B.M.

S COLLEGE OF ENGINEERING
Bull Temple Road, Basavanagudi, Bangalore - 560 019, Karnataka, India

PROJECT WORK – III

SYNOPSIS

ON

“Automobile black box”

Submitted in partial fulfilment of the requirement for completion of PROJECT
WORK - III [22EC5PWPJ3]

Submitted by
ESHWAR BEVOOR [1BM21EC035]
LOCHAN G [1BM21EC072]
HANUMESH BURLI [1BM21EC042]
ALOK KUMAR [1BM21EC012]

2023–2024
Under the guidance

Smt. SHAILA V HEGDE

Associate Professor

Department of Electronics and Communication Engineering

INTRODUCTION:

A car's black box, formally known as an Event Data Recorder (EDR), is a device installed in
vehicles to record various data related to the vehicle's operation. The primary purpose of the
black box is to provide crucial information in the event of an accident or other incidents. Here's
an introduction to the key aspects of a car's black box. The main purpose of the black box is to
gather and store data about the vehicle's performance and driver behaviour before, during, and
after a collision or significant event.
This data is often used by authorities, insurance companies, and vehicle manufacturers to
understand the circumstances leading to an incident and to improve vehicle safety. In summary,
the black box in a car serves as a valuable tool for understanding and improving vehicle safety.
While it raises privacy concerns, its primary function is to provide accurate and objective data
in the aftermath of an incident.
The black box, nestled discreetly within the vehicle's architecture, continuously collects and
retains data, creating a digital footprint of the car's journey. This treasure trove of information
includes details such as vehicle speed and even the deployment of safety features like airbags.
In essence, the automotive black box acts as a guardian of truth, offering investigators,
engineers, and law enforcement officials’ invaluable insights into the dynamics of an accident.
In legal proceedings following an accident, black box data can serve as an objective source of
information, helping to determine liability.
This can be crucial in insurance claims, court cases, and settlement negotiations, providing an
unbiased account of the events leading up to the incident. In essence, the car's black box serves
as a critical tool for understanding, improving, and regulating various aspects of vehicular
safety and transportation. Its importance lies not only in its role in post-accident analysis but
also in its contribution to the ongoing efforts to make road travel safer for everyone.
LITERATURE SURVEY:
In the last years many accurate decisions support systems have been constructed as black
boxes, that is as systems that hide their internal logic to the user.[1] This lack of explanation
constitutes both a practical and an ethical issue. The literature reports many approaches aimed
at overcoming this crucial weakness sometimes at the cost of scarifying accuracy for
interpretability. The applications in which black box decision systems can be used are various,
and each approach is typically developed to provide a solution for a specific problem and, as a
consequence, delineating explicitly or implicitly its own definition of interpretability and
explanation. The aim of this paper is to provide a classification of the main problems addressed
in the literature with respect to the notion of explanation and the type of black box system.
Given a problem definition, a black box type, and a desired explanation this survey should help
the researcher to find the proposals more useful for his own work. The proposed classification
of approaches to open black box models should also be useful for putting the many research
open questions in perspective.

The Automobile Black Box has functions similar to an airplane black box. It is used to analyze
the cause of vehicular accidents and prevent the loss of life and property arising from vehicle
accidents. This paper proposes a prototype of an Automobile Black Box System that can be
installed into vehicles. The system aims to achieve accident analysis by objectively tracking
what occurs in vehicles. The system also involves enhancement of security by preventing
tampering of the Black Box data.[2] In addition, the Black Box sends an alert message to a pre-
stored mobile number via Short Message Service (SMS) in the case of occurrence of an
accident. The proposed system makes use of 12 sensors to record the various driving data
parameters. The Raspberry Pi controller (RPi) and Arduino controllers are used to regulate
these sensors. The data received from the sensors are stored on the SD card mounted on RPi
for retrieval after the accident. The system uses external sensors such as camera and Global
Positioning System (GPS) to collect video and location data.

