High‐Performance Graphene‐Fiber‐Based Neural Recording Microelectrodes

Fabrication of flexible and free‐standing graphene‐fiber‐ (GF‐) based microelectrode arrays with a thin platinum coating, acting as a current collector, results in a structure with low impedance, high surface area, and excellent electrochemical properties. This modification results in a strong synergistic effect between these two constituents leading to a robust and superior hybrid material with better performance than either graphene electrodes or Pt electrodes. The low impedance and porous structure of the GF results in an unrivalled charge injection capacity of 10.34 mC cm^?2 with the ability to record and detect neuronal activity. Furthermore, the thin Pt layer transfers the collected signals along the microelectrode efficiently. In vivo studies show that microelectrodes implanted in the rat cerebral cortex can detect neuronal activity with remarkably high signal‐to‐noise ratio (SNR) of 9.2 dB in an area as small as an individual neuron.     

Condition‐based Maintenance Optimization Using Neural Network‐based Health Condition Prediction

Artificial neural network (ANN)‐based methods have been extensively investigated for equipment health condition prediction. However, effective condition‐based maintenance (CBM) optimization methods utilizing ANN prediction information are currently not available due to two key challenges: (i) ANN prediction models typically only give a single remaining life prediction value, and it is hard to quantify the uncertainty associated with the predicted value; (ii) simulation methods are generally used for evaluating the cost of the CBM policies, while more accurate and efficient numerical methods are not available, which is critical for performing CBM optimization. In this paper, we propose a CBM optimization approach based on ANN remaining life prediction information, in which the above‐mentioned key challenges are addressed. The CBM policy is defined by a failure probability threshold value. The remaining life prediction uncertainty is estimated based on ANN lifetime prediction errors on the test set during the ANN training and testing processes. A numerical method is developed to evaluate the cost of the proposed CBM policy more accurately and efficiently. Optimization can be performed to find the optimal failure probability threshold value corresponding to the lowest maintenance cost. The effectiveness of the proposed CBM approach is demonstrated using two simulated degradation data sets and a real‐world condition monitoring data set collected from pump bearings. The proposed approach is also compared with benchmark maintenance policies and is found to outperform the benchmark policies. The proposed CBM approach can also be adapted to utilize information obtained using other prognostics methods. Copyright © 2012 John Wiley & Sons, Ltd.     

Neural network‐based image restoration using scaled residual with space‐variant regularization

Image restoration is aimed to recover the original scene from its degraded version. This paper presents a new method for image restoration. In this technique, an evaluation function which combines a scaled residual with space‐variant regularization is established and minimized using a Hopfield network to obtain a restored image from a noise corrupted and blurred image. Simulation results demonstrate that the proposed evaluation function leads to a more efficient restoration process which offers a fast convergence and improved restored image quality. © 2003 Wiley Periodicals, Inc. Int J Imaging Syst Technol 12, 247–253, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.10034     

High‐Density Stretchable Electrode Grids for Chronic Neural Recording

Electrical interfacing with neural tissue is key to advancing diagnosis and therapies for neurological disorders, as well as providing detailed information about neural signals. A challenge for creating long‐term stable interfaces between electronics and neural tissue is the huge mechanical mismatch between the systems. So far, materials and fabrication processes have restricted the development of soft electrode grids able to combine high performance, long‐term stability, and high electrode density, aspects all essential for neural interfacing. Here, this challenge is addressed by developing a soft, high‐density, stretchable electrode grid based on an inert, high‐performance composite material comprising gold‐coated titanium dioxide nanowires embedded in a silicone matrix. The developed grid can resolve high spatiotemporal neural signals from the surface of the cortex in freely moving rats with stable neural recording quality and preserved electrode signal coherence during 3 months of implantation. Due to its flexible and stretchable nature, it is possible to minimize the size of the craniotomy required for placement, further reducing the level of invasiveness. The material and device technology presented herein have potential for a wide range of emerging biomedical applications.     

Neuro‐genetic algorithm for non‐linear active control of structures

In a companion paper, a new non‐linear control model was presented for active control of three‐dimensional (3D) building structures including geometrical and material non‐linearities, coupling action between lateral and torsional motions, and actuator dynamics (Int. J. Numer. Meth. Engng; DOI: 10.1002/nme.2195 ). A dynamic fuzzy wavelet neuroemulator was presented for predicting the structural response in future time steps. In this paper, a new neuro‐genetic algorithm or controller is presented for finding the optimal control forces. The control algorithm does not need the pre‐training required in a neural network‐based controller, which improves the efficiency of the general control methodology significantly. Two 3D steel building structures, a 12‐story structure with vertical setbacks and an 8‐story structure with plan irregularity, are used to validate the neuro‐genetic control algorithm under three different seismic excitations. Numerical validations demonstrate that the new control methodology significantly reduces the displacements of buildings subjected to various seismic excitations including structures with plan and elevation irregularities. Copyright © 2008 John Wiley & Sons, Ltd.     

