Search results

To present a neural network‐based approach to the design of electromagnetic devices.

A neural model is created which reproduces the relationship between the design parameters of the device and the performance parameters, typically field values.

The neural model is a single hidden layer MLP network, trained by using a set of cases calculated, for example, by means of a finite element analysis. The design problem can be solved by fixing the performance values at the output of the network and by calculating the corresponding input values. The relationship between the input and the output of the neural network is represented by three equations systems. By means of these three systems, we can forward the domain of the input, and we can back propagate the desired output throughout the network layers. In such a way, both the domain of the design parameters and the domain of the desired performances values can be projected in the same space. Whatever point inside the intersection between the two projected domains corresponds to a solution of the design problem.

Presents a procedure which is able to find a point belonging to such an intersection.

In keystroke‐based authentication systems, an input device to enter a password is needed. Users are verified by checking the validity of the password and typing characteristics. However, some devices have no standard desktop keyboard such as personal digital assistants and mobile phones. With these types of electronics, the system cannot successfully work in the authentication phase while the registration process is implemented based on a computer keyboard. This results in a reduction of system portability. The purpose of this paper is to employ the rhythm clicked by a mouse as another identifiable factor to authenticate a user's identity.

Mouse click can be replaced by a stylus and fingers on touch screens or numeral buttons on mobile phones. A total of 25 users participated and the click data are based on time instances of pressing and releasing the mouse button, which are captured while the user clicks a rhythm. Three features are calculated using these click data, and a reasonable amount of results with neural networks and other classifiers shows the click characteristics are able to function as another identifiable factor.

A reasonable amount of results with neural networks and other classifiers shows the click characteristics are able to function as another identifiable factor.

The paper presents a personalized rhythm click‐based authentication system.

Knowledge of the microwave transistor parameters at various bias conditions is often required in computer‐aided design of complex microwave low‐noise circuit. Since the measurements of noise parameters are very complex and time‐consuming, microwave circuit designers usually use the catalogues' data or noise models. The noise data that can be found in the catalogues are often limited to a few frequencies and to one or few bias points. Further, most of the existing noise models require recalculation of elements/parameters of an equivalent circuit for every bias point. Microwave HEMT transistor noise prediction based on a multilayer perceptron neural network, proposed in this paper, enables noise prediction for all operating points over a wide frequency range. Neural networks are trained to learn noise parameters' dependence on bias conditions and frequency. After network training, noise prediction for a specified bias point requires only a network response calculation without changes in the network structure.

The purpose of this paper is to examine two different approaches in the prediction of the economic recession periods in the US economy.

A logit regression was applied and the prediction performance in two out‐of‐sample periods, 2007‐2009 and 2010 was examined. On the other hand, feed‐forwards neural networks with Levenberg‐Marquardt error backpropagation algorithm were applied and then neural networks self‐organizing map (SOM) on the training outputs was estimated.

The paper presents the cluster results from SOM training in order to find the patterns of economic recessions and expansions. It is concluded that logit model forecasts the current financial crisis period at 75 percent accuracy, but logit model is useful as it provides a warning signal three quarters before the current financial crisis started officially. Also, it is estimated that the financial crisis, even if it reached its peak in 2009, the economic recession will be continued in 2010 too. Furthermore, the patterns generated by SOM neural networks show various possible versions with one common characteristic, that financial crisis is not over in 2009 and the economic recession will be continued in the USA even up to 2011‐2012, if government does not apply direct drastic measures.

Both logistic regression (logit) and SOMs procedures are useful. The first one is useful to examine the significance and the magnitude of each variable, while the second one is useful for clustering and identifying patterns in economic recessions and expansions.

The aim of the paper is to find a simple structure of speed controller robust against drive parameters variations. Application of artificial neural network (ANN) in the controller of PI type creates proper non‐linear characteristics, which ensures controller robustness.

The robustness of the controller is based on its non‐linear characteristic introduced by ANN. The paper proposes a novel approach to neural controller synthesis to be performed in two stages. The first stage consists in training the ANN to form the proper shape of the control surface, which represents the non‐linear characteristic of the controller. At the second stage, the PI controller settings are adjusted by means of the random weight change (RWC) procedure, which optimises the control quality index formulated in the paper. The synthesis is performed using simulation techniques and subsequently the behaviour of a laboratory speed control system is validated in the experimental set‐up. The control algorithms of the system are performed by a microprocessor floating point DSP control system.

The proposed controller structure with proper control surface created by ANN guarantees expected robustness.

The original method of robust controller synthesis was proposed and validated by simulation and experimental investigations.

According to UN estimates more than 2,000 people are killed or maimed every month by land‐mines. Although some mechanical solutions to their removal have been proposed, this is still heavily dependent on human manipulation. This study seeks to posit a robotic solution to this extremely hazardous operation.

Examines an active tele‐operated master‐slave robot hand system in which the master and slave hands have completely different structures.

