摘要:
The number of spectral bands obtained by hyperspectral sensors improves the ability to distinguish physical objects and materials. But it also brings new challenges to image classification and analysis. In this study, a novel deep learning-based hybrid model called CNN-CVWNN is presented for the hyperspectral images classification (HSIs). The model uses a convolutional neural network (CNN) to extract multilayer image representation and uses the complex valued wavelet neural network (CVWNN) to classify the image using extracted features. The process steps of the proposed method are briefly as follows. First of all, the CNN algorithm has been applied to hyperspectral images. After this stage, efficient features have been obtained. These extracted features were then converted into a complex-valued number format using a novel random based transformation method. Thus, a novel complex-valued attribute set has been obtained for the HSI classification. The obtained features have been presented as input to the CVWNN algorithm. The hybrid method replaces real valued neural network inside CNN with CVWNN to enhance robustness and generalization of CNN. The experiments have been carried out on three data sets consisted of three popular hyperspectral airborne images. The developed method increases classification accuracy compared to other classification approaches.
摘要:
In this study, we report the poly-L-lysine (PLL) coated extended large area p-Si/n-ZnO heterojunction based biosensing device to analyze the influence of functional behavior of primary cortical neuronal cells. Wherein, the proliferation of rat embryonic neurons and neural stem cells is highly influenced by the physicochemical and structural properties of the underlying substrate mimicking the extracellular microenvironment. We observed a significant increase in the impedance values while adhesion of the neuronal cells on the substrate;however, it further got significantly decreased with the progression of various cellular functions neurite outgrowth and network formation. Such neuronal processes might have increased the propagation of flow of current by reducing the resistivity of the PLL treated n-ZnO thin film sensing area. Additionally, through the Nyquist plot, we observed a noticeable decrease in the magnitude of impedance values of the fabricated device. Hence, we believe that the fabricated PLL coated extended large area p-Si/n-ZnO heterojunction biosensor can serve as a favourable device to monitor the influence of functional behavior of neuronal cells.
M. Valladares-Ayerbes M. Toledano Fonseca J. Vieitez de Prado E. Inga-Saavedra S. Gil B. Graña Suarez B. García-Paredes A. Salud F. Rivera Herrero M. Salgado Fernandez P. García-Alfonso R. López-López R. Ferreiro Monteagudo J. Sastre E. Diaz-Rubio E. Aranda
Hospital Virgen del Rocío IBIS Sevilla SpainIMIBIC Universidad de Córdoba CIBERONC Instituto de Salud Carlos III. Hospital Universitario Reina Sofía Córdoba Spain Córdoba SpainHospital Universitario Central de Asturias Oviedo SpainIMIBIC Universidad de Córdoba CIBERONC Instituto de Salud Carlos III. Hospital Universitario Reina Sofía Córdoba SpainHospital Universitario Regional y Virgen de la Victoria Malaga SpainComplejo Hospitalario Universitario A Coruña. Instituto Investigación Biomédica INIBIC A Coruña SpainHospital Clínico San Carlos. Instituto de Investigación Hospital Clínico San Carlos (IdISSC) University Complutense. CIBERONC Madrid SpainHospital de Lleida Arnau de Vilanova Lérida SpainHospital Marqués de Valdecilla. IDIVAL Santander SpainComplejo Hospitalario Universitario de Ourense Ourense SpainHospital Universitario Gregorio Marañón Madrid SpainUniversity Clinical Hospital and Health Research Institute (IDIS) CIBERONC. Santiago de Compostela University School of Medicine Santiago de Compostela SpainIRYCIS CIBERONC Hospital Universitario Ramón y Cajal Madrid SpainHospital Clínico San Carlos. Instituto de Investigación Hospital Clínico San Carlos (IdISSC) University Complutense CIBERONC Madrid Spain