Doppler-Based Sound Localization and Its Application in AI-empowered Traffic Warning for Deafness
Bibliographic record
Abstract
Hearing is essential for information processing and our safety, especially in traffic. For patients with hearing impairments, sound localization devices help identify threatening sound sources and reduce traffic safety risk. Existing methods typically rely on measuring time delay using microphone arrays. Unfortunately, this method faces critical challenges for dynamic sound sources, posing major threats. Addressing this challenge, we propose a wearable sound localization system that combines interaural time differences and Doppler frequency shifts to determine the position, direction, and speed of moving sound sources. The method's feasibility is first evaluated through a combination of theoretical calculations and experimental verifications. A proof-of-concept setup was established by engaging three microphones as the receiver and a toy car emitting a constant tone as the sound source. An AI algorithm based on artificial neural network was further trained using the received sound signal when the source moved at different locations and directions. The results demonstrated accurate detection of Doppler shifts, with classification accuracies of 100% for front/back, 87.5% for distance, and 62.5% for left/right. Finally, the system was integrated into a wristband with feedback motors, providing vibrational alerts based on the detected motion and proximity of sound sources. These results validate the feasibility of using Doppler shifts and machine learning for motion detection in real time. The proposed system offers a portable solution to enhance the awareness of the environment for individuals with hearing impairments and lays the groundwork for future warning devices in traffic safety applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".