Search

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Radio Frequency IDentification (RFID) Network Planning (RNP) is the problem of placing RFID readers in a working area where a tag is interrogated by at least one reader and at the same time satisfies some constraints such as minimum number of placed readers, minimal interference, and minimal outside coverage. The RNP optimization has been proven NP-hard; thus, natural-inspired approaches are often used to find the optimal solution. The paper proposes an energy-efficient RNP approach in which the positions of placed readers are optimized by a Hopfield network, and the energy efficiency is achieved through a placement area restriction technique. A mechanism of redundant reader elimination is also added to minimize the number of placed readers. Simulation results show that the Hopfield network-based energy-efficient RNP approach achieves the maximum tag coverage and energy efficiency by reducing interference, outside coverage, and the number of placed readers.

We construct a chaotic discrete-time continuous-state Hopfield networkwith piecewise-affine nonnegative activation functions and weight matrix with small positive entries. More precisely, there exists a Cantor set $ C $ in the state space such that the network has sensitive dependence on initial conditions at initial states in $ C $ and the network orbit of each initial state in $ C $ has $ C $ as its $ \omega $-limit set. The approach we use is based on tools developed and employed recently in the study of the topological dynamics of piecewise-contractions. The parameters of the chaotic network are explicitly given. [ABSTRACT FROM AUTHOR]

This study presents a new way of increasing 3SAT logic programming's efficiency in the Hopfield network. A new model of merging fuzzy logic with 3SAT in the Hopfield network is presented called HNN-3SATFuzzy. The hybridised dynamic model can avoid locally minimal solutions and lessen the computing burden by utilising fuzzification and defuzzification techniques in fuzzy logic. In addressing the 3SAT issue, the proposed hybrid approach can select neuron states between zero and one. Aside from that, unsatisfied neuron clauses will be changed using the alpha-cut method as a defuzzifier step until the correct neuron state is determined. The defuzzification process is a mapping stage that converts a fuzzy value into a crisp output. The corrected neuron state using alpha-cut in the defuzzification stage is either sharpening up to one or sharpening down to zero. A simulated data collection was utilised to evaluate the hybrid techniques' performance. In the training phase, the network for HNN-3SATFuzzy was weighed using RMSE, SSE, MAE and MAPE metrics. The energy analysis also considers the ratio of global minima and processing period to assess its robustness. The findings are significant because this model considerably impacts Hopfield networks' capacity to handle 3SAT problems with less complexity and speed. The new information and ideas will aid in developing innovative ways to gather knowledge for future research in logic programming. Furthermore, the breakthrough in dynamic learning is considered a significant step forward in neuro-symbolic integration. [ABSTRACT FROM AUTHOR]

Machine learning based approaches for automatic disease prediction is a novel research area in healthcare informatics. Electronic Health Records in medical settings improves early-stage illness diagnosis. However, when standard rule-based approaches, like doctor's prescription or laboratory test reports are employed for disease diagnosis, the advantages of EHRs are not accomplished adequately. As a result, there is a requirement of technology based solution which helps in prediction of psychological diseases in a more efficient way. The proposed research work offers a hybrid Hopfield recurrent neural network (H2RN2) approach to predict psychological diseases by using amorphous clinical EHRs taken from Kaggle database. The proposed model automatically learns inherent semantic characteristics from available clinical data items. It uses fivefold cross validation technique within a recurrent neural network which detracts over fitting of the model. In addition to effective learning during training of the model, the hybrid approach also helps in accurate prediction of the disease with improved accuracy. The proposed model is assessed using three measuring parameters, accuracy, recall and F1-score and yields an accuracy of 97.53% in experimental evaluation, which is superior to several existing approaches for psychological disease prediction. The results demonstrate that the proposed model outperforms several other techniques in predicting the risk of psychiatric disorders. In future, the similar approach may be employed to predict gender-based psychological diseases or to anticipate the risk of various physiological diseases.

The results of current method of traffic sign detection gets hindered by environmental conditions and the traffic sign’s condition as well. Therefore, in this paper, we propose a method of improving detection performance of damaged traffic signs by utilizing Hopfield Network and Fuzzy Max-Min Neural Network. In this proposed method, the characteristics of damaged traffic signs are analyzed and those characteristics are configured as the training pattern to be used by Fuzzy Max-Min Neural Network to initially classify the characteristics of the traffic signs. The images with initial characteristics that has been classified are restored by using Hopfield Network. The images restored with Hopfield Network are classified by the Fuzzy Max-Min Neural Network onces again to finally classify and detect the damaged traffic signs. 8 traffic signs with varying degrees of damage are used to evaluate the performance of the proposed method which resulted with an average of 38.76% improvement on classification performance than the Fuzzy Max-Min Neural Network. [ABSTRACT FROM AUTHOR]

