BP ANN Research Articles

Whole Stand Growth Model for Natural Dahurian Larch Forests Based on BP ANN

Based on 688 permanent sample plots,the whole stand growth model of BP ANN was developed for natural dahurian larch(Larix gemelinii Rupr.) forests in area of the Daxing'an Mountains,using log-sigmoid function(logsig) and linearity function(purelin) of MATLAB as the neural functions.According to the concept of whole stand growth model,the Age(A),Site Class Index(SCI) and Stand Density Index(SDI) were considered as input variables and the Stand Volume(M) was as the output variable in the model.A comparative study between BP ANN model and the common method was also conducted.The result of the model performance analysis was showed that the BP ANN model in this paper had high fitting accuracy(99.6%) and precision(98.9%),it is better than the common methods in fitting and adaptability and it was suitable to predicting stand growth.

Application of a Back-Propagation Artificial Neural Network to Regional Grid-Based Geoid Model Generation Using GPS and Leveling Data

The height difference between the ellipsoidal height h and the orthometric height H is called undulation N. The key issue in transforming the global positioning system GPS-derived ellipsoidal height to the orthometric height is to determine the undulation value accurately. If the undulation N for a point whose position is determined by a GPS receiver can be estimated in the field, then the GPS-derived three-dimensional geocentric coordinate in WGS-84 can be transformed into a local coordinate system and the orthometric height in real-time. In this paper, algorithms of applying a back-propagation artificial neural network BP ANN to develop a regional grid-based geoid model using GPS data e.g., ellipsoidal height and geodetic leveling data e.g., orthometric height are proposed. In brief, the proposed algorithms include the following steps: 1 establish the functional relationship between the point's plane coordinates and its undulation using the BP ANN according to the measured GPS data and leveling data; 2 develop a regional grid-based geoid model using the imaginary grid plane coordinates with a fixed grid interval and the trained BP ANN; 3 develop an undulation interpolation algorithm to estimate a specific point's undulation using the generated grid-based geoid model; and 4 estimate the point's undulation in the field and transform the GPS ellipsoidal height into the orthometric height in real-time. Three data sets from the Taiwan region are used to test the proposed algorithms. The test results show that the undulation interpolation estimation accuracy using the generated grid-based geoid is in the order of 2-4 cm. The proposed algorithms and the detailed test results are presented in this paper.

Support vector classification for SAR of 5-HT3 receptor antagonists

In this work, support vector classification (SVC) algorithm was used to build structure-activity relationship (SAR) model of the 5-hydroxytryptamine type 3 (5-HT3) receptor antagonists with 26 compounds. In a benchmark test, SVC was compared with several techniques of machine learning currently used in the field. The prediction performance of the model was discussed on the basis of the leave-one-out cross-validation. The results show that the accuracy of prediction of SVC model was higher than those of back propagation artificial neural network (BP ANN), K-nearest neighbor (KNN) and Fisher methods.

Support vector regression based QSPR for the prediction of some physicochemical properties of alkyl benzenes

Physicochemical properties of alkyl benzenes are essential to separate pure component from alkyl benzene mixture. Support vector regression (SVR), a novel powerful machine learning technology based on statistical learning theory (SLT), integrated with topological indices was applied to the prediction of five physicochemical properties of alkyl benzenes including the normal boiling point (bp), enthalpy of vaporization at the boiling point ( H vb), critical temperature ( T c), critical pressure ( P c), and critical volume ( V c). In a benchmark test, SVR models for bp, H vb, T c, P c, and V c were compared with several modeling techniques currently used in this field. The prediction accuracy of the model was discussed on the basis of the leave-one-out cross-validation. The results show that the prediction accuracy of SVR model was higher than those of back propagation artificial neural network (BP ANN) and partial least squares (PLS) methods.

Artificial neural network as an incremental non-linear constitutive model for a finite element code

A back propagation artificial neural network (BP ANN) is proposed as a tool for numerical modelling of the constitutive behaviour of a physically non-linear body. Training process of the ANN using experimental data is discussed in details and illustrated with an example. In particular, some difficulties in the constitutive description proposed in consistent, incremental form are discovered and two solutions are proposed to overcome them. Two numerical examples are presented. The first one deals with modelling of elasto-plastic hysteresis, the second shows the application of ANN to approximation of biaxial non-linear behaviour.

Solving the Chemical Mass Balance Problem Using an Artificial Neural Network

A back-propagation artificial neural network (BP ANN) is proposed as a receptor modeling method for solving air pollution source apportionment problems. In order to examine the utility of this method, the simulated aerosol composition data generated by the National Bureau of Standards (NBS) for the EPA workshop on mathematical and empirical receptor modeling held at Quail Roost, NC, in 1982 were examined. Based on the assumption of mass conservation, training sets containing the linear mixing fractions for ambient samples were constructed from input source profiles for the network's learning. The NBS data sets were the prediction sets. Because of the good generalization property of BP ANN, satisfactory prediction results were obtained for NBS data sets I and II. Moreover, when a training set containing as many as possible emission sources some of which were not necessarily active was used, the network was able to identify the actual active sources and quantify their source contributions.

Expression of P55 and P75 TNF receptors on neoplastic cells from patients with chronic lymphocytic leukemia: [formula omitted] Section of Haematology, and Institute of Cancer Research, University of Trondheim, N-7006 Trondheim, Norway

The melting points of ionic liquids (ILs) of imidazolium bromides and imidazolium chlorides have been investigated by means of quantitative structure–activity relationship (QSAR) approach in order to develop prediction models for predicting the melting points of ionic liquid salts. The cationic structures of these ILs were optimized by means of Hyperchem software and MOPAC program. QSAR module of Materials Studio software and Genetic Algorithm (GA) programs were employed to calculate and select the structure descriptors of ILs, then prediction models correlating the selected structure descriptors and melting points of ionic liquids were set up by using the multiple linear regressions (MLR) method and the back-propagation artificial neural network (BP ANN) method, separately. Finally, the obtained QSAR models, including MLR model and BP ANN model, were validated by external test sets. In this work, three data sets, which were 30 imidazolium bromides, 20 imidazolium chlorides and the merging of above two data sets, respectively, were used to investigate the QSAR correlation of the melting points of ILs. The results demonstrated that the prediction mean absolute errors (MAEs) of MLR models for test sets of those three data sets were in the order of 20.52 K, 13.59 K and 21.95 K, and the prediction MAEs of BP ANN models were 8.77 K, 4.98 K and 9.31 K, respectively. It indicated that the predictions of two models for all melting points of ILs were reliable, and the prediction precision of BP ANN model was higher than that of MLR model.