Hopfield Neural Network Approach Research Articles

Neural network to solve fuzzy constraint satisfaction problems

<p>It has been proven that solving the constraint satisfaction problem (CSP) is an No Polynomial hard combinatorial optimization problem. This holds true even in cases where the constraints are fuzzy, known as fuzzy constraint satisfaction problems (FCSP). Therefore, the continuous Hopfield neural network model can be utilized to resolve it. The original algorithm was developed by Talaavan in 2005. Many practical problems can be represented as a FCSP. In this paper, we expand on a neural network technique that was initially developed for solving CSP and adapt it to tackle problems that involve at least one fuzzy constraint. To validate the enhanced effectiveness and rapid convergence of our proposed approach, a series of numerical experiments are carried out. The results of these experiments demonstrate the superior performance of the new method. Additionally, the experiments confirm its fast convergence. Specifically, our study focuses on binary instances with ordinary constraints to test the proposed resolution model. The results confirm that both the proposed approaches and the original continuous Hopfield neural network approach exhibit similar performance and robustness in solving ordinary constraint satisfaction problems.</p>

Adsorbate-adsorbent potential energy function from second virial coefficient data: a non-linear Hopfield Neural Network approach.

The Hopfield Neural Network has been successfully applied to solve ill-posed inverse problems in different fields of chemistry and physics. In this work, the non-linear approach for this method will be applied to retrieve the empirical parameters of potential energy function, [Formula: see text], between adsorbate and adsorbent from experimental data. Since the adsorption data is related to the second virial coefficient and therefore to [Formula: see text] through an integral equation, the Hopfield Neural Network will be used to find the best parameters which fits the experimental data. Initially simulated results will be analyzed to verify the method performance for data sets with and without noise addition. Then, experimental data for adsorption of propionitrile on activated carbon will be treated. Results presented here corroborate to the robustness of this method.

Radial distribution function for liquid gallium from experimental structure factor: a Hopfield neural network approach.

Hopfield neural network was used to retrieve liquid gallium radial distribution function from an experimental structure factor, obtained at 959 K. The inversion framework was carried out under two initial conditions: (a) a constant radial distribution function corresponding to an ideal gas and (b) a step function, simulating a gas with square well potential of interaction. Both situations lead to accurate inverse results if compared with the radial distribution function obtained by Bellisent-Funel et al., using the Fourier transform method and Monte Carlo simulation. The Hopfield neural network has shown to be a powerful strategy to calculate the radial distribution function from experimental data.

Hopfield learning‐based and non‐linear programming methods for resource allocation in OCDMA networks

This study proposes the deployment of the Hopfield neural network (H-NN) approach to optimally assign power in optical code division multiple access (OCDMA) systems. Figures of merit such as the feasibility of solutions and complexity are compared with the classical power allocation methods found in the literature, such as sequential quadratic programming (SQP) and augmented Lagrangian method. The analysed methods are used to solve constrained non-linear optimisation problems in the context of resource allocation for optical networks, especially to deal with energy efficiency in OCDMA networks. The promising performance-complexity trade-off of the modified H-NN is demonstrated through numerical results performed in comparison with classic methods for general problems in non-linear programming. The evaluation is carried out considering challenging OCDMA networks in which different levels of service quality required were considered for large numbers of optical users. The numerical results demonstrated that the three power allocation methods attain suitable convergence for different network sizes, while both the mH-NN and SQP methods achieve suitable equilibrium with less complexity.

Algorithm for Solving Economical and Environmental Dispatch Problems of Thermal Power Plants

This paper presents a modified tabu search algorithm which uses a real-valued solution vector and an adaptive mechanism for generating neighbors. The neighbors are produced by adding an adjusted coefficient at each iteration which enables us to find the most promising region of the search space. By consequent, a modified tabu search algorithm is applied to economic and environmental economic dispatch problems. The proposed method has achieved efficient and accurate solutions for power systems with 3, 6, 10, 20, 40, 80, 120, 160 and 240 units respectively. The results of the proposed method are compared with those of an improved Hopfield neural network approach, a fuzzy logic controlled genetic algorithm, an advanced engineered-conditioning genetic approach, and an advanced Hopfield neural network approach. It is shown that the proposed method is superior in providing optimal allocation of generation units which minimizes the total fuel cost. Simulation results show that the proposed method yields better solutions when compared to the alternate techniques.

