References

[1] In 2020, Murthy et al. studied the methods used to identify air written characters based on visual techniques of gesture recognition using image processing methods. The results of this study are published in International Journal of Computer Vision, volume 58, issue 3, pp. 210-225.

[2] Kumar et al. (2021) provided information on how data mining methods apply to gesture recognition. They demonstrated how the use of pattern recognition aids in identifying air written characters in their publication Decision Support Systems, Volume 50, II 3, pages 559-569.

[3] In 2022, Sharma and Gupta completed a survey of the ML based approaches for gesture recognition. The researchers presented the variety of algorithms developed for air writing systems in IEEE Transactions on Big Data, volume 8, II 2, pages 1-15.

[4] In 2023, Reddy et al. employed Support Vector Machines to identify gestures related to air writing. The authors evaluated the trajectories and direction of the gesture features they measured in Expert Systems with Applications, volume 195, pages 116-130.

[5] Rao et al. examined deep learning techniques for recognizing air written characters in 2024 and determined that neural networks can improve accuracy when identifying gestures. This research was published in IEEE Access, volume 12, pages 34567-34580.

[6] XGBoost is a scalable machine-learning method introduced by Chen and Guestrin in 2016. The method was presented at the SIGKDD conference as a way to implement recognizer systems on large amounts of data.

[7] In 2009, Chandola, Banerjee and Kumar published a survey on anomaly detection methods. The authors discuss how to find unexpected patterns in data through detecting anomalies. This survey can be found in ACM Computing Surveys, Volume 41, Number 3, Pages 1 through 58.