A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques

Jorge Martinez Carracedo; Jonathan Etumusei; Sally I McClean

A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques

Jorge Martinez Carracedo, Jonathan Etumusei, Sally I McClean

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The subject of human activity recognition is be- coming eminent in the study of human movement patterns and disabilities. Many existing approaches are effective in identi- fying change points in physical activities; however, algorithm optimisation could potentially be applied to improve some of these models. In this paper, we proposed a method known as mean of the geometric moving average of the Martingale sequence that can detect changes in human activity recognition. Furthermore, the suggested method is optimised for enhanced performance using meta-heuristic optimisation techniques based on the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithms. Experimentation shows that the suggested method improves the performance of the previous Martingale method.

Original language	English
Title of host publication	International Conference on Electrical, Computer, Communications and Mechatronics Engineering
Publisher	IEEE
Publication status	Accepted/In press - 21 Aug 2023
Event	International Conference on Electrical, Computer, Communications and Mechatronics Engineering - Hotel Escuela Santa Cruz , Santa Cruz de Tenerife, Spain Duration: 19 Jul 2023 → 21 Jul 2023 Conference number: 2023 http://www.iceccme.com

Conference

Conference	International Conference on Electrical, Computer, Communications and Mechatronics Engineering
Abbreviated title	ICECCME
Country/Territory	Spain
City	Santa Cruz de Tenerife
Period	19/07/23 → 21/07/23
Internet address	http://www.iceccme.com

Cite this

@inproceedings{9a4fc2b99b1c4611a7cf9f4e2b2cc143,

title = "A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques",

abstract = "The subject of human activity recognition is be- coming eminent in the study of human movement patterns and disabilities. Many existing approaches are effective in identi- fying change points in physical activities; however, algorithm optimisation could potentially be applied to improve some of these models. In this paper, we proposed a method known as mean of the geometric moving average of the Martingale sequence that can detect changes in human activity recognition. Furthermore, the suggested method is optimised for enhanced performance using meta-heuristic optimisation techniques based on the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithms. Experimentation shows that the suggested method improves the performance of the previous Martingale method.",

author = "{Martinez Carracedo}, Jorge and Jonathan Etumusei and McClean, {Sally I}",

year = "2023",

month = aug,

day = "21",

language = "English",

booktitle = "International Conference on Electrical, Computer, Communications and Mechatronics Engineering",

publisher = "IEEE",

address = "United States",

note = "International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME ; Conference date: 19-07-2023 Through 21-07-2023",

url = "http://www.iceccme.com",

}

Martinez Carracedo, J, Etumusei, J & McClean, SI 2023, A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques. in International Conference on Electrical, Computer, Communications and Mechatronics Engineering. IEEE, International Conference on Electrical, Computer, Communications and Mechatronics Engineering, Santa Cruz de Tenerife, Spain, 19/07/23.

A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques. / Martinez Carracedo, Jorge; Etumusei, Jonathan; McClean, Sally I.
International Conference on Electrical, Computer, Communications and Mechatronics Engineering. IEEE, 2023.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques

AU - Martinez Carracedo, Jorge

AU - Etumusei, Jonathan

AU - McClean, Sally I

N1 - Conference code: 2023

PY - 2023/8/21

Y1 - 2023/8/21

N2 - The subject of human activity recognition is be- coming eminent in the study of human movement patterns and disabilities. Many existing approaches are effective in identi- fying change points in physical activities; however, algorithm optimisation could potentially be applied to improve some of these models. In this paper, we proposed a method known as mean of the geometric moving average of the Martingale sequence that can detect changes in human activity recognition. Furthermore, the suggested method is optimised for enhanced performance using meta-heuristic optimisation techniques based on the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithms. Experimentation shows that the suggested method improves the performance of the previous Martingale method.

AB - The subject of human activity recognition is be- coming eminent in the study of human movement patterns and disabilities. Many existing approaches are effective in identi- fying change points in physical activities; however, algorithm optimisation could potentially be applied to improve some of these models. In this paper, we proposed a method known as mean of the geometric moving average of the Martingale sequence that can detect changes in human activity recognition. Furthermore, the suggested method is optimised for enhanced performance using meta-heuristic optimisation techniques based on the genetic algorithm (GA) and particle swarm optimisation (PSO) algorithms. Experimentation shows that the suggested method improves the performance of the previous Martingale method.

M3 - Conference contribution

BT - International Conference on Electrical, Computer, Communications and Mechatronics Engineering

PB - IEEE

T2 - International Conference on Electrical, Computer, Communications and Mechatronics Engineering

Y2 - 19 July 2023 through 21 July 2023

ER -

A Novel Martingale Model for Human Activity Recognition using Robust Optimisation Techniques

Abstract

Conference

Fingerprint

Cite this