A New Algorithm for Solving Environmental Issues in Power Engineering

Ope vbrating at absolute minimum cost can no longer be the only criterion for dispatching electric power due to increasing concern the environmental consideration. The environmentally constrained economic dispatch problem which accounts for minimization of both cost and emission is a multiple objective function problem. In this paper, tabu search is used to solve the economic dispatch problems for a couple of reasons. The modified tabu search algorithm uses a real-valued solution vector and adaptive mechanism for producing neighbors. However, the classical TS algorithm uses a binary solution vector. The neighbors are produced by adding an adjusted coefficient at each iteration. This neighbor production mechanism enables us to find the most promising region of the searched space. The proposed method has achieved efficient and accurate solutions for power systems with 3, 6, 10, 20, 40, 80, 120, 160 and 240 units respectively. The results of the proposed method are compared with those of an improved Hopfield neural network approach, an advance engineered-conditioning genetic approach, an advance Hopfield neural network approach and a fuzzy logic controlled genetic algorithm. It will demonstrate that the proposed method is superior in providing optimal allocation of generation units which minimizes the total fuel cost. Simulation results show that the proposed method yields better solutions when compared to the alternate techniques.

Inter-domain routing for communication networks using Hierarchical Hopfield Neural Networks

This paper presents the Hierarchical Hopfield Neural Networks (HHNN). HHNN is a novel Hopfield Neural Network (HNN) approach. HHNN is composed of a hierarchy of self-sufficient HNNs, aiming to reduce the neural network structure and mitigate convergence problems. The HNNN composition depends on the applied problem. In this paper, the problem approached is the inter-domain routing for communication networks. Thus, the hierarchy of HNNs mimics the structure of communication networks (domains, nodes, and links). The proof of concept and the comparison between HNNN with the state-of-art HNN occurs using an implementation of them in the Java programming language. Besides, the performance analysis of the HHNN runs on a parallel hardware platform, using VHDL to develop it. The results have demonstrated a reduction of 93.75% and 99.98% in the number of neurons and connections to build the neural network, respectively. Furthermore, the mean time to achieve convergence of HHNN is rough 1.52% of the total time needed by the current state-of-art HNN approach. It is also less susceptible to early convergence problems when used in communications networks with a large number of nodes. Last, but not least, the VHDL implementation shows that convergence time of HHNN is comparable to routing algorithms used in practical applications.

Detection of Rogue Access Point in WLAN using Hopfield Neural Network

The serious issue in the field of wireless communication is the security and how an organization implements the steps against security breach. The major attack on any organization is Man in the Middle attack which is difficult to manage. This attack leads to number of unauthorized access points, called rogue access points which are not detected easily. In this paper, we proposed a Hopfield Neural Network approach for an automatic detection of these rogue access points in wireless networking. Here, we store the passwords of the authentic devices in the weight matrix format and match the patterns at the time of login. Simulation experiment shows that this method is more secure than the traditional one in WLAN.

Hopfield Neural Network Approach for Supervised Nonlinear Spectral Unmixing

Nonlinear unmixing, which has attracted considerable interest from researchers and developers, has been successfully applied in many real-world hyperspectral imaging scenarios. Hopfield neural network (HNN) machine learning has already proven successful in solving the linear mixture model; this study utilized an HNN machine learning approach to solve the generalized bilinear model (GBM) optimization problem. Two HNNs were constructed in a successive manner to solve respective seminonnegative matrix factorization problems intended for abundance and nonlinear coefficient estimation. In the proposed HNN-based GBM unmixing method, both HNNs evolve to stable states after a number of iterations to obtain unmixing results related to the states of neurons. In experiments on synthetic data, the proposed method showed more efficient performance in regard to abundance estimation accuracy than other GBM optimization algorithms, especially when given reliable endmember spectra. The proposed method was also applied to real hyperspectral data and still demonstrated notable advantages despite the obvious increase in unmixing difficulty.

