Selection of network and learning parameters for an adaptive neural robotic control scheme

This paper presents the results of a study in the design of a neural network based adaptive robotic control scheme. The neural network used here is a two hidden layer feedforward network and the learning scheme is the well-known backpropagation algorithm. The neural network essentially provides the inverse of the plant and acts in conjunction with a standard PD controller in the feedback loop. The objective of the controller is to accurately control the end position of a single link manipulator in the presence of large payload variations, variations in the link length and also variations in the damping constant. Based on results of this study, guidelines are presented in selecting the number of neurons in the hidden layers and also the parameters for the learning scheme used for training the network. Results also indicate that increasing the number of neurons in the hidden layer will improve the convergence speed of learning scheme up to a certain limit beyond which the addition of neurons will cause oscillations and instability. Guidelines for selecting the proper learning rate, momentum and fast backpropagation constant that ensure stability and convergence are presented. Also, a relationship between the r.m.s. error and the number of iterations used in training the neural network is established.     

Effects of flux enhancing polymer on the characteristics of sludge in membrane bioreactor process.

A newly developed membrane performance enhancer (MPE) was used to prevent membrane fouling in a membrane bioreactor (MBR) process. It transpired that 1,000 mg/l of MPE reduced polysaccharide levels from 41 mg/I to 21 mg/I on average under the experimental condition. Repeated experiments also confirmed that 50-1,000 mg/l of MPE could reduce membrane fouling significantly and increase the intervals between membrane cleanings. Depending on MPE dosages and experimental conditions, trans-membrane pressure (TMP) increase was suppressed for 20-30 days, while baseline TMP surged within a few days. In addition, MPE allowed MBR operation even at 50,000 mg/l of total solid and reduced permeate COD. However, no evidence of toxicity for sludge was found from respiratory works.     

CMOS integrated elliptic diaphragm capacitive pressure sensor in SiGe MEMS

A novel CMOS integrated Micro-Electro-Mechanical capacitive pressure sensor in SiGe MEMS (Silicon Germanium Micro-Electro-Mechanical System) process is designed and analyzed. Excellent mechanical stress–strain behavior of Polycrystalline Silicon Germanium (Poly-SiGe) is utilized effectively in this MEMS design to characterize the structure of the pressure sensor diaphragm element. The edge clamped elliptic structured diaphragm uses semi-major axis clamp springs to yield high sensitivity, wide dynamic range and good linearity. Integrated on-chip signal conditioning circuit in 0.18 μm TSMC CMOS process (forming the host substrate base for the SiGe MEMS) is also implemented to achieve a high overall gain of 102 dB for the MEMS sensor. A high sensitivity of 0.17 mV/hPa (@1.4 V supply), with a non linearity of around 1 % is achieved for the full scale range of applied pressure load. The diaphragm with a wide dynamic range of 100–1,000 hPa stacked on top of the CMOS circuitry, effectively reduces the combined sensor and conditioning implementation area of the intelligent sensor chip.     

Iterative control approach to high-speed force-distance curve measurement using AFM: time-dependent response of PDMS example

Force-distance curve measurements using atomic force microscope (AFM) has been widely used in a broad range of areas. However, currently force-curve measurements are hampered the its low speed of AFM. In this article, a novel inversion-based iterative control technique is proposed to dramatically increase the speed of force-curve measurements. Experimental results are presented to show that by using the proposed control technique, the speed of force-curve measurements can be increased by over 80 times--with no loss of spatial resolution--on a commercial AFM platform and with a standard cantilever. High-speed force curve measurements using this control technique are utilized to quantitatively study the time-dependent elastic modulus of poly(dimethylsiloxane) (PDMS). The force-curves employ a broad spectrum of push-in (load) rates, spanning two-order differences. The elastic modulus measured at low-speed compares well with the value obtained from dynamic mechanical analysis (DMA) test, and the value of the elastic modulus increases as the push-in rate increases, signifying that a faster external deformation rate transitions the viscoelastic response of PDMS from that of a rubbery material toward a glassy one.     

Recurrent Network Based Protocol Design for Spectrum Sensing in Cognitive Users

Wireless Personal Communications - This work focuses on cognitive users and its utilization of spectrum with channel bonding. Recurrent Channel Bonding Cognitive Users protocol (RCBCU) has been...     

Synthesis of Co3 O4 /graphene nanocomposite using paraffin wax for adsorption of methyl violet in water

