changes of interstitial cells of Cajal in vitro

AIM: To study the method of dissociation, culture and investigate its morphologic changes in vitro of interstitial cells of Cajal (ICC).METHODS: Enzymatic digestion and Ficoll density centrifugation were used to dissociate ICC from the ileal segment of mice. Factors including contamination, Ca2+, Mg2+ and collagenase, and stem cell factor, etc., were investigated.ACK2, the antibody of c-kit, was used to identify the cultured ICC. Both light microscope and fluorescence microscope were used to observe the changes of ICC in vitro.RESULTS: The method for dissociation and culture of ICC in vitro was successfully established. After 24 h, cultured ICC exhibited a few axis-cylinders, and longer axis-cylinders were observed to form synapse of each other after 3 d. More widespread connections formed within 7 d in vitro. The changes of its morphologic character were obvious within 7 d; however, there were no obvious morphologic changes after 30 d.CONCLUSION: Many factors can influence the dissociation and culture of ICC.

Wavelet neural network aerodynamic modeling from flight data based on pso algorithm with information sharing and velocity disturbance

For the accurate description of aerodynamic characteristics for aircraft,a wavelet neural network (WNN) aerodynamic modeling method from flight data,based on improved particle swarm optimization (PSO) algorithm with information sharing strategy and velocity disturbance operator,is proposed.In improved PSO algorithm,an information sharing strategy is used to avoid the premature convergence as much as possible;the velocity disturbance operator is adopted to jump out of this position once falling into the premature convergence.Simulations on lateral and longitudinal aerodynamic modeling for ATTAS (advanced technologies testing aircraft system) indicate that the proposed method can achieve the accuracy improvement of an order of magnitude compared with SPSO-WNN,and can converge to a satisfactory precision by only 60 120 iterations in contrast to SPSO-WNN with 6 times precocities in 200 times repetitive experiments using Morlet and Mexican hat wavelet functions.Furthermore,it is proved that the proposed method is feasible and effective for aerodynamic modeling from flight data.

Study on resource quantity of surface water based on phase space reconstruction and neural network

Proposed a new method to disclose the complicated non-linearity structure of the water-resource system, introducing chaos theory into the hydrology and water resources field, and combined with the chaos theory and artificial neural networks. Training data construction and networks structure were determined by the phase space reconstruction, and establishing nonlinear relationship of phase points with neural networks, the forecasting model of the resource quantity of the surface water was brought forward. The keystone of the way and the detailed arithmetic of the network training were given. The example shows that the model has highly forecasting precision.

Spatial quality evaluation for drinking water based on GIS and ant colony clustering algorithm

To develop a better approach for spatial evaluation of drinking water quality, an intelligent evaluation method integrating a geographical information system(GIS) and an ant colony clustering algorithm(ACCA) was used. Drinking water samples from 29 wells in Zhenping County, China, were collected and analyzed. 35 parameters on water quality were selected, such as chloride concentration, sulphate concentration, total hardness, nitrate concentration, fluoride concentration, turbidity, pH, chromium concentration, COD, bacterium amount, total coliforms and color. The best spatial interpolation methods for the 35 parameters were found and selected from all types of interpolation methods in GIS environment according to the minimum cross-validation errors. The ACCA was improved through three strategies, namely mixed distance function, average similitude degree and probability conversion functions. Then, the ACCA was carried out to obtain different water quality grades in the GIS environment. In the end, the result from the ACCA was compared with those from the competitive Hopfield neural network(CHNN) to validate the feasibility and effectiveness of the ACCA according to three evaluation indexes, which are stochastic sampling method, pixel amount and convergence speed. It is shown that the spatial water quality grades obtained from the ACCA were more effective, accurate and intelligent than those obtained from the CHNN.

