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.
The author obtains an estimate for the spatial gradient of solutions of the heat equation, subject to a homogeneous Neumann boundary condition, in terms of the gradient of the initial data. The proof is accomplished via the maximum principle; the main assumption is that the sufficiently smooth boundary be convex.
There are several ways that can be implemented in a vehicle tracking system such as recognizing a vehicle color, a shape or a vehicle plate itself. In this paper, we will concentrate ourselves on recognizing a vehicle on a highway through vehicle plate recognition. Generally, recognizing a vehicle plate for a toll-gate system or parking system is easier than recognizing a car plate for the highway system. There are many cameras installed on the highway to capture images and every camera has different angles of images. As a result, the images are captured under varied imaging conditions and not focusing on the vehicle itself. Therefore, we need a system that is able to recognize the object first. However, such a system consumes a large amount of time to complete the whole process. To overcome this drawback, we installed this process with grid computing as a solution. At the end of this paper, we will discuss our obtained result from an experiment.
The split graph $K_r+\overline {K_s}$ on $r+s$ vertices is denoted by $S_{r,s}$. A non-increasing sequence $\pi =(d_1,d_2,\ldots ,d_n)$ of nonnegative integers is said to be potentially $S_{r,s}$-graphic if there exists a realization of $\pi $ containing $S_{r,s}$ as a subgraph. In this paper, we obtain a Havel-Hakimi type procedure and a simple sufficient condition for $\pi $ to be potentially $S_{r,s}$-graphic. They are extensions of two theorems due to A. R. Rao (The clique number of a graph with given degree sequence, Graph Theory, Proc. Symp., Calcutta 1976, ISI Lect. Notes Series 4 (1979), 251–267 and An Erdős-Gallai type result on the clique number of a realization of a degree sequence, unpublished).
Slurry transport in horizontal and vertical pipelines is one of the major means of transport of sands and gravels in the dredging industry. There exist 4 main flow regimes, the fixed or stationary bed regime, the sliding bed regime, the heterogeneous flow regime and the homogeneous flow regime. Of course the transitions between the regimes are not very sharp, depending on parameters like the particle size distribution. The focus in this paper is on the homogeneous regime. Often the so called equivalent liquid model (ELM) is applied, however many researchers found hydraulic gradients smaller than predicted with the ELM, but larger that the hydraulic gradient of liquid. Talmon (2011, 2013) derived a fundamental equation (method) proving that the hydraulic gradient can be smaller than predicted by the ELM, based on the assumption of a particle free viscous sub-layer. He used a 2D velocity distribution without a concentration distribution. In this paper 5 methods are described (and derived) to determine the hydraulic gradient in homogeneous flow, of which the last method is based on pipe flow with a concentration distribution. It appears that the use of von Driest (Schlichting, 1968) damping, if present, dominates the results, however applying a concentration distribution may neutralise this. The final equation contains both the damping and a concentration distribution giving the possibility to calibrate the constant in the equation with experimental data. The final equation is flexible and gives a good match with experimental results in vertical and horizontal pipelines for a value of ACv = 1.3. Data of horizontal experiments Dp = 0.05-0.30 m, d = 0.04 mm, vertical experiments Dp = 0.026 m, d = 0.125, 0.345, 0.560, and 0.750 mm.
This paper presents an observation on adaptation of Hopfield neural network dynamics configured as a relaxation-based search algorithm for static optimization. More specifically, two adaptation rules, one heuristically formulated and the second being gradient descent based, for updating constraint weighting coefficients of Hopfield neural network dynamics are discussed. Application of two adaptation rules for constraint weighting coefficients is shown to lead to an identical form for update equations. This finding suggests that the heuristically-formulated rule and the gradient descent based rule are analogues of each other. Accordingly, in the current context, common sense reasoning by a domain expert appears to possess a corresponding mathematical framework.
This paper presents a neuro-based approach for annual transport energy demand forecasting by several socio-economic indicators. In order to analyze the influence of economic and social indicators on the transport energy demand, gross domestic product (GDP), population and total number of vehicles are selected. This approach is structured as a hierarchical artificial neural networks (ANNs) model based on the supervised multi-layer perceptron (MLP), trained with the back-propagation (BP) algorithm. This hierarchical ANNs model is designed properly. The input variables are transport energy demand in the last year, GDP, population and total number of vehicles. The output variable is the energy demand of the transportation sector in Million Barrels Oil Equivalent (MBOE). This paper proposes a hierarchical artificial neural network by which the inputs to the ending level are obtained as outputs of the starting levels. Actual data of Iran from 1968-2007 is used to train the hierarchical ANNs and to illustrate capability of the approach in this regard. Comparison of the model predictions with conventional regression model predictions shows its superiority. Furthermore, the transport energy demand of Iran for the period of 2008 to 2020 is estimated.
High resolution (0.C5 A) spectra are used for the determlnatlon of the profiles of the diffuse Interstellar bands 5780 and 5797 orlginatlng in single clouds. It is shown that some of the clouds may contain agents of certain diffuse bands whereas others may not. The proflles of diffuse bands observed in dlstant stars contaln contributions from several clouds, differing In optical properties, which share the Doppler displacements observed in interstellar sodium lines. The Doppler splitting inside the diffuse bands´ profiles is, however, efficlently veiled because of the large intrinslc widths of the bands under consideration.
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.