Research and Development

Heaton, Alan

doi:10.1007/978-94-011-0613-9_4

Cited by 40 publications

(48 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A NN is composed of neurons and synapses, and neurons are interconnected with synapses which store weights. A NN can solve the problem by changing the weights from the learning of the neurons [11,12].…”

Section: Neural Network (Nn)mentioning

confidence: 99%

Extending Ionospheric Correction Coverage Area By Using A Neural Network Method

Kim¹,

Kim²

2016

International Journal of Aeronautical and Space Sciences

View full text Add to dashboard Cite

The coverage area of a GNSS regional ionospheric delay model is mainly determined by the distribution of GNSS ground monitoring stations. Extrapolation of the ionospheric model data can extend the coverage area. An extrapolation algorithm, which combines observed ionospheric delay with the environmental parameters, is proposed. Neural network and least square regression algorithms are developed to utilize the combined input data. The bi-harmonic spline method is also tested for comparison. The IGS ionosphere map data is used to simulate the delays and to compute the extrapolation error statistics. The neural network method outperforms the other methods and demonstrates a high extrapolation accuracy. In order to determine the directional characteristics, the estimation error is classified into four direction components. The South extrapolation area yields the largest estimation error followed by North area, which yields the second-largest error.

show abstract

Section: Neural Network (Nn)mentioning

confidence: 99%

Extending Ionospheric Correction Coverage Area By Using A Neural Network Method

Kim¹,

Kim²

2016

International Journal of Aeronautical and Space Sciences

View full text Add to dashboard Cite

show abstract

“…By trial and error around L hd in equation (6), 39 seven neurons' hidden layers are used which minimized the training error. The output is the throughput of the FMS…”

Section: Numerical Example 1:(3m3p3o)mentioning

confidence: 99%

On multistage approach for flexible routing in flexible manufacturing systems

Qudeiri

Umer

Abidi

et al. 2016

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Optimizing flexible routing in flexible manufacturing systems is one of the aspects that increase the efficiency of flexible manufacturing systems especially in dynamic environment systems. This article presents a multistage approach to solve flexible routing problem in flexible manufacturing systems. Multistage approach includes three stages; the first stage is a production simulation system to find the fitness of the flexible manufacturing systems corresponding to different products' routes' groups. The second stage proposes an artificial neural network approach to predict the products' routes' group in flexible manufacturing systems. The last stage combines genetic algorithms and artificial neural network to optimize proper routes for all product types in flexible manufacturing systems. Multistage approach proposed in this study aims to reduce the computational time required to obtain and optimize the flexible routes in flexible manufacturing systems. The results of this study show that the artificial neural network can be used efficiently to predict the flexible routes in flexible manufacturing systems and it reduces the computational time for routes' optimization required with production simulation system. This characteristic improves the flexibility of flexible manufacturing systems since it can be adapted frequently against any change in production ratios.

show abstract

“…The result is concluded as unknown amulet if there is no or many output nodes activated. For multi-layer perceptron, the number of hidden nodes is defined as 54 which are the most possible smallest number [12], and it can be increased if the 54 is not sufficient. The activation function of perceptron and multi-layer perceptron are described in (5) and (6) [13] respectively where x = sum of weighted input.…”

Section: (4)mentioning

confidence: 99%

Thai Buddhist Amulet Recognition System

2014

International Academy of Engineers (IA-E) Dec. 30-31, 2014 Bangkok, Thailand

View full text Add to dashboard Cite

Abstract-The objective of this research is to recognize digital images of Thai Buddhist amulets by using image processing techniques and artificial neural network (ANN). The scope is to recognize 100 kinds of powder Buddhist amulet. To extract features from collected samples, the extraction process considers on shape, color, and texture. In total, 54 feature values are calculated fed into recognition process. To recognize those features, there are two ANN models applied, which are perceptron and multi-layer perceptron. In the experiment, those two models are tested with a test set. On average, the perceptron can recognize the amulet images correctly at 97.67 percent, and the multi-layer perceptron can produce the best classification result at 100 percent. The average computational time for image preprocessing and feature extraction step is about 7.18 seconds per image. To proceed recognition step, the system approximately takes 0.19 second per image for the perceptron and 0.18 second per image for multi-layer perceptron on average.Index Terms-Buddhist amulet, pattern recognition, image processing, artificial neural network.

show abstract

Research and Development

Cited by 40 publications

References 0 publications

Extending Ionospheric Correction Coverage Area By Using A Neural Network Method

Extending Ionospheric Correction Coverage Area By Using A Neural Network Method

On multistage approach for flexible routing in flexible manufacturing systems

Thai Buddhist Amulet Recognition System

Contact Info

Product

Resources

About