2018 International Conference on Artificial Intelligence and Big Data (ICAIBD) 2018
DOI: 10.1109/icaibd.2018.8396184
|View full text |Cite
|
Sign up to set email alerts
|

Transfer learning with convolutional neural networks for moving target classification with micro-Doppler radar spectrograms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
6
3
1

Relationship

1
9

Authors

Journals

citations
Cited by 40 publications
(13 citation statements)
references
References 15 publications
0
9
0
1
Order By: Relevance
“…The most commonly employed radar signal characteristic for automatic target classification is the micro-Doppler (m-D) signature [40]. The m-D signature has been utilized by many works for automatic target classification such as ground moving target classification [41,42,43], ship detection [44], human gait recognition [45,46], and human activity classification [47,48]. In recent years, it has been an active area of research in the field of c-UAV radar based applications.…”
Section: Radar Sensormentioning
confidence: 99%
“…The most commonly employed radar signal characteristic for automatic target classification is the micro-Doppler (m-D) signature [40]. The m-D signature has been utilized by many works for automatic target classification such as ground moving target classification [41,42,43], ship detection [44], human gait recognition [45,46], and human activity classification [47,48]. In recent years, it has been an active area of research in the field of c-UAV radar based applications.…”
Section: Radar Sensormentioning
confidence: 99%
“…Ortaklama katmanında, küçük aktivasyon haritaları oluşturmak için bağımsız olarak her bir aktivasyon haritasının üzerinde çalışan bir aşağı örnekleme işlemi gerçekleştirilmektedir. Tam bağlantılı katmanda ise evrişim katmanları tarafından çıkarılan ve katmanları birleştirerek aşağı örneklenen özellikler üzerinde doğrusal işlemler gerçekleştirilmektedir [24]. ESA uygulamalarından birisi olan transfer öğrenimi ön eğitilmiş ESA mimarilerine yeni bir görev yüklemek için ağın yeniden eğitilmesi işlemidir.…”
Section: Evri̇şi̇mli̇ Si̇ni̇r Ağlari (Esa)unclassified
“…In machine learning terms, the transfer learning roughly translates to transferring the weights of already trained deep neural network model for one task, to the model tackling second related task [13]. Based on previous work [16,2,25], such approaches work especially well if we have a small, insufficient dataset.…”
Section: Transfer Learningmentioning
confidence: 99%