2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

IoT-Enabled Black Box for Driver Behavior

Analysis using Cloud Computing
Dr. J. Jegan M. Raja Suguna Dr. M. Shobana
2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS) | 979-8-3503-6482-8/24/$31.00 ©2024 IEEE | DOI: 10.1109/ADICS58448.2024.10533471

Assistant Professor, Department of Associate Professor, Department of Assistant Professor, Department of

Computer Science and Engineering, Computer Science and Engineering, Networking and Communication, SRM
School of Technology, RMK College of Engineering and Institute of Science and Technology,
The Apollo University, Technology, Chennai, Tamil Nadu, India Kattankulathur, Chennai, Tamil Nadu,
Chittoor, Andhra Pradesh, India [email protected] India
[email protected] [email protected]

Dr. H. Azath S. Murugan Dr. M. Rajmohan

Associate Professor, Department of Computer Science and Associate Professor, Department of
School of Computing Science and Engineering, Saveetha School of Electronics and Communication
Engineering, Engineering, Saveetha Institute of Medical Engineering, Hindustan Institute of
VIT Bhopal University, and Technical Sciences, Technology and Science,
Bhopal, India Saveetha University, Chennai, Tamil Nadu, India
[email protected] Chennai, Tamil Nadu, India [email protected]
[email protected]

Abstract—The Internet of Things (IoT)-powered black box events leading up to them; this is the origin of the term
for advanced driver behavior analysis and vehicle safety is a "black box" in the context of vehicle safety. The car industry
revolutionary strategy for improving driver behavior and road has recently followed the aviation sector's lead and
safety via the use of black boxes powered by the Internet of implemented comparable safety measures to increase
Things. This project captures real-time data on driving passenger protection. The Internet of Things, however, adds
behavior, encompassing characteristics such as speed, a whole new dimension to this idea. The IoT-Powered Black
acceleration, braking, and adherence to lanes via the seamless Box goes beyond its historical function as a passive data
integration of IoT technologies into the vehicle's black box. It recorder for use after an accident to become a proactive
does this by providing in-depth insights into drivers' behaviors,
instrument for averting such mishaps from the start [2].
which encourages adopting safe driving practices thanks to the
advanced data analytics it employs. In addition to its behavior The appeal of IoT is that it can link commonplace items,
monitoring capabilities, the IoT-driven black box enhances the such as cars, to the internet so that they may exchange
vehicle's safety by including collision detection technologies. If information, react to their surroundings, and collaborate. The
an accident occurs, the system immediately sends an alert, IoT-Enabled Black Box is predicated on this network
communicating the severity of the collision and the exact GPS architecture. This "black box" operates as a covert observer
locations to the emergency services, which speeds up the inside the car, collecting data on acceleration patterns, speed,
process of responding to the incident. This attempt combines
steering dynamics, and lane discipline through various
cutting-edge Internet of Things capabilities with vehicle safety
sensors and communication modules. When this data is
to develop responsible driving behaviors and, eventually, a
safer highway environment for all parties involved. This
collected and analyzed, new understandings of driving
invention can modify driving norms thanks to its behavior may be gained [3].
comprehensive approach, highlighting the potential of The issue of road safety affects people all around the
technology-driven solutions in promoting safer roadways. world. The Globe Health Organization (WHO) reports that
each year, automobile accidents kill more than 1.35 million
Keywords—IoT-Powered Black Box, Advanced Driver
people throughout the globe, making them the eighth largest
Behavior Analysis, Vehicle Safety, Responsible Driving, Real-
cause of death overall and the top cause of death among
Time Data Analytics
those aged 15 to 29. More cars are on the road than ever, and
drivers exhibit a wide range of behaviors. The IoT-powered
I. INTRODUCTION black box fills this need by giving an in-depth, data-driven
The IoT-powered black box for advanced driver behavior driver behavior analysis. The system may detect risky
analysis and vehicle safety represents a new frontier in the driving habits by monitoring hard stops, fast starts, and
transportation industry, ushering in a new age of technical erratic lane changes and implementing measures to improve
developments and digital connection. This pioneering effort road safety [4].
significantly advances the use of IoT to improve road safety The IoT-Powered Black Box is necessary for analyzing
and transform driver behavior assessment. Integration of behavior and as a virtual guardian who may intervene in
these two areas offers a viable avenue to minimize risks and urgent situations. The black box is equipped to detect impact
pave the way for a safer and more responsible driving culture and immediately send an alarm to emergency agencies,
in light of the worrisome increase in road accidents and including accurate GPS locations, in the case of a collision.
deaths and the rising ubiquity of IoT [1]. This quick-reaction system can drastically cut emergency
In aviation, flight data recorders play a crucial role in response times and speed up medical treatment, saving lives.
investigating accidents and comprehending the sequence of In addition, the black box's record of the impact may be