Reliability Forecasting of a Load‐Haul‐Dump Machine: A Comparative Study of ARIMA and Neural Networks

Both the autoregressive integrated moving average (ARIMA or the Box–Jenkins technique) and artificial neural networks (ANNs) are viable alternatives to the traditional reliability analysis methods (e.g., Weibull analysis, Poisson processes, non‐homogeneous Poisson processes, and Markov methods). Time series analysis of the times between failures (TBFs) via ARIMA or ANNs does not have the limitations of the traditional methods such as requirements/assumptions of a priori postulation and/or statistically independent and identically distributed observations for TBFs. The reliability of an LHD unit was investigated by analysis of TBFs. Seasonal autoregressive integrated moving average (SARIMA) was employed for both modeling and forecasting the failures. The results were compared with a genetic algorithm‐based (ANNs) model. An optimal ARIMA model, after a Box–Cox transformation of the cumulative TBFs, outperformed ANNs in forecasting the LHD's TBFs. Copyright © 2015 John Wiley & Sons, Ltd.     

Using Neural Networks to Detect and Classify Out‐of‐control Signals in Autocorrelated Processes

This paper presents an artificial neural network model for detecting and classifying three types of non‐random disturbances referred to as level shift, additive outlier and innovational outlier which are common in autocorrelated processes. To the best of our knowledge, this is the first time that a neural network has been considered for simultaneous detection and classification of such non‐random disturbances. An AR (1) model is considered to characterize the quality characteristic of interest in a continuous process where autocorrelated observations are generated over time. The performance of the proposed procedure is evaluated through the use of a numerical example. Preliminary results indicate that the procedure can be used effectively to detect and classify unusual shocks in autocorrelated processes. Copyright © 2003 John Wiley & Sons, Ltd.     

Automated texture‐based characterization of fibrosis and carcinoma using low‐dose lung CT images

Lung cancer is the most common cause of cancer deaths worldwide and account for 1.38 million deaths per year. Patients with lung cancer are often misdiagnosed as pulmonary tuberculosis (TB) leading to delay in the correct diagnosis as well as exposure to inappropriate medication. The diagnosis of TB and lung cancer can be difficult as symptoms of both diseases are similar in computed tomography (CT) images. However, treating TB leads to inflammatory fibrosis in some of the patients. There comes the need of an efficient computer aided diagnosis (CAD) of the fibrosis and carcinoma diseases. To design a fully automated CAD for characterizing fibrous and carcinoma tissues without human intervention using lung CT images. The 18 subjects in this study include seven healthy, two fibrosis and eight carcinoma, and one necrosis cases. The dataset is built by CT cuts representing healthy is 113, fibrosis is 103, necrosis is 39, and carcinoma is 185 totalling 440 images. The gray‐level spatial dependence matrix and gray level run length matrix approach are used for extracting texture‐based features. These features are given to neural network classifier and statistical classifier. These classifier performances are evaluated using receiver‐operating characteristics (ROC). The proposed method characterizes these tissues without human intervention. Sensitivity, specificity, precision, and accuracy followed by ROC curves were obtained and also studied. Thus, the proposed automated image‐based classifier could act as a precursor to histopathological analysis, thereby creating a way to class specific treatment procedures.     

Structural optimization by gradient‐based neural networks

In this paper a neurocomputing strategy is presented which combines data processing capabilities of neural networks and numerical structural optimization. In this strategy, an improved counterpropagation neural network is used. Two artificial neural networks are trained, one for the constraints and the other for the gradients of the constraints and structural optimization is accomplished by using these nets. All required parameters such as weight matrices in the neural networks or the gradient computations are automated in this neuro‐optimizer strategy. Numerical examples are included to demonstrate the accuracy of the results. Copyright © 1999 John Wiley & Sons, Ltd.     

On‐line Identification and Quantification of Mean Shifts in Bivariate Processes using a Neural Network‐based Approach

Many statistical process control (SPC) problems are multivariate in nature because the quality of a given process or product is determined by several interrelated variables. Various multivariate control charts (e.g. Hotelling's , multivariate cumulative sum and multivariate exponentially weighted moving average charts) have been designed for detecting mean shifts. However, the main shortcoming of such charts is that they can detect an unusual event but do not directly provide the information required by a practitioner to determine which variable or group of variables has caused the out‐of‐control signal. In addition, these charts cannot provide more detailed shift information, for example the shift magnitude, which would be very useful for quality practitioners to search the assignable causes that give rise to the out‐of‐control situation. This work proposes a neural network‐based model that can identify and quantify the mean shifts in bivariate processes on‐line. The performance evaluation performed by the simulation demonstrates that the proposed model outperforms the conventional multivariate control schemes in terms of average run length, and can accurately estimate the magnitude of the shift of each of the shifted variables in a real‐time mode. Extensive simulation is also carried out to examine the effects of correlation on the performance of the proposed model. A numerical example is presented to illustrate the usage of the proposed model. Although a mean shift identification and quantification tool for bivariate SPC is the particular application presented here, the proposed neural network‐based methodology can be applied to multivariate SPC in general. Copyright © 2006 John Wiley & Sons, Ltd.     

