Online modeling with tunable RBF network

In this paper, we propose a novel online modeling algorithm for nonlinear and nonstationary systems using a radial basis function (RBF) neural network with a fixed number of hidden nodes. Each of the RBF basis functions has a tunable center vector and an adjustable diagonal covariance matrix. A multi-innovation recursive least square (MRLS) algorithm is applied to update the weights of RBF online, while the modeling performance is monitored. When the modeling residual of the RBF network becomes large in spite of the weight adaptation, a node identified as insignificant is replaced with a new node, for which the tunable center vector and diagonal covariance matrix are optimized using the quantum particle swarm optimization (QPSO) algorithm. The major contribution is to combine the MRLS weight adaptation and QPSO node structure optimization in an innovative way so that it can track well the local characteristic in the nonstationary system with a very sparse model. Simulation results show that the proposed algorithm has significantly better performance than existing approaches.

Elastic-net prefiltering for two-class classification

A two-stage linear-in-the-parameter model construction algorithm is proposed aimed at noisy two-class classification problems. The purpose of the first stage is to produce a prefiltered signal that is used as the desired output for the second stage which constructs a sparse linear-in-the-parameter classifier. The prefiltering stage is a two-level process aimed at maximizing a model's generalization capability, in which a new elastic-net model identification algorithm using singular value decomposition is employed at the lower level, and then, two regularization parameters are optimized using a particle-swarm-optimization algorithm at the upper level by minimizing the leave-one-out (LOO) misclassification rate. It is shown that the LOO misclassification rate based on the resultant prefiltered signal can be analytically computed without splitting the data set, and the associated computational cost is minimal due to orthogonality. The second stage of sparse classifier construction is based on orthogonal forward regression with the D-optimality algorithm. Extensive simulations of this approach for noisy data sets illustrate the competitiveness of this approach to classification of noisy data problems.

Modelling human visual navigation using multi-view scene reconstruction

It is often assumed that humans generate a 3D reconstruction of the environment, either in egocentric or world-based coordinates, but the steps involved are unknown. Here, we propose two reconstruction-based models, evaluated using data from two tasks in immersive virtual reality. We model the observer’s prediction of landmark location based on standard photogrammetric methods and then combine location predictions to compute likelihood maps of navigation behaviour. In one model, each scene point is treated independently in the reconstruction; in the other, the pertinent variable is the spatial relationship between pairs of points. Participants viewed a simple environment from one location, were transported (virtually) to another part of the scene and were asked to navigate back. Error distributions varied substantially with changes in scene layout; we compared these directly with the likelihood maps to quantify the success of the models. We also measured error distributions when participants manipulated the location of a landmark to match the preceding interval, providing a direct test of the landmark-location stage of the navigation models. Models such as this, which start with scenes and end with a probabilistic prediction of behaviour, are likely to be increasingly useful for understanding 3D vision.

Methods of sensory augmentation through electro-tactile stimulation of the tongue

This paper details an investigation into sensory substitution by means of direct electrical stimulation of the tongue for the purpose of information input to the human brain. In particular, a device has been constructed and a series of trials have been performed in order to demonstrate the efficacy and performance of an electro-tactile array mounted onto the tongue surface for the purpose of sensory augmentation. Tests have shown that by using a low resolution array a computer-human feedback loop can be successfully implemented by humans in order to complete tasks such as object tracking, surface shape identification and shape recognition with no training or prior experience with the device. Comparisons of this technique have been made with visual alternatives and these show that the tongue based tactile array can match such methods in convenience and accuracy in performing simple tasks.

User-friendly free-text keystroke dynamics authentication for practical applications

This paper introduces a novel approach for free-text keystroke dynamics authentication which incorporates the use of the keyboard’s key-layout. The method extracts timing features from specific key-pairs. The Euclidean distance is then utilized to find the level of similarity between a user’s profile data and his/her test data. The results obtained from this method are reasonable for free-text authentication while maintaining the maximum level of user relaxation. Moreover, it has been proven in this study that flight time yields better authentication results when compared with dwell time. In particular, the results were obtained with only one training sample for the purpose of practicality and ease of real life application.

