Rapid Analysis Model of Apple Sugar Degree Using Portable Near-Infrared Spectrometer(应用便携式近红外光谱仪研究苹果糖度的快速分析模型) [PDF]
Shipin kexue jishu xuebao, 2018 In order to realize the fast lossless field detection of apple sugar by portable near infrared spectrometer, the K-S algorithm was used to divide the sample set.
LEI Ying(雷鹰) +2 more
doaj +1 more source
Research of Topic Detection Method for Food Safety Surveillance(面向食品安全监理话题检测方法的研究) [PDF]
Shipin kexue jishu xuebao, 2016 Food safety problem has been a hot topic of national concern, which related to many areas of society. In order to know hot issues that relate to food safety in timely, food safety hot topics and other hot topics of the similarities and differences in ...
FENG Zhenhai(冯振海) +1 more
doaj +1 more source
Study on Food Safety Surveillance and Risk Assessment Based on Cloud Model(基于云模型的食品安全监理风险评估研究) [PDF]
Shipin kexue jishu xuebao, 2016 In order to predict the problems of food safety in time and reduce the food safety risks, this study analyzed and established the risk factors system of food safety in three layers.
PANG Hongmei(庞红美) +1 more
doaj +1 more source
智能科学与技术学报, 2021 近年来，基于自注意力机制的神经网络在计算机视觉任务中得到广泛的应用。随着智能交通系统的广泛应用，面对复杂多变的交通场景，车牌识别任务的难度不断提高，准确识别的需求更加迫切。因此提出一个基于自注意力的免矫正的车牌识别方法T-LPR。首先对图像进行切片和序列化，并使用3D卷积对切片序列进行特征提取，从而得到图像的嵌入向量序列。然后将嵌入向量序列输入基于Transformer Encoder的编码器中，学习各个嵌入向量之间的关系并输出最终的编码结果。最后使用分类器进行分类。在多个公共数据集上的实验结果表明 ...
曾淦雄, 柯逍
doaj
Application of Improved Association Rules on Food Safety Early Warning(改进的关联规则在食品安全预警上的应用) [PDF]
Shipin kexue jishu xuebao, 2017 In order to the effective application of the massive detection data in food safety early warning, this paper analyzed the characteristics of the food detection data, and the insufficient of traditional Apriori algorithm on food detection data, then ...
XIAO Kejing(肖克晶) +3 more
doaj +1 more source
Data Mining on Food Safety Sampling Inspection Data Based on BP Neural Network(基于BP神经网络的食品安全抽检数据挖掘) [PDF]
Shipin kexue jishu xuebao, 2016 Data mining technology has great application values and potential in the food safety field. The feasibility and advantage of the BP neural network algorithm were explained.
WANG Xingyun(王星云) +3 more
doaj +1 more source
Study on Food Safety Surveillance System in China(我国食品安全监理体系研究) [PDF]
Shipin kexue jishu xuebao, 2014 Food safety issues are related to the national life, which affect many areas and are global. Based on the problems of China's food safety surveillance system, several countermeasures were applied to improve the institutional system, such as setting up ...
ZHANG Yun-xiao(张云霄) +1 more
doaj +1 more source
Research on Classifying Chicken Based on Near-infrared Spectroscopy(近红外光谱分析技术在鸡肉分类检测中的应用) [PDF]
Shipin kexue jishu xuebao, 2014 One quick and accurate method of distinguishing broiler chicken and native chicken was studied due to the disorder of chicken market. The discriminated model of chicken classification was built based on near infrared (NIR) spectroscopy technology and ...
XIANG Lingzi(向灵孜) +1 more
doaj +1 more source
Study on Real-time Analysis in Food Safety Surveillance Based on Cloud Service(基于云服务的食品安全监理实时化研究) [PDF]
Shipin kexue jishu xuebao, 2015 In order to detect the problems of food safety in time and reduce the incidence, a food safety supervision of real-time analysis and prediction model based on the storm cloud platform and the Elman neural network optimizing by the bat algorithm was ...
HAN Fuxia(韩福霞) +1 more
doaj +1 more source
智能科学与技术学报, 2021 植株叶片检测是植株科学培育和精准农业过程中重要的环节之一。传统植株叶片检测的做法对操作人员的专业知识提出了较高要求，且人工成本高、耗时周期长。基于此，提出基于多尺度卷积神经网络特征融合（MCFF）的植株叶片检测技术。从深度学习技术辅助植株培育的需求出发，基于多尺度卷积神经网络特征融合，针对莲座模式植物、拟南芥和烟草3种不同类型、不同分辨率的植株进行叶片计数检测。经过与其他主流算法的比较，发现MCFF具备较高的检测精确度，平均精度均值（mAP）为0.662，实现了高度竞争的性能（AP=0.946 ...
李颖 +4 more
doaj