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 pastfuture 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 outperforms 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 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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.