SkullCap – An IoT based Smart Helmet for Accident Detection - PPT

November 22, 2024 CSD 416 1
MAR BASELIOS INSTITUTE OF TECHNOLOGY AND SCIENCE
NELLIMATTOM, KOTHAMANGALAM
SkullCap – An IoT based Smart Helmet for
Accident Detection
DEPARTMENT
OF
COMPUTER SCIENCE AND ENGINEERING
Guided by:
Asst. Prof. Teena Skaria
Project Guide
Dept. of CSE
Presented By: Group 11
Arjun Saji (MBI19CS015)
Basil Pappy Roy (MBI19CS018)
Basil Varghese (MBI19CS019)
Geevarghese S Isaac (MBI19CS030)

Contents
• Abstract
• Introduction
• Literature Surveys
• Drawbacks of existing system
• Proposed System
• Modules
• Architecture of proposed system
• Method of implementation
• Hardware and software requirements
• Data Flow Diagram

Contents
• Screenshots
• Conclusion
• Future Scope
• References

Abstract
• A smart helmet is designed which is capable of detecting fall of riders and then
transmitting a message through a global system of mobile (GSM) module along
with the location of fall using global positioning system (GPS) avoiding delays to
rescue.
• Accelerometer sensors with a three axis sensing unit, are placed within the helmet
and controlled via ARDUINO based microcontroller for fall detection.

Introduction
• Every 5 minutes, a person dies in a road accident! Still the cases increase each year.
• These deaths have one thing in common, the victim is left to die on the road even
though the hospitals and authorities are very near. People die even though they’re
taken only 10-15 mins late.
• This is because the human brain can survive only 3-6 minutes without Oxygen,
thus, taking the injured to the hospital quickly should be a priority.
• There must be a way to quickly inform authorities within seconds of an accident.
We may use GPS and normal SMS technology for that and detect sudden impact of
gravity.

Literature survey
1. Automatic Fall Detection Using Smartphone Accelerometer
• The proposed technique consists of 2 algorithms: fall detection and long lie
detection.
• The former is used to check the occurrence of a fall, while the latter is used to find
out if there is a lying down state after that fall.
• The proposed technique is then implemented as an Android application for
experiment.

Literature survey
2. Combined Smart Watch And Smart Phone Fall Detection System
• This paper specifically looks into the accuracy of a fall detection system based on
an off-the-shelf smartwatch and smartphone.
• In this system which combines threshold based and pattern recognition techniques
in both devices, with the intent of having the watch to contribute to the specificity
of the fall detection strategy.

Literature survey
3. Smart Helmet An Intelligent Bike System
• In order to overcome this they has introduces an intelligent system, Smart Helmet,
which automatically checks whether the person is wearing the helmet and has non-
alcoholic breath while driving.
• An alcohol sensor is placed near to the mouth of the driver in the helmet to detect the
presence of alcohol. MCU controls the function of relay and thus the ignition, it control
the engine through a relay and a relay interfacing circuit.
• If rider getting drunk it gets automatically ignition switch is locked, and send message
automatically to their register number with their current location. The distinctive utility
of project is fall detection, if the bike rider fall from bike it will send
message automatically.

Literature survey
4. Fall Detection for Elderly Persons Using Android-Based Platform
• Since fall event has become the most common accident occurred among elderly
persons, the development of fall detection system has received much attention in
recent years.
• By simultaneously considering the detections for linear and non-linear
movements, the proposed system achieves an accuracy of 92.5%, which is an
improvement of 12% as compared to the previous scheme

November 22, 2024 CSD 416 10
Literature survey
5. SPEEDY: A Fall Detector in a Wrist Watch
• It present a wrist worn fall detector for elderly people.
• The detector is easy to wear and offers the full functionality of a small
transportable wireless alarm system.
• The system combines complex data analysis and wireless communication
capabilities in a truly wearable watch-like form.

November 22, 2024 CSD 416 11
Literature survey
6. Android Based Fall Detection Alert System using Multi-Sensor
• An enhanced fall detection system is proposed for elderly person monitoring that is
based on-body sensor operating through consumer home networks.
• By utilizing information gathered from an accelerometer, cardiotachometer and
smart sensors, the impacts of falls can be logged and distinguished from normal
daily activities.
• This system is connected to GPS and GSM for communication purpose which is
unique.

