There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

This is the second-part paper of the survey on fault diagnosis and fault-tolerant techniques, where fault diagnosis methods and applications are overviewed, respectively, from the knowledge-based and hybrid/active viewpoints. With the aid of the first-part survey paper, the second-part review paper completes a whole overview on fault diagnosis techniques and their applications. Comments on the advantages and constraints of various diagnosis techniques, including model-based, signal-based, knowledge-based, and hybrid/active diagnosis techniques, are also given. An overlook on the future development of fault diagnosis is presented.

A Survey of Fault Diagnosis and Fault-Tolerant Techniques—Part II: Fault Diagnosis With Knowledge-Based and Hybrid/Active Approaches

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems The promise of the technology is to create a brain-like ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed

A Survey of Neuromorphic Computing and Neural Networks in Hardware.

This paper presents a hardware implementation of multilayer feedforward neural networks (NN) using reconfigurable field-programmable gate arrays (FPGAs). Despite improvements in FPGA densities, the numerous multipliers in an NN limit the size of the network that can be implemented using a single FPGA, thus making NN applications not viable commercially. The proposed implementation is aimed at reducing resource requirement, without much compromise on the speed, so that a larger NN can be realized on a single chip at a lower cost. The sequential processing of the layers in an NN has been exploited in this paper to implement large NNs using a method of layer multiplexing. Instead of realizing a complete network, only the single largest layer is implemented. The same layer behaves as different layers with the help of a control block. The control block ensures proper functioning by assigning the appropriate inputs, weights, biases, and excitation function of the layer that is currently being computed. Multilayer networks have been implemented using Xilinx FPGA "XCV400hq240." The concept used is shown to be very effective in reducing resource requirements at the cost of a moderate overhead on speed. This implementation is proposed to make NN applications viable in terms of cost and speed for online applications. An NN-based flux estimator is implemented in FPGA and the results obtained are presented

Feedforward Neural Network Implementation in FPGA Using Layer Multiplexing for Effective Resource Utilization

The first decade of the 21st-century has seen a rapid development in infrared photodetector technology. At the end of the last millennium there were two dominant IR systems, InSb- and HgCdTe-based detectors, which were well developed and available in commercial systems. While these two systems saw improvements over the last twelve years, their change has not nearly been as marked as that of the quantum-based detectors (i.e., QWIPs, QDIPs, DWELL-IPs, and SLS-based photodetectors). In this paper, we review the progress made in all of these systems over the last decade plus, compare the relative merits of the systems as they stand now, and discuss where some of the leading research groups in these fields are going to take these technologies in the years to come.

Progress in Infrared Photodetectors Since 2000

In this article, efficient hardware architectures for particle filter (PF) are presented. We propose three different architectures for Sequential Importance Resampling Filter (SIRF) implementation. The first architecture is a two-step sequential PF machine, where particle sampling, weight, and output calculations are carried out in parallel during the first step followed by sequential resampling in the second step. For the weight computation step, a piecewise linear function is used instead of the classical exponential function. This decreases the complexity of the architecture without degrading the results. The second architecture speeds up the resampling step via a parallel, rather than a serial, architecture. This second architecture targets a balance between hardware resources and the speed of operation. The third architecture implements the SIRF as a distributed PF composed of several processing elements and central unit. All the proposed architectures are captured using VHDL synthesized using Xilinx environment, and verified using the ModelSim simulator. Synthesis results confirmed the resource reduction and speed up advantages of our architectures.

https://link.springer.com/content/pdf/10.1186%2F1687-6180-2012-17.pdf

Proposed hardware architectures of particle filter for object tracking

ANN based Sensor Faults Detection, Isolation, and Reading Estimates – SFDIRE: Applied in a nuclear process

This paper presents a method to evaluate and improve the performance of quantum dot infrared photodetectors (QDIPs) We proposed a device model for QDIPs The developed model accounts for the self-consistent potential distribution, features of the electron capture and transport in realistic QDIPs in dark and illumination conditions This model taking the effect of donor charges on the spatial distribution of the electric potential in the QDIP active region The model is used for the calculation of the dark current, photocurrent and detectivity as a function of the structural parameters such as applied voltage, doping QD density, QD layers, and temperature It explains strong sensitivity of dark current to the density of QDs and the doping level of the active region In order to confirm our models and their validity on the practical applications, a comparison between the results obtained by proposed models and that experimentally published are conducted and full agreement is observed Results show the effectiveness of methodology introduced

Performance improvement of quantum dot infrared photodetectors through modeling

This paper has introduced a digital process aimed at automatically identify and classify flaws in the weld joints. Therefore, various algorithms are presented for computer aided detection (CAD) and classification. These algorithms include preprocessing algorithms using Gaussian pyramidal transform, contrast enhancement algorithm using contrast stretch and normalization method, noise reduction algorithm by blind image separation (BIS), measurement of the noise separation quality and image segmentation algorithm based on expectation-maximization (EM) method. Also, an algorithm for detection and classification of welding defects from radiographic images is presented. This algorithm is based on multi-scale wavelet packet (MWP) technique for feature extraction. Also, extraction of features from its transform domains is proposed to assist in achieving a higher classification rate. Moreover, the support vector machine (SVM) is applied for matching the extracted features. Consequently, classification error was computed for both normal and defect images. The obtained results confirm that much higher classification error was computed for defect image due to various objects may be in the image. Moreover, the accuracy of the considered algorithms is determined by statistical measurements. These algorithms have the potential for further improvement because of their simplicity and encouraging results. Therefore, it will motivate real-time flaws detection and classification for many CAD applications.

Classification of Welding Flaws in Gamma Radiography Images Based on Multi-scale Wavelet Packet Feature Extraction Using Support Vector Machine

This paper presents algorithms for overcoming a common problem of gamma ray spectroscopy, namely the peak pileup recovery problem. Three different approaches are studied and evaluated within a spectroscopy system. The algorithms are evaluated by the means of parameters error and fitting error calculations. The first approach is a direct search based on Nelder-Mead technique without any derivatives in order to find the local minimum points. A Gaussian shape in conjunction with the peak height and its position of each pulse are used to construct the pulse. So, the main pulse parameters such as peak amplitude, position and width can be determined. The second algorithm is based on the nonlinear least square method. In this paper another technique is tried. This technique which is proposed as third algorithm is based on a maximum peak search method combined with the first derivative method to determine peak position of each pulse. Comparison among these approaches is conducted in terms of parameters errors. The pulse parameters have been calculated and compared with the actual one. The second approach shows the best accuracy, for determining peak height and position, but the width parameter scored the highest error.

http://iopscience.iop.org/article/10.1088/1748-0221/7/09/P09013/pdf

Imbaby I. Mahmoud

Papers

Proposed hardware architectures of particle filter for object tracking

ANN based Sensor Faults Detection, Isolation, and Reading Estimates – SFDIRE: Applied in a nuclear process

Performance improvement of quantum dot infrared photodetectors through modeling

Classification of Welding Flaws in Gamma Radiography Images Based on Multi-scale Wavelet Packet Feature Extraction Using Support Vector Machine

Pileup recovery algorithms for digital gamma ray spectroscopy