Whale Optimization Algorithm for Feature Selection in Human Fall Detection
Author Information
Author(s): Cao Haolin, Yan Bingshuo, Dong Lin, Yuan Xianfeng
Primary Institution: Shandong University, Weihai, China
Hypothesis
Can a multispiral whale optimization algorithm improve feature selection for human fall detection?
Conclusion
The proposed multispiral whale optimization algorithm outperforms existing methods in feature selection for human fall detection.
Supporting Evidence
- The MSWOA showed superior performance in feature selection compared to six other algorithms.
- MSWOA achieved a higher classification accuracy on 17 out of 20 datasets.
- The algorithm effectively reduced the number of selected features while maintaining accuracy.
- MSWOA was tested on a dataset specifically designed for human fall detection.
Takeaway
This study created a new algorithm to help computers pick the best features for detecting when someone falls, making it better at recognizing falls.
Methodology
The study used a multispiral whale optimization algorithm tested on 20 UCI datasets and a human fall detection dataset.
Potential Biases
Potential bias in dataset selection and participant demographics.
Limitations
The algorithm may not perform as well on all datasets, particularly those with complex feature distributions.
Participant Demographics
Seven participants, including two females and five males, average age 22 years.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website