Hybrid Latent Space Autoencoder and OCSVM Framework for Unknown Class Recognition in Partial Discharge Diagnostics
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Access"
DOI: 10.1109/access.2025.3634203
Abstract: Partial discharge classification is vital for identifying the type of insulation defects in high-voltage equipment. However, conventional models typically operate under a closed-set assumption, where the model assumes that every input belongs to one of… read more here.
Keywords: unknown classes; framework; recognition; partial discharge ... See more keywords
DOI: A Systematic Framework for Incremental Identification of Specific Emitters in Open-set Scenarios
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Cognitive Communications and Networking"
DOI: 10.1109/tccn.2025.3569554
Abstract: Specific emitter identification (SEI) technology can be used for identity recognition, passive authentication, and safety management of target emitters, which is of great significance in enhancing information security. In response to the demand for identifying… read more here.
Keywords: unknown classes; emitters open; open set; incremental identification ... See more keywords
An Open-Set Classification Method With Small Samples for Rotating Machinery
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Instrumentation and Measurement"
DOI: 10.1109/tim.2024.3481570
Abstract: With the development of artificial intelligence, deep learning (DL)-based methods for rotating machinery fault diagnosis are emerging. However, these data-driven DL methods rely heavily on a large amount of labeled data, which is often scarce… read more here.
Keywords: classification; unknown classes; small samples; open set ... See more keywords
Few-shot SAR target classification via meta-learning with hybrid models
Sign Up to like & getrecommendations! Published in 2024 at "Frontiers in Earth Science"
DOI: 10.3389/feart.2024.1469032
Abstract: Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large… read more here.
Keywords: unknown classes; shot sar; meta learning; target ... See more keywords