3-photon fluorescence and third-harmonic generation imaging of myelin sheaths in mouse digital skin in vivo:A comparative study

Myelin sheaths wrapping axons are key structures that help maintain the propagation speed of action potentials in both central and peripheral nervous systems(CNS and PNS).However,noninvasive,deep imaging technologies visualizing myelin sheaths in the digital skin in vivo are lacking in animal models.3-photon°uorescence(3PF)imaging excited at the 1700-nm window enables deep imaging of myelin sheaths,but necessitates labeling by exogenous°uorescent dyes.Since myelin sheaths are lipid-rich structures which generate strong third-harmonic signals,in this paper,we perform a detailed comparative experimental study of both third-harmonic generation(THG)and 3PF imaging in the mouse digital skin in vivo.Our results show that THG imaging also enables visualization of myelin sheaths deep in the mouse digital skin,which shows colocalization with 3PF signals from labeled myelin sheaths.Besides its superior label-free advantage,THG does not su®er from photobleaching due to its 3PF property.

A Robust Transfer Dictionary Learning Algorithm for Industrial Process Monitoring

Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge.However,most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution.In fact,due to the harsh environment of industrial systems,the collected data from real industrial processes are always affected by many factors,such as the changeable operating environment,variation in the raw materials,and production indexes.These factors often cause the distributions of online monitoring data and historical training data to differ,which induces a model mismatch in the process-monitoring task.Thus,it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring.In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments,a robust transfer dictionary learning(RTDL)algorithm is proposed in this paper for industrial process monitoring.The RTDL is a synergy of representative learning and domain adaptive transfer learning.The proposed method regards historical training data and online testing data as the source domain and the target domain,respectively,in the transfer learning problem.Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework,which can reduce the distribution divergence between the source domain and target domain.In this way,a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment.Such a dictionary can effectively improve the performance of process monitoring and mode classification.Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.