Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor

Technology for Improved Driver Safety

P Subramanyam Raju

, Mohammed Taher

†

, C Charan

‡

, M Varun Teja and S Munavvar Hussain

Department of ECE, B V Raju Institute of Technology, Narsapur, Medak(dist). Telangana, India

* † ‡

Keywords: Controller(MyRIO-1900), Anti-Sleep, Sleep Calculation, Infrared Sensor, Drowsiness Detection

Abstract: Since fatigue in drivers is a major contributing factor to traffic accidents, new safety technology is required.

The goal of this project is to lower the risk of falling asleep while driving by introducing a Pilot Anti-Sleep

Alarm system. The system uses the National Instruments myRIO platform for realtime processing, an eye

blink sensor for non-intrusive drowsiness detection, a buzzer for instantaneous alarm, and a driver circuit for

simple integration. The myRIO technology enables fast eye blink pattern analysis to identify fatigue

symptoms early. Without creating discomfort, the driver’s eyes are monitored by the infrared-based eye blink

sensor. In order to notify and wake the driver, the system uses the driver circuit to trigger the buzzer when it

detects drowsiness. By offering real-time monitoring and prompt alerts for driver weariness, this system aims

to increase road safety. In order to build a more comprehensive solution for reducing accidents brought on by

sleepy driving, further advances will involve improving detection algorithms, adding more sensors, and

working with cutting-edge driver aid systems.

1 INTRODUCTION

As the need for contemporary transportation has

grown over time, car parks must expand at faster

rates. Nowadays, a major mode of mobility for

individuals is the automobile. According to some

estimates, the total number of automobiles in use

worldwide surpasses the number of people. Even so,

the automobile has altered people’s lifestyles and

made going about everyday tasks more convenient.

Due to micro-sleeps, a drowsy driver is potentially far

more dangerous on the road than one who is speeding.

Researchers and automakers are attempting to address

this issue by developing a number of technical

solutions that will prevent a disaster of this kind. A

face feature-based real-time detection system for

driver sleepiness is introduced. The system monitors

video streams as well as records facial expressions

that indicate signs of tiredness, such as eye

movements, blinking rates, and frequency of

yawning. It has a high level of emphasis on robustness

and real-time performance under different driving and

lighting conditions (Deng and Wu, 2019). An

overview of the most recent methods for identifying

driver drowsiness is given in this study. It covers both

cutting-edge machine learning techniques and more

conventional techniques like eye tracking. The study

serves as a thorough resource for academics working

in the subject by assessing the advantages and

disadvantages of these approaches (Fernandez, Fern,

et al. , 2019). It creates a system for detection of

sleepiness combining two most crucial indicators:

head position and eye blink rate. In developing the

said study, reliable detection of the presence of sleep

behaviour is devised combining different types of

measurements and, hence can find practical

utility(Majumdar, Roy, et al. , 2019), Newer

technologies for driver drowsiness detection involve

advanced algorithms, including real-time facial

recognition and behavioural pattern analysis with

Convolutional Neural Networks (CNNs) and

Recurrent Neural Networks (RNNs). examines the

use of EEG signals for the extraction of temporal

features in order to detect tiredness. The study

provides a highly precise method for identifying early

indicators of weariness by identifying particular EEG

patterns linked to drowsinesss (Garcia, Vargas, et al.

, 2019). Video-based systems are supported by sensor

integration, such as wearable devices that are fitted

with electroencephalogram (EEG) uses infrared

sensors to track eye blinks to gauge how sleepy a

driver is. Because of its non-invasive and real-time

architecture, the device is reliable in a variety of

694

Subramanyam Raju, P., Taher, M., Charan, C., Varun Taja, M. and Munavvar Hussain, S.

Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor Technology for Improved Driver Safety.