Autoassociative neural networks provide a simple model of how memories can be stored through Hebbian synaptic plasticity as retrievable patterns of neural activity. Although progress has been made along the last decades in understanding the biological implementation of autoassociative networks, their modest theoretical storage capacity has remained a major constraint. While most previous approaches utilize randomly connected networks, here we explore the possibility of optimizing network performance by selective connectivity between neurons, that could be implemented in the brain through creation and pruning of synaptic connections. We show through numerical simulations that a reconfiguration of the connectivity matrix can improve the storage capacity of autoassociative networks up to one order of magnitude compared to randomly connected networks, either by reducing the noise or by making it reinforce the signal. Our results indicate that the signal-reinforcement scenario is not only the best performing but also the most adequate for brain-like highly diluted connectivity. In this scenario, the optimized network tends to select synapses characterized by a high consensus across stored patterns. We also introduced an online algorithm in which the network modifies its connectivity while learning new patterns. We observed that, similarly to what happens in the human brain, creation of connections dominated in an initial stage, followed by a stage characterized by pruning, leading to an equilibrium state that was independent of the initial connectivity of the network. Our results suggest that selective connectivity could be a key component to make attractor networks in the brain viable in terms of storage capacity. [ABSTRACT FROM AUTHOR]

The ideal Hopfield network would be able to remember information and recover the missing information based on what has been remembered. It is expected to have applications in areas such as associative memory, pattern recognition, optimisation computation, parallel implementation of VLSI and optical devices, but the lack of memory capacity and the tendency to generate pseudo-attractors make the network capable of handling only a very small amount of data. In order to make the network more widely used, we propose a scheme to optimise and improve its memory and resilience by introducing quantum perceptrons instead of Hebbian rules to complete its weight matrix design. Compared with the classical Hopfield network, our scheme increases the threshold of each node in the network while training the weights, and the memory space of the Hopfield network changes from being composed of the weight matrix only to being composed of the weight matrix and the threshold matrix together, resulting in a dimensional increase in the memory capacity of the network, which greatly solves the problem of the Hopfield network’s memory The problem of insufficient memory capacity and the tendency to generate pseudo-attractors was solved to a great extent. To verify the feasibility of the proposed scheme, we compare it with the classical Hopfield network in four different dimensions, namely, non-orthogonal simple matrix recovery, incomplete data recovery, memory capacity and model convergence speed. These experiments demonstrate that the improved Hopfield network with quantum perceptron has significant advantages over the classical Hopfield network in terms of memory capacity and recovery ability, which provides a possibility for practical application of the network.

Autoassociative neural networks provide a simple model of how memories can be stored through Hebbian synaptic plasticity as retrievable patterns of neural activity. Although progress has been made along the last decades in understanding the biological implementation of autoassociative networks, their modest theoretical storage capacity has remained a major constraint. While most previous approaches utilize randomly connected networks, here we explore the possibility of optimizing network performance by selective connectivity between neurons, that could be implemented in the brain through creation and pruning of synaptic connections. We show through numerical simulations that a reconfiguration of the connectivity matrix can improve the storage capacity of autoassociative networks up to one order of magnitude compared to randomly connected networks, either by reducing the noise or by making it reinforce the signal. Our results indicate that the signal-reinforcement scenario is not only the best performing but also the most adequate for brain-like highly diluted connectivity. In this scenario, the optimized network tends to select synapses characterized by a high consensus across stored patterns. We also introduced an online algorithm in which the network modifies its connectivity while learning new patterns. We observed that, similarly to what happens in the human brain, creation of connections dominated in an initial stage, followed by a stage characterized by pruning, leading to an equilibrium state that was independent of the initial connectivity of the network. Our results suggest that selective connectivity could be a key component to make attractor networks in the brain viable in terms of storage capacity.