Nonlinear identification using orthogonal forward regression with nested optimal regularization

An efficient data based-modeling algorithm for nonlinear system identification is introduced for radial basis function (RBF) neural networks with the aim of maximizing generalization capability based on the concept of leave-one-out (LOO) cross validation. Each of the RBF kernels has its own kernel width parameter and the basic idea is to optimize the multiple pairs of regularization parameters and kernel widths, each of which is associated with a kernel, one at a time within the orthogonal forward regression (OFR) procedure. Thus, each OFR step consists of one model term selection based on the LOO mean square error (LOOMSE), followed by the optimization of the associated kernel width and regularization parameter, also based on the LOOMSE. Since like our previous state-of-the-art local regularization assisted orthogonal least squares (LROLS) algorithm, the same LOOMSE is adopted for model selection, our proposed new OFR algorithm is also capable of producing a very sparse RBF model with excellent generalization performance. Unlike our previous LROLS algorithm which requires an additional iterative loop to optimize the regularization parameters as well as an additional procedure to optimize the kernel width, the proposed new OFR algorithm optimizes both the kernel widths and regularization parameters within the single OFR procedure, and consequently the required computational complexity is dramatically reduced. Nonlinear system identification examples are included to demonstrate the effectiveness of this new approach in comparison to the well-known approaches of support vector machine and least absolute shrinkage and selection operator as well as the LROLS algorithm.

A fast adaptive tunable RBF network for nonstationary systems

This paper describes a novel on-line learning approach for radial basis function (RBF) neural network. Based on an RBF network with individually tunable nodes and a fixed small model size, the weight vector is adjusted using the multi-innovation recursive least square algorithm on-line. When the residual error of the RBF network becomes large despite of the weight adaptation, an insignificant node with little contribution to the overall system is replaced by a new node. Structural parameters of the new node are optimized by proposed fast algorithms in order to significantly improve the modeling performance. The proposed scheme describes a novel, flexible, and fast way for on-line system identification problems. Simulation results show that the proposed approach can significantly outperform existing ones for nonstationary systems in particular.

Medical image retrieval based on complexity analysis

Texture is one of the most important visual attributes used in image analysis. It is used in many content-based image retrieval systems, where it allows the identification of a larger number of images from distinct origins. This paper presents a novel approach for image analysis and retrieval based on complexity analysis. The approach consists of a texture segmentation step, performed by complexity analysis through BoxCounting fractal dimension, followed by the estimation of complexity of each computed region by multiscale fractal dimension. Experiments have been performed with MRI database in both pattern recognition and image retrieval contexts. Results show the accuracy of the method and also indicate how the performance changes as the texture segmentation process is altered.

Expert system to calculate the cofficient of friction : an approach to enhance traffic safety

Friction plays a key role in causing slipperiness as a low coefficient of friction on the road may result in slippery and hazardous conditions. Analyzing the strong relation between friction and accident risk on winter roads is a difficult task. Many weather forecasting organizations use a variety of standard and bespoke methods to predict the coefficient of friction on roads. This article proposes an approach to predict the extent of slipperiness by building and testing an expert system. It estimates the coefficient of friction on winter roads in the province of Dalarna, Sweden using the prevailing weather conditions as a basis. Weather data from the road weather information system, Sweden (RWIS) was used. The focus of the project was to use the expert system as a part of a major project in VITSA, within the domain of intelligent transport systems

Color detection and segmentation for road and traffic signs

This paper aims to present three new methods for color detection and segmentation of road signs. The images are taken by a digital camera mounted in a car. The RGB images are converted into IHLS color space, and new methods are applied to extract the colors of the road signs under consideration. The methods are tested on hundreds of outdoor images in different light conditions, and they show high robustness. This project is part of the research taking place in Dalarna University / Sweden in the field of the ITS.

An web content based data mining for car consumption in China

This paper introduces an incremental FP-Growth approach for Web content based data mining and its application in solving a real world problem The problem is solved in the following ways. Firstly, we obtain the semi-structured data from the Web pages of Chinese car market and structure them and save them in local database. Secondly, we use an incremental FP-Growth algorithm for mining association rules to discover Chinese consumers' car consumption preference. To find more general regularities, an attribute-oriented induction method is also utilized to find customer's consumption preference among a range of car categories. Experimental results have revealed some interesting consumption preferences that are useful for the decision makers to make the policy to encourage and guide car consumption. Although the current data we used may not be the best representative of the actual market in practice, it is still good enough for the decision making purpose in terms of reflecting the real situation of car consumption preference under the two assumptions in the context.

