Page 504 - Kaleidoscope Academic Conference Proceedings 2024

S4.3 Artificial Intelligence Driven Tilt Sensor Based Smart Drinking Device for Stroke Survivors
Preeta Sharan (The Oxford College of Engineering: Bangalore, India); Anup M Upadhyaya (The
Oxford College of Engineering, India); R Vasanthan (The Oxford College of Physiotherapy, India)

The proposed work introduces a tilt sensor device designed to monitor glass orientation during
drinking activities in stroke survivors. Phase 1 of the study assessed the device's reliability in 96
normal individuals, achieving a correlation coefficient (r) of 0.99. In Phase 2, 96 stroke survivors
were divided into six subgroups based on specific tilt orientations of the glass during activity. The
device's concurrent validity, measured by Pearson's correlation, was 0.78 compared to motion
analysis data from KINOVEA. Intraclass correlation (ICC) analysis demonstrated high agreement
of 0.99 between the actual angle readings and the measurement angle from each trial. Results
indicated that the device significantly reduced orientation range from 2.31 degrees without
feedback to 0.85 degrees with feedback, highlighting its effectiveness in providing real-time
feedback during drinking tasks. Additionally, the test-retest reliability (interclass correlation) was
0.99, supporting the device's consistency over time. Further work will involve the path for
development of an AI-driven app using SQL files from data collected from stroke survivors,
aiming to provide personalized rehabilitation strategies. The developed tilt sensor device shows
promise as a reliable tool for monitoring glass orientation during drinking activities in stroke
survivors, with potential implications for enhancing rehabilitation outcomes in this population.
S4.4 Alpha-Bit: An Android App for Enhancing Pattern Recognition Using CNN and Sequential Deep
Learning

Gobi Ramasamy (Christ University, India); Antoine Bagula (University of the Western Cape,
South Africa); Arokia Paul Rajan and Priyadharshini Rengasamy (Christ University, India)

This research paper introduces Alpha-Bit, an Android application pioneering Optical Character
Recognition (OCR) through cutting-edge deep learning models, including Convolutional Neural
Networks (CNNs) and Sequential Networks. With a core focus on enhancing educational
accessibility and quality, Alpha-Bit specifically targets foundational elements of the English
language and numbers. Beyond conventional OCR applications, Alpha-Bit distinguishes itself by
offering guided instruction and individual progress reports, providing a nuanced and tailored
educational experience. Significantly, this work extends beyond technological innovation; Alpha-
Bit's potential impact encompasses addressing educational inequalities, contributing to
sustainability goals, and advancing the achievement of Sustainable Development Goal 4 (SDG 4).
By democratizing education through innovative OCR technologies, Alpha-Bit emerges as a
transformative force with the capacity to revolutionize learning experiences, making quality
education universally accessible and empowering learners across diverse socio-economic
backgrounds.

– 460 –