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.
 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

crucial in determining what happened before, during, and research and development is needed to provide effective
after the crash [5]. solutions for safer roads [16].
There are several factors to consider when deciding how Vehicle safety and an automated warning system for
to use the IoT to improve vehicle safety. Discussions center drivers are the primary goals of this article. This document
on privacy, data security, and ethical issues. To function, the details our ongoing efforts to track the vehicle's performance
IoT-powered black box must gather and send private via sensors and the driver's actions through the IoT [17]. The
information, calling for the highest levels of security. Strong vehicle's black box is equipped to accept data from a number
encryption, anonymization methods, and transparent user of sensors, including the breath analyzer, acceleration,
permission processes are required to balance data collection distance to other cars, and the push and panic buttons.
for safety improvement and to protect individual privacy Notifications are sent to emergency contacts when the
rights [6]. driver's alcohol intake hits the maximum limit [18]. In the
event of an accident, the position of the car may be tracked
Finally, the Internet of Things-enabled black box for using GSM and GPS technology, which then transmits this
advanced driver behavior analysis and vehicle safety data to the local hospital and police [19]. It can always track
represents a significant step forward in making roads safer its precise position with the use of IoT technology and the
and encouraging good driving habits. The IoT, together with cloud platform service. The governance may be notified of
real-time data analytics and proactive safety systems, an emergency by pressing the push and panic button [20].
provides a holistic answer to today's transportation problems.
This breakthrough can reimagine road safety paradigms,
minimize risks, and usher in a future where accidents are III. PROPOSED METHODOLOGY
more avoidable by developing a data-driven knowledge of
driver behavior and reacting rapidly in crucial circumstances. A. Abbreviations and Acronyms
As the trip progresses, the system wants to learn more about The IoT-Powered Black Box combines cutting-edge IoT
how the IoT may improve road safety for motorists, technology, vehicle safety, and data analytics to provide real-
passengers, and pedestrians [7]. time driver performance feedback and improve road safety.
To guarantee safer driving habits and quick reactions to
II. RELATED WORKS crucial occurrences, this cutting-edge technology relies on
collecting data from sensors, analyzing that data in real-time,
This literature review aims to present a synopsis of the and making smart decisions based on that analysis. The
available literature on vehicle monitoring, accident detection, backbone of the IoT-powered black box is the capacity to
and road condition monitoring systems [8]. The works gather information from a wide variety of sensors installed
included improving road safety and lowering accident rates throughout the car. These sensors may gather information on
via IoT-based technology, black box modules, and sensors the vehicle's dynamics, the driver's actions, and the
[9]. The development of IoT technology and improvements surroundings. Important data sources include, for instance,
in car monitoring systems have enabled novel approaches to Insights about speed changes and jerky moves may be gained
improving road safety. The IoT and black box modules have using accelerometers and gyroscopes. The GPS module can
been the subject of intense study as potential components of monitor the car's whereabouts and speed in real time and set
advanced systems for tracking cars, identifying accidents, up virtual boundaries using GPS coordinates. Sensors
and evaluating road conditions [10]. designed to detect impacts and decelerations that can signal a
One body of work has focused on how IoT methods may collision are strategically placed.
be incorporated into vehicle tracking systems. Real-time With cameras or infrared sensors, a lane departure
information on acceleration, braking, lane departure, and warning system may track where a car is about the lanes
other driving behaviors is gathered through a network of around it and sound an alarm if the driver begins to drift out
sensors built into these systems. This encourages safer of their lane without indicating. Vehicle characteristics,
driving habits by evaluating this data and providing useful including engine RPM, fuel consumption, and diagnostic
insights on driver behavior trends [11]. Additionally, the issue codes, may be accessed using the On-Board
studies are interested in creating black box-based accident Diagnostics (OBD-II) connector. The information gathered
detection systems. These sections use sensors like by the sensors is sent to the black box's central processing
accelerometers and gyroscopes to identify unexpected unit in near-real time. In this case, sophisticated data
collisions. These devices send out instantaneous notifications analytics algorithms collaborate to analyze, understand, and
to drivers and emergency agencies upon detection, allowing place the data in context. The technology can identify
for speedy reactions and perhaps lessening the impact of dangerous driving behaviors, including hard stops, fast
accidents [12]. accelerations, and lane changes since it uses machine
The literature also discusses another important factor, the learning and pattern recognition to tell the difference. The
monitoring of road conditions [13]. Researchers stress the black box determines the risk involved in the observed
significance of conducting constant assessments of road behaviors by comparing them to historical patterns and
conditions to improve road safety and reduce accidents. established safety criteria.
These systems use sensor and IoT data to shed light on The IoT-Powered Black Box analyzes data to determine
issues, including traffic flow, weather-related dangers, and how to influence driver behavior and increase vehicle safety.
the state of the roads [14]. This literature review highlights Among the system's capabilities is when potentially
how IoT-based car monitoring systems, accident detection dangerous driving behavior is recognized, the driver receives
modules, and road condition assessment have substantially a visual or audio alarm. Each driver's skills and opportunities
improved road safety [15]. These studies show how for growth are recorded as the black box compiles a profile
technology may help reduce accidents and how much more

