BSC: Belief Shift Clustering

Zhang, Zuowei; Liu, Zhun-ga; Martin, Arnaud; Zhou, Kuang

doi:10.1109/tsmc.2022.3205365

Cited by 25 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of deep learning techniques, it is widely used for classification, forecasting, and clustering. [33,34] In particular, CNNs and recurrent neural networks are widely used in HRRP recognition. For example, Xiang et al [5] proposed a recognition method based on 1D CNN, which can extract valid structure information of targets in HRRP through 1D-CNN, and introduced an aggregation-perception-recalibration module for feature enhancement.…”

Section: Related Workmentioning

confidence: 99%

High‐Resolution Range Profile Sequence Recognition Based on Transformer with Temporal–Spatial Fusion and Label Smoothing

Wang,

Song

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Radar high‐resolution range profile (HRRP) is widely used in radar automatic target recognition due to its advantages such as easy availability, convenient processing, and small storage space. Current recognition methods for HRRP sequences mainly focus on the temporal information of HRRP sequences, which cannot fully utilize the temporal and spatial information contained in HRRP sequences. Moreover, most of these methods fail in long‐range modeling and global information extraction of HRRP sequences. To solve above problems, a HRRP sequence recognition method based on transformer with temporal–spatial fusion and label smoothing (TSF–transformer–LS) is proposed. TSF–transformer–LS contains temporal transformer blocks and spatial transformer blocks, which are used to extract deep global features of HRRP sequences in the time domain and space domain, respectively. Then, an attention fusion mechanism is developed to realize the adaptive fusion of temporal and spatial features. Moreover, label smoothing is used to add noise to sample labels, which can solve the overfitting problem of transformer caused by a large amount of noise hidden in HRRP in real scenes. Experiments on MSTAR, a standard dataset, show that the proposed method outperforms other methods in recognition performance. Furthermore, the effectiveness and interpretability of the method are explored.

show abstract

Section: Related Workmentioning

confidence: 99%

High‐Resolution Range Profile Sequence Recognition Based on Transformer with Temporal–Spatial Fusion and Label Smoothing

Wang,

Song

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

show abstract

Imprecise Deep Networks for Uncertain Image Classification

Liu,

Zhang,

Liu

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Evidence generalization-based discounting method: assigning unreliable information to partial ignorance

Hu,

Zhou,

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Conflict management is an important topic when dealing with unreliable sources information fusion in Dempster–Shafer theory. Discounting unreliable bodies of evidence has proven to be effective to decrease conflict. Based on the generalization of belief functions, a new generalization-based discounting method is proposed. When resolving conflicts with the same degree, our method can realize less information loss in comparison with other discounting methods. By simulating the process of resolving conflicts of randomly generated bodies of evidence, using entropy measurements and binary conflict as evaluation index, we show our method’s rationality and superiority. Finally, the hyperparameters of the conflict metrics are generated and generalization-based discounting is applied to classify real-world datasets. The improved classification performance further illustrates the usefulness of the method.

show abstract

BSC: Belief Shift Clustering

Cited by 25 publications

References 56 publications

High‐Resolution Range Profile Sequence Recognition Based on Transformer with Temporal–Spatial Fusion and Label Smoothing

High‐Resolution Range Profile Sequence Recognition Based on Transformer with Temporal–Spatial Fusion and Label Smoothing

Imprecise Deep Networks for Uncertain Image Classification

Evidence generalization-based discounting method: assigning unreliable information to partial ignorance

Contact Info

Product

Resources

About