Stereo correspondence estimation using multiwavelets scale-space representation-based multiresolution analysis

A multiresolution technique based on multiwavelets scale-space representation for stereo correspondence estimation is presented. The technique uses the well-known coarse-to-fine strategy, involving the calculation of stereo correspondences at the coarsest resolution level with consequent refinement up to the finest level. Vector coefficients of the multiwavelets transform modulus are used as corresponding features, where modulus maxima defines the shift invariant high-level features (multiscale edges) with phase pointing to the normal of the feature surface. The technique addresses the estimation of optimal corresponding points and the corresponding 2D disparity maps. Illuminative variation that can exist between the perspective views of the same scene is controlled using scale normalization at each decomposition level by dividing the details space coefficients with approximation space. The problems of ambiguity, explicitly, and occlusion, implicitly, are addressed by using a geometric topological refinement procedure. Geometric refinement is based on a symbolic tagging procedure introduced to keep only the most consistent matches in consideration. Symbolic tagging is performed based on probability of occurrence and multiple thresholds. The whole procedure is constrained by the uniqueness and continuity of the corresponding stereo features. The comparative performance of the proposed algorithm with eight famous existing algorithms, presented in the literature, is shown to validate the claims of promising performance of the proposed algorithm.

The sexualised body : the cyborg

The word cyborg was created through an amalgamation of the terms cybernetics and organism. The expression was coined during a 1960s NASA conference to describe the internal technological modification of the body. This new term resonated within popular culture and was quickly embraced by science fiction, where the cyborg became a popular character. The image of the cyborg is often hyper-physical and hyper-sexual. The super sexualised woman who can shoot bullets from her breasts is a popular comic book cyborg representation. The Replicants from Riddley Scott’s Blade Runner are other examples of hyper human, super sexualised cyborgs. Increasingly, the future of our physicality is one that is intertwined with technology. Although the image of the cyborg is often exaggerated, it holds within it real future possibilities. This paper argues that cultural anxieties, in relation to the impact of technology on our bodies, can be identified through the cyborg image.

The imagined body – the cyborg

During a NASA conference in the 1960s, the term cyborg was created through an amalgamation of the terms ‘cybernetics’ and ‘organism’. Coined by concert pianist Manfred Clynes and research colleague Nathan Kline to describe the internal technological modification of the body. This new term resonated within popular culture and was quickly embraced by science fiction where the cyborg became a popular character. The image of the cyborg is often hyper-physical and hyper-sexual. The super sexualised woman who can shoot bullets from her breasts is a popular comic book cyborg representation. The Replicants from Riddley Scott’s Blade Runner and Arnold Schwaznegger’s role the Terminator are other examples where the technological and physical combination produces a terrifying hyper humans. Increasingly the future of our physicality is one that is intertwined with technology. Although the image of the cyborg is often an exaggerated character it holds within it real future possibilities. Consider the portable arm wrist communicator from the scifi classic Star Trek. The watch phone communication device was once an object of the imagination but now a reality in the personal mobile phone. This paper argues that through imagined imagery of the cyborg, future possibilities can be seen.

One example of the image of the cyborg representing possible human futures is the performance work Cyborpyg. Cyborpyg is a 40-minute contemporary dance work that integrates three dimensional (3D) animation and video media within the performance. Projected 3D animated prosthetic limbs appear to extend the dancers from within. These digital limbs integrate with dancer’s bodies transforming them into cyborgs. The animations are an extreme form of aesthetic modification reflecting the possible consequences of the integration of technology within the body. Cyborpyg also explores both utopic and dystipic themes within the cyborg paradigm. The dancing hybrid bodies perform magical feats not possible with an unmodified body. Feet twist into talons and flippers, eyes extend from the head, arms transform into robotic attachments. The dancer’s bodies also appear trapped in an unrelenting environment with prosthesis that appear to torture and inflict serious harm. This paper explores the idea that the imagined image of the cyborg reflects future possibilities for the human physicality.