In the hippocampal dentate gyrus (DG), pattern separation mainly depends on the concepts of 'expansion recoding', meaning random mixing of different DG input channels. However, recent advances in neurophysiology have challenged the theory of pattern separation based on these concepts. In this study, we propose a novel feed-forward neural network, inspired by the structure of the DG and neural oscillatory analysis, to increase the Hopfield-network storage capacity. Unlike the previously published feed-forward neural networks, our bio-inspired neural network is designed to take advantage of both biological structure and functions of the DG. To better understand the computational principles of pattern separation in the DG, we have established a mouse model of environmental enrichment. We obtained a possible computational model of the DG, associated with better pattern separation ability, by using neural oscillatory analysis. Furthermore, we have developed a new algorithm based on Hebbian learning and coupling direction of neural oscillation to train the proposed neural network. The simulation results show that our proposed network significantly expands the storage capacity of Hopfield network, and more effective pattern separation is achieved. The storage capacity rises from 0.13 for the standard Hopfield network to 0.32 using our model when the overlap in patterns is 10%. [ABSTRACT FROM AUTHOR]

The Continuous Hopfield Network (CHN) became one of the major breakthroughs in the come back of Neural Networks in the mid 80s, as it could be used to solve combinatorial optimization problems such as the Traveling Salesman Problem. Once researchers provided a mechanism, not based in trial-and-error, to guarantee the feasibility of the CHN, the quality of the solution was inferior to the ones provided by other heuristics. The next natural step is to study the behavior of the CHN as an optimizer, in order to improve its performance. With this regard, this paper analyzes the attractor basins of the CHN and establishes the mathematical foundations that guarantee the behavior of the network as a 2-opt; with the aim to open a new research line in which the CHN may be used, given the appropriate parameter setting, to solve a k-opt, which would make the network highly competitive. The analysis of the attraction basins of the CHN and its interpretation as a 2-opt is the subject of this article. [ABSTRACT FROM AUTHOR]

This paper revisits the dense associative memory (DAM) networks and studies rigorously the capacity of the DAM networks. We present the capacity theorem of the DAM networks with an attraction radius or a noise level from the messages and prove that the probe can converge to the targeted message just after the one-step update. Under this convergence, the capacity of DAM networks is between a lower bound and an upper bound. Although when the attraction radius is 0.0 away from the messages, i.e. noiseless, previous literature provides an approximate result. However, a rigorous proof is not given in this study. In addition, we consider a more general notion of capacity which allows the retrieval of messages from noisy probes (the attraction radius is not 0.0). We demonstrates that the convergence result can be acquired just after the one-step update when the probe is a corrupted version with a Gaussian noise from one message. We further provide simulated experiments to validate theorems herein. [ABSTRACT FROM AUTHOR]

In the current work, we devised a hybrid method involving a Double-Layer Neural Network (DLNN) for solving a quadratic Bi-Level Programming Problem (BLPP). For an efficient and effective solution of such problems, the proposed potential methodology includes an improved Artificial Bee Colony (ABC) algorithm, a Hopfield Network (HN), and a Boltzmann Machine (BM). The improved ABC algorithm accommodates upper-level decision problems by selecting a set of potential solutions from all combinations of solutions. However, for lower-level decision problem, HN and BM are amalgamated to manifest a DLNN that initially generates its structure by choosing a limited number of units, and will subsequently converge to an optimal solution/unit among those units and hence, constitutes an effective, efficient solution technique.We compared the accuracy, computational time and effectiveness (ability to find the true optimum) of the proposed DLNN with improved-ABC, DLNN with PSO (where PSO replaces the improved-ABC in the upper-level problem of the proposed DLNN with improved-ABC), DLNN with GA (where GAreplaces the improved-ABC in the upper-level of the proposed algorithm) and other conventional approaches and found the proposed DLNN with improved-ABC can yield high quality global optimal solutions with higher accuracy in relatively smaller time.

The purpose of this work was to demonstrate the feasibility of building recurrent artificial neural networks with hybrid complementary metal oxide semiconductor (CMOS)/memristor circuits. To do so, we modeled a Hopfield network implementing an analog-to-digital converter (ADC) with up to 8 bits of precision. Major shortcomings affecting the ADC's precision, such as the non-ideal behavior of CMOS circuitry and the specific limitations of memristors, were investigated and an effective solution was proposed, capitalizing on the in-field programmability of memristors. The theoretical work was validated experimentally by demonstrating the successful operation of a 4-bit ADC circuit implemented with discrete Pt/TiO2- x /Pt memristors and CMOS integrated circuit components.

