SBIR Phase I: Neural Algorithms for Multimodal Sensory Analysis

The broader impact/commercial potential of this project is to enable continuous sensing applications in a wide range of energy-constrained devices like smartphones, smartwatches, and other wearables. Without dramatic innovations in the development of ultralow power sensory processing, continuous sensing will remain a niche application limited to environments with a stable and plentiful power source. The technology described in this proposal will demonstrate the viability and potential widespread deployment of continuous sensing devices in mobile or remote environments with strict energy constraints. An important immediate market for the proposed technology with significant customer base is the smartphone and wearables market, where many new and emerging end user applications could leverage environmental sensing to trigger context-based and anticipatory actions. The proposed technology is broadly applicable to a number of other markets and domains, including medical, health, and safety monitoring of critical patient sensors, personal fitness devices, military applications, and environmental monitors. The ability to flexibly deploy continuous sensing for these and other applications has the potential to revolutionize these markets and create entirely new and unforeseen application domains. This Small Business Innovation Research (SBIR) Phase I project will develop a novel platform technology--inspired by the mammalian neural pathways, which process sensory information--to enable ?always listening? audio processing capability within energy-constrained devices such as smartphones, tablets, smart watches, and other sensor-enabled wearable devices. The core technology, which provides the sensor processing capability, will model many of the computational properties and capabilities of the biological neurons that humans use to analyze information from their various senses. This research will allow a broad range of devices to continuously monitor their microphones, using streaming audio input to interpret various user commands, infer the current context and needs of the user from background noise, and even identify dangerous and harmful situations heard by the device. The research will target deployment of these capabilities on low power microprocessors and microcontrollers, often referred to as sensor hubs, which are included in many modern smartphones, tablets, and wearables. Targeting deployment on the sensor hubs will enable ?always listening? devices without compromising the battery life of the device.