2018/09/27 by Hidetomo Kataoka, Kataoka, Hidetomo, Takashi Ijiri +7
Agricultural and Biological Sciences · Engineering · #Smart Agriculture and AI #Food Supply Chain Traceability #Advanced Chemical Sensor Technologies
paper · pdf · doi:10.48550/arxiv.1809.10581
This paper introduces an acoustic probing technique to estimate the storage\ntime and firmness of fruits; we emit an acoustic signal to fruit from a small\nspeaker and capture the reflected signal with a tiny microphone. We collect\nreflected signals for fruits with various storage times and firmness\nconditions, using them to train regressors for estimation. To evaluate the\nfeasibility of our acoustic probing, we performed experiments; we prepared 162\ntomatoes and 153 mandarin oranges, collected their reflected signals using our\ndeveloped device and measured their firmness with a fruit firmness tester, for\na period of 35 days for tomatoes and 60 days for mandarin oranges. We performed\ncross validation by using this data set. The average estimation errors of\nstorage time and firmness for tomatoes were 0.89 days and 9.47 g/mm2. Those for\nmandarin oranges were 1.67 days and 15.67 g/mm2. The estimation of storage time\nwas sufficiently accurate for casual users to select fruits in their favorite\ncondition at home. In the experiments, we tested four different acoustic probes\nand found that sweep signals provide highly accurate estimation results.\n