Modelling the dependency of the Smith–Watson–Topper parameter on the cycles‐to‐failure using serial hybrid neural networks

Calculating the fatigue damage with a strain‐based approach requires an ?–N durability curve that links the strain amplitude to the corresponding number of cycles‐to‐failure. This ?–N curve is usually modelled by the Coffin–Manson relationship. If a loading mean‐level also needs to be considered, the original Coffin–Manson relationship is modified using a Smith–Watson–Topper parameter. In this article a methodology for modelling the dependence of the Smith–Watson–Topper parameter on the number of cycles‐to‐failure is presented. The core of the presented methodology represents a multilayer perceptron neural network combined with the Smith–Watson–Topper analytical model. The article presents the theoretical background of the methodology, which is applied for the case of the experimental fatigue data. The results show that it is possible to model ?–N curves for different influential parameters, such as the specimen's diameter and the testing temperature. The results further show that it is possible to predict ?–N curves even for those combinations of the influential parameters for which no experimental data about the material endurance is available. This fact makes the presented model very suitable for the application in an R&D process when a durability of a product should be estimated on the basis of a very limited set of experimental data about the material endurance characteristics.     

Attenuated Glial Reactivity on Topographically Functionalized Poly(3,4‐Ethylenedioxythiophene):P‐Toluene Sulfonate (PEDOT:PTS) Neuroelectrodes Fabricated by Microimprint Lithography

Following implantation, neuroelectrode functionality is susceptible to deterioration via reactive host cell response and glial scar‐induced encapsulation. Within the neuroengineering community, there is a consensus that the induction of selective adhesion and regulated cellular interaction at the tissue–electrode interface can significantly enhance device interfacing and functionality in vivo. In particular, topographical modification holds promise for the development of functionalized neural interfaces to mediate initial cell adhesion and the subsequent evolution of gliosis, minimizing the onset of a proinflammatory glial phenotype, to provide long‐term stability. Herein, a low‐temperature microimprint‐lithography technique for the development of micro‐topographically functionalized neuroelectrode interfaces in electrodeposited poly(3,4‐ethylenedioxythiophene):p‐toluene sulfonate (PEDOT:PTS) is described and assessed in vitro. Platinum (Pt) microelectrodes are subjected to electrodeposition of a PEDOT:PTS microcoating, which is subsequently topographically functionalized with an ordered array of micropits, inducing a significant reduction in electrode electrical impedance and an increase in charge storage capacity. Furthermore, topographically functionalized electrodes reduce the adhesion of reactive astrocytes in vitro, evident from morphological changes in cell area, focal adhesion formation, and the synthesis of proinflammatory cytokines and chemokine factors. This study contributes to the understanding of gliosis in complex primary mixed cell cultures, and describes the role of micro‐topographically modified neural interfaces in the development of stable microelectrode interfaces.     

ANN approach to sorption hysteresis within a coupled hygro‐thermo‐mechanical FE analysis

Non‐linear deformable porous media with sorption (capillary condensation) hysteresis are considered. An artificial neural network with two hidden layers is trained to interpolate the sorption hysteresis using a set of experimental data. The performance of the ANN, which is applied as a procedure in the FE code, is investigated, both from numerical, as well as from physical viewpoint. The ANN‐FE code has been developed and tested for 1‐D and 2‐D problems concerning cyclic wetting–drying of concrete elements. In general, the application of the ANN procedure inside the classical FE program does not have any negative effect on the numerical performance of the code. The results obtained indicate that the sorption isotherm hysteresis is of importance during analysis of hygrothermal and mechanical behaviour of capillary‐porous materials. The most distinct differences are observed for the saturation and displacement solutions. The ANN‐FE approach seems to be an efficient way to take into account the influence of hysteresis during analysis of hygro‐thermal behaviour of capillary‐porous materials. Copyright © 2001 John Wiley & Sons, Ltd.     

The Design of 3D‐Interface Architecture in an Ultralow‐Power,Electrospun Single‐Fiber Synaptic Transistor for Neuromorphic Computing

Synaptic electronics is a new technology for developing functional electronic devices that can mimic the structure and functions of biological counterparts. It has broad application prospects in wearable computing chips, human–machine interfaces, and neuron prostheses. These types of applications require synaptic devices with ultralow energy consumption as the effective energy supply for wearable electronics, which is still very difficult. Here, artificial synapse emulation is demonstrated by solid‐ion gated organic field‐effect transistors (OFETs) with a 3D‐interface conducting channel for ultralow‐power synaptic simulation. The basic features of the artificial synapse, excitatory postsynaptic current (EPSC), paired‐pulse facilitation (PPF), and high‐pass filtering, are successfully realized. Furthermore, the single‐fiber based artificial synapse can be operated by an ultralow presynaptic spike down to ?0.5 mV with an ultralow reading voltage at ?0.1 mV due to the large contact surface between the ionic electrolyte and fiber‐like semiconducting channel. Therefore, the ultralow energy consumption at one spike of the artificial synapse can be realized as low as ≈3.9 fJ, which provides great potential in a low‐power integrated synaptic circuit.