This paper presents a study of the efficacy of comparative controller design methods that aim to produce generalised problem solving behaviours. In this case study, the goal was to use neuro-evolution to evolve generalised maze solving behaviours. That is, evolved robot controllers that solve a broad range of mazes. To address this goal, this study compares objective, non-objective and hybrid a...

In this paper, a hybrid network based on the combination of Radial Basis Function Networks (RBFNs) and Gaussian Mixture Models (GMMs) is proposed and used for speaker recognition. The hybrid network is a hierarchical one, where a GMM is built for each speaker and an RBFN is built for each group of speakers. The GMMs and RBFNs are trained independently. The RBFNs are used as a rst stage coarse c...

In a companion paper (Nonlinear Impulsive Dynamical Systems. Part I: Stability and Dissipativity) Lyapunov and invariant set stability theorems and dissipativity theory were developed for non-linear impulsive dynamical systems. In this paper we build on these results to develop general stability criteria for feedback interconnections of non-linear impulsive systems. In addition, a uni®ed framew...

Use of adaptive energy management strategies is essential in improving energy utilization, efficiency, and sustainable operation of embedded systems. Accordingly, this paper presents embedded system applications, which are suitable for employing adaptive energy management utilized reinforcement learning. We proposed rewarding function for embedded system applications in stimulating the learning...

In this paper, a hybrid artificial network model called DIAGADHD is proposed for the diagnosis of ADHD (Attention Deficit/ Hyperactivity Disorder) using neuro fuzzy technique. This model is a combination of unsupervised training algorithm using self organizing maps and supervised training algorithm using radial basis function. The linguistic values of suspected children are received from the pa...

We construct hybrid loops that augment continuous-time control systems. We consider a continuous-time nonlinear plant in feedback with a (possibly non stabilizing) given nonlinear dynamic continuous-time state feedback controller. The arising hybrid closed loops are guaranteed to follow the underlying continuous-time closed-loop dynamics when flowing and to jump in suitable regions of the close...

In this paper, a hybrid artificial network model called DIAGADHD is proposed for the diagnosis of ADHD (Attention Deficit/ Hyperactivity Disorder) using neuro fuzzy technique. This model is a combination of unsupervised training algorithm using self organizing maps and supervised training algorithm using radial basis function. The linguistic values of suspected children are received from the pa...

In the present study, we propose a method for bio-nano hybrid formation by coupling a redox metalloprotein, Azurin, with CdSe-ZnS quantum dot for the development of a nanoscale resistive memory device. The covalent interaction between the two nanomaterials enables a strong and effective binding to form an azurin/CdSe-ZnS hybrid, and also enabled better controllability to couple with electrodes ...

We propose the notion of nondecreasing Lyapunov functions which can be used to prove stability or other properties of the system in question. This notion is in particular useful in studying switched or hybrid systems. We illustrate the concept by a general construction of such a nondecreasing Lyapunov function for a class of planar hybrid systems. It is noted that this class encompasses switche...