This study proposed a novel object-based hybrid classification model named GMNN that combines Grasshopper Optimization Algorithm(GOA)and the multiple-class Neural network(MNN)for urban pattern detection in Hanoi,Vietn...This study proposed a novel object-based hybrid classification model named GMNN that combines Grasshopper Optimization Algorithm(GOA)and the multiple-class Neural network(MNN)for urban pattern detection in Hanoi,Vietnam.Four bands of SPOT 7 image and derivable NDVI,NDWI were used to generate image segments with associated attributes by PCI Geomatics software.These segments were classified into four urban surface types(namely water,impervious surface,vegetation and bare soil)by the proposed model.Alternatively,three training and validation datasets of different sizes were used to verify the robustness of this model.For all tests,the overall accuracies of the classification were approximately 87%,and the Area under Receiver Operating Characteristic curves for each land cover type was 0.97.Also,the performance of this model was examined by comparing several statistical indicators with common benchmark classifiers.The results showed that GMNN out-performed established methods in all comparable indicators.These results suggested that our hybrid model was successfully deployed in the study area and could be used as an alternative classification method for urban land cover studies.In a broader sense,classification methods will be enriched with the active and fast-growing contribution of metaheuristic algorithms.展开更多
The integration of nanomaterials such as carbon nanotubes (CNTs) into microsystems is highly desirable, in order to make use of the unique nanomaterial properties in real devices. However, the CNTtomicrosystem integ...The integration of nanomaterials such as carbon nanotubes (CNTs) into microsystems is highly desirable, in order to make use of the unique nanomaterial properties in real devices. However, the CNTtomicrosystem integration is challenging to implement in a manufacturable, cost effective industrial process. This paper presents our work towards a process for making complete, integrated CMOS / MEMS systems with integrated CNT. We demonstrate the feasibility of the process, using roomtemperature process ing, lowcost equipment and consumables, and electrical control with automation possibilities. CNTs are directly integrated at the desired positions in the Si microsystem, forming closed Si / CNT / Si circuits. We explore different designs with the aim to obtain uniform and welldefined CNT synthesis conditions, and show that simplified designs can perform comparably to more complex ones. The Si / CNT / Si circuits obtained can show rectifying (Schottky like) or nearohmic behavior. Gas sensing possibilities are demonstrated, indicating the possibility of monitoring aging/ fermenting of food. Functionalization of CNTs is demon strated, using thermal evaporation of Sn and Pd, opening for selective and sensitive sensors for various gases and ana lytes. Detailed microscopic characterization of the obtained CNTs are presented.展开更多
基金Vietnam National Foundation for Science and Technology Development(NAFOSTED)under Grant Number[105.99-2016.05].
文摘This study proposed a novel object-based hybrid classification model named GMNN that combines Grasshopper Optimization Algorithm(GOA)and the multiple-class Neural network(MNN)for urban pattern detection in Hanoi,Vietnam.Four bands of SPOT 7 image and derivable NDVI,NDWI were used to generate image segments with associated attributes by PCI Geomatics software.These segments were classified into four urban surface types(namely water,impervious surface,vegetation and bare soil)by the proposed model.Alternatively,three training and validation datasets of different sizes were used to verify the robustness of this model.For all tests,the overall accuracies of the classification were approximately 87%,and the Area under Receiver Operating Characteristic curves for each land cover type was 0.97.Also,the performance of this model was examined by comparing several statistical indicators with common benchmark classifiers.The results showed that GMNN out-performed established methods in all comparable indicators.These results suggested that our hybrid model was successfully deployed in the study area and could be used as an alternative classification method for urban land cover studies.In a broader sense,classification methods will be enriched with the active and fast-growing contribution of metaheuristic algorithms.
文摘The integration of nanomaterials such as carbon nanotubes (CNTs) into microsystems is highly desirable, in order to make use of the unique nanomaterial properties in real devices. However, the CNTtomicrosystem integration is challenging to implement in a manufacturable, cost effective industrial process. This paper presents our work towards a process for making complete, integrated CMOS / MEMS systems with integrated CNT. We demonstrate the feasibility of the process, using roomtemperature process ing, lowcost equipment and consumables, and electrical control with automation possibilities. CNTs are directly integrated at the desired positions in the Si microsystem, forming closed Si / CNT / Si circuits. We explore different designs with the aim to obtain uniform and welldefined CNT synthesis conditions, and show that simplified designs can perform comparably to more complex ones. The Si / CNT / Si circuits obtained can show rectifying (Schottky like) or nearohmic behavior. Gas sensing possibilities are demonstrated, indicating the possibility of monitoring aging/ fermenting of food. Functionalization of CNTs is demon strated, using thermal evaporation of Sn and Pd, opening for selective and sensitive sensors for various gases and ana lytes. Detailed microscopic characterization of the obtained CNTs are presented.