Video sensors and agricultural IoT(internet of things) have been widely used in the informationalized orchards.In order to realize intelligent-unattended early warning for disease-pest,this paper presents convolutiona...Video sensors and agricultural IoT(internet of things) have been widely used in the informationalized orchards.In order to realize intelligent-unattended early warning for disease-pest,this paper presents convolutional neural network(CNN) early warning for apple skin lesion image,which is real-time acquired by infrared video sensor.More specifically,as to skin lesion image,a suite of processing methods is devised to simulate the disturbance of variable orientation and light condition which occurs in orchards.It designs a method to recognize apple pathologic images based on CNN,and formulates a self-adaptive momentum rule to update CNN parameters.For example,a series of experiments are carried out on the recognition of fruit lesion image of apple trees for early warning.The results demonstrate that compared with the shallow learning algorithms and other involved,wellknown deep learning methods,the recognition accuracy of the proposal is up to 96.08%,with a fairly quick convergence,and it also presents satisfying smoothness and stableness after convergence.In addition,statistics on different benchmark datasets prove that it is fairly effective to other image patterns concerned.展开更多
Electronic skins and flexible pressure sensors are important devices for advanced healthcare and intelligent robotics.Sensitivity is a key parameter of flexible pressure sensors.Whereas introducing surface microstruct...Electronic skins and flexible pressure sensors are important devices for advanced healthcare and intelligent robotics.Sensitivity is a key parameter of flexible pressure sensors.Whereas introducing surface microstructures in a capacitive-type sensor can significantly improve its sensitivity,the signal becomes nonlinear and the pressure response range gets much narrower,significantly limiting the applications of flexible pressure sensors.Here,we designed a pressure sensor that utilizes a nanoscale iontronic interface of an ionic gel layer and a micropillared electrode,for highly linear capacitance-to-pressure response and high sensitivity over a wide pressure range.The micropillars undergo three stages of deformation upon loading:initial contact(0-6 k Pa)and structure buckling(6-12 k Pa)that exhibit a low and nonlinear response,as well as a post-buckling stage that has a high signal linearity with high sensitivity(33.16 k Pa-1)over a broad pressure range of 12-176 k Pa.The high linearity lies in the subtle balance between the structure compression and mechanical matching of the two materials at the gel-electrode interface.Our sensor has been applied in pulse detection,plantar pressure mapping,and grasp task of an artificial limb.This work provides a physical insight in achieving linear response through the design of appropriate microstructures and selection of materials with suitable modulus in flexible pressure sensors,which are potentially useful in intelligent robots and health monitoring.展开更多
基金Supported by the National Natural Science Foundation of China(No.61271257)Beijing National Science Foundation(No.4151001)Hunan Education Department Project(No.16A131)
文摘Video sensors and agricultural IoT(internet of things) have been widely used in the informationalized orchards.In order to realize intelligent-unattended early warning for disease-pest,this paper presents convolutional neural network(CNN) early warning for apple skin lesion image,which is real-time acquired by infrared video sensor.More specifically,as to skin lesion image,a suite of processing methods is devised to simulate the disturbance of variable orientation and light condition which occurs in orchards.It designs a method to recognize apple pathologic images based on CNN,and formulates a self-adaptive momentum rule to update CNN parameters.For example,a series of experiments are carried out on the recognition of fruit lesion image of apple trees for early warning.The results demonstrate that compared with the shallow learning algorithms and other involved,wellknown deep learning methods,the recognition accuracy of the proposal is up to 96.08%,with a fairly quick convergence,and it also presents satisfying smoothness and stableness after convergence.In addition,statistics on different benchmark datasets prove that it is fairly effective to other image patterns concerned.
基金supported by the Science Technology and Innovation Committee of Shenzhen Municipality(JCYJ20170817111714314)the National Natural Science Foundation of China(52073138 and 51771089)+2 种基金the Guangdong Innovative and Entrepreneurial Research Team Program(2016ZT06G587)the Shenzhen Sci-Tech Fund(KYTDPT20181011104007)the Tencent Robotics X Lab Rhino-Bird Focused Research Program(JR201984)。
文摘Electronic skins and flexible pressure sensors are important devices for advanced healthcare and intelligent robotics.Sensitivity is a key parameter of flexible pressure sensors.Whereas introducing surface microstructures in a capacitive-type sensor can significantly improve its sensitivity,the signal becomes nonlinear and the pressure response range gets much narrower,significantly limiting the applications of flexible pressure sensors.Here,we designed a pressure sensor that utilizes a nanoscale iontronic interface of an ionic gel layer and a micropillared electrode,for highly linear capacitance-to-pressure response and high sensitivity over a wide pressure range.The micropillars undergo three stages of deformation upon loading:initial contact(0-6 k Pa)and structure buckling(6-12 k Pa)that exhibit a low and nonlinear response,as well as a post-buckling stage that has a high signal linearity with high sensitivity(33.16 k Pa-1)over a broad pressure range of 12-176 k Pa.The high linearity lies in the subtle balance between the structure compression and mechanical matching of the two materials at the gel-electrode interface.Our sensor has been applied in pulse detection,plantar pressure mapping,and grasp task of an artificial limb.This work provides a physical insight in achieving linear response through the design of appropriate microstructures and selection of materials with suitable modulus in flexible pressure sensors,which are potentially useful in intelligent robots and health monitoring.
