Summary of Carspeednet: a Deep Neural Network-based Car Speed Estimation From Smartphone Accelerometer, by Barak Or
CarSpeedNet: A Deep Neural Network-based Car Speed Estimation from Smartphone Accelerometer
by Barak Or
First submitted to arxiv on: 15 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary CarSpeedNet is a deep learning model that estimates car speed using data from smartphones’ three-axis accelerometers. The model uses 13 hours of data collected from various roads and achieves high-frequency speed estimation by incorporating historical data, with a precision of less than 0.72 m/s during extended driving tests. This model relies solely on smartphone accelerometer data without any connection to the car. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We’ve created a special computer model that can guess how fast a car is going just from the phone’s movements! It looks at how the phone wobbles and bumps around when it’s in a moving car, and uses that information to figure out how fast the car is going. The model is really good at this and can even use old data to make better guesses about what’s happening now. And the best part? It doesn’t need any special equipment or connections to the car – just the phone itself! |
Keywords
* Artificial intelligence * Deep learning * Precision
