Automatic reading task prediction on tablet (PC) under the influence of noise and illumination via optimized LSTM. (June 2023)

• Record Type: Journal Article
• Authors: Dua, Bharat Bhushan; Singh, Sudhir Kumar; Khan, Iqbal Ahmed
• Is Part Of: Advances in engineering software. Volume 180(2023)
• Publication Date: 2023-06
• Subjects: Reading -- tablet -- Behaviour prediction -- Noise -- Illumination -- Improved correlation -- Improved entropy and statistical features -- LSTM -- GWAC; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103391
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: The highlights of the article are given below for your kind perusal. Kindly, consider and forward my article for further processes. This research work analysis the impact of the noise and illumination on the performance of reading tasks carried out by female (18–25 Years) and males (18–25 Years) on a Tablet (PC). The behaviors of participants during reading process were recorded under two different perspectives like noise and illumination. To the most relevant features like improved correlation, improved entropy from the pre-processed data for enhancing the prediction accuracy. To construct three mathematical models namely optimized LSTM1, LSTM2 and LSTM3, respectively for automatic detection of the variation in the left pupil diameter, right pupil diameter as well as their reading capability (i.e. Count of characters read/second) To enhance the prediction accuracy of the three mathematical models, weight of them is fine-tuned using a new hybrid optimization model- grey wolf optimization appended cuckoo (GWAC). The projected new hybrid optimization model (GWAC) is the conceptual blending of the standard Cuckoo search algorithm (CSA) and Grey Wolf Optimizer (GWO), respectively. Abstract: Everyone has long recognized smart phones and other mobile technology's capability to enhance cognitive abilities. The majority of studies on smart phones and tablets while driving have focused on distraction, reaction times, and overall safety. In this study, the effects of light and noise on the tablet reading tasks completed by males and females (18 to 25 years old) are investigated. Initially, the collected data are pre-processed via data cleaning process. Subsequently, the most relevant features like improved correlation, improved entropy and statistical features are retrieved from the pre-processed information. The final prediction with respect to the automatic identification of variations in pupil diameter of the left eye, right eye, and reading ability (count of characters read/second) is made using three mathematical models: optimized Long Short-Term Memory1 (LSTM1), optimized LSTM2 and optimized LSTM3 respectively. The optimized LSTM1, optimized LSTM2 and optimized LSTM3 are trained with the fused features. Further, to improve the prediction efficiency of the three mathematical models, weight of them is fine-tuned employing aunique approach known as Grey Wolf Optimization Appended Cuckoo (GWAC). At last, a comparative assessment is undergone to verify the efficiency of the projected model in terms of various measures.