BACNN: Multi-scale feature fusion-based bilinear attention convolutional neural network for wood NIR classification

Effective development and utilization of wood resources is critical.Wood modification research has become an integral dimension of wood science research,however,the similarities between modified wood and original wood render it challenging for accurate identification and classification using conventional image classification techniques.So,the development of efficient and accurate wood classification techniques is inevitable.This paper presents a one-dimensional,convolutional neural network(i.e.,BACNN)that combines near-infrared spectroscopy and deep learning techniques to classify poplar,tung,and balsa woods,and PVA,nano-silica-sol and PVA-nano silica sol modified woods of poplar.The results show that BACNN achieves an accuracy of 99.3%on the test set,higher than the 52.9%of the BP neural network and 98.7%of Support Vector Machine compared with traditional machine learning methods and deep learning based methods;it is also higher than the 97.6%of LeNet,98.7%of AlexNet and 99.1%of VGGNet-11.Therefore,the classification method proposed offers potential applications in wood classification,especially with homogeneous modified wood,and it also provides a basis for subsequent wood properties studies.

Recent advances and trends of single-atom catalysts for proton exchange membrane fuel cell cathodes

Proton exchange membrane fuel cells(PEMFCs),which have the advantages of high-power density,zero emission,and low noise,are considered ideal electrochemical conversion systems for converting hydrogen(H2)and oxy-gen(O_(2))/air into electricity.However,the oxygen reduction reaction(ORR),which is accompanied by multiple electrons,results in voltage loss and low conversion efficiency of PEMFCs.Currently,PEMFCs mainly use high-load precious platinum(Pt)to promote the ORR process;however,the high cost of Pt hinders the widespread commercialization of PEMFCs.Over the past few years,metal-nitrogen-carbon single-atom catalysts(M-N-C SACs)have attracted considerable attention and have been recognized as potential Pt-based catalysts owing to their outstanding ORR activity.This review briefly introduces the components of PEMFCs.Second,we discuss the catalytic mechanisms of the M-N-C SACs for the ORR.Third,the latest advances in noble,non-noble,and heteroatom-doped M-N-C SACs used as ORR and PEMFCs cathode catalysts are systematically reviewed.In sum-mary,we have outlined the current challenges and proposed a future perspective of M-N-C SACs for PEMFCs cathodes.