November 22, 2024 CSD 416 12
Literature survey
7. Falls, Injuries Due to Falls, and the Risk of Admission to a Nursing Home
• Falls warrant investigation as a risk factor for nursing home admission because
falls are common and are associated with functional disability and because they
may be preventable.
• The primary outcome studied was the number of days from the initial assessment to
a first long-term admission to a skilled-nursing facility during three years of
follow-up.

November 22, 2024 CSD 416 13
Literature survey
8. A Dynamic Motion Pattern Analysis Approach To F&l Detection
• The algorithm works on the digital signal output from waist-mounted
accelerometry.
• It first filters noisy components with a Gaussian filter; secondly sets up a 3D body
motion model which relates various body postures to the outputs of accelerometry;
finally a dynamic detection process is applied to make decision.
• Our work is an important part of elder care and rehabilitation.

November 22, 2024 CSD 416 14
Literature survey
9. A Smartphone-based Fall Detection System
• Thus, the caregiving process and the quality of life of older adults can be improved
by adopting systems for the automatic detection of falls.
• This paper presents a smartphone-based fall detection system that monitors the
movements of patients, recognizes a fall, and automatically sends a request for help
to the caregivers.
• To reduce the problem of false alarms, the system includes novel techniques for the
recognition of those activities of daily living that could be erroneously mis detected
as falls (such as sitting on a sofa or lying on a bed).

November 22, 2024 CSD 416 15
Literature survey
10. Recognition Of False Alarms In Fall Detection Systems
• The detrimental effects of falls, as well as the negative impact on health services
costs, have led to a great interest on fall detection systems by the health-care
industry.
• This paper presents a novel approach for improving the detection accuracy which is
based on the idea of identifying specific movement patterns into the acceleration
data.

November 22, 2024 CSD 416 16
Drawbacks of existing system
• Inconvenience due to wearing/attaching the sensor on a part of the body
• Detection is difficult outside the area where the sensor is installed
• False alarms frequently occur
• Deployment of the environmental sensors based systems is limited to
indoor environments

November 22, 2024 CSD 416 17
Proposed system
• We’ve researched and innovated a significant addition to the existing “protective-
helmets,” that will automatically detect the accident, as well as report the accident’s
location to the nearest police station through SMS. It also alerts the nearby people
through an emergency buzzer.

November 22, 2024 CSD 416 18
Proposed system
Detection Mechanism
• An Accelerometer, for
detection of accidents
by identifying the
sudden change in the
person’s position &
acceleration.
• A GPS Module, to
find out the location
of the accident.
Power Source
• 9V Batteries have been
used due to their longer
duration of use & their
efficiency.
Alerting Mechanism
• A GSM Module, for
messaging & alerting the
authorities by providing
the location of the
accident.
• A Buzzer, so that nearby
people can be gathered
for quick help.

November 22, 2024 CSD 416 19
Architecture of proposed system
 List of Modules
• Helmet Design
• Data Acquisition
• Feature Extraction And Selection
• Classification

Accelerometer
GSM
Module
Data Acquisition
Feature Extraction and
Selection
Classification
Gathers Sensor Data
Extracts
Features
Location
Data
Pre-processing
Arduino Uno R3 Board
GPS
Module
Fall
Detection
Motion
and
Orientatio
n
Detection
Alert Message
with Location
Smart Helmet
Emergency Contact
Smart Helmet Architecture

November 22, 2024 CSD 416 21
Modules
 Helmet Design
• Input: Requirements and specifications for the smart helmet, such as the sensors to
be integrated, the size and weight of the helmet, and the materials to be used.
• Output: A functional and ergonomic design of the smart helmet that meets the
specified requirements.
• Function: A well-designed helmet is critical for the success of the smart helmet
project, as it ensures that the sensors are accurately and reliably capturing the
necessary data while also being comfortable and safe for the wearer.

November 22, 2024 CSD 416 22
Modules
 Data Acquisition
• Input: Data from sensors such as GPS and accelerometer.
• Output: Digital signal of the captured data.
• Function: Captures and processes sensor data for accurate and reliable
measurement of the helmet wearer's activity and location, performs initial data
processing, and passes the data to other modules for analysis and transmission.

November 22, 2024 CSD 416 23
Modules
 Feature Extraction and Selection
• Input: Raw data collected from the sensors.
• Output: Extracted and selected features that are relevant and useful for further
analysis.
• Function: Feature extraction and selection are critical steps in data analysis, as they
reduce the complexity and dimensionality of the data while preserving the most
relevant and informative aspects.

