Self-developing fuzzy expert system: a novel learning approach,fitting for manufacturing domain

The foremost challenge faced by expert systems, for their applicability to real world problems, is their inherent deficiency of dynamism. For an expert system to be more pragmatic and applicable, the whole structure of an expert system—including rule-base, fuzzy sets, and even user-interface—needs to be upgraded continuously. This continuous up gradation demands full-time, repetitive, and cumbersome involvement of knowledge engineers. Machine learning is an answer to this problem, but unfortunately, the solutions that have been provided are limited in scope. For example, most of the researchers put forward techniques of either generating just rules from data, or self-expanding and self-correcting knowledge-base only. The innovative approach presented in this paper is broader in scope. It enhances the efficacy and viability of expert systems to be more capable of coping with dynamic and ever-changing industrial environments. The objective is facilitated by rendering, concurrently, the self-learning, self-correcting, and self-expanding abilities to the expert system, without requiring knowledge engineering skills of the developers. This means that the user needs just to feed data in form of the values of input/output variables and the complete development of expert system is done automatically. The superiority of the proposed expert system, regarding its continuous self-development, has been explained with the help of three examples related to prediction and optimization of milling and welding processes.     

MTPSO algorithm for solving planar graph coloring problem

In this paper, we proposed a modified turbulent particle swarm optimization (named MTPSO) model for solving planar graph coloring problem based on particle swarm optimization. The proposed model is consisting of the walking one strategy, assessment strategy and turbulent strategy. The proposed MTPSO model can solve the planar graph coloring problem using four-colors more efficiently and accurately. Compared to the results shown in Cui et al. (2008), not only the experimental results of the proposed model can get smaller average iterations but can get higher correction coloring rate when the number of nodes is greater than 30.     

Learning from demonstration in robots: Experimental comparison of neural architectures

Robots have played an important role in the automation of computer aided manufacturing. The classical robot control implementation involves an expensive key step of model-based programming. An intuitive way to reduce this expensive exercise is to replace programming with machine learning of robot actions from demonstration where a (learner) robot learns an action by observing a demonstrator robot performing the same. To achieve this learning from demonstration (LFD) different machine learning techniques such as Artificial Neural Networks (ANN), Genetic Algorithms, Hidden Markov Models, Support Vector Machines, etc. can be used. This piece of work focuses exclusively on ANNs. Since ANNs have many standard architectural variations divided into two basic computational categories namely the recurrent networks and feed-forward networks, representative networks from each have been selected for study, i.e. Feed Forward Multilayer Perceptron (FF) network for feed-forward networks category and Elman (EL), and Nonlinear Autoregressive Exogenous Model (NARX) networks for the recurrent networks category. The main objective of this work is to identify the most suitable neural architecture for application of LFD in learning different robot actions. The sensor and actuator streams of demonstrated action are used as training data for ANN learning. Consequently, the learning capability is measured by comparing the error between demonstrator and corresponding learner streams. To achieve fairness in comparison three steps have been taken. First, Dynamic Time Warping is used to measure the error between demonstrator and learner streams, which gives resilience against translation in time. Second, comparison statistics are drawn between the best, instead of weight-equal, configurations of competing architectures so that learning capability of any architecture is not forced handicap. Third, each configuration's error is calculated as the average of ten trials of all possible learning sequences with random weight initialization so that the error value is independent of a particular sequence of learning or a particular set of initial weights. Six experiments are conducted to get a performance pattern of each architecture. In each experiment, a total of nine different robot actions were tested. Error statistics thus obtained have shown that NARX architecture is most suitable for this learning problem whereas Elman architecture has shown the worst suitability. Interestingly the computationally lesser MLP gives much lower and slightly higher error statistics compared to the computationally superior Elman and NARX neural architectures, respectively.     

Iterative methods for solving extended general mixed variational inequalities

In this paper, we introduce and consider a new class of mixed variational inequalities involving four operators, which are called extended general mixed variational inequalities. Using the resolvent operator technique, we establish the equivalence between the extended general mixed variational inequalities and fixed point problems as well as resolvent equations. We use this alternative equivalent formulation to suggest and analyze some iterative methods for solving general mixed variational inequalities. We study the convergence criteria for the suggested iterative methods under suitable conditions. Our methods of proof are very simple as compared with other techniques. The results proved in this paper may be viewed as refinements and important generalizations of the previous known results.     

