Abnormal Usage Sequence Detection for Identification of User Needs via Recurrent Neural Network Semantic Variational Autoencoder.
Younghoon LeeSungzoon ChoPublished in: Int. J. Hum. Comput. Interact. (2020)
Keyphrases
- recurrent neural networks
- feedforward neural networks
- complex valued
- neural network
- automatic identification
- hidden layer
- feed forward
- anomaly detection
- user profiles
- detection algorithm
- viterbi algorithm
- detection method
- user interaction
- relevance feedback
- natural language
- image segmentation
- end users
- false positives
- user interface
- artificial neural networks
- usage patterns
- recurrent networks
- echo state networks
- back propagation
- abnormal behavior
- neural model
- gaussian process
- context dependent
- user preferences
- semantic web
- search engine
- machine learning