DOI: 10.5220/0013600200004664

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 2, pages 694-701

ISBN: 978-989-758-763-4

settings, even dimly illuminated ones (Zhang and Ko,

2019) sensors to monitor brain activity. The accuracy

of detection increases in multimodal systems that

combine vehicle telemetry data (such as steering

patterns) with physiological sensors, like heart rate.

demonstrates an Android application that uses a CNN

based sleepiness detection model. In real-time, the

portable system processes face information and

records the driver’s attention (Jabbar, Shinoy, et al. ,

2020). highlights the use of respiratory rate and heart

rate variability (HRV) as a means of detecting

weariness in physiological evaluation. By

incorporating wearable sensors to continuously

evaluate these attributes, the study demonstrates early

identification of fatigue (Ko and Kim, 2020). For the

diagnosis of fatigue, a hybrid feature extraction

technique that blends physiological and video-based

data analysis is proposed. This endeavour attempts to

increase detection accuracy while maintaining

substantial processing efficiency for real-time

applications (Bourassa, Thompson, et al. , 2020). It

develops an embedded system to gauge driver

concentration by fusing sensors. By integrating

information from multiple sources, including

physiological and facial sensors, the system provides

a comprehensive solution for drowsiness detection

(Bakheet, Hamadi, et al. , 2021). An updated

Histogram of Oriented Gradients (HOG) feature-

based framework for identifying driver drowsiness is

introduced. When combined with Natıve Bayesian

classification, the method offers a strong balance

between efficiency and usability, which makes it

suitable for real-time applications (Babu, Meena, et

al. , 2020). Describes how an eye blink tracking

system is equipped with a module that can detect

fatigue. The system provides a practical means of

ensuring driver safety, with a focus on reliability and

ease of deployment (Subramanyamraju, Chinnaaiah,

et al. , 2019). suggests a novel approach for multi-

channel second-order blind identifications in the

detection of drowsiness. The study aims to accurately

identify drowsiness by the interpretation of

physiological indicators, including

electroencephalogram (EEG) data. The method offers

a compromise between computational economy and

detection accuracy (Zhang, Wu, et al. , 2019). builds

a drowsiness detection system using information from

the steering wheel. By employing adaptive neuro-

fuzzy feature selection to extract relevant attributes

from drivers’ steering behaviour, it offers a non-

invasive and efficient method of detecting early signs

of fatigue (Arefnezhad, Samiee, et al. , 2019).

Investigates the use of surface electromyography

(sEMG) data to classify driver attentiveness levels. To

assess fatigue, sEMG data is collected using a driving

simulator, and patterns of muscle activation are

analyzed. The emphasis is on high accuracy in

controlled environments (Mahmoodi, Nahvi, et al. ,

2019). presents a system based on image analysis for

monitoring driver attention. The gadget provides a

practical method of determining how sleepy a person

is by identifying eye blinks using video processing. It

also highlights the potential for integrating it into real-

time applications to enhance traffic safety(Rana,

Singh, et al. , 2019). Real-world deployment

challenges include problems with lighting conditions

inside vehicles, which can impact the accuracy of

vision-based systems. Diversity in facial features,

such as age, ethnicity, and gender, also requires

systems to be highly robust. Driver adaptation, where

individuals consciously alter expressions or head

positions, presents an additional obstacle to reliable

detection. Data privacy is an important issue since

real-time monitoring systems collect sensitive

information, which raises questions regarding

storage, usage, and possible misuse. Lack of

universally accepted standards for drowsiness

detection systems leads to inconsistencies across

different implementations. It further extends into the

detection of driver or user drowsiness using facial

feature analysis. The system recognizes all the above

with deep learning-identified drowsiness signs like

slower blink rates, eye closure, yawning, or change of

head position. Real-time processing implies the

framework is designed for immediate detection,

suitable for environments like driving or workplace

monitoring(Santhiya, Divyabharathi, et al. , 2023).

Future research may include hybrid systems that

combine vision-based methods with voice analysis to

identify slurred or slowed speech as another indicator

of fatigue. Adaptive learning models that tailor AI

systems to the unique behaviours and patterns of

individual drivers can be effective. Real-time

feedback mechanisms, such as haptic or auditory

alerts, are essential for immediate risk mitigation.