Selective determination of urea using urease immobilized on ZnO nanowires

Well-aligned zinc oxide (ZnO) nanowire arrays were fabricated on gold-coated plastic substrates using a low-temperature aqueous chemical growth (ACG) method. The ZnO nanowire arrays with 50–130 nm diameters and ∼1 μm in lengths were used in an enzyme-based urea sensor through immobilization of the enzyme urease that was found to be sensitive to urea concentrations from 0.1 mM to 100 mM. Two linear sensitivity regions were observed when the electrochemical responses (EMF) of the sensors were plotted vs. the logarithmic concentration range of urea from 0.1 mM to 100 mM. The proposed sensor showed a sensitivity of 52.8 mV/decade for 0.1–40 mM urea and a fast response time less than 4 s was achieved with good selectivity, reproducibility and negligible response to common interferents such as ascorbic acid and uric acid, glucose, K⁺ and Na⁺ ions.     

Trading Off Cache Capacity for Low-Voltage Operation

Two proposed techniques let microprocessors operate at low voltages despite high memory-cell failure rates. They identify and disable defective portions of the cache at two granularities: individual words or pairs of bits. Both techniques use the entire cache during high-voltage operation while sacrificing cache capacity during low-voltage operation to reduce the minimum voltage below 500 mV.     

Numerical study of asymmetric laminar flow of micropolar fluids in a porous channel

A numerical study is presented for the two-dimensional flow of a micropolar fluid in a porous channel. The channel walls are of different permeability. The fluid motion is superimposed by the large injection at the two walls and is assumed to be steady, laminar and incompressible. The micropolar model due to Eringen is used to describe the working fluid. The governing equations of motion are reduced to a set of non-linear coupled ordinary differential equations (ODEs) in dimensionless form by using an extension of Berman’s similarity transformations. A numerical algorithm based on finite difference discretization is employed to solve these ODEs. The results obtained are further improved by Richardson’s extrapolation for higher order accuracy. Comparisons with the previously published work are performed and are found to be in a good agreement. It has been observed that the velocity and microrotation profiles change from the most asymmetric shape to the symmetric shape across the channel as the parameter R or the permeability parameter A are varied between their extreme values. The results indicate that larger the injection velocity at a wall relative to the other is, smaller will be the shear stress at it than that at the other. The position of viscous layer has been found to be more sensitive to the permeability parameter A than to the parameter R. The micropolar fluids reduce shear stress and increase couple stress at the walls as compared to the Newtonian fluids.     

Customized kernel execution on reconfigurable hardware for embedded applications

To conserve space and power as well as to harness high performance in embedded systems, high utilization of the hardware is required. This can be facilitated through dynamic adaptation of the silicon resources in reconfigurable systems in order to realize various customized kernels as execution proceeds. Fortunately, the encountered reconfiguration overheads can be estimated. Therefore, if the scheduling of time-consuming kernels considers also the reconfiguration overheads, an overall performance gain can be obtained. We present our policy, experiments, and performance results of customizing and reconfiguring Field-Programmable Gate Arrays (FPGAs) for embedded kernels. Experiments involving EEMBC (EDN Embedded Microprocessor Benchmarking Consortium) and MiBench embedded benchmark kernels show high performance using our main policy, when considering reconfiguration overheads. Our policy reduces the required reconfigurations by more than 50% as compared to brute-force solutions, and performs within 25% of the ideal execution time while conserving 60% of the FPGA resources. Alternative strategies to reduce the reconfiguration overhead are also presented and evaluated.     

Multi-Scale Adaptive Sampling with Mobile Agents for Mapping of Forest Fires

The use of robotics in distributed monitoring applications requires wireless sensors that are deployed efficiently. A very important aspect of sensor deployment includes positioning them for sampling at locations most likely to yield information about the spatio-temporal field of interest, for instance, the spread of a forest fire. In this paper, we use mobile robots (agents) that estimate the time-varying spread of wildfires using a distributed multi-scale adaptive sampling strategy. The proposed parametric sampling algorithm, “EKF-NN-GAS” is based on neural networks, the extended Kalman filter (EKF), and greedy heuristics. It combines measurements arriving at different times, taken at different scale lengths, such as from ground, airborne, and spaceborne observation platforms. One of the advantages of our algorithm is the ability to incorporate robot localization uncertainty in addition to sensor measurement and field parameter uncertainty into the same EKF model. We employ potential fields, generated naturally from the estimated fire field distribution, in order to generate fire-safe trajectories that could be used to rescue vehicles and personnel. The covariance of the EKF is used as a quantitative information measure for sampling locations most likely to yield optimal information about the sampled field distribution. Neural net training is used infrequently to generate initial low resolution estimates of the fire spread parameters. We present simulation and experimental results for reconstructing complex spatio-temporal forest fire fields “truth models”, approximated by radial basis function (RBF) parameterizations. When compared to a conventional raster scan approach, our algorithm shows a significant reduction in the time necessary to map the fire field.