In this work, we study an application of fractional-order Hopfield neural networks for optimization problem solving. The proposed network was simulated using a semi-analytical method based on Adomian decomposition,, and it was applied to the on-line estimation of time-varying parameters of nonlinear dynamical systems. Through simulations, it was demonstrated how fractional-order neurons influence the convergence of the Hopfield network, improving the performance of the parameter identification process if compared with integer-order implementations. Two different approaches for computing fractional derivatives were considered and compared as a function of the fractional-order of the derivatives: the Caputo and the Caputo–Fabrizio definitions. Simulation results related to different benchmarks commonly adopted in the literature are reported to demonstrate the suitability of the proposed architecture in the field of on-line parameter estimation. [ABSTRACT FROM AUTHOR]

Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks (QRPNNs). Briefly, the QRPNNs are obtained by combining the non-local projection learning with the quaternion-valued recurrent correlation neural network (QRCNNs). We show that the QRPNNs overcome the cross-talk problem of the QRCNNs. Thus, they are appropriate to implement associative memories. Furthermore, computational experiments reveal that the QRPNNs exhibit greater storage capacity and noise tolerance than their corresponding QRCNNs. [ABSTRACT FROM AUTHOR]

This paper describes a methodology for object recognition categorized as polyhedron and non-polyhedron. This recognition is achieved through digital image processing combined with artificial intelligence algorithms, such as Hopfield networks. The procedure consists of processing images in search of patterns to train the system. The process is carried out through three stages: i) Segmentation, ii) Smart recognition, and iii) Feature extraction; as a result, images of objects are obtained and trained in the designed neuronal network. Finally, Hopfield's network is used to establish the object type as soon as it receives one. The proposed methodology was evaluated in a real environment with a considerable number of detected images; the noisy images recognition uncertainty was 2.6%, an acceptable result considering variable light, shape and color. The results obtained from this experiment show a high recognition level, which represents 97.4%. Out of this procedure, we can assume that it is possible to train new patterns, and it is expected that the model will be able to recognize them. Potentially, the proposed methodology could be used in a vast range of applications, such as object identification in industrial environments, grasping objects using manipulators or robotic arms, tools for blind patients, among other applications.

Cancer is a genetic disease for which traditional treatments cause harmful side effects. After two decades of genomics technological breakthroughs, personalized medicine is being used to improve treatment outcomes and mitigate side effects. In mathematical modeling, it has been proposed that cancer matches an attractor in Waddington's epigenetic landscape. The use of Hopfield networks is an attractive modeling approach because it requires neither previous biological knowledge about protein-protein interactions nor kinetic parameters. In this report, Hopfield network modeling was used to analyze bulk RNA-Seq data of paired breast tumor and control samples from 70 patients. We characterized the control and tumor attractors with respect to their size and potential energy and correlated the Euclidean distances between the tumor samples and the control attractor with their corresponding clinical data. In addition, we developed a protocol that outlines the key genes involved in tumor state stability. We found that the tumor basin of attraction is larger than that of the control and that tumor samples are associated with a more substantial negative energy than control samples, which is in agreement with previous reports. Moreover, we found a negative correlation between the Euclidean distances from tumor samples to the control attractor and patient overall survival. The ascending order of each node's density in the weight matrix and the descending order of the number of patients that have the target active only in the tumor sample were the parameters that withdrew more tumor samples from the tumor basin of attraction with fewer gene inhibitions. The combinations of therapeutic targets were specific to each patient. We performed an initial validation through simulation of trastuzumab treatment effects in HER2+ breast cancer samples. For that, we built an energy landscape composed of single-cell and bulk RNA-Seq data from trastuzumab-treated and non-treated HER2+ samples. The trajectory from the non-treated bulk sample toward the treated bulk sample was inferred through the perturbation of differentially expressed genes between these samples. Among them, we characterized key genes involved in the trastuzumab response according to the literature.

In the race to achieve better performance, artificial intelligence has become more about the end rather than the means, which is general intelligence. This work aims to bridge the gap between the two by finding a complementary midline. The objective of this work is to project the role of Dentate Gyrus in enhancing the performance of an autoassociative network, paving the way to develop a biologically plausible neural network which, in the future, would help in simulating the network present in our brain. The proposed network imbibes biological similarities with respect to connectivity, weight updation, and activation function. Dentate Gyrus uses pre-integration lateral inhibition form of learning, and the autoassociative network is implemented using Hopfield network. The performance of the autoassociative network in the presence and absence of Dentate Gyrus is observed across multiple parameters. The results show an increase of 38% in storage capacity and a decrease of 15% in the error tolerance capability of the network in the presence of Dentate Gyrus. [ABSTRACT FROM AUTHOR]

In this paper we construct a new continuous recurrent neural network from the fixed points given a priori of quadratic polynomials. Our goal is to provide a criterion for the assignment of synaptic weights of the network, which will allow us to demonstrate the stability of the neural network, without using the energy function used in Hopfield networks. In addition, we give an application to recognition of a pattern. [ABSTRACT FROM AUTHOR]

Copyright of Revista Facultad de Ingeniería - UPTC is the property of Universidad Pedagogica y Tecnologica de Colombia, Facultad de Ingenieria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)