These developments provide tremendous

opportunities for improving transportation safety and

overcoming fatigue-related challenges in various

fields.

2 DEVICE AND METHOD

MyRIO-1900 is a palm-sized reconfigurable I/O

device that may be used to design and control

mechatronics and robotic systems. The myRIO is a

versatile hardware platform designed by National

Instruments, combining a real-time processor, a field-

Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor Technology for Improved Driver Safety

695

programmable gate array (FPGA), and various I/O

capabilities. It’s commonly used for rapid

prototyping, control systems, and data acquisition in

fields like robotics, mechatronics, and industrial

automation. Its blend of computing power and FPGA

flexibility makes it an attractive choice for engineers

and students looking to develop and deploy a wide

range of applications.

MyRIO is a hardware platform developed by

National Instruments that combines a reconfigurable

field-programmable gate array (FPGA) with a real-

time processor.

Figure 1: Block diagram

Figure 2: NI-myRIO 1900

A laptop running the LabVIEW platform is

connected to myRIO through Wi-Fi and LabVIEW

software data. Myrio is linked to a less integrated

human body and system. The driver’s eye activity is

detected via an Eye Blink Sensor that uses infrared

technology. The indicators of drowsiness are detected

by this non-invasive eye closure pattern monitoring

sensor. National Instruments myRIO Platform:

myRIO is chosen for processing and acquiring data in

real time. This platform serves as the main processor,

keeping track of the eye blink patterns and sending

out a signal that could trigger an alarm. Buzzer and

Driver Circuit The driver circuit is straightforward; it

connects the myRIO platform to a buzzer so that the

alarm will sound as soon as drowsiness is detected.

Acquisition and Processing of Data: In order to make

deductions about indicators of weariness, the myRIO

platform is configured to continuously receive data

from the eye blink sensor and analyze blink frequency

and length. Feeling sleepy to distinguish between

extended eye closures brought on by fatigue and

normal blinking, a threshold-based algorithm is used.

Real-time monitoring is made possible by the

algorithm’s low latency optimization. Alert

Mechanism: The myRIO platform promptly alerts the

driver by turning on the driving circuit and setting off

the buzzer when it detects drowsiness. to verify that

the sensor, detection algorithm, and alarm mechanism

are working properly, the system is first tested in a

controlled setting. Installed in a car, the technology is

tested in actual driving scenarios. Metrics including

user comfort, response speed, and detection accuracy

are used to gauge the system’s performance.

Algorithm Optimization: To increase accuracy and

decrease false positives and negatives, the sleepiness

detection algorithm is refined based on test results to

make sure the device doesn’t uncomfortable alert test

drivers or divert their attention from driving, feedback

is gathered from them. In order to guarantee a

thorough approach to road safety, this investigates

cooperation with cutting-edge driver-assistance

technologies.

3 RELATED WORK

A major area of research in pilot’s safety is the

creation of anti-sleep alarm systems for pilots that use

technology such as buzzers, eye blink sensors,

myRIO, and driver circuits to address the high risks

of accidents caused by weariness. These systems

usually use non-intrusive techniques to track the

pilot’s level of awareness in real time, paying close

attention to physiological markers including facial

expressions and eye blink frequency. Because eye

blink sensors can measure quick eye movements,

which are accurate markers of a pilot’s attentiveness,

they have been effectively adapted for usage in

aviation applications. Eye blink sensors are

commonly used in vehicle drowsiness detection.