This prototype can be designed with minimum number of circuits. This can contribute to
construct safer vehicles, improving the treatment for crash victims, helping insurance
companies with their vehicle crash investigations, and enhancing road status in order to
decrease the death rate.[3] The hardware part consists of the components and the sensors used
in the black box system. This part mainly collects the status of the sensors and stores it into the
micro controller ‘s EEPROM. Recent years have seen a tremendous growth in Artificial
Intelligence (AI)-based methodological development in a broad range of domains. In this
rapidly evolving field, large number of methods are being reported using machine learning
(ML) and Deep Learning (DL) models. Majority of these models are inherently complex and
lacks explanations of the decision making process causing these models to be termed as 'Black-
Box'. [4] One of the major bottlenecks to adopt such models in mission-critical application
domains, such as banking, e-commerce, healthcare, and public services and safety, is the
difficulty in interpreting them. Due to the rapid proliferation of these AI models, explaining
their learning and decision making process are getting harder which require transparency and
easy predictability.
PROBLEM DEFINITION:

A black box in a car, also known as an event data recorder (EDR) or vehicle data recorder, is a
device that records various pieces of data related to the vehicle's operation. The primary
purpose of a black box in a car is to gather information about the vehicle's performance and
the driver's behavior before, during, and after a crash or other significant events. With
increasing number of vehicles on the road, the number of accidents has also increased. As a
result the implementation of a black box is very crucial so that the data before and after
accidents are recorded and also it is crucial to alert medics as soon as possible. Here are some
reasons why a black box might be needed in a car:

Accident Investigation: In the event of a crash, the data recorded by the black box can be
crucial for accident investigators.

Improving Safety: Car manufacturers and safety organizations use data from black boxes to
study accidents and improve vehicle safety.

Insurance Claims: Black box data can be used by insurance companies to assess the
circumstances surrounding an accident.
IMPLEMENTATION:

LCD

ALCOHOL SENSOR GPS/GSM

MODEM

MICROCONTROLLER
TEMPERATURE
SENSOR

SEATBELT SENSOR

COLLISION
SENSOR

EEPROM

Figure 1. Block diagram

 Alcohol sensor: This sensor provides both digital and analog outputs and is suitable
for detecting the alcohol concentration on your breath.
 Temperature sensor: This sensor is used to measure the temperature of the automobile
engine.
 Seatbelt sensor: To detect whether the seatbelt strapped on or not.
 Collision sensor: To detect collision.
 GPS/GSM modem: To detect location and to send information about any accident that
has occurred.
 EEPROM: To store all the data.
ESTIMATED PRICE OF ALL THE COMPONENTS

COMPONENTS PRICE (in rupees)

Arduino 2560 1500
GPS/GSM Module 412

Temperature scanner 199

Alcohol scanner 300

Vibration sensor 176

Gyroscope 449

SD card module 200

LCD 285

L293D 250

DC Motor 20

Power supply(batteries) 20

Buzzer 80

LED 15

Switch 20

Push buttons 30

Capacitors 20

Resistors 20

TOTAL 3996
EXPECTED OUTPUT:
Working prototype of a car’s blackbox designed, developed and tested.

REFERENCES:
1)J. Adebayo and L. Kagal. Iterative orthogonal feature projection for diagnosing bias in black-
box models. arXiv preprint arXiv:1611.04967, 2016.

2)P.Adler,C.Falk,S. A.Friedler,G.Rybeck,C. Scheidegger, B. Smith, and Venkatasubramanian.

Auditing black-box models for indirect influence. In Data Mining (ICDM), 2016 IEEE 16th
International Conference on IEEE, 2016.

3) Kim, J.H.; Kim, S.K.; Lee, S.H.; Lee, T.M.; Lim, J. License plate detection and recognition
algorithm for vehicle black box. In Proceedings of the International Automatic Control
Conference (CACS).

4) Kumar, M.A Suman, M.V. Misra, Y. Pratyusha, M.G. Intelligent vehicle black box using
IoT. Int. J. Eng. Technol.

5)Watthanawisuth, N.Lomas,T.Tuantranont, A. Wireless Black Box Using MEMS

Accelerometer and GPS Tracking for Accidental Monitoring of Vehicles. In Proceedings of
the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)

6) Kang, C.; Heo, S.W. Intelligent Safety Information Gathering System Using a Smart Black
Box. In Proceedings of the IEEE International Conference on Consumer Electronics (ICCE),
Las Vegas, NV, USA.

7) Kassem, A.; Jabr, R.; Salamouni, G.; Maalouf, Z.K. Vehicle Black Box System. In
Proceedings of the 2nd Annual IEEE System Conference, Montreal, QC, Canada, 7–10 April
2008
REVIEWERS COMMENTS

1)

2)

3)