Enhanced hyperspectral image segmentation and classification using K-means clustering with connectedness theorem and swarm intelligent-BiLSTM

Christilda, A. Josephine; Manoharan, R.

doi:10.1016/j.compeleceng.2023.108897

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, a comprehensive comparative experimental analysis is conducted to ensure objectivity and rigor. This analysis encompasses the proposed model algorithm and benchmarked it against alternative model algorithms, namely CNN [ 34 ], STGNN [ 35 ], BiLSTM [ 36 ], Ren (2023), and Meng & Qiao (2023). The evaluation of these alternative models was grounded in a range of essential metrics, including accuracy, precision, recall, and the F1 score.…”

Section: Resultsmentioning

confidence: 99%

The intelligent football players’ motion recognition system based on convolutional neural network and big data

Wang,

Guo

2023

Heliyon

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

The intelligent football players’ motion recognition system based on convolutional neural network and big data

Wang,

Guo

2023

Heliyon

View full text Add to dashboard Cite

An improved sparrow search algorithm using chaotic opposition‐based learning and hybrid updating rules

Lian

2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryMetaheuristic algorithms have special effects in solving optimization problems in real life and have become the focus of researchers. The sparrow search algorithm (SSA) is a newly proposed swarm‐based metaheuristic algorithm that has shown excellent optimization performance. Although compared with other algorithms, SSA shows good performance, the original SSA algorithm still has problems such as weak optimization ability, leading to falling into the local optimum, and being unable to balance exploration and exploitation well. Therefore, this paper proposes an improved SSA using chaotic opposition‐based learning and hybrid updating rules (CHSSA). First, chaotic opposition‐based learning is proposed to improve the diversity of the population. Second, two strategies, including adaptive weights and spiral search, are adopted to update the position. Finally, to evaluate the performance of the proposed CHSSA, this paper uses 23 benchmark functions, IEEE CEC 2017 functions and 4 practical engineering optimization problems to evaluate the algorithm performance. The experimental results show that compared with other advanced optimization algorithms, CHSSA has the characteristics of fast convergence speed, high search accuracy, and strong robustness.

show abstract

Balanced spatio-spectral feature extraction for hyperspectral and multispectral image fusion

Rajaei,

Abiri,

Helfroush

2024

Computers and Electrical Engineering

View full text Add to dashboard Cite

Enhanced hyperspectral image segmentation and classification using K-means clustering with connectedness theorem and swarm intelligent-BiLSTM

Cited by 4 publications

References 23 publications

The intelligent football players’ motion recognition system based on convolutional neural network and big data

The intelligent football players’ motion recognition system based on convolutional neural network and big data

An improved sparrow search algorithm using chaotic opposition‐based learning and hybrid updating rules

Balanced spatio-spectral feature extraction for hyperspectral and multispectral image fusion

Contact Info

Product

Resources

About