Search

In today’s information age, the scale of the Internet is growing, the information capacity is also expanding explosively, and network security is becoming more and more important. Intrusion detection is regarded as a traditional security protection technology and is a key means to ensure the security of the network environment. Among them, the deep belief network performs well, and it can automatically learn abstract features for classification. In order to further improve the detection rate and reduce the false positive rate, it is necessary to improve the detection rate of small sample data. This paper builds an intelligent deep learning model and analysis model for intrusion detection data based on TensorFlow. By learning to identify network intrusion characteristic data, the characteristic data and model are stored in the big data storage system built by Hadoop. This algorithm has achieved good experiment result. Build a model knowledge base and an intrusion feature behavior library, use the decision tree model to automatically match the security control strategy, realize a highly intelligent security control model with self-learning ability, and solve the rapid identification of unknown intrusion behaviors. Experiments show that the algorithm can effectively improve the detection rate.

A stably acquiring and accurately demodulating interferogram is crucial for the interferometer to achieve ultra-high precision and sensitivity measurements. In this study, a robust orbital angular momentum (OAM) beams-based Fizeau interferometer is proposed and experimentally demonstrated, which is more compact and stable than the OAM interferometers with other structures due to the common optical path characteristic. In accordance with such an interferometric scheme, a phase-demodulation method operated in the domain of the OAM complex spectrum is also proposed and demonstrated in this study. In contrast to other phase-demodulation techniques, the proposed phase-demodulation technique neither requires phase shifters or phase modulators nor brings spectral leakage, which provides a robust alternative enabling to accurately and quickly extract the phase from the OAM interferogram. As a proof-of-concept of the proposed scheme, tiny displacements ranging from 0 to 800 nm were measured. The proposed OAM beams-based Fizeau interferometer and the corresponding azimuthal phase demodulation method may provide a feasible way for exploring further applications of the OAM-based interferometer in metrology.

In this study, a modified OAM Mach-Zehnder (M-Z) interferometer for displacement measurement has been proposed and experimentally proved, where two conjugate OAM beams propagate on two arms respectively. The traditional M-Z OAM interferometer was modified by introducing a reflection module in the reference arm. As a result, the optical path shift mismatched reflections on two arms is eliminated, which improves the quality of the petal-like pattern produced by the interference between two conjugate OAM beams. And a significant rotation angle of the petal-like pattern vs. the tiny displacement of the tested object can be clearly observed. By accurately measuring the rotation angle of the petal-like pattern, a tiny displacement ranging from 50 to 800 nm with resolution of ~50 pm has been measured successfully.

Semi-supervised learning (SSL) has proven to be a powerful algorithm in different domains by leveraging unlabeled data to mitigate the reliance on the tremendous annotated data. However, few efforts consider the underlying temporal relation structure of unlabeled time series data in the semi-supervised learning paradigm. In this work, we propose a simple and effective method of Semi-supervised Time series classification architecture (termed as SemiTime) by gaining from the structure of unlabeled data in a self-supervised manner. Specifically, for the labeled time series, SemiTime conducts the supervised classification directly under the supervision of the annotated class label. For the unlabeled time series, the segments of past-future pair are sampled from time series, where two segments of pair from the same time series candidate are in positive temporal relation, while two segments from the different candidates are in negative temporal relation. Then, the temporal relation between those segments is predicted by SemiTime in a self-supervised manner. Finally, by jointly classifying labeled data and predicting the temporal relation of unlabeled data, the useful representation of unlabeled time series can be captured by SemiTime. Extensive experiments on multiple real-world datasets show that SemiTime consistently out-performs the state-of-the-arts, which demonstrates the effectiveness of the proposed method. Code and data are publicly available at https://haoyfan.github.io.

In this study, a simple and reliable method enabling to well synthesize the complex orbit-angular-momentum (OAM) spectrum of hybrid mode in a few-mode fiber is proposed and numerically demonstrated, which is realized by using the so-called inverse scattering method based on the genetic algorithm (GA), where the main Fourier components of a specially-selected ring in intensity distribution of the hybrid mode is used as the optimization objective. As a proof-of-concept example, power spectrum of a hybrid mode consisted of the first- and second-order OAM modes was successfully reconstructed with an accuracy higher than 0.99. This is the first time, to the best of our knowledge, that the complex OAM spectrum of a fiber hybrid mode consisted of more than two kinds of OAM modes is synthesized directly from the intensity distribution of the hybrid mode itself.

This article designed a repository which can save the information about the changes of geographical feature by the means of extending the vector geospatial database, and support multi-user concurrent editing through the branching and merging of the versions. Then, the plug-in of version management based on GIS platform software was designed. This plug-in edited news by addressing the vector feature issued by GIS platform, achieved the function of version management of vector space database, and then carried out the version back by version record added, deleted, and updated vector data. The plug-in had a plug and play, and the benefit of transparency to other GIS functions.