These systems are able to identify early indicators of

tiredness by examining eye blink patterns, including

blink rate, length, and intensity. The device helps

prevent mishaps before weariness severely impairs

performance by triggering a buzzer alarm when it

detects irregular blink activity or prolonged eyelid

INCOFT 2025 - International Conference on Futuristic Technology

696

closure. This alert helps the pilot avoid accidents. The

integration of embedded systems like myRIO has

been helpful in developing portable and real-time

solutions that gather and process data from various

sources, including sensors that track head movement,

facial expressions, and physiological signals, in

addition to eye blink monitoring. The warning system

can be kept responsive in changing flight conditions

thanks to myRIO, a small and adaptable hardware

platform that can manage the computational demands

of processing big datasets. Additionally,

sophisticated machine learning algorithms have

demonstrated promise in enhancing the precision and

dependability of sleepiness detection systems,

especially those that integrate sensor data with facial

feature analysis. These algorithms lower false alarms

and increase overall system efficiency by allowing the

system to learn and adjust to each pilot’s particular

features. A more thorough method of identifying

weariness is provided by the integration of several

indications, including head position, eye blink

sensors, and machine learning-based facial

expression analysis. In order to increase the

monitoring system’s dependability, researchers have

also looked at combining eye blink detection with

steering behaviour analysis, which is typically

employed in automotive applications. Even though

there has been a lot of progress, issues like reducing

false positives and guaranteeing a smooth connection

with current cockpit systems still persist. However,

the continued advancement and improvement of

embedded systems such as myRIO, in conjunction

with sophisticated sensor technology and real-time

data processing, offer a promising path toward the

development of anti-sleep alarm systems that can

greatly increase pilot safety, lower the number of

incidents related to fatigue, and improve overall

aviation performance. By regularly assessing pilot

alertness, these technologies guarantee a proactive

approach to sleepiness management, which

eventually leads to safer and more dependable flight

operations.

4 METHODOLOGY

Alarm for Driver Anti-Sleep Employing the Driver

Circuit, Eye Blink Sensor, Buzzer, and myRIO. The

practical implementation of a driver anti-sleep

warning system using myRIO, a buzzer, an eye blink

sensor, and a driving circuit is described in this article.

To improve road safety, the technology seeks to

identify patterns of driver drowsiness and send out

appropriate alerts. Average Blink Interval = Number

of Blinks Total Duration of Observation Humans

blink approximately 15–20 times per minute,

averaging 3–4 seconds between blinks. This rate helps

lubricate and protect the eyes. Factors like fatigue,

stress, screen use, or dry environments can influence

blinking. Prolonged or frequent blinks may indicate

drowsiness or health conditions, making blink

patterns crucial for monitoring well-being. Place the

eye blink sensor such that it can see the driver’s eyes

clearly from inside the car. Using the appropriate

connectors and cables, connect the analog output of

the sensor to the analog input pins of myRIO. Buzzer

and Driver Circuit Integration: Use the driver circuit

to link the buzzer to the digital output pins on your

myRIO. Create the driver circuit to regulate the

buzzer’s activation based on the output of myRIO and

to condition the sensor outputs. Launch LabVIEW

and start a new project. Configure the digital output

channels and analog input channels after adding a

myRIO device to the project. Make a new Virtual

Instrument (VI) and create the program flow that

follows. Analog Input: Read analog data from the eye

blink sensor continuously. Decision Logic: Set a

digital output pin to sound the buzzer if drowsiness is

detected. Reset Alert: After the driver becomes more

attentive, reset the alert system. Construct the user

interface so that sensor data, detection outcomes, and

system status may be seen. Start: The system starts

functioning after booting. This might include the

turning on of hardware parts such as processors and

sensors. Eye Blinking Sensor: This part of the system

tracks the eye blinking behaviour of the user

continuously. It can decide whether the eyes are open

or closed. Blinking of the Eyes Found: No: The device

keeps running in a monitoring loop if no blinking is

seen. This entails monitoring the user’s condition

continuously. yes: The system advances to the

following stages if blinking is detected. Five second

delay: The system waits five seconds after detecting

blinking. Verifying the user’s blinking pattern’s

consistency is one purpose for this delay.

