Current Issue : October - December Volume : 2018 Issue Number : 4 Articles : 6 Articles
Intercriteria analysis (ICA) is a new method, which is based on the concepts of index matrices and intuitionistic fuzzy sets, aiming\nat detection of possible correlations between pairs of criteria, expressed as coefficients of the positive and negative consonance\nbetween each pair of criteria. Here, the proposed method is applied to study the behavior of one type of neural networks, the\nmodular neural networks (MNN), that combine several simple neuralmodels for simplifying a solution to a complex problem.They\nare a tool that can be used for object recognition and identification. Usually the inputs of the MNN can be fed with independent\ndata. However, there are certain limits when we may use MNN, and the number of the neurons is one of the major parameters\nduring the implementation of theMNN. On the other hand, a high number of neurons can slow down the learning process, which\nis not desired. In this paper, we propose a method for removing part of the inputs and, hence, the neurons, which in addition leads\nto a decrease of the error between the desired goal value and the real value obtained on the output of the MNN. In the research\nwork reported here the authors have applied the ICA method to the data fromreal datasets with measurements of crude oil probes,\nglass, and iris plant.The method can also be used to assess the independence of data with good results....
This paper focuses on the global exponential almost periodic synchronization of quaternion-valued neural networks with timevarying\ndelays. By virtue of the exponential dichotomy of linear differential equations, Banach�s fixed point theorem, Lyapunov\nfunctional method, and differential inequality technique, some sufficient conditions are established for assuring the existence\nand global exponential synchronization of almost periodic solutions of the delayed quaternion-valued neural networks, which\nare completely new. Finally, we give one example with simulation to show the applicability and effectiveness of our main results....
Thecentralized Kalman filter is always applied in the velocity and attitude matching of Transfer Alignment (TA). But the centralized\nKalman hasmany disadvantages, such as large amount of calculation, poor real-time performance, and low reliability. In the paper,\nthe federal Kalman filter (FKF) based on neural networks is used in the velocity and attitude matching of TA, the Kalman filter\nis adjusted by the neural networks in the two subfilters, the federal filter is used to fuse the information of the two subfilters,\nand the global suboptimal state estimation is obtained. The result of simulation shows that the federal Kalman filter based on\nneural networks is better in estimating the initial attitude misalignment angle of inertial navigation system (INS) when the system\ndynamic model and noise statistics characteristics of inertial navigation system are unclear, and the estimation error is smaller and\nthe accuracy is higher....
The aim of this work is to develop a new method to overcome the increased training time when a recognition model is updated\nbased on the condition of new features extracted from new samples. As a common complex system, red wine has a rich\nchemical composition and is used as an object of this research. The novel method based on incremental learning support vector\nmachine (I-SVM) combined with ultravioletââ?¬â??visible (UV-Vis) spectroscopy was applied to discriminant analysis of the brands\nof red wine for the first time. In this method, new features included in the new training samples were introduced into the\nrecognition model through iterative learning in each iteration, and the recognition model was rapidly updated without\nsignificantly increasing the training time. Experimental results show that the recognition model established by this method\nobtains a good balance between training efficiency and recognition accuracy....
This research presents a novel hybrid prediction technique, namely, self-tuning least squares support vector machine (STLSSVM),\nto accurately model the friction capacity of driven piles in cohesive soil. The hybrid approach uses LS-SVM as\na supervised-learning-based predictor to build an accurate input-output relationship of the dataset and SOS method to optimize\nthe ÃÆ? and c parameters of the LS-SVM. Evaluation and investigation of the ST-LSSVM were conducted on 45 training data and 20\ntesting data of driven pile load tests that were compiled from previous studies. The prediction accuracy of the ST-LSSVM was then\ncompared to other machine learning methods, namely, LS-SVM and BPNN, and was benchmarked with the previous results by\nneural network (NN) from Goh using coefficient of correlation (R), mean absolute error (MAE), and root mean square error\n(RMSE). The comparison showed that the ST-LSSVM performed better than LS-SVM, BPNN, and NN in terms of R, RMSE, and\nMAE. This comprehensive evaluation confirmed the capability of hybrid approach SOS and LS-SVM to modeling the accurate\nfriction capacity of driven piles in clay. It makes for a reliable and robust assistance tool in helping all geotechnical engineers\nestimate friction pile capacity....
Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely\nused in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has\nachieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course\nof parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is\nintroduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm\nso as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertiaweights such\nas constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition.The\nexperimental results show that the model training time of the proposedMKL-SVM-PSO algorithm is only 1/7 of the training time\nof theMKL-SVMgrid search algorithm, achieving better recognition effect.Moreover, Euclidean norm of normalized error vector\nis proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence.Through\nstatistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial\nweight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the\nparameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence ismuch closer to the\noptimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified....
Loading....