Deep-Stacking Network Approach by Multisource Data Mining for Hazardous Risk Identification in IoT-Based Intelligent Food Management Systems

Table 1

Attributive categories of the grain database.

Attributive name	Value
Province	Anhui | Beijing | Chongqing | Fujian | Guangdong | Guangxi | Guizhou | Hainan | Hebei | Heilongjiang | Henan | Hubei | Hunan | Jiangsu | Jiangxi | Jilin | Liaoning | Qinghai | Shaanxi | Shandong | Shanghai | Shanxi | Sichuan | Tianjin | Yunnan | Zhejiang
Grain type	Rice | wheat | corn | roughage| rice-processed products | wheat-processed products | else
Link	Production | circulation | sale
Production area	City | village
Sampling sites	Planting bases | warehouse | workshop| transportation facility | farmer markets | supermarkets |restaurants | hotel| laboratories|
Hazard type	AFB1| OTA| ZON| DON| T2| fumonisin| Al | As| Cd| Cr| Hg| Pb | COLI | Salmonella| MRSA| tebuconazole| benzopyrene (BaP) | malathion|
Risk item	Heavy metals| microorganisms| mycotoxins| pesticide residues|
Content and unit	mg/kg | μg/kg | CFU/g | MPN/g
Temperature	−10°C–40°C
Humidity	0%–100%
Light exposure	0 Lux–1500 Lux
Oxygen	17%–25%
Carbon dioxide	0 ppm–1200 ppm
Weight	0 kg–100 kg
Expiration date	3–24 months
Production data	2015.01–2019.07
Risk level	I | II | III | IV | V | VI | VII | VIII