Multimodal Biometric Human Recognition for Perceptual Human-Computer Interaction

In this paper, a novel video-based multimodal biometric verification scheme using the subspace-based low-level feature fusion of face and speech is developed for specific speaker recognition for perceptual human--computer interaction (HCI). In the proposed scheme, human face is tracked and face pose is estimated to weight the detected facelike regions in successive frames, where ill-posed faces and false-positive detections are assigned with lower credit to enhance the accuracy. In the audio modality, mel-frequency cepstral coefficients are extracted for voice-based biometric verification. In the fusion step, features from both modalities are projected into nonlinear Laplacian Eigenmap subspace for multimodal speaker recognition and combined at low level. The proposed approach is tested on the video database of ten human subjects, and the results show that the proposed scheme can attain better accuracy in comparison with the conventional multimodal fusion using latent semantic analysis as well as the single-modality verifications. The experiment on MATLAB shows the potential of the proposed scheme to attain the real-time performance for perceptual HCI applications.

Kinematic modeling of Exechon parallel kinematic machine

The studies on PKMs have attracted a great attention to robotics community. By deploying a parallel kinematic structure, a parallel kinematic machine (PKM) is expected to possess the advantages of heavier working load, higher speed, and higher precision. Hundreds of new PKMs have been proposed. However, due to the considerable gaps between the desired and actual performances, the majorities of the developed PKMs were the prototypes in research laboratories and only a few of them have been practically applied for various applications; among the successful PKMs, the Exechon machine tool is recently developed. The Exechon adopts unique over-constrained structure, and it has been improved based on the success of the Tricept parallel kinematic machine. Note that the quantifiable theoretical studies have yet been conducted to validate its superior performances, and its kinematic model is not publically available. In this paper, the kinematic characteristics of this new machine tool is investigated, the concise models of forward and inverse kinematics have been developed. These models can be used to evaluate the performances of an existing Exechon machine tool and to optimize new structures of an Exechon machine to accomplish some specific tasks.

Scheme for enhancing efficiency in resonant-cavity Schottky photodetectors

It is shown that structuring the top layers of a resonant cavity Schottky photodetector in a way that allows coupling between the wavevector of incident radiation and that of electron-collective oscillations (plasmons) at the surface of the metallic electrode leads to practically zero reflectance in the case of front illuminated devices. This is expected to result in a consequential enhancement in the quantum efficiency in these photodetectors. (C) 2001 Elsevier Science Ltd. All rights reserved.

Whole-Life Costing for Capability

In recent years, there has been growing emphasis on the need to provide transparency in the costs of engineering programmes, leading to growing emphasis on Whole Life Cost (WLC) modelling techniques. This has arisen largely due to the increased interested in longer timescale projects and programmes, combined with the emergence of system-of-systems and network enabled capability concepts. This change in the implementation and management of large scale projects has necessitated the development of alternative methods of evaluating performance. This work seeks to address the shortfalls in current costing methodologies when applied to these highly flexible environments, and to propose a conceptual model for dealing with the encountered complexities. The approach has a fundamental role and potential significance in the future of whole life costing for Network Enabled Capability (NEC) but can also offer a potential paradigm shift for costing in traditional engineering environments.

Workspace evaluation of manipulators through finite-partition of SE(3)

Workspace analysis and optimization are important in a manipulator design. As the complete workspace of a 6-DOF manipulator is embedded into a 6-imensional space, it is difficult to quantify and qualify it. Most literatures only considered the 3-D sub workspaces of the complete 6-D workspace. In this paper, a finite-partition approach of the Special Euclidean group SE(3) is proposed based on the topology properties of SE(3), which is the product of Special Orthogonal group SO(3) and R^3. It is known that the SO(3) is homeomorphic to a solid ball D^3 with antipodal points identified while the geometry of R^3 can be regarded as a cuboid. The complete 6-D workspace SE(3) is at the first time parametrically and proportionally partitioned into a number of elements with uniform convergence based on its geometry. As a result, a basis volume element of SE(3) is formed by the product of a basis volume element of R^3 and a basis volume element of SO(3), which is the product of a basis volume element of D^3 and its associated integration measure. By this way, the integration of the complete 6-D workspace volume becomes the simple summation of the basis volume elements of SE(3). Two new global performance indices, i.e., workspace volume ratio Wr and global condition index GCI, are defined over the complete 6-D workspace. A newly proposed 3 RPPS parallel manipulator is optimized based on this finite-partition approach. As a result, the optimal dimensions for maximal workspace are obtained, and the optimal performance points in the workspace are identified.

