Musical Query-by-Semantic-Description Based on Convolutional Neural Network

Qin, Jing; Lin, Hongfei; Zhang, Dongyu; Zhang, Shaowu; Wei, Xiaocong

doi:10.1007/978-3-319-68699-8_19

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quality of feature selection has a significant impact on network traffic recognition rate. Therefore, in order to meet the reliability evaluation requirements of smart grid communication networks, it is possible to try using deep learning models and combining domain knowledge for training and optimization [2,3]. Deep learning models have stronger learning and expression abilities, which can better capture the complexity and nonlinear relationships of smart grid communication networks.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction and Attack Correlation Detection in Power Communication Networks Based on Convolutional Neural Networks

Wang,

Zhang,

et al. 2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

To solve the problem of low feature recognition in existing feature extraction methods in power communication networks, a CNN model is adopted for network data feature extraction and attack correlation detection. Firstly, a basic framework for data preprocessing and further system analysis is proposed for the communication protocol and link basic structure of intelligent substations, as well as general network communication flow collection and analysis methods. Then, detailed design will be performed for different functional modules, including data collection, traffic extraction, and SVM based classification and recognition. Then, convolutional neural networks are used to classify the associated and non associated traffic feature maps, in order to determine whether they are related. Finally, an experiment is conducted with a real power communication network. The results show that the data feature extraction method proposed in the article can achieve reliability prediction from actual operating data of the power communication network, greatly improving feature identification and reducing storage and calculation costs while maintaining accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%