Modified Kanerva model. Results for real time word recognition

This paper describes results obtained using the modified Kanerva model to perform word recognition in continuous speech after being trained on the multi-speaker Alvey 'Hotel' speech corpus. Theoretical discoveries have recently enabled us to increase the speed of execution of part of the model by two orders of magnitude over that previously reported by Prager & Fallside. The memory required for the operation of the model has been similarly reduced. The recognition accuracy reaches 95% without syntactic constraints when tested on different data from seven trained speakers. Real time simulation of a model with 9,734 active units is now possible in both training and recognition modes using the Alvey PARSIFAL transputer array. The modified Kanerva model is a static network consisting of a fixed nonlinear mapping (location matching) followed by a single layer of conventional adaptive links. A section of preprocessed speech is transformed by the non-linear mapping to a high dimensional representation. From this intermediate representation a simple linear mapping is able to perform complex pattern discrimination to form the output, indicating the nature of the speech features present in the input window.

Real time feature-based facial tracking using Lie algebras

We have developed a novel human facial tracking system that operates in real time at a video frame rate without needing any special hardware. The approach is based on the use of Lie algebra, and uses three-dimensional feature points on the targeted human face. It is assumed that the roughly estimated facial model (relative coordinates of the three-dimensional feature points) is known. First, the initial feature positions of the face are determined using a model fitting technique. Then, the tracking is operated by the following sequence: (1) capture the new video frame and render feature points to the image plane; (2) search for new positions of the feature points on the image plane; (3) get the Euclidean matrix from the moving vector and the three-dimensional information for the points; and (4) rotate and translate the feature points by using the Euclidean matrix, and render the new points on the image plane. The key algorithm of this tracker is to estimate the Euclidean matrix by using a least square technique based on Lie algebra. The resulting tracker performed very well on the task of tracking a human face.

Embodied energy as an environmental impact indicator for basement wall construction

Attempts were made to quantify the environmental impacts of the basement walls of two commercial buildings in London. Four different retaining wall options were designed based on steel and concrete systems for each of the sites. It was considered that excavation would take place with the aid of a one or two anchors system. Evaluation of embodied energy (EE) and CO2 emissions for each of the wall designs and anchoring systems were compared. Results show that there are notable differences in EE between different wall designs. Using the averaged set of Embodied Energy Intensity (EEI) values, the use of recycled steel over virgin steel would reduce the EE of the wall significantly. The difference in anchor designs is relatively insignificant, and therefore the practicality of the design for the specific site should be the deciding factor for anchor types. Generally, the scale of environmental impacts due to constructions is large compared to other aspects in life as demonstrated with the comparisons to car emissions and household energy consumption. Copyright ASCE 2008.