An efficient parallel algorithm for LISSOM neural network

Chang, Li-Chiu; Chang, Fi‐John

doi:10.1016/s0167-8191(02)00166-7

Cited by 6 publications

(2 citation statements)

References 21 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this type of ANN, multiple independent networks are created which are equal to the number of outputs. Each network is trained to produce a single output which makes such models useful for parallel computation [ 7 ], where the data volume is huge. A typical structure of the MISO network is shown in Figure 4 .…”

Section: Background and Preliminary Analysismentioning

confidence: 99%

Real-Time Analysis of a Sensor’s Data for Automated Decision Making in an IoT-Based Smart Home

Khan

Ghani

Haider

2018

Sensors

View full text Add to dashboard Cite

IoT devices frequently generate large volumes of streaming data and in order to take advantage of this data, their temporal patterns must be learned and identified. Streaming data analysis has become popular after being successfully used in many applications including forecasting electricity load, stock market prices, weather conditions, etc. Artificial Neural Networks (ANNs) have been successfully utilized in understanding the embedded interesting patterns/behaviors in the data and forecasting the future values based on it. One such pattern is modelled and learned in the present study to identify the occurrence of a specific pattern in a Water Management System (WMS). This prediction aids in making an automatic decision support system, to switch OFF a hydraulic suction pump at the appropriate time. Three types of ANN, namely Multi-Input Multi-Output (MIMO), Multi-Input Single-Output (MISO), and Recurrent Neural Network (RNN) have been compared, for multi-step-ahead forecasting, on a sensor’s streaming data. Experiments have shown that RNN has the best performance among three models and based on its prediction, a system can be implemented to make the best decision with 86% accuracy.

show abstract

Section: Background and Preliminary Analysismentioning

confidence: 99%

Real-Time Analysis of a Sensor’s Data for Automated Decision Making in an IoT-Based Smart Home

Khan

Ghani

Haider

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Even though n networks for n-step-ahead forecasting would need to be individually constructed, compared with MIMO, MISO networks would efficiently reduce the training time and increase the accuracy. Moreover, a standard search algorithm, such as BP or CG, can be easily implemented into all the n constructed networks, and a parallel computation algorithm (Chang & Chang, 2002) for simultaneously training these networks is also quite straightforward. The major reason for the accuracy of the MISO architecture being better than MIMO may be due to the number of parameters.…”

Section: Architecture Of Neural Network-based Multi-step-ahead Forecamentioning

confidence: 99%

Multi-step-ahead neural networks for flood forecasting

Chang¹,

Chiang²,

Chang³

2007

Hydrological Sciences Journal

Self Cite

120

View full text Add to dashboard Cite

A reliable flood warning system depends on efficient and accurate forecasting technology. A systematic investigation of three common types of artificial neural networks (ANNs) for multi-stepahead (MSA) flood forecasting is presented. The operating mechanisms and principles of the three types of MSA neural networks are explored: multi-input multi-output (MIMO), multi-input single-output (MISO) and serial-propagated structure. The most commonly used multi-layer feed-forward networks with conjugate gradient algorithm are adopted for application. Rainfall-runoff data sets from two watersheds in Taiwan are used separately to investigate the effectiveness and stability of the neural networks for MSA flood forecasting. The results indicate consistently that, even though the MIMO is the most common architecture presented in ANNs, it is less accurate because its multi-objectives (predicted many time steps) must be optimized simultaneously. Both MISO and serial-propagated neural networks are capable of performing accurate short-term (one-or two-step-ahead) forecasting. For longterm (more than two steps) forecasts, only the serial-propagated neural network could provide satisfactory results in both watersheds. The results suggest that the serial-propagated structure can help in improving the accuracy of MSA flood forecasts.

show abstract

Computational Grid vs. Parallel Computer for Coarse-Grain Parallelization of Neural Networks Training

Turchenko

2005

On the Move to Meaningful Internet Systems 2005: OTM 2005 Workshops

View full text Add to dashboard Cite

An efficient parallel algorithm for LISSOM neural network

Cited by 6 publications

References 21 publications

Real-Time Analysis of a Sensor’s Data for Automated Decision Making in an IoT-Based Smart Home

Real-Time Analysis of a Sensor’s Data for Automated Decision Making in an IoT-Based Smart Home

Multi-step-ahead neural networks for flood forecasting

Computational Grid vs. Parallel Computer for Coarse-Grain Parallelization of Neural Networks Training

Contact Info

Product

Resources

About