2018 · 14 citations · 12 references
ComputingComputer ScienceVisualizationArtificial IntelligenceData VisualizationMachine LearningAnomaly DetectionDeep LearningNeural NetworksPattern RecognitionConvolutional Neural NetworksData-driven VisualizationDeep Learning For Intrusion DetectionDeep Learning-based Anomaly DetectionDeep Learning-based Detection
Recently, artificial intelligence technology has aroused wide attention and application worldwide, and is considered to be the next technology to create a new paradigm in the industry. The convolutional neural network (CNN), which is beneficial in fields such as imaging and voice analysis, is a type of representative algorithm of artificial intelligence. Increasing fields of study are introducing CNN into their research. However, CNN primarily handle image data, which is entirely different from the data form generated in other fields of study. Blindly processing the data by directly using CNN leads to incorrect training results or instances where training efficiency is too low. In this study, we use the idea of“making data fit model putting forward CNN based on data visualization, named V-CNN. V-CNN integrates the data visualization front before CNN model so that the data in the system is suitable for the CNN, which is, in turn, suitable for image recognition. This article further uses intelligent network intrusion detection as an example to verify the V-CNN performance. The results show that all the four categories of invasion of the AWID data set in each type of the recall rate is more than 99.8%, which is significantly better than that in the existing literature. To the best of our knowledge, this article is the first to propose V-CNN based on data visualization. V-CNN is general to handle data from almost all fields. Therefore, we call it “All can be image.
12
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Convolutional Sequence to Sequence Learning
Jonas Gehring, Michael Auli, David Grangier et al. · International Conference on Machine Learning · 2017 · 1.3K citations
Big Data Deep Learning: Challenges and Perspectives
Xuewen Chen, Xiaotong Lin · IEEE Access · 2014 · 1.3K citations · Full text