A 2D Hopfield Neural Network approach to mechanical beam damage detection

The aim of this paper is to present a method based on a 2D Hopfield Neural Network for online damage detection in beams subjected to external forces. The underlying idea of the method is that a significant change in the beam model parameters can be taken as a sign of damage occurrence in the structural system. In this way, damage detection can be associated to an identification problem. More concretely, a 2D Hopfield Neural Network uses information about the way the beam vibrates and the external forces that are applied to it to obtain time-evolving estimates of the beam parameters at the different beam points. The neural network organizes its input information based on the Euler---Bernoulli model for beam vibrations. Its performance is tested with vibration data generated by means of a different model, namely Timonshenko's, in order to produce more realistic simulation conditions.

A spatial–temporal Hopfield neural network approach for super-resolution land cover mapping with multi-temporal different resolution remotely sensed images

The mixed pixel problem affects the extraction of land cover information from remotely sensed images. Super-resolution mapping (SRM) can produce land cover maps with a finer spatial resolution than the remotely sensed images, and reduce the mixed pixel problem to some extent. Traditional SRMs solely adopt a single coarse-resolution image as input. Uncertainty always exists in resultant fine-resolution land cover maps, due to the lack of information about detailed land cover spatial patterns. The development of remote sensing technology has enabled the storage of a great amount of fine spatial resolution remotely sensed images. These data can provide fine-resolution land cover spatial information and are promising in reducing the SRM uncertainty. This paper presents a spatial–temporal Hopfield neural network (STHNN) based SRM, by employing both a current coarse-resolution image and a previous fine-resolution land cover map as input. STHNN considers the spatial information, as well as the temporal information of sub-pixel pairs by distinguishing the unchanged, decreased and increased land cover fractions in each coarse-resolution pixel, and uses different rules in labeling these sub-pixels. The proposed STHNN method was tested using synthetic images with different class fraction errors and real Landsat images, by comparing with pixel-based classification method and several popular SRM methods including pixel-swapping algorithm, Hopfield neural network based method and sub-pixel land cover change mapping method. Results show that STHNN outperforms pixel-based classification method, pixel-swapping algorithm and Hopfield neural network based model in most cases. The weight parameters of different STHNN spatial constraints, temporal constraints and fraction constraint have important functions in the STHNN performance. The heterogeneity degree of the previous map and the fraction images errors affect the STHNN accuracy, and can be served as guidances of selecting the optimal STHNN weight parameters.

Fault diagnosis using partial syndromes: a modified Hopfield neural network approach

This paper presents a modified Hopfield neural network (HNN) for solving the system-level fault diagnosis problem which aims at identifying the set of faulty nodes. This problem has been extensively studied in the last three decades. Nevertheless, identifying the set of all faulty nodes using only partial syndromes, i.e. when some of the testing or comparison outcomes are missing prior to initiating the diagnosis phase, remains an outstanding research issue. The new HNN-based diagnosis algorithm does not require any prior learning or knowledge about the system, nor about any faulty situation, hence providing a better generalisation performance. Results from a thorough simulation study demonstrate the effectiveness of the HNN-based fault diagnosis algorithm in terms of diagnosis correctness, diagnosis latency and diagnosis scalability, for randomly generated diagnosable systems of different sizes and under various fault scenarios. We have also conducted extensive simulations using partial syndromes. Simulations showed that the HNN-based diagnosis performed efficiently, i.e. diagnosis correctness was around 99% when at most half of the test or comparison outcomes are missing, making it a viable alternative to existing diagnosis algorithms.

Efficient modeling of vector hysteresis using a novel Hopfield neural network implementation of Stoner–Wohlfarth-like operators

Incorporation of hysteresis models in electromagnetic analysis approaches is indispensable to accurate field computation in complex magnetic media. Throughout those computations, vector nature and computational efficiency of such models become especially crucial when sophisticated geometries requiring massive sub-region discretization are involved. Recently, an efficient vector Preisach-type hysteresis model constructed from only two scalar models having orthogonally coupled elementary operators has been proposed. This paper presents a novel Hopfield neural network approach for the implementation of Stoner–Wohlfarth-like operators that could lead to a significant enhancement in the computational efficiency of the aforementioned model. Advantages of this approach stem from the non-rectangular nature of these operators that substantially minimizes the number of operators needed to achieve an accurate vector hysteresis model. Details of the proposed approach, its identification and experimental testing are presented in the paper.

