View Proposal

---

Proposer

Heba Elshimy

Title

Enabling Environmental Awareness for Hard of Hearing Users through Haptic-Enabled Wearable Devices

Goal

Description

Deliverable: a smartwatch app with background monitoring of ambient sounds; classifying them; and alerting the user via haptic feedback and on-screen notifications of the type pf sound. The haptic feedback would be different based on the severity and importance of the detected sound. This should alert the users to ambient sounds that needs their immediate attention.

Resources

Datasets: 1. urbansound8k: https://urbansounddataset.weebly.com/urbansound8k.html 2. ESC-50: Dataset for Environmental Sound Classification: https://github.com/karolpiczak/ESC-50 Suggested Reading: 1. Environmental Sound Classification: A descriptive review of the literature: https://doi.org/10.1016/j.iswa.2022.200115 2. Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification: https://doi.org/10.1109/LSP.2017.2657381 3. Deep Learning-based Environmental Sound Classification Using Feature Fusion and Data Enhancement: https://doi.org/10.32604/cmc.2023.032719

Background

Python, PyTorch/TensorFlow/ Keras

Url

Difficulty Level

Moderate

Ethical Approval

None

Number Of Students

1

Supervisor

Heba Elshimy

Keywords

deep learning, audio signal processing

Degrees

Bachelor of Science in Computer Science
Master of Science in Artificial Intelligence
Master of Science in Data Science
Bachelor of Science in Computing Science