Defect Detection in Reinforced Concrete Using Random Neural Architectures

Butcher, John B.; Day, Charles; Austin, J. Christopher; Haycock, P.W.; Verstraeten, David; Schrauwen, Benjamin

doi:10.1111/mice.12039

Cited by 88 publications

(50 citation statements)

References 47 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A PNN is a feedforward neural network [20,51] with four layers: an input layer, a pattern layer, a summation layer, and an output layer [49], shown in Fig. 1 for the classification of HC, SWEDDs, and PD subjects using the PPMI database.…”

Section: Probabilistic Neural Networkmentioning

confidence: 99%

Computer-Aided Diagnosis of Parkinson’s Disease Using Enhanced Probabilistic Neural Network

2015

View full text Add to dashboard Cite

Early and accurate diagnosis of Parkinson's disease (PD) remains challenging. Neuropathological studies using brain bank specimens have estimated that a large percentages of clinical diagnoses of PD may be incorrect especially in the early stages. In this paper, a comprehensive computer model is presented for the diagnosis of PD based on motor, non-motor, and neuroimaging features using the recently-developed enhanced probabilistic neural network (EPNN). The model is tested for differentiating PD patients from those with scans without evidence of dopaminergic deficit (SWEDDs) using the Parkinson's Progression Markers Initiative (PPMI) database, an observational, multi-center study designed to identify PD biomarkers for diagnosis and disease progression. The results are compared to four other commonly-used machine learning algorithms: the probabilistic neural network (PNN), support vector machine (SVM), k-nearest neighbors (k-NN) algorithm, and classification tree (CT). The EPNN had the highest classification accuracy at 92.5% followed by the PNN (91.6%), k-NN (90.8%) and CT (90.2%). The EPNN exhibited an accuracy of 98.6% when classifying healthy control (HC) versus PD, higher than any previous studies.

show abstract

Section: Probabilistic Neural Networkmentioning

confidence: 99%

Computer-Aided Diagnosis of Parkinson’s Disease Using Enhanced Probabilistic Neural Network

2015

View full text Add to dashboard Cite

show abstract

“…More recently, they have been used in domains such as electric load forecasting [15], sports activity classification [16] and shape recognition [17]. ESNs have also previously been used in a structural health monitoring context: for fault diagnosis in a water network [18] and defect detection in reinforced concrete [19]. In all of these studies, ESNs were found to equal, or outperform, a number of other state-of-theart techniques.…”

Section: B Echo State Networkmentioning

confidence: 99%

An Echo State Network approach to structural health monitoring

Wootton

Day

Haycock

2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Abstract-Echo State Networks (ESNs) have been applied to time-series data arising from a structural health monitoring multi-sensor array placed onto a test footbridge which has been subjected to a number of potentially damaging interventions over a three year period. The time-series data, sampled approximately every five minutes from ten temperature sensors, have been used as inputs and the ESNs were tasked with predicting the expected output signal from eight tilt sensors that were also placed on the footbridge. The networks were trained using temperature and tilt sensor data up to the first intervention and subsequent discrepancies in the ESNs' prediction accuracy allowed inferences to be made about when further interventions occurred and also the level of damage caused. Comparing the error in signals with the location of each of the tilt sensors allowed damaged regions to be determined.

show abstract

“…The ability of ESNs to exhibit a short term memory means that most applications have involved either time-series data -in areas such as audio classification [16] and recognition of forehands in tennis [17] -or spatially varying data, such as raw magnetic flux leakage data [18], [19], and microscopic cellular image segmentation [20]. The use of ESNs on static data is not new but is quite rare and, of the few approaches that do exist, most involve a procedure for allowing the state of the reservoir to settle as each static input pattern is repeatedly presented: a process characterised as clamping [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Echo State Networks for Static Pattern Recognition

et al. 2017

View full text Add to dashboard Cite

Conflict of Interest: Adam Wootton declares that he has no conflict of interest. Sarah Taylor received a research grant from NERC FSF. Charles Day declares that he has no conflict of interest. Peter Haycock declares that he has no conflict of interest. STRUCTURED ABSTRACTBackground: Static Pattern recognition requires a machine to classify an object on the basis of a combination of attributes, and is typically performed using machine learning techniques such as Support Vector Machines and Multilayer Perceptrons.Unusually, in this study we applied a successful time-series processing neural network architecture, the Echo State Network (ESN), to a static pattern recognition task. Methods: The networks were presented with clamped input data patterns, but in this work they were allowed to run until their output units delivered a stable set of output activations, in a similar fashion to previous work that focused on the behaviour of ESN reservoir units. Our aim was to see if the short term memory developed by the reservoir and the clamped inputs could deliver improved overall classification accuracy. The study utilized a challenging, high dimensional, real-world plant species spectroradiometry classification dataset with the objective of accurately detecting one of the world's top 100 invasive plant species. Results: Surprisingly, the ESNs performed equally well with both unsettled and settled reservoirs. Delivering a classification accuracy of 96.60%, the clamped ESNs outperformed three widely used machine learning techniques, namely Support Vector Machines, Extreme Learning Machines and Multilayer Perceptrons. Contrary to past work, where inputs were clamped until reservoir stabilization, it was found that it was possible to obtain similar classification accuracy (96.49%) by clamping the input patterns for just two repeats. Conclusions: The chief contribution of this work is that a recurrent architecture can get good classification accuracy, even while the reservoir is still in an unstable state.

show abstract

Defect Detection in Reinforced Concrete Using Random Neural Architectures

Cited by 88 publications

References 47 publications

Computer-Aided Diagnosis of Parkinson’s Disease Using Enhanced Probabilistic Neural Network

Computer-Aided Diagnosis of Parkinson’s Disease Using Enhanced Probabilistic Neural Network

An Echo State Network approach to structural health monitoring

Optimizing Echo State Networks for Static Pattern Recognition

Contact Info

Product

Resources

About