A Hopfield neural network approach to decentralized self-synchronizing sensor networks

Decentralized inference of a sensor network in the difficult case of a nonreciprocal nonlinear context is investigated by transforming the sensor network into a Hopfield neural network. Equilibrium states of the latter correspond to situations of global consensus in the sensor network, characterized by suitable regions (consensus regions) in the space of its parameters. The said transformation was recently proposed by the author and applied to the simple case of three sensors. The general case of more than three sensors is investigated in the present paper. A procedure is developed for determining the structure and the properties of the consensus regions.

A Hopfield neural network approach for power optimization of real-time operating systems

A Hopfield neural network approach for power optimization of real-time operating systems

A Hopfield neural network approach for power optimization of real-time operating systems

The RTOS (Real-Time Operating System) is a critical component in the SoC (System-on-a-Chip), which is the main body for consuming total system energy. Power optimization based on hardware–software partitioning of a RTOS (RTOS–Power partitioning) can significantly minimize the energy consumption of a SoC. This paper presents a new model for RTOS–Power partitioning, which helps in understanding the essence of the RTOS–Power partitioning techniques. A discrete Hopfield neural network approach for implementing the RTOS–Power partitioning is proposed, where a novel energy function, operating equation and coefficients of the neural network are redefined. Simulations are carried out with comparison to other optimization techniques. Experimental results demonstrate that the proposed method can achieve higher energy savings up to 60% at relatively low costs of less than 4k PLBs while increasing the performance compared to the purely software realized SoC–RTOS.

Hardware–software partitioning of real-time operating systems using Hopfield neural networks

The hardware–software automated partitioning of a real-time operating system in the system-on-a-chip (SoC-RTOS partitioning) is a NP-complete problem, and a crucial step in the hardware–software co-design of SoC. In this paper, a new model for SoC-RTOS partitioning is introduced, which can help in understanding the essence of the SoC-RTOS partitioning. A discrete Hopfield neural network approach for implementing the SoC-RTOS partitioning is proposed, where a novel energy function, operating equation and coefficients of the neural network are redefined. Simulations are carried out with comparison to other optimization techniques. Experimental results demonstrate the feasibility and effectiveness of the proposed method.

A Hopfield Neural Network Approach to the Dual Response Problem

AbstractThe application of neural networks to optimization problems has been an active research area since the early 1980s. Unconstrained optimization, constrained optimization and combinatorial optimization problems have been solved using neural networks. This study presents a new approach using Hopfield neural networks (HNNs) for solving the dual response system (DRS) problems. The major aim of the proposed method is to produce a string of solutions, rather than a ‘one‐shot’ optimum solution, to make the trade‐offs available between the mean and standard deviation responses. This gives more flexibility to the decision‐maker in exploring alternative solutions. The proposed method has been tested on two examples. The HNN results are very close to those obtained by using the NIMBUS (Nondifferentiable Interactive Multiobjective Bundle‐based Optimization System) algorithm. Choosing an appropriate solution method for a certain multi‐objective optimization problem is not easy, as has been made abundantly clear. Unlike the NIMBUS method, the HNN approach does not set any specific assumptions on the behaviour or the preference structure of the decision maker. As a result, the proposed method will still work and generate alternative solutions whether or not the decision maker has enough time and capabilities for co‐operation. Copyright © 2005 John Wiley & Sons, Ltd.

Classification with incomplete survey data: a Hopfield neural network approach

Survey data are often incomplete. Classification with incomplete survey data is a new subject. This study proposes a Hopfield neural network based model of classification for incomplete survey data. Using this model, an incomplete pattern is translated into fuzzy patterns. These fuzzy patterns, along with patterns without missing values, are then used as the exemplar set for teaching the Hopfield neural network. The classifier also retains information of fuzzy class membership for each exemplar pattern. When presenting a test sample, the neural network would find an exemplar that best matches the test pattern and give the classification result. Compared with other classification techniques, the proposed method can utilize more information provided by the data with missing values, and reveal the risk of the classification result on the individual observation basis.

Classification with incomplete survey data: a Hopfield neural network approach

Classification with incomplete survey data: a Hopfield neural network approach