Robot teleoperation systems have been limited in their utility due to the need for operator motion, lack of portability and limitation to singular input modalities. In this article, the design and construction of a dual-mode human-machine interface system for robot teleoperation addressing all these issues is presented. The interface is capable of directing robotic devices in response to tongue movement and/or speech without insertion of any device in the vicinity of the oral cavity. The interface is centered on the unique properties of the human ear as an acoustic output device. Specifically, we present: (1) an analysis of the sensitivity of human ear canals as acoustic output device1 (2) the design of a new sensor for monitoring airflow in the aural canal1 (3) pattern recognition procedures for recognition of both speech and tongue movement by monitoring aural flow across several human test subjects1 and (4) a conceptual design and simulation of the machine interface system. We believe this work will lay the foundation for a new generation of human machine interface systems for all manner of robotic applications.

A hierarchical approach to the classification of digital modulation types in multipath environments Approved for public release; distribution is unlimited.The report was prepared by: Approved for public release; distribution is unlimited A ABSTRACT (Maximum 200 words)This study presents a hierarchical classification approach to the classification of digital modulation schemes of types [2,4,8]-PSK, [2,4,64,256]-QAM in low SNR levels and multi path propagation channel conditions. A hierarchical tree-based classification approach is selected as it leads to a relatively simple overall scheme with few parameters needed to differentiate between the various modulation types. Back-propagation neural network units are adopted at each tree node because they offer the flexibility needed to cope with varying propagation environments, as is the case in real-world communications. The selection of robust and well-defined higher-order statistics-based class features is considered and a small number of cumulants and moments chosen to differentiate between all various types of modulation types, except for specific M-QAM types. Simulations show that M-QAM types may be so affected by multipath and fading that higher-order statistic parameters become of very limited use. While being part of the hierarchical procedure, the identification of specific M-QAM types is conducted via equalization algorithms. Extensive simulations show overall classification performances to be strongly affected by the amount of multipath distortion and noise in the transmission channels. Results also show a much higher sensitivity of high-order M-QAM types to fading and multi path propagation distortions than other modulation types.

No abstract

This study investigates the application of orthogonal, non-orthogonal Wavelet-based procedures, and AR modeling as feature extraction techniques to classify several classes of underwater signals consisting of sperm whale, killer whale, gray whale, pilot whale, humpback whale, and underwater earthquake data. A two-hidden-layers backpropagation neural network is used for the classification procedure. Performances obtained using the two Wavelet-based schemes are compared with those obtained using reduced-rank AR modeling tools.Results show that the non-orthogonal undecimated A-trous implementation with multiple voices leads to the highest classification rate of 96.7%.

This study investigates the application of orthonormal wavelet analysis to the removal of noise from acoustic transients. Results show that Wavelet based denoising schemes perform better than classical Wiener fdtering.