iot based drivers fatigue monitoring system using machine learning6051
A dataset of various drivers while driving will be adopted and considered to be classified according to condition of a driver. Usual classes of a driver while driving a vehicle include normal, happy, tired or sleepy. To detect the severity, we use machine learning based video classificat
2025-06-28 16:33:25 - Adil Khan
A dataset of various drivers while driving will be adopted and considered to be classified
according to condition of a driver. Usual classes of a driver while driving a vehicle include
normal, happy, tired or sleepy. To detect the severity, we use machine learning based video
classification model. The machine learning method detects, in which condition currently a
driver is. This information can be used to alert the authorities and nearby vehicles to handle the
situation when the driver is feeling sleepy. It can help to avoid the accidents and big damage.
We will be using neural network model to extract the features in a video and recurrent neural
network method to classify the videos accordingly.
TO MONITOR THE DRIVER’S FATIGUE USING IOT
AN AUTOMATED SYSTEM
Project Implementation MethodThe emergence of artificial intelligence and the rapid development of electronic and
information technology provide more opportunity to detect driver fatigue using machine
learning approaches. Deep learning is proving to be a very helpful in every field of life of
humans to provide easy and accuracy simultaneously. There is a need to promote road safety
as well using machine learning.
Problem Statement:
Road safety is becoming a big concern as we move toward a technological world. Drivers health
is necessary to be checked during driving not only to protect others with but outside a vehicle.
So, it is crucial to promote the technologies for detecting driver fatigue.
Proposed Methodology:
A dataset of various drivers while driving will be adopted and considered to be classified
according to condition of a driver. Usual classes of a driver while driving a vehicle include
normal, happy, tired or sleepy. To detect the severity, we use machine learning based video
classification model. The machine learning method detects, in which condition currently a
driver is. This information can be used to alert the authorities and nearby vehicles to handle the
situation when the driver is feeling sleepy. It can help to avoid the accidents and big damage.
We will be using neural network model to extract the features in a video and recurrent neural
network method to classify the videos accordingly.
Drivers' fatigue monitoring.
less mishaps.
Save deaths
Automatic handling of vehicle
save passengers
Technical Details of Final DeliverableAutomated system
managed vehicle
AI based implementations
Auto controlling
auto messaging
Alarm generation
Final Deliverable of the Project HW/SW integrated systemCore Industry ITOther IndustriesCore Technology Internet of Things (IoT)Other TechnologiesSustainable Development Goals Industry, Innovation and Infrastructure, Life on LandRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 70000 | |||
| Sensors | Equipment | 12 | 1500 | 18000 |
| Display Screens | Equipment | 1 | 10000 | 10000 |
| Ardino | Equipment | 4 | 2000 | 8000 |
| GPS module,Multi-sensor Modules | Equipment | 1 | 3000 | 3000 |
| Cables, Resistors, Batteries | Equipment | 2 | 10000 | 20000 |
| Hardware and Models | Equipment | 1 | 10000 | 10000 |
| Chips and other accessories | Equipment | 1 | 1000 | 1000 |