This study discusses the use of Co₃ O₄ impregnated graphene (CoOIG) as an efficient adsorbent for the removal of methyl violet (MV) dye from wastewater. CoOIG nanocomposites have been prepared by pyrolyzing paraffin wax with cobalt acetate. The synthesised nanocomposite was characterised by X‐ray diffraction, field emission scanning electron microscope, transmission electron microscope, Fourier transform infrared spectroscope, Raman spectroscopy, and Brunauer–Emmett–Teller isotherm studies. The above studies indicate that the composites have cobalt oxide nanoparticles of size 51–58 nm embedded in the graphene nanoparticles. The adsorption studies were conducted with various parameters, pH, temperature and initial dye concentration, adsorbent dosage and contact time by the batch method. The adsorption of MV dye by the adsorbent CoOIG was about 90% initially at 15 min and 98% dye removal at pH 5. The data were fitted in Langmuir, Freundlich, Temkin, and Dubinin–Radushkevich and Sips isotherm models. Various thermodynamic parameters like Gibbs free energy, enthalpy, and entropy of the on‐going adsorption process have also been calculated.Inspec keywords: cobalt compounds, graphene, nanoparticles, nanocomposites, nanofabrication, adsorption, dyes, scanning electron microscopy, field emission electron microscopy, transmission electron microscopy, Raman spectra, Fourier transform infrared spectra, free energy, enthalpy, entropyOther keywords: nanocomposite, paraffin wax, adsorption, methyl violet dye, water, X‐ray diffraction, field emission scanning electron microscopy, transmission electron microscopy, Fourier transform infrared spectroscopy, Raman spectroscopy, Brunauer‐Emmett‐Teller isotherm, cobalt oxide nanoparticles, graphene nanoparticles, thermodynamic parameters, Gibbs free energy, enthalpy, entropy, Co₃ O₄ ‐C     

A combined scheme of edge-based and node-based smoothed finite element methods for Reissner–Mindlin flat shells

In this paper, a combined scheme of edge-based smoothed finite element method (ES-FEM) and node-based smoothed finite element method (NS-FEM) for triangular Reissner–Mindlin flat shells is developed to improve the accuracy of numerical results. The present method, named edge/node-based S-FEM (ENS-FEM), uses a gradient smoothing technique over smoothing domains based on a combination of ES-FEM and NS-FEM. A discrete shear gap technique is incorporated into ENS-FEM to avoid shear-locking phenomenon in Reissner–Mindlin flat shell elements. For all practical purpose, we propose an average combination (aENS-FEM) of ES-FEM and NS-FEM for shell structural problems. We compare numerical results obtained using aENS-FEM with other existing methods in the literature to show the effectiveness of the present method.     

Classification of primitive shapes using brain–computer interfaces

Brain–computer interfaces (BCIs) are recent developments in alternative technologies of user interaction. The purpose of this paper is to explore the potential of BCIs as user interfaces for CAD systems. The paper describes experiments and algorithms that use the BCI to distinguish between primitive shapes that are imagined by a user. Users wear an electroencephalogram (EEG) headset and imagine the shape of a cube, sphere, cylinder, pyramid or a cone. The EEG headset collects brain activity from 14 locations on the scalp. The data is analyzed with independent component analysis (ICA) and the Hilbert–Huang Transform (HHT). The features of interest are the marginal spectra of different frequency bands (theta, alpha, beta and gamma bands) calculated from the Hilbert spectrum of each independent component. The Mann–Whitney U-test is then applied to rank the EEG electrode channels by relevance in five pair-wise classifications. The features from the highest ranking independent components form the final feature vector which is then used to train a linear discriminant classifier. Results show that this classifier can discriminate between the five basic primitive objects with an average accuracy of about 44.6% (compared to naïve classification rate of 20%) over ten subjects (accuracy range of 36%–54%). The accuracy classification changes to 39.9% when both visual and verbal cues are used. The repeatability of the feature extraction and classification was checked by conducting the experiment on 10 different days with the same participants. This shows that the BCI holds promise in creating geometric shapes in CAD systems and could be used as a novel means of user interaction.     

Performance evaluation of a sequential minimal radial basisfunction (RBF) neural network learning algorithm

Presents a detailed performance analysis of the minimal resource allocation network (M-RAN) learning algorithm, M-RAN is a sequential learning radial basis function neural network which combines the growth criterion of the resource allocating network (RAN) of Platt (1991) with a pruning strategy based on the relative contribution of each hidden unit to the overall network output. The resulting network leads toward a minimal topology for the RAN. The performance of this algorithm is compared with the multilayer feedforward networks (MFNs) trained with 1) a variant of the standard backpropagation algorithm, known as RPROP and 2) the dependence identification (DI) algorithm of Moody and Antsaklis (1996) on several benchmark problems in the function approximation and pattern classification areas. For all these problems, the M-RAN algorithm is shown to realize networks with far fewer hidden neurons with better or same approximation/classification accuracy. Further, the time taken for learning (training) is also considerably shorter as M-RAN does not require repeated presentation of the training data.     

Structure and Properties of Nano-Scale Oxide-Dispersed Iron

Bulk samples of pure iron and yttria dispersed iron with and without titanium (i.e., Fe, Fe-Y₂O₃, and Fe-Y₂O₃-Ti) were prepared by hot extrusion of high-energy ball-milled powders. An examination of the microstructure using TEM revealed that the addition of titanium resulted in the reduction of the dispersoid size with a concomitant increase in the volume fraction of the dispersoids. As a result, Fe-Y₂O₃-Ti exhibited a substantial increase in hardness and tensile properties as compared to Fe and Fe-Y₂O₃. The higher hardness and strength of Fe-Y₂O₃-Ti is shown to be due to the presence of finer and higher number density of Y-Ti-O complex oxides. Dynamic strain aging in the temperature range of 423 K to 573 K (150 °C to 300 °C) was observed in all the compositions studied.