Removing quick state changes or erroneous

positives. allowing time. Now, when certain

conditions are satisfied, the machine goes into ”Sleep

Mode”. Sleep Mode can be seen as engaging control

systems to battle sleepiness. for example, slow down

system to a low activity level. Buzzer Delay: It uses

an audible buzzer to alert the driver or anyone nearby.

The delay ensures that the alarm is both timely and

clear in its message. User safety; it gives immediate

feedback on the statuses sensed gradually slows down

with control. This ensures smooth braking without

sudden stops in a car. This safeguards machines from

operational hazards or damage. Stop: Eventually,

Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor Technology for Improved Driver Safety

697

either for safety reasons or while waiting for further

user input, the system comes to a complete stop. At

this stage, the user may need to car bikes apply or

reset the system. However, in order to verify the

condition and lower the possibility of false alarms, a

5-second delay is added when aberrant blinking is

identified, suggesting possible drowsiness.

Figure 3: Flow chart

When tiredness is verified, the device switches to

sleep mode and, after a short pause, sounds a buzzer

alarm to let the user know they are tired. In order to

maintain safety and avoid collisions, the system

simultaneously starts a progressive speed reduction.

When the necessary corrective actions have been

completed, the procedure comes to an end, enabling

the system to restart or shut down. In order to

effectively reduce fatigue related events, this design

places a strong emphasis on several safety procedures,

validation, and ongoing monitoring.

5 WORKING PRINCIPLE

MyRio is developed by National Instruments (now

part of NI), the myRIO is a state-of-the-art embedded

hardware platform intended to meet the various needs

of scientists, engineers, and students. Fundamentally,

myRIO is a powerful yet small device for developing

and implementing real-time control and data-

gathering systems. It does this by fusing the

adaptability of a Xilinx FPGA with the sturdy

capabilities of a dual-core ARM Cortex-A9 CPU.

Thanks to its dual-core ARM Cortex-A9 processor,

the myRIO’s processing power allows users to run

intricate algorithms, analyze data in realtime, and

communicate with a wide range of peripherals with

ease. The addition of a Xilinx FPGA, a programmable

hardware element that enables users to create unique

digital logic circuits, complements this computing

power. Applications needing low latency, high-speed

signal processing, and specialized hardware

interfaces can benefit greatly from the FPGA’s

graphical programming environment, which can be

programmed using NI LabVIEW FPGA. An amazing

technical advancement created to record and analyze

eye movements in humans blinking in particular is the

eye blink sensor. This sensor, which was created to

handle a variety of uses, including human-machine

interaction and health monitoring, is essential to

deriving insightful information from a basic human

gesture. A key element in the field of electronics is the

driver circuit, which serves as a bridge between

control systems and different loads like motors,

LEDs, or sensors. This circuit is essential to supplying

the power, voltage, or current required to drive and

regulate various loads. It is a flexible and adaptable

component in electronic systems whose design and

operation are determined by the particular needs of

the linked load and the features of the control system.

The driver circuit, which acts as a link between

control systems and various loads like motors, LEDs,

or sensors, is a crucial component in the field of

electronics. To deliver the power, voltage, or current

needed to drive and regulate different loads, this

circuit is crucial. It is a versatile and adaptive portion

of electronic systems, its operation, and design are

dictated by the characteristics of the control system

and the specific requirements of the linked load.

frequently used in the context of motors to regulate

the torque, speed, and direction of electric motors. In

a motor control application, for example, the driver

INCOFT 2025 - International Conference on Futuristic Technology

698

circuit modifies the power provided to the motor

based on signals it receives from a microcontroller or

other control unit. This is especially common in fields

where precise control over motorized components is

crucial, like robotics, industrial automation, and

electric vehicle systems. Light-emitting diodes

(LEDs) are used in situations where the driver circuit

controls the current passing through the LEDs to

maintain a constant brightness and avoid overcurrent

damage. Dimming and colour management are two

common capabilities found in LED driver circuits.