Convergence of the iterative algorithm for a general Hammerstein system identification

The convergence of the iterative identification algorithm for a general Hammerstein system has been an open problem for a long time. In this paper, it is shown that the convergence can be achieved by incorporating a regularization procedure on the nonlinearity in addition to a normalization step on the parameters.

Improved Nonlinear PCA for Process Monitoring Using Support Vector Data Description

Nonlinear principal component analysis (PCA) based on neural networks has drawn significant attention as a monitoring tool for complex nonlinear processes, but there remains a difficulty with determining the optimal network topology. This paper exploits the advantages of the Fast Recursive Algorithm, where the number of nodes, the location of centres, and the weights between the hidden layer and the output layer can be identified simultaneously for the radial basis function (RBF) networks. The topology problem for the nonlinear PCA based on neural networks can thus be solved. Another problem with nonlinear PCA is that the derived nonlinear scores may not be statistically independent or follow a simple parametric distribution. This hinders its applications in process monitoring since the simplicity of applying predetermined probability distribution functions is lost. This paper proposes the use of a support vector data description and shows that transforming the nonlinear principal components into a feature space allows a simple statistical inference. Results from both simulated and industrial data confirm the efficacy of the proposed method for solving nonlinear principal component problems, compared with linear PCA and kernel PCA.

Automated nonlinear system modelling with multiple neural networks

This article discusses the identification of nonlinear dynamic systems using multi-layer perceptrons (MLPs). It focuses on both structure uncertainty and parameter uncertainty, which have been widely explored in the literature of nonlinear system identification. The main contribution is that an integrated analytic framework is proposed for automated neural network structure selection, parameter identification and hysteresis network switching with guaranteed neural identification performance. First, an automated network structure selection procedure is proposed within a fixed time interval for a given network construction criterion. Then, the network parameter updating algorithm is proposed with guaranteed bounded identification error. To cope with structure uncertainty, a hysteresis strategy is proposed to enable neural identifier switching with guaranteed network performance along the switching process. Both theoretic analysis and a simulation example show the efficacy of the proposed method.

Dynamic evolution of the genetic search region through fuzzy coding

A technique for automatic exploration of the genetic search region through fuzzy coding (Sharma and Irwin, 2003) has been proposed. Fuzzy coding (FC) provides the value of a variable on the basis of the optimum number of selected fuzzy sets and their effectiveness in terms of degree-of-membership. It is an indirect encoding method and has been shown to perform better than other conventional binary, Gray and floating-point encoding methods. However, the static range of the membership functions is a major problem in fuzzy coding, resulting in longer times to arrive at an optimum solution in large or complicated search spaces. This paper proposes a new algorithm, called fuzzy coding with a dynamic range (FCDR), which dynamically allocates the range of the variables to evolve an effective search region, thereby achieving faster convergence. Results are presented for two benchmark optimisation problems, and also for a case study involving neural identification of a highly non-linear pH neutralisation process from experimental data. It is shown that dynamic exploration of the genetic search region is effective for parameter optimisation in problems where the search space is complicated.

Strategies for adding features to CAD models in order to optimize performance

This paper presents an approach which enables new parameters to be added to a CAD model for optimization purposes. It aims to remove a common roadblock to CAD based optimization, where the parameterization of the model does not offer the shape sufficient flexibility for a truly optimized shape to be created. A technique has been developed which uses adjoint based sensitivity maps to predict
the sensitivity of performance to the addition to a model of four different feature types, allowing the feature providing the greatest benefit to be selected. The optimum position to add the feature is also discussed. It is anticipated that the approach could be used to iteratively add features to a model, providing greater flexibility to the shape of the model, and allowing the newly-added parameters to be used as design variables in a subsequent shape optimization.

The Influence of Friction Stir Welding Process Idealization on Residual Stress and Distortion Predictions for Future Airframe Assembly Simulations

The ability to accurately predict residual stresses and resultant distortions is a key product from process assembly simulations. Assembly processes necessarily consider large structural components potentially making simulations computationally expensive. The objective herein is to develop greater understanding of the influence of friction stir welding process idealization on the prediction of residual stress and distortion and thus determine the minimum required modeling fidelity for future airframe assembly simulations. The combined computational and experimental results highlight the importance of accurately representing the welding forging force and process speed. In addition, the results emphasize that increased CPU simulation times are associated with representing the tool torque, while there is potentially only local increase in prediction fidelity.