Modeling Sports Event Tasks in Augmentative and Alternative Communication Using Deep Learning

Noora Hani Sherif1,*, Eay Fahidhil2, Najlaa Nsrulaah Faris3, Hussein Alaa Diame4, Raaid Alubady5, Seifedine Kadry6, 7, 8

1Computer Technologies Engineering, Al-Turath University College, Baghdad, Iraq

2Medical instruments engineering techniques, Al-farahidi University, Baghdad, Iraq

3Department of Medical Devices Engineering Technologies, National University of Science and Technology, Dhi Qar, Nasiriyah, Iraq

4Technical Computer Engineering Department, Al-Kunooze University College, Basrah, Iraq

5Technical Engineering College, Al-Ayen University, Thi-Qar, Iraq

6Department of Applied Data Science, Noroff University College, Kristiansand, Norway

7Artificial Intelligence Research Center (AIRC), Ajman University, Ajman, 346, United Arab Emirates

8Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon

Abstract

Rapid changes in modern technology and sports have impacted society and lifestyle. Augmentative and Alternative Communication (AAC) technology helps to speak and play videos in various sports applications. In the current sports event, AAC's utilization to validate the players' complex moves exclusively has been considered a significant challenge that includes athlete moves in athletics and penalty shots in Soccer. Deep Learning-based Video Segmentation and Video mining (DL-VSVM) with eyeball tracking assistance are proposed to validate the task modeling of sports event video streaming in AAC. The user could select the specific event in the sport and sub-event using eyeball tracking assistance. The AAC is installed with unique icons to identify circumstances. A deep learning-based Sports Task model is created to recognize the required data to be streamed, and the model will help them view the specific sports event they need to watch. The numerical outcomes demonstrate that the suggested DL-VSVM model enhances the segmentation accuracy ratio of 95.3%, tracking ratio of 97.6%, prediction ratio of 98.7%, and reduces the cost function of 5.6% and the error rate of 20.1% compared to other existing models.

Emails: noura.hani@turath.edu.iq; EayFahidhil@uoalfarahidi.edu.iq; najlaa.faris@nust.edu.iq;  Hussein.Alaa@kunoozu.edu.Iq; alubadyraaid@alayen.edu.iq; skadry@gmail.com

 

*Corresponding Author: noura.hani@turath.edu.iq

Received: February 21, 2023   Revised: May 13, 2023   Accepted: September 04, 2023

Keywords: Segmentation; deep learning; video streaming Task model and eyeball tracking.