Network intrusion detection systems (NIDS) are essential tools in ensuring network information security, and neural networks have become an increasingly popular solution for NIDS. However, with the gradual complexity of the network environment, the existing solutions using the conventional neural network cannot make full use of the rich information in the network traffic data due to its single structure. More importantly, this will lead to the existing NIDS have incomplete knowledge of the intrusion detection domain, and making it unable to achieve a high detection rate and good stability in the new environment. In this paper, we take a step forward and extract the different level features from the network connection, rather than a long feature vector used in the traditional approach, which can process feature information separately more efficiently. And further, we propose multimodal-sequential intrusion detection approach with special structure of hierarchical progressive network, which is supported by multimodal deep auto encoder (MDAE) and LSTM technologies. By design the special structure of hierarchical progressive network, our approach can efficiently integrate the different level features information within a network connection and automatically learn temporal information between adjacent network connections at the same time. Based on the three benchmark datasets from 1999 to 2017, including NSL-KDD, UNSW-NB15, and CICIDS 2017, we investigated the performance of our proposed approach on the task of detecting attacks within modern network. The experimental results show that the average accuracy of this method is 94% in binary classification and 88% in multi-class classification, which is at least 2% and 4% super than other methods respectively, and demonstrated that our model has excellent stability. Moreover, we further explore the multimodality and complementarity in traffic data, the experimental results show that the performance of detection model can be further improved in the range 2% to 5% when using our MDAE model to process the features of traffic data.

Numerous countries in the world pay close attention to the change of air quality and the control of air pollution. Air quality prediction has become a challenging issue owing to the complex characteristics with time-space nonlinearity and multi-dimensional feature interaction. This paper inventively proposes a three-dimensional presentation of the air quality data and establishes a deep model using spatiotemporal collaborative strategy to predict regional air quality, which can properly deal with multiple characteristics of air quality. Firstly, a theory of regional air quality prediction is given with reasonable analyses and scientific definitions, for systematically analyzing the closely connected areas and simultaneously predicting multiple locations. Secondly, a three-dimensional data structure called Relevance Data Cube is constructed utilizing a clustering algorithm, time sliding windows and correlation analysis of factors. This structure depicts the whole relationships among multiple dimensions of air quality data clearly and provides a basic analysis foundation for subsequent processing. Thirdly, based on the above theory and data structure, a prediction model is proposed to demonstrate the applicability of our work. Spatial relevance and factor influence are processed using dimension reduction technique provided by CNN, which performs automatic mining of spatial correlation and factors reaction of air quality. Besides, LSTM is combined with CNN to deal with the temporal dependency among the data dynamically. Finally, the proposed model is compared with other neural networks by a large number of experiments. The model is proved to better adapt to the characteristics and predict the air quality more accurately, which is more suitable and reliable for the field of air quality.

With the rapidly increasing complexity and indispensable status of software systems, unprecedented challenges have been brought to software debugging and fault repair. Among the states of art automated fault localization techniques, spectrum-based fault localization (SBFL) is one of the most widely studied heuristic approaches. While, existing SBFL techniques are mostly focused on the analysis of the test spectrum, which loses sight of the effectiveness implied in interactions of software entities. In this paper, an optimized fault localization approach is proposed, which integrates spectrum-based fault localization and fault influence propagation analysis. The intuition is that the entity associated with more suspicious entities is more likely to be faulty. (1) A dynamic-instrumenting execution tracer is developed to record test coverage data and method call relations simultaneously. (2) The Fault Influence Network (FIN) based on complex network theory is constructed, of which the network topology is abstracted from method call relations and the weights of nodes are calculated applying a raw fault locator. Thus, the test spectrum and the method interactive relations are combined for further collaborative analysis. (3) A PageRank-based fault localization approach is proposed. By the computation of fault influence propagation, the suspiciousness score PR-Susp of the real faulty method can be enhanced significantly. Also, a candidate set pruning based on failing tests is implemented, which is used for the narrowing of investigation. Experiments are conducted over real-world fault dataset Defects4J with 33 raw spectrum-based fault locators, which proves that the proposed approach improves the baseline 14.9% averagely on the metric acc@5 with a growth rate of over 39% on all metrics of acc@1, acc@3, acc@5, MAP, and MWE.