November 22, 2024 CSD 416 24
Modules
 Classification
• Input: Extracted and selected features from the sensor data.
• Output: Classification results, such as predicted labels or probabilities, indicating
the class or category of the data.
• Function: Classification is a fundamental task in data analysis, as it enables
automated decision-making and identification of relevant patterns or anomalies in
the data.

November 22, 2024 CSD 416 25
Methods of Implementation
• The user puts on the helmet and turns on the system using the switch.
• The accelerometer sensor detects any sudden movements or impacts, and sends this
data to the Arduino board.
• The GPS module determines the location of the helmet wearer and sends this data
to the Arduino board.
• The Arduino board processes the data received from the sensors and sends control
signals to the buzzer.
• If the sensors detect any sudden movements or impacts, the buzzer produces an
audible warning or alert to the helmet wearer.

November 22, 2024 CSD 416 26
Methods of Implementation
• The Arduino board also sends the location data to the GSM module for data
transmission.
• The GSM module transmits the location data wirelessly over a cellular network to a
remote server or a mobile phone.
• The system continues to monitor the helmet wearer's location and movement, and
provides warnings or alerts if necessary.
• The user can turn off the system using the switch when they are no longer using the
helmet.

November 22, 2024 CSD 416 27
System Requirements
Software Requirements
• Arduino IDE
• GPS library
• GSM library
• Accelerometer library
• Operating System
Hardware Requirements
• Arduino board
• GPS module
• GSM module
• Accelerometer sensor
• Buzzer
• Switch
• Battery

November 22, 2024 CSD 416 28
Level-0 Data Flow Diagram

November 22, 2024 CSD 416 29
Level-1 Data Flow Diagram

November 22, 2024 CSD 416 30
Screenshots

November 22, 2024 CSD 416 31
Conclusion
• A helmet is designed to detect fall and avoid delays to rescue automatically.
• An IoT-based Smart Helmet for accident detection offers enhanced safety in daily life.
• Sensors, connectivity, and intelligent algorithms are integrated into the helmet to detect
accidents and provide timely alerts.
• The helmet's sensor suite includes accelerometers, and impact sensors for real-time
monitoring.
• The Smart Helmet can quickly detect abnormal patterns indicating potential accidents, such
as falls or collisions.
• Immediate notifications can be sent to emergency services, designated contacts, or nearby
personnel for prompt assistance.
• The helmet's GPS module enables accurate location tracking, aiding emergency responders
in finding the injured person quickly.

November 22, 2024 CSD 416 32
Future Scope
• Integration with other sensors for health and well-being monitoring.
• Wireless charging for convenience and ease of use.
• Real-time data analytics for safety and efficiency improvements.
• Cloud integration for advanced features like real-time tracking and remote
maintenance.
• Machine learning algorithms for hazard detection and prediction.
• Augmented reality for additional visual information and guidance.

November 22, 2024 CSD 416 33
References
• Reference to a journal publication:
[1] H. R. Choi, M. H. Ryu, Y. S. Yang, N. B. Lee, and D. J. Jang, “Evaluation of algorithm for the fall and fall direction
detection during bike riding,” Int. J. Control Autom., 2013.
• Reference to a book:
[2] P. P. Chitte, S. S. Akshay, N. T. Aniruddha, and T. B. Nilesh, “Smart Helmet & Intelligent Bike System,” Int. Res. J.
Eng. Technol., vol. 3, no. 5, 2016.
• Reference to a chapter in an edited book:
[3] N. R. Singh1 , P. R. Rothe2 , and A. P. Rathkanthiwar3 , “Android Based Fall Detection Alert System using Multi-
Sensor,” Int. J. Eng. Trends Technol., vol. 46, 2017..
• Reference to a website:
[4] K. de Miguel, A. Brunete, M. Hernando, and E. Gambao, “Home camera-based fall detection system for the
elderly,” Sensors, vol. 17, no. 12, p. 2864, 2017..
• Reference to a dataset:
[5] T. Tri, H. Truong, and T. Khanh, “Automatic Fall Detection using Smartphone Acceleration Sensor,” Int. J. Adv.
Comput. Sci. Appl., 2017.

November 22, 2024 CSD 416 34
THANK YOU

SkullCap – An IoT based Smart Helmet for Accident Detection - PPT

More Related Content

Similar to SkullCap – An IoT based Smart Helmet for Accident Detection - PPT (20)

Recently uploaded (20)

SkullCap – An IoT based Smart Helmet for Accident Detection - PPT