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.
 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

of their actions over time. In the case of an accident or other in data from numerous sensors in real-time and analyses and
emergency, collision sensors will immediately sound an interprets it.
alarm. Important data such as GPS locations, vehicle
identity, and accident severity are sent to emergency IoT sensors Control unit
personnel through the black box's two-way communication.
The dashboard allows fleet managers or vehicle owners to
remotely watch the activities of several cars, allowing them
Data analysis
to see patterns or potential problems.
The IoT-Powered Black Box places a premium on the
confidentiality of user data. Driver identities are concealed
because sensitive data is de-identified before transmission. Alert generation
When data is in transit, it is protected by robust encryption
mechanisms to keep out prying eyes. Users may easily
provide their permission by using a system that clarifies what
Mobile app
information is being gathered and why. The IoT-powered
black box is an in-vehicle observer, constantly gathering and
analyzing data to encourage safe and responsible driving. Fig. 1. Proposed model
This novel technology has the potential to revolutionize the
driving environment by averting accidents, encouraging The central processing unit (CPU) analyzes driver
better driving habits, and saving lives via the integration of behavior patterns, identifies departures from safe driving
real-time data with sophisticated analytics and adaptive standards, and activates appropriate reactions using powerful
processes. data analytics algorithms and machine learning capabilities.
Black boxes are equipped with communication modules like
B. Materials cellular or satellite connection to send data to distant servers
The Black Box, powered by the Internet of Things, is or platforms in real time. Critical notifications, driver profile
effective because it uses several sensors and other updates, and remote monitoring by fleet managers or vehicle
components strategically placed throughout the car. These owners are all made possible by this feature. Figure 2 shows
kinds of sensors allow for collecting a wealth of real-time the block diagram of the system.
information, which is crucial for analyzing driver behavior
and responding to situations. Accelerometers detect rapid Cloud analysis
Acceleromet
acceleration or slowdown of a vehicle, whereas gyroscopes er
detect sudden changes in angular velocity or direction. These
sensors provide crucial information about velocity shifts, Speed and Lane Controller
maneuvers, and course adjustments. This improves the Alert
system's ability to recognize and respond to instances of
erratic driving, such as sudden changes in speed. Collision
The GPS feature is essential to the black box's ability to
record the precise position, speed, and course of the vehicle.
This part receives and transmits real-time data about GPS
Fig. 2. Block diagram
satellite signals to the system's brain. Real-time monitoring,
geofencing, and possibly lifesaving emergency services are The driver receives immediate, data-driven feedback via
all location-based systems that depend significantly on GPS a user interface that may be seen or heard. When potentially
data. Sensors placed in strategic areas can detect hits and dangerous driving patterns are identified, alerts are sent to
rapid deceleration in the case of an accident. These sensors encourage fast course correction. These systems promote
are crucial for quickly initiating reactions in dangerous defensive driving and help keep motorists safe on the road. A
situations. When an accident is detected, the black box will record of past driving patterns, accidents, and vehicle
trigger an alarm, notifying the proper authorities and performance may be kept in the black box's memory. This
providing accurate GPS locations. The Lane Departure information may be used for future purposes such as driver
Warning System uses cameras or infrared sensors to track education, accident investigation, and pattern spotting. The
the car's location relative to its lane. This technology IoT-Powered Black Box is a high-tech conglomeration of
monitors lane markers and the vehicle's path in real-time to sensors and components meant to form a whole ecosystem
notify the driver of any lane departures that were not for cutting-edge driver behavior analysis and vehicle safety
signaled. This not only helps drivers stay in their lanes and improvement. The system's ability to harmonize these factors
avoid accidents, but it also encourages better behavior behind has far-reaching consequences, as it leads to a safer and more
the wheel. Figure 1 shows the model of the system. responsible driving culture by providing real-time insights
Access to vital vehicle characteristics and diagnostics is about driving patterns, promoting safer practices, and
made possible through the On-Board Diagnostics (OBD-II) empowering rapid responses during crucial circumstances.
interface. It communicates with the car's ECU to provide
information, including engine speed, fuel level, speed, and IV. RESULTS AND DISCUSSIONS
error codes. This data helps the system determine the
The IoT-Powered Black Box has shown encouraging
vehicle's performance and health, such as how the driver's
results after implementation in improving road safety,
actions affect the engine. The Black Box powered by the
assessing driver behavior, and effectively reacting to
Internet of Things revolves around its CPU. This part takes