Repeated morphine treatment influences operant and spatial learning differentially

Objective To investigate whether repeated morphine exposure or prolonged withdrawal could influence operant and spatial learning differentially. Methods Animals were chronically treated with morphine or subjected to morphine withdrawal. Then, they were subjected to two kinds of learning: operant conditioning and spatial learning. Results The acquisition of both simple appetitive and cued operant learning was impaired after repeated morphine treatment. Withdrawal for 5 weeks alleviated the impairments. Single morphine exposure disrupted the retrieval of operant memory but had no effect on rats after 5-week withdrawal. Contrarily, neither chronic morphine exposure nor 5-week withdrawal influenced spatial learning task of the Morris water maze. Nevertheless, the retrieval of spatial memory was impaired by repeated morphine exposure but not by 5-week withdrawal. Conclusion These observations suggest that repeated morphine exposure can influence different types of learning at different aspects, implicating that the formation of opiate addiction may usurp memory mechanisms differentially.

Neuro-Space Mapping for Modeling Heterojunction Bipolar Transistor

A neuro-space mapping(Neuro-SM) for modeling heterojunction bipolar transistor(HBT) is presented, which can automatically modify the input signals of the given model by neural network. The novel Neuro-SM formulations for DC and small-signal simulation are proposed to obtain the mapping network. Simulation results show that the errors between Neuro-SM models and the accurate data are less than 1%, demonstrating that the accurcy of the proposed method is higher than those of the existing models.

Applying Neural Network in Evaporative Cooler Performance Prediction

The back-propagation （BP） neural network is created to predict the performance of a direct evaporative cooling （DEC） air conditioner with GLASdek pads. The experiment data about the performance of the DEC air conditioner are obtained. Some experiment data are used to train the network until these data can approximate a function, then, simulate the network with the remanent data. The predicted result shows satisfying effects.

Neural Network Ensemble Residual Kriging Application for Spatial Variability of Soil Properties

High quality, agricultural nutrient distribution maps are necessary for precision management, but depend on initial soil sample analyses and interpolation techniques. To examine the methodologies for and explore the capability of interpolating soil properties based on neural network ensemble residual kriging, a silage field at Hayes, Northern Ireland, UK, was selected for this study with all samples being split into independent training and validation data sets. The training data set, comprised of five soil properties: soil pH, soil available P, soil available K, soil available Mg and soil available S,was modeled for spatial variability using 1) neural network ensemble residual kriging, 2) neural network ensemble and 3) kriging with their accuracies being estimated by means of the validation data sets. Ordinary kriging of the residuals provided accurate local estimates, while final estimates were produced as a sum of the artificial neural network (ANN)ensemble estimates and the ordinary kriging estimates of the residuals. Compared to kriging and neural network ensemble,the neural network ensemble residual kriging achieved better or similar accuracy for predicting and estimating contour maps. Thus, the results demonstrated that ANN ensemble residual kriging was an efficient alternative to the conventional geo-statistical models that were usually used for interpolation of a data set in the soil science area.

Prevalence and determinants of delayed gastric emptying in hospitalised Type 2 diabetic patients

AIM: To determine the prevalence of delayed gastric emptying (GE) in older patients with Type 2 diabetes mellitus. METHODS: One hundred and forty seven patients with Type 2 diabetes, of whom 140 had been hospitalised, mean age 62.3 ± 8.0 years, HbA1c 9.1% ± 1.9%, treated with either oral hypoglycemic drugs or insulin were studied. GE of a solid meal (scintigraphy), autonomic nerve function, upper gastrointestinal symptoms, acute and chronic glycemic control were evaluated. Gastric emptying results were compared to a control range of hospitalised patients who did not have diabetes. RESULTS: Gastric emptying was delayed (T50 > 85 min) in 17.7% patients. Mean gastric emptying was slower in females (T50 72.1 ± 72.1 min vs 56.9 ± 68.1 min, P = 0.02) and in those reporting nausea (112.3 ± 67.3 vs 62.7 ± 70.0 min, P < 0.01) and early satiety (114.0 ± 135.2 vs 61.1 ± 62.6 min, P = 0.02). There was no correlation between GE with age, body weight, duration of diabetes, neuropathy, current glycemia or the total score for upper gastrointestinal symptoms. CONCLUSION: Prolonged GE occurs in about 20% of hospitalised elderly patients with Type 2 diabetes when compared to hospitalised patients who do not have diabetes. Female gender, nausea and early satiety areassociated with higher probability of delayed GE.