Accurate and timely classification of diseases during strawberry planting can help growers deal with them in timely manner, thereby reducing losses. However, the classification of strawberry diseases in real planting ...Accurate and timely classification of diseases during strawberry planting can help growers deal with them in timely manner, thereby reducing losses. However, the classification of strawberry diseases in real planting environments is facing severe challenges, including complex planting environments, multiple disease categories with small differences, and so on. Although recent mobile vision technology based deep learning has achieved some success in overcoming the above problems, a key problem is how to construct a non-destructive, fast and convenient method to improve the efficiency of strawberry disease identification for the multi-region, multi-space and multi-time classification requirements. We develop and evaluate a rapid, low-cost system for classifying diseases in strawberry cultivation. This involves designing an easy-to-use cloudbased strawberry disease identification system, combined with our novel self-supervised multi-network fusion classification model, which consists of a Location network, a Feedback network and a Classification network to identify the categories of common strawberry diseases. With the help of a novel self-supervision mechanism, the model can effectively identify diseased regions of strawberry disease images without the need for annotations such as bounding boxes. Using accuracy, precision, recall and F1 to evaluate the classification effect, the results of the test set are 92.48, 90.68, 86.32 and 88.45%, respectively. Compared with popular Convolutional Neural Networks(CNN) and five other methods, our network achieves better disease classification effect. Currently, the client(mini program) has been released on the We Chat platform. The mini program has perfect classification effect in the actual test, which verifies the feasibility and effectiveness of the system, and can provide a reference for the intelligent research and application of strawberry disease identification.展开更多
The influence of dry etching damage on the internal quantum efficiency of InGaN/GaN nanorod multiple quantum wells (MQWs) is studied.The samples were etched by inductively coupled plasma (ICP) etching via a selfassemb...The influence of dry etching damage on the internal quantum efficiency of InGaN/GaN nanorod multiple quantum wells (MQWs) is studied.The samples were etched by inductively coupled plasma (ICP) etching via a selfassembled nickel nanomask,and examined by room-temperature photoluminescence measurement.The key parameters in the etching process are rf power and ICP power.The internal quantum efficiency of nanorod MQWs shows a 5.6 times decrease substantially with the rf power increasing from 3W to 100W.However,it is slightly influenced by the ICP power,which shows 30% variation over a wide ICP power range between 30W and 600W.Under the optimized etching condition,the internal quantum efficiency of nanorod MQWs can be 40% that of the as-grown MQW sample,and the external quantum efficiency of nanorod MQWs can be about 4 times that of the as-grown one.展开更多
Roughened surfaces of light-emitting diodes(LEDs)provide substantial improvement in light extraction efficiency.By preparing the self-assemble nanoporous Ni template through rapid annealing of a thin Ni film,followed ...Roughened surfaces of light-emitting diodes(LEDs)provide substantial improvement in light extraction efficiency.By preparing the self-assemble nanoporous Ni template through rapid annealing of a thin Ni film,followed by a low damage dry etching process,a p-side-up LED with a roughened surface has been fabricated.Compared to a conventional LED with plane surface,the light output of LEDs with nanoporous p-GaN surface increases up to 71%and 36%at applied currents of 1 mA and 20 mA,respectively.Meanwhile,the electrical characteristics are not degraded obviously after surface roughening.展开更多
基金supported by the Science and Technology Innovation Project of Chinese Academy of Agricultural Sciences(CAAS-ASTIP-2016-AII)。
文摘Accurate and timely classification of diseases during strawberry planting can help growers deal with them in timely manner, thereby reducing losses. However, the classification of strawberry diseases in real planting environments is facing severe challenges, including complex planting environments, multiple disease categories with small differences, and so on. Although recent mobile vision technology based deep learning has achieved some success in overcoming the above problems, a key problem is how to construct a non-destructive, fast and convenient method to improve the efficiency of strawberry disease identification for the multi-region, multi-space and multi-time classification requirements. We develop and evaluate a rapid, low-cost system for classifying diseases in strawberry cultivation. This involves designing an easy-to-use cloudbased strawberry disease identification system, combined with our novel self-supervised multi-network fusion classification model, which consists of a Location network, a Feedback network and a Classification network to identify the categories of common strawberry diseases. With the help of a novel self-supervision mechanism, the model can effectively identify diseased regions of strawberry disease images without the need for annotations such as bounding boxes. Using accuracy, precision, recall and F1 to evaluate the classification effect, the results of the test set are 92.48, 90.68, 86.32 and 88.45%, respectively. Compared with popular Convolutional Neural Networks(CNN) and five other methods, our network achieves better disease classification effect. Currently, the client(mini program) has been released on the We Chat platform. The mini program has perfect classification effect in the actual test, which verifies the feasibility and effectiveness of the system, and can provide a reference for the intelligent research and application of strawberry disease identification.
基金Supported by the National Basic Research Program of China under Grant No 2011CB301900the National Natural Science Foundation of China(61176063,60990311,60820106003,60906025,60936004)+1 种基金The Natural Science Foundation of Jiangsu Province(BK2008019,BK2010385,BK2009255,BK2010178)the Research Funds from NJU-Yangzhou Institute of Optoelectronics.
文摘The influence of dry etching damage on the internal quantum efficiency of InGaN/GaN nanorod multiple quantum wells (MQWs) is studied.The samples were etched by inductively coupled plasma (ICP) etching via a selfassembled nickel nanomask,and examined by room-temperature photoluminescence measurement.The key parameters in the etching process are rf power and ICP power.The internal quantum efficiency of nanorod MQWs shows a 5.6 times decrease substantially with the rf power increasing from 3W to 100W.However,it is slightly influenced by the ICP power,which shows 30% variation over a wide ICP power range between 30W and 600W.Under the optimized etching condition,the internal quantum efficiency of nanorod MQWs can be 40% that of the as-grown MQW sample,and the external quantum efficiency of nanorod MQWs can be about 4 times that of the as-grown one.
基金Supported by the National Basic Research Program of China(2011CB301900)the National Natural Science Foundation of China(61176063,60990311,60820106003,60906025,60936004)+1 种基金The Nature Science Foundation of Jiangsu Province(BK2008019,BK2010385,BK2009255,BK2010178)the Research Funds from NJU-Yangzhou Institute of Optoelectronics.
文摘Roughened surfaces of light-emitting diodes(LEDs)provide substantial improvement in light extraction efficiency.By preparing the self-assemble nanoporous Ni template through rapid annealing of a thin Ni film,followed by a low damage dry etching process,a p-side-up LED with a roughened surface has been fabricated.Compared to a conventional LED with plane surface,the light output of LEDs with nanoporous p-GaN surface increases up to 71%and 36%at applied currents of 1 mA and 20 mA,respectively.Meanwhile,the electrical characteristics are not degraded obviously after surface roughening.
