ZeCA: Zero-Configuration Alarms for Preventing Smartphone Usage during Driving
The rising ubiquity of smartphones for navigation, driver mode, etc., has increased their use significantly among drivers; however, there are growing numbers of road fatalities being reported due to distractions from the phone while driving. Notably, existing studies indicate that drivers know the harmful consequences of using a phone while driving; however, they get tempted to use it for multiple reasons, like texting a friend, exploring navigation routes, browsing music, etc. In this work, we developed a smartphone based application to identify whether the user of the smartphone is a driver or a passenger and whether the driver’s interaction with the smartphone leads to distraction or not. To the best of our knowledge, this is a first of its kind application that does not use any preconfiguration or connection with the vehicle, but passively identifies the user of the smartphone based on the noise and vibration analysis within the vehicle, and figures out the level of distraction due to the smartphone usage.
Key Features
- Zero Pre-configurations: Unlike existing approaches that need connection with the vehicle system or explicit feedback from the user, our method does not need any pre-configuration to run the application.
- Exploiting the NVM (Noise Vibration Harshness) Analysis of the Vehicle: Our method uses a novel analysis of the NVM characteristics of the vehicle to identify the user of a smartphone in a passive and pervasive way.
- Low-resource Footprint: Unlike camera-based approaches, the proposed method has a very low energy and computation footprint, thus is suitable to run as a background application of a smartphone.
- Large-scale testing: We have tested the proposed approach over 50 different car models driven by 70 different drivers, with a total driving data of 986 km, demonstrating its robustness and usefulness.
Licensing:The platform source and the collected dataset is free to download and can be used with GNU General Public License for non-commercial purposes. All participants signed forms consenting to the collected dataset and associated labels for non-commercial research purposes. The institute’s ethical review committee has approved the field study (Order No: IIT/SRIC/DEAN/2023, Dated July 31, 2023).
Contributors
Sugandh Pargal
IIT Kharagpur, India
Neha Dalmia
IIT Kharagpur
Soumyajit Chatterjee
Nokia Bell Labs, UK
Sandip Chakraborty
IIT Kharagpur, India
Teaser Video
Publications
- Sugandh Pargal, Neha Dalmia, Harsh Borse, Bivas Mitra, and Sandip Chakraborty: "Zero-configuration Alarms: Towards Reducing Distracting Smartphone Interactions while Driving", ACM Journal on Computing and Sustainable Societies (ACM JCSS), Volume 2, Issue 3, Article No 29, Pages 1-30, presented in ACM COMPASS 2024
- Sugandh Pargal, Soumyajit Chatterjee, Utkarsh Sinha, Bivas Mitra and Sandip Chakraborty: "My Mobile Knows that I am Driving! In-Vehicle (Relative) Blind Localization of a Smartphone", IEEE MUST 2022 (in conjunction with IEEE MDM 2022)
- Sugandh Pargal, Soumyajit Chatterjee, Bivas Mitra, Sandip Chakraborty: "Who is Using the Phone within the Car? Blind Device Localization in a Car with Unimodal Acoustic Signature", ACM HotMobile 2022 (Posters)