6 RESULTS

Expected results based on the design and principles of

such a system This is the normal state of the model.

Figure 4: Normal state

Here the wheel will be continuously rotating till

the eye blinking is going to be detected. And the

rotating of the wheel is indicated with the “car shuts

on/off” led.

Figure 5: Eye blink detection

In this state when the eye blinking is detected the

“Eye closure indication” led will be glow, when eye

is again open the led turns off. In this state when eye

is closed for about 4-5 seconds the “Drowsiness

perception” led is going to be turned into red colour

so that it indicates that the drowsiness is detected. The

driver is warned with a beep sound with buzzer and

the wheel slowly slows down. When the wheel stops

rotating the “car shuts on/off” led is going to be turned

off. As the drowsiness is detected the wheel stops

rotating. Drowsiness Detection: The system should be

able to accurately detect prolonged eye closures and

patterns consistent with drowsiness in the driver.

Figure 6: Drowsiness detection

Figure 7: Wheel stops Rotating

The detection accuracy and false positive/negative

rates will vary based on the sensitivity of the

algorithms and the quality of the eye blink sensor.

When drowsiness is detected, the buzzer should be

promptly activated to emit an audible alert. The

timing and effectiveness of the alert will be a critical

measure of the system’s success in waking up the

driver. The myRIO platform’s real-time capabilities

are expected to ensure swift data processing and alert

activation, minimizing any delays between

drowsiness detection and alert generation. The

effectiveness of the system is also dependent on how

well the driver responds to the alert. Ideally, the driver

should become more alert and take appropriate

actions to avoid accidents. The system’s performance

should be evaluated in various scenarios, including

different levels of drowsiness simulation and varying

environmental conditions. The system’s accuracy,

Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor Technology for Improved Driver Safety

699

reliability, and robustness will be important indicators

of its practical utility. One of the challenges is to

strike a balance between minimizing false alarms

(false positives) and ensuring that genuine instances

of drowsiness are not missed (false negatives). The

system’s design should ensure that the alert

mechanism (buzzer) effectively wakes up the driver

without causing undue discomfort or startling them.

Rigorous testing in both controlled environments and

real-world driving scenarios is crucial to validate the

system’s performance and fine-tune its algorithms

and thresholds. For accurate and specific results, you

would need to refer to research papers, project reports,

or case studies that have implemented a similar

system and documented their outcomes. If you have

conducted such an implementation, I recommend

analysing and documenting your own results based on

your testing and experimentation.

7 CONCLUSION

A novel solution to the grave issue of driver

drowsiness, the leading cause of traffic accidents, is

the Pilot Anti-Sleep Alarm system. This device uses a

non-intrusive infrared eye blink sensor to measure

tiredness and the National Instruments myRIO for

real-time processing. To increase road safety, a

buzzer and driver circuit are included to help wake up

a sleepy driver as soon as possible. It demonstrates

pragmatism and efficacy in identifying driver

drowsiness and promptly responding, hence lowering

the number of accidents brought on by driving

fatigue. Cutting-edge technology detects tiredness

accurately without bothering users. Additionally, the

adaptability and use of this technology into a specific

vehicle can be easily incorporated into the majority of

modern solutions regarding.

REFERENCES

W. Deng and R. Wu, ”Real-Time Driver-Drowsiness

Detection System Using Facial Features,” IEEE Access,

vol.7,pp.118727118738,2019.

F. Guede-Fernandez, M. Fern ´ andez-Chimeno, J. Ramos-

Castro,M. A. ´ Garc´ıa-Gonzalez, ”Driver Drowsiness

Detection Based on Respiratory ´ Signal Analysis,”

IEEE Access,vol.7,pp.8182681838,2019.

P. Majumdar, S. Roy, and S. Dutta, ”Driver Drowsiness

Detection System Based on Eye Blink Rate and Head

Position,” International Journal of Advanced Research

in Computer Science and Software Engineering, vol. 9,

no. 7, pp. 1-6, 2019.

