CAREER: Computational Models for Sensor-Based Machine Olfaction

这是为期4年的持续奖的第一年资助。PI将专注于开发基于传感器的机器嗅觉(SBMO)的生物学框架，重点是计算、分析和仪器。具体目标是：(1)开发基于生物嗅觉系统的神经形态模型的计算体系结构，以提高SBMO的信号处理和认知能力；(2)通过与嗅觉“黄金标准”-人体面板感觉分析的比较研究，验证计算体系结构的感知可信；(3)开发先进的传感器询问技术，以提高商用电导型气体传感器阵列的选择性、灵敏度和稳健性。这一结果将有助于弥合多元化学感知和人类嗅觉之间的差距，从而为新一代SBMO系统奠定基础。由于信号处理和传感器仪器的进步，分析能力的提高将扩大SBM0的应用范围。

This is the first year of funding of a 4-year continuing award. The PI will focus on the development of a biologically plausible framework for sensor-based machine olfaction (SBMO), with an emphasis on computation, analysis and instrumentation. The specific objectives are: (1) To develop a computational architecture based on neuro-morphic models of the biological olfactory system in order to improve the signal-processing and cognitive capabilities of SBMO; (2) To validate the perceptual plausibility ofthe computational architecture through comparative studies with the "gold standard" for olfactory perception - human-panel sensory analysis; (3) To develop advanced sensor interrogation techniques in order to improve selectivity, sensitivity and robustness of commercial conductivity-based gas sensor arrays. The results will lay the foundations fora new generation of SBMO systems by helping bridge the gap between multivariate chemical sensing and human olfactory perception. Improved analytical capabilities, as a result of advances in both signal processing and sensor instrumentation, will broaden the range of applications for SBM0.