Frame Optimization using Neural Network

Meon, Mohd Suhairil; Anuar, Muhammad Azhan; Ramli, Mohd Hanif Mohd; Kuntjoro, Wahyu; Muhammad, Zulkifli

doi:10.18517/ijaseit.2.1.148

Cited by 13 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This suggests for future works the realization of the dynamical relaying motif with plastic synapses [28]. Fig.6: Pipeline of the implemented method for the validation of the circuit Neural networks are being used today for a plenty of application, ranging from classification [29], [30], prediction [31]- [34], or optimization [35] problems, as well as for the emulation of brain dynamics [36], [37]. Considering the latter context, the dynamical relaying mechanism has been reproduced with larger neural networks, where single neurons are replaced by neuron populations, and links are replaced by bundles of connections [10], [12].…”

Section: Resultsmentioning

confidence: 99%

Towards Neuro-Inspired Electronic Oscillators Based on The Dynamical Relaying Mechanism

Susi

Acciarito

Pascual

et al. 2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Electronic oscillators are used for the generation of both continuous and discrete signals, playing a fundamental role in today's electronics. In both contexts, these systems require stringent performances such as spectral purity, low phase noise, frequency and temperature stability. In state of the art oscillators the preservation of some of these aspects is jeopardized by specific critical issues, e.g., the sensitivity to load capacitance or the component aging over time. This leaves room for the search of new technologies for their realization. On the other hand, in the last decade electronics has been influenced by a growing number of neuro-inspired mechanisms, which allowed for alternative techniques aimed at solving some classical critical issues. In this paper we present an exploratory study for the development of electronic oscillators based on the neuro-inspired mechanism dynamical relaying, which relies on a structure composed of three delay coupled units (as neurons or even neuron populations) able to resonate and self-organise to generate and maintain a given rhythm with great reliability over a considerable parameter range, showing robustness to noise. We used the recent leaky integrated and fire with latency (LIFL) as neuron model. We have initially developed the mathematical model of the neuro-inspired oscillator, and implemented it using Matlab®; then, we have realized the schematic of such system in PSpice®. Finally, the model has been validated to verify whether it observes the fundamental properties of the dynamical relaying mechanisms described in computational neuroscience studies, and if the circuit implementation presents the same behaviour of the mathematical model. Validation results suggest that the dynamical relaying mechanism can be proficuously taken in consideration as alternative strategy for the design of electronic oscillators.Keywords-LIFL neuron model; electronic oscillators; dynamical relaying; spiking neural networks.

show abstract

Section: Resultsmentioning

confidence: 99%

Towards Neuro-Inspired Electronic Oscillators Based on The Dynamical Relaying Mechanism

Susi

Acciarito

Pascual

et al. 2019

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…The main advantage of using neural networks is their ability to learn from experience, generalizing from previous situations to new cases and differentiating essential information from that which is irrelevant. ANNs are able to represent and learn both linear and non-linear relationships directly from the data [2].…”

Section: Introductionmentioning

confidence: 99%

“…In addition, ANNs have gained a relevant position in solving industrial design problems. It is worth mentioning that the identification of the optimum design within an industrial process is not always possible due the size of the problem and lack of knowledge, as the design stage is essential [2]. However, ANNs are able to perform constraint checks, requiring less computing time to provide adequate results.…”

Section: Introductionmentioning

confidence: 99%

“…In civil engineering, ANNs have been successfully used in automation and optimization [2,5,8], in material formulation [9], and in system identification and monitoring [10,11]. In structural analysis and design, the following applications could be highlighted [2,6,12]: structural analysis of systems with large degrees of freedom, size optimization of structural members, joint location, shape optimization of structural types (e.g., truss geometry), topology optimization (based on deletion of ineffective structural members), and maximum stress identification and location. Focusing on the application to specific structural problems, Intelligent Finite Element Analysis (IFEA), which combines the Finite Element Method (FEM) together with an ANN, has been used for simulating or predicting constitutive models [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Structural Design of a Prefab Concrete Connection by Using Artificial Neural Networks

2020

View full text Add to dashboard Cite

In the built environment, one of the main concerns during the design stage is the selection of adequate structural materials and elements. A rational and sensible design of both materials and elements results not only in economic benefits and computing time reduction, but also in minimizing the environmental impact. Nowadays, Artificial Neural Networks (ANNs) are showing their potential as design tools. In this research, ANNs are used in order to foster the implementation of efficient tools to be used during the early stages of structural design. The proposed networks are applied to a dry precast concrete connection, which has been modelled by means of the Finite Element Method (FEM). The parameters are: strength of concrete and screws, diameter of screws, plate thickness, and the posttensioning load. The ANN input data are the parameters and nodal stresses obtained from the FEM models. A multilayer perceptron combined with a backpropagation algorithm is used in the ANN architecture, and a hyperbolic tangent function is applied as an activation function. Comparing the obtained predicted stresses to those of the FEM analyses, the difference is less than 9.16%. Those results validate their use as an efficient structural design tool. The main advantage of the proposed ANNs is that they can be easily and effectively adapted to different connection parameters. In addition, their use could be applied both in precast or cast in situ concrete connection design.

show abstract

“…Since then, a huge proliferation in the ANN methodologies has been taking place. In particular there are many applications to the civil engineering, such as structural optimization [13][14][15], damage identification of structural elements [16], frame optimization [17], traffic sign classification [18], optimal design of continuous reinforced concrete beams [19], etc.…”

Section: Introductionmentioning

confidence: 99%

Application of Genetic Algorithms Coupled with Neural Networks to Optimization of Reinforced Concrete Footings

Yeh

2016

TMLAI

View full text Add to dashboard Cite

This paper first applies genetic algorithms to optimally design reinforced concrete isolated footings subjected to concentric loading. Based on the ACI Building Code, constraints are built by considering widebeam and punching shears, bending moment, allowable soil pressure, the development length for deformed bars and clear distance between deformed bars. Design variables consist of the width, length and thickness of the footing and the number of bars in the long and short directions, all of which are discrete. The objective function is to minimize the cost of steel and concrete in the footing. There are totally 144 cases of reinforced concrete isolated footings considered. The optimal results are randomly divided into three groups for the use of neural networks: training data, validation data and testing data. Two kinds of artificial neural networks are employed in this paper: two-layer feedforward backpropagation networks and radial basis networks. Linear regression analysis between the network outputs and targets of the testing data is performed to judge the accuracy of the neural networks. Numerical results show that the feedforward backpropagation network is very effective and has high accuracy with the correlation coefficients and the slope of the regression line being close to one and the y-intercept close to zero. Besides, it is better than the radial basis networks and needs much fewer neurons in the hidden layer.

show abstract

Frame Optimization using Neural Network

Cited by 13 publications

References 21 publications

Towards Neuro-Inspired Electronic Oscillators Based on The Dynamical Relaying Mechanism

Towards Neuro-Inspired Electronic Oscillators Based on The Dynamical Relaying Mechanism

Efficient Structural Design of a Prefab Concrete Connection by Using Artificial Neural Networks

Application of Genetic Algorithms Coupled with Neural Networks to Optimization of Reinforced Concrete Footings

Contact Info

Product

Resources

About