J. Lopez-Garcia, P. C. Vargas, and J. Delgado, ”Using

Infrared Sensors for Eye Blink Detection in Drowsiness

MonitoringSystems,”Sensors,vol.19,issue5,pp.102110

34,2019.

C. Zhang and S. J. Ko, ”EEG-Based Driver Drowsiness

Detection Using Temporal Feature Extraction,”

Neurocomputing, vol. 356, pp. 85-96, 2019.

R. Jabbar, M. Shinoy, M. Kharbeche, K. Al-Khalifa, M.

Krichen, K. Barkaoui, ”Driver Drowsiness Detection

Model Using Convolutional Neural Networks

Techniques for Android Application,” 2020 IEEE

International Conference on Informatics, IoT, and

Enabling Technologies (ICIoT), Doha, Qatar, pp. 237-

242, 2020.

S. Y. Ko and Y. T. Kim, ”Driver Drowsiness Detection

Using Heart Rate Variability and Respiratory Rate,”

Biomedical Signal Processingand

Control,vol.58,pp.101110,2020.

A. W. Bourassa, D. W. Thompson, and J. T. Fleming,

”Development of an Embedded Driver Alertness

Monitoring System,” ASME International Design

Engineering Technical Conferences (IDETC), pp.

110,2020.

S. Bakheet, A. Al-Hamadi, ”A Framework for

Instantaneous Driver Drowsiness Detection Based on

Improved HOG Features and Na¨ıve Bayesian

Classification,” Brain Sciences, vol. 11, issue 2, 2021,

doi: [10.3390/brainsci11020240].

R. V. Babu and P. K. Meena, ”Eye Blink Monitoring and

Drowsiness Detection System for Drivers,”

International Journal of Engineering Trends and

Technology (IJETT), vol. 69, no. 5, pp. 158-163, 2021.

Subramanyamraju, P., Chinnaaiah, M. C., Anusha, ”A

Portable Wireless Sleep Monitor System Using MyRIO

1900,” 2022 2nd International Conference on

Intelligent Technologies (CONIT),Hubli,India,2022

C. Zhang, X. Wu, X. Zheng, S. Yu, ”Driver Drowsiness

Detection Using Multi-Channel Second

OrderBlindIdentifications,”IEEEAccess,vol.7,pp.1182

911843,2019.

S. Arefnezhad, S. Samiee, A. Eichberger,A. Nahvi, ”Driver

Drowsiness Detection Based on Steering Wheel Data

Applying Adaptive Neuro-Fuzzy Feature Selection,”

Sensors, vol. 19,issue 4, 2019.

M. Mahmoodi A. Nahvi, ”Driver Drowsiness Detection

Based on Classification of Surface Electromyography

Features in a Driving Simulator,” Journal of

Engineering in Medicine, vol. 233, no. 4, pp.

395406,2019.

P. S. Rana, N. A. Singh, and A. Vats, ”Driver Alert System

Using Image Processing Techniques,” International

Journal of Innovative Technology and Exploring

Engineering (IJITEE), vol. 8, no. 9S2, pp. 503-508,

2019.

M. Ramzan, H. U. Khan, S. M. Awan, A. Ismail, M. Ilyas,

A. Mahmood, ”A Survey on State-of-the-Art

Drowsiness Detection Techniques,” IEEE Access, vol.

7, pp.6190461919,2019.

Santhiya, S., T. Divyabharathi, J. Jeno, and D. Kawin.

”Improved Authentication and Drowsiness Detection

INCOFT 2025 - International Conference on Futuristic Technology

700

from Facial Features using Deep Learning Framework

in Real Time Environments.” In 2023 9th International

Conference on Advanced Computing and

Communication Systems (ICACCS), vol. 1, pp. 1638-

1642. IEEE, 2023.

Pilot Anti-Sleep Alarm System Leveraging Infrared Sensor Technology for Improved Driver Safety

701