Food Recognition via Monitoring Power Leakage from a Microwave Oven
Food Recognition via Monitoring Power Leakage from a Microwave Oven
复制标题
通过监测微波炉漏电进行食物识别
DOI：
--
复制
发表时间：
2015
影响因子：
--
通讯作者：
T. Asami
中科院分区：
文献类型：
--
作者：
Wei Wei;Akihiro Nakamata;Y. Kawahara;T. Asami
在本文中，我们演示了一种通过监测家用微波炉的电源泄漏来识别食物的方法。通用软件无线电外设（USRP）作为一种低成本的频谱分析仪，用于测量微波炉泄漏作为接收信号强度指示（RSSI）。我们的目标是识别18类通常在微波炉中烹饪的食物。通过对180个包含加热时间差信息的特征进行分析，平均识别准确率达到82.3%。利用138个特征剔除加热时间差异信息，平均识别准确率为56.2%。研究了不同条件下的识别精度，如使用不同的微波炉，不同的微波炉与USRP之间的距离以及不同的数据降采样率。最后，通过一个食品识别应用来验证我们的方法。
: In this paper, we demonstrate a food recognition method by monitoring power leakage from a domestic microwave oven. Universal Software Radio Peripheral (USRP) is applied as a low-cost spectrum analyzer to measure the microwave oven leakage as received signal strength indication (RSSI). We aim to recognize 18 categories of food that are commonly cooked in a microwave oven. By analyzing 180 features that contain the information of heating-time di ff erence, we attain an average recognition accuracy of 82.3%. Using 138 features excluding the heating-time di ff erence information, the average recognition accuracy is 56.2%. The recognition accuracy under di ff erent conditions is also investigated, for instance, utilizing di ff erent microwave ovens, di ff erent distances between the microwave oven and the USRP as well as di ff erent data down-sampling rates. Finally, a food recognition application is implemented to demonstrate our method.