This paper introduces a neurodynamics optimization model to compute the solution of mathematical programming with equilibrium constraints (MPEC). A smoothing method based on NPC-function is used to obtain a relaxed optimization problem. The optimal solution of the global optimization problem is estimated using a new neurodynamic system, which, in finite time, is convergent with its equilibrium point. Compared to existing models, the proposed model has a simple structure, with low complexity. The new dynamical system is investigated theoretically, and it is proved that the steady state of the proposed neural network is asymptotic stable and global convergence to the optimal solution of MPEC. Numerical simulations of several examples of MPEC are presented, all of which confirm the agreement between the theoretical and numerical aspects of the problem and show the effectiveness of the proposed model. Moreover, an application to resource allocation problem shows that the new method is a simple, but efficient, and practical algorithm for the solution of real-world MPEC problems.
Artificial neural networks (ANN) are one of the highly preferred artificial intelligence techniques for brain image segmentation. The commonly used ANN is the supervised ANN, namely Back Propagation Neural Network (BPN). Even though BPNs guarantee high efficiency, they are computationally non-feasible due to the huge convergence time period. In this work, the aspect of computational complexity is tackled using the proposed high speed BPN algorithm (HSBPN). In this modified approach, the weight vectors are calculated without any training methodology. Magnetic resonance (MR) brain tumor images of three stages, namely severe, moderate and mild, are used in this work. An extensive feature set is extracted from these images and used as input for the neural network. A comparative analysis is performed between the conventional BPN and the HSBPN in terms of convergence time period and segmentation efficiency. Experimental results show the superior nature of HSBPN in terms of the performance measures.
Time series consists of complex nonlinear and chaotic patterns that are difficult to forecast. This paper proposes a novel hybrid forecasting model which combines the group method of data handling (GMDH) and the least squares support vector machine (LSSVM), known as GLSSVM. The GMDH is used to determine the useful input variables for the LSSVM model and the LSSVM model that works as time series forecasting. Three well-known time series data sets are used in this study to demonstrate the effectiveness of the forecasting model. These data are utilized to forecast through an application aimed to handle real life time series. The results found by the proposed model were compared with the results of the GMDH and LSSVM models. Experiment result indicates that the hybrid model was a powerful tool to model time series data and provides a promising technique in time series forecasting methods.
The paper preseiits an investigation on vibrations of mechanical systems arising from unbalanced masses. At the experimental stage, a power transmission shaft is driven at different operating speeds, therefore, the paranieters, such as displacement, velocity and acceleration in vertical direction due to body vibrations are measured at various points on the frame before and after balancing. Balancing has provided a definite decrease in the amplitudes of vibration parameters.
In addition to these studies mentioned above, the use of Neural Network (NN) for vibration analysis of a frame due to unbalanced transmission shaft is also achieved. The results show that the NN approach exactly follows the foregoing results. This implies the necessity of the non-linear modelling capabilities of the NN for vibration problems of mechanical systems.
Swarm intelligence is an emerging field with wide-reaching application opportunities in problems of optimization, analysis and machine learning. While swarm systems have proved very effective when applied to a variety of problems, swarm-based methods for computer vision have received little attention. This paper proposes a swarm system capable of extracting and exploiting the geometric properties of objects in images for fast and accurate recognition. In this approach, computational agents move over an image and affix themselves to relevant features, such as edges and corners. The resulting feature profile is then processed by a classification subsystem to categorize the object. The system has been tested with images containing several simple geometric shapes at a variety of noise levels, and evaluated based upon the accuracy of the system's predictions. The swarm system is able to accurately classify shapes even with high image noise levels, proving this approach to object recognition to be robust and reliable.
Time series forecasting, such as stock price prediction, is one of the most important complications in the financial area as data is unsteady and has noisy variables, which are affected by many factors. This study applies a hybrid method of Genetic Algorithm (GA) and Artificial Neural Network (ANN) technique to develop a method for predicting stock price and time series. In the GA method, the output values are further fed to a developed ANN algorithm to fix errors on exact point. The analysis suggests that the GA and ANN can increase the accuracy in fewer iterations. The analysis is conducted on the 200-day main index, as well as on five companies listed on the NASDAQ. By applying the proposed method to the Apple stocks dataset, based on a hybrid model of GA and Back Propagation (BP) algorithms, the proposed method reaches to 99.99% improvement in SSE and 90.66% in time improvement, in comparison to traditional methods. These results show the performances and the speed and the accuracy of the proposed approach.
The aim of this paper is to present a cheap post-production test for MEMS (Micro Electro Mechanical Systems) accelerometers. The method is based on the impulse response (IR) using neural network predicting values of crucial parameters of MEMS component. Current mechanical testing is time consuming and costly. The MEMS structure combining electro-thermal excitation and piezoresistive sensing was selected for this experiment including the structure model generated using the Simulink software package (MATLAB). The simulation results demonstrate an excellent prediction of neural network and their outstanding agreement with the proposed model. and Cílem tohoto článku je představit levný povýrobní test MEMS (Micro Electro Mechanical Systems) akcelerometrů. Tato metoda je založena na vyhodnocování impulsové odezvy (IR) pomocí neuronové sítě, která předpovídá hodnotu důležitých parametrů MEMS součástky. Současné mechanické testování je časově i finančně náročné. Pro účely tohoto experimentu byla zvolena MEMS struktura kombinující elektro-tepelné vybuzení a piezorezistivní detekci. Pro účely tohoto experimentu byl také použit model této struktury vytvořený v SW Matlab/Simulink. Výsledky demonstrují výbornou předpověď neuronové sítě a excelentní shodu výsledků simulace s vytvořeným modelem.
Arithmetic networks consist of neural, Boolean and fuzzy ones. Supposing the acyclic structure, decomposition of arithmetic network is possible. There are three results of our analysis: node unification, edge unification and network decomposition. We obtain only 14 node types and 4 edge types for realization of a wide class of traditional arithmetic networks from literature. The main result of our work is the splitting of the competitive neurons (nodes) to distance and soft extreme nodes. The side result of analysis is using the group of nodes instead of layer. It enables grouping the nodes of the same type but with the possibility of long interconnections. The main aiin of our work was to realize the system of arithmetic networks in the SQL language on any SQL server. The database realization enables not only saving, watching and editing the network structures and parameters but also studying the response of archived networks. The learning process was not included because of being iterative in general and unrealizable without loops on database server at that time.
A model for the design of rectangular microstrip antennas, based on
artificial neural networks, is presented. The multiple output design parameters are calculated by using only one network. The extended delta-bar-delta algorithm is used to train the network. The neural model is simple and is useful for the computer-aided design (CAD) of microstrip antennas. The design results obtained by using the neural model are in very good agreement with the results available in the literatuře.
The retinopathy diseases occur when the neurons do not transmit signals from retina to the brain. These disorders are: Diabetic retinopathy, hypertensive retinopathy, macular degeneration, vein branch occlusion, vitreous hemorrhage, and normal retina. This work presents a novel detection algorithm about retinopathy disorders from retina images. For this purpose, the retina images were pre-processed and resized at first. Then the discrete cosine transform was used as feature extraction before applying a neural network classifier. The performance of recognition rates of the novel detection algorithm were found as 50%, 70%, 85%, 90%, and 95% for testing five retinopathy cases respectively.