A secure grasping strategy with a neuro‐fuzzy position control is optional, involving robust position control and accurate force control.

To the best of the authors' knowledge, the configuration and control system of the tele‐operation master‐slave robotic hand is novel in the applied robotics research field.

The trend of “Deep Learning for Internet of Things (IoT)” has gained fresh momentum with enormous upcoming applications employing these models as their processing engine and Cloud as their resource giant. But this picture leads to underutilization of ever-increasing device pool of IoT that has already passed 15 billion mark in 2015. Thus, it is high time to explore a different approach to tackle this issue, keeping in view the characteristics and needs of the two fields. Processing at the Edge can boost applications with real-time deadlines while complementing security.

This review paper contributes towards three cardinal directions of research in the field of DL for IoT. The first section covers the categories of IoT devices and how Fog can aid in overcoming the underutilization of millions of devices, forming the realm of the things for IoT. The second direction handles the issue of immense computational requirements of DL models by uncovering specific compression techniques. An appropriate combination of these techniques, including regularization, quantization, and pruning, can aid in building an effective compression pipeline for establishing DL models for IoT use-cases. The third direction incorporates both these views and introduces a novel approach of parallelization for setting up a distributed systems view of DL for IoT.

DL models are growing deeper with every passing year. Well-coordinated distributed execution of such models using Fog displays a promising future for the IoT application realm. It is realized that a vertically partitioned compressed deep model can handle the trade-off between size, accuracy, communication overhead, bandwidth utilization, and latency but at the expense of an additionally considerable memory footprint. To reduce the memory budget, we propose to exploit Hashed Nets as potentially favorable candidates for distributed frameworks. However, the critical point between accuracy and size for such models needs further investigation.

To the best of our knowledge, no study has explored the inherent parallelism in deep neural network architectures for their efficient distribution over the Edge-Fog continuum. Besides covering techniques and frameworks that have tried to bring inference to the Edge, the review uncovers significant issues and possible future directions for endorsing deep models as processing engines for real-time IoT. The study is directed to both researchers and industrialists to take on various applications to the Edge for better user experience.

Reviews some of the good reasons for looking to real neural nets for guidance on ways of implementing effective parallel computation. Discusses existing artificial neural nets with particular attention to the extent to which they model real neural activity. Indicates some serious mismatches, but shows that there are also important correspondences. The successful applications are to image processing, pattern classification and automatic optimization, in various guises. Reviews important issues raised by extension to the symbolic problem solving of “intellectual” thought, the prime concern of classical AI. These illustrate the importance of recursion, and of a degree of continuity associated with any evolutionary process.

Humans acquire knowledge through their central nervous system and models of this process are the first connection between cognition and cybernetics. Taking this as its starting point, this article examines parallels between human psychology and the central nervous system, and models of computer systems; both are required to receive, process and interpret information. The author discusses the human neural system and neural nets and how these can be likened to Computer‐Aided Knowledge systems.

The purpose of this paper is to introduce new non‐classical implementations of neural networks (NNs). The developed implementations are performed in the quantum, nano, and optical domains to perform the required neural computing. The various implementations of the new NNs utilizing the introduced architectures are presented, and their extensions for the utilization in the non‐classical neural‐systolic networks are also introduced.

The introduced neural circuits utilize recent findings in the quantum, nano, and optical fields to implement the functionality of the basic NN. This includes the techniques of many‐valued quantum computing (MVQC), carbon nanotubes (CNT), and linear optics. The extensions of implementations to non‐classical neural‐systolic networks using the introduced neural‐systolic architectures are also presented.

Novel NN implementations are introduced in this paper. NN implementation using the general scheme of MVQC is presented. The proposed method uses the many‐valued quantum orthonormal computational basis states to implement such computations. Physical implementation of quantum computing (QC) is performed by controlling the potential to yield specific wavefunction as a result of solving the Schrödinger equation that governs the dynamics in the quantum domain. The CNT‐based implementation of logic NNs is also introduced. New implementations of logic NNs are also introduced that utilize new linear optical circuits which use coherent light beams to perform the functionality of the basic logic multiplexer by utilizing the properties of frequency, polarization, and incident angle. The implementations of non‐classical neural‐systolic networks using the introduced quantum, nano, and optical neural architectures are also presented.

The introduced NN implementations form new important directions in the NN realizations using the newly emerging technologies. Since the new quantum and optical implementations have the advantages of very high‐speed and low‐power consumption, and the nano implementation exists in very compact space where CNT‐based field effect transistor switches reliably using much less power than a silicon‐based device, the introduced implementations for non‐classical neural computation are new and interesting for the design in future technologies that require the optimal design specifications of super‐high speed, minimum power consumption, and minimum size, such as in low‐power control of autonomous robots, adiabatic low‐power very‐large‐scale integration circuit design for signal processing applications, QC, and nanotechnology.