2024
DOI: 10.3390/app14020603
|View full text |Cite
|
Sign up to set email alerts
|

A Deep Bidirectional LSTM Model Enhanced by Transfer-Learning-Based Feature Extraction for Dynamic Human Activity Recognition

Najmul Hassan,
Abu Saleh Musa Miah,
Jungpil Shin

Abstract: Dynamic human activity recognition (HAR) is a domain of study that is currently receiving considerable attention within the fields of computer vision and pattern recognition. The growing need for artificial-intelligence (AI)-driven systems to evaluate human behaviour and bolster security underscores the timeliness of this research. Despite the strides made by numerous researchers in developing dynamic HAR frameworks utilizing diverse pre-trained architectures for feature extraction and classification, persisti… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 17 publications
(8 citation statements)
references
References 67 publications
0
8
0
Order By: Relevance
“…It fulfills the diverse computational needs as the magnitude and dimensions of the network can be modified [23]. The spatial features are captured from the last max-pooling layer with a size of 1 × 1 × 1280.…”
Section: Model Architecturementioning
confidence: 99%
“…It fulfills the diverse computational needs as the magnitude and dimensions of the network can be modified [23]. The spatial features are captured from the last max-pooling layer with a size of 1 × 1 × 1280.…”
Section: Model Architecturementioning
confidence: 99%
“…Finally, they applied SVM as a classifier for the RGB-based JSL and obtained 97.8% accuracy. Ito et al proposed a CNN to extract features from the JSL dataset, applied SVM for the classification, and achieved 84.20% accuracy [20]. As we know, there are a total of 46 JSL sign alphabets.…”
Section: Related Workmentioning
confidence: 99%
“…Angle features are particularly valuable for distinguishing signs with the same shape but different orientations, such as "ma" and "mi" or "na" and "ni" [20]. Figure 5b illustrates the perspective of angle calculations, while Table 5 provides details on the angles computed in our study.…”
Section: Distance Based Featurementioning
confidence: 99%
See 2 more Smart Citations