Real-time climate monitoring using an AVHRR-based vegetation index

A normalized difference vegetation index (NDVI) has been produced and archived on a 1° latitude by 1° longitude grid between 55°S and 75°N. The many sources of data errors in the NDVI include cloud contamination, scan angle biases, changes in solar zenith angle, and sensor degradation. Week-to-week variability, primarily caused by cloud contamination and scan angle biases, can be minimized by temporally filtering the data. Orbital drift and sensor degradation introduces interannual variability into the dataset. These trends make the usefulness of a long-term climatology uncertain and limit the usefulness of the NDVI. Elimination of these problems should produce an index that can be used for climate monitoring.

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.