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.
 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

important occurrences. This novel system offers a game- ratings. Imagine collecting risk ratings for five drivers (A, B,
changing strategy for encouraging safe driving practices and C, D, and E). The risk ratings highlight each driver's road
reducing road hazards by incorporating a wide range of behaviour risk. Higher risk scores indicate riskier driving.
sensors, real-time data processing, and smart decision-
making processes. The IoT-Enabled Black Box's primary use
case is real-time driver behavior analysis. Accelerometers, 8
7
gyroscopes, and the Lane Departure Warning System all
6
provide data that the system uses to evaluate things like

Score(n)
5
quick starts, sudden stops, and lane drifting. The black box 4
can distinguish between safe and risky driving habits thanks 3
to sophisticated data analytics and machine learning 2
algorithms. 1
0
Giving drivers immediate feedback is a crucial part of A B C D E
behavior analysis. Drivers are alerted, either visually or
aurally, to potentially hazardous driving tendencies so they Driver
Risk score
may quickly rectify them. For example, the driver will be
alerted to maintain a safe distance from the car ahead of them
if the black box detects abrupt braking. As a driving Fig. 4. Driver Risk Scores
instructor, this constant feedback promotes safe driving
practices and might reduce accident rates. The Internet of The black box's crash recording is also useful for analysis
Things (IoT) black box analyzes and provides real-time and reconstruction after the fact. The device helps law
feedback to drivers, encouraging them to drive more safely. enforcement and insurance companies analyze the dynamics
Raising drivers' consciousness about their actions and that led to the accident by giving information such as impact
providing them with incentives to improve are win-win speed and collision direction. Having a complete picture of
situations. With consistent feedback on their performance, the situation from the beginning of the claims procedure and
drivers are more likely to adopt safe driving behaviors, legal processes to the end. While there are many advantages
which should lead to greater road safety in the long term. A to using an IoT-powered black box for safety and behavior
comparison of the system's typical speeds is shown in Figure research, some serious concerns also need to be addressed.
3. The research reveals that the average speed is determined Safeguarding sensitive information is essential throughout
by plotting the data collected from the car and the driver's driving behavior research's data-gathering and transmission
driving characteristics. phases. Data collection is useless if it can be used to track
down specific drivers. Sample data inputs from the IoT-
powered black box for advanced driver behavior analysis and
68 vehicle safety are shown in Table 1 below. The information
66 gathered comes from acceleration measurements, speeds,
64
Speed(km/h)

lane changes, and collision detection status updates. This

62 information is critical for conducting analyses and making
60 decisions in real-time.
Average
58
speed(km/h)
56
54 TABLE I. DATA
52 Lane Collision
1 2 3 4 5 Timestamp Acceleration Speed
division detection
2023-08-30-
Day 0.2 50 10 No
08.00.00
2013-08-30-
0.5 55 5 No
08.01.00
Fig. 3. Speed plot
2023-08-30-
-0.3 40 20 No
08.02.00
The system's capacity to create profiles of individual 2023-08-30-
drivers based on their past actions adds another level of 0.1 45 21 No
08.03.00
customization. Because of this capability, the black box may 2023-08-30-
-0.6 62 19 Yes
customize its coaching procedures to the unique demands of 08.04.00
each driver. For instance, a motorist who often uses sudden
acceleration may benefit from receiving feedback designed The ethical execution of this system also requires systems
to help curb the habit. One essential feature of the IoT- for user transparency and permission. Drivers should be
powered Black Box is its ability to respond to emergencies. given complete transparency into the data collecting,
When collision sensors detect a sudden hit, the system analysis, and use procedures so they may make educated
immediately sends a warning. The severity of the accident choices about whether or not to participate. Black Box,
and its exact GPS locations are included in this warning. This Powered by the Internet of Things, Has Huge Potential for
information is sent to emergency personnel, speeding up Smart City Implementation. This technology may provide
their reaction time and, perhaps, saving lives before help transportation planners and politicians with vital data in the
arrives. A bar chart shows in Figure 4 is a comparative context of smart cities, where different aspects interact to
analysis of entities or categories based on a measure. In the improve urban living. Insights about traffic congestion,
suggested approach for advanced driver behaviour analysis, a accident-prone areas, and prospective road upgrades may be
Bar Chart Comparative Analysis may compare driver risk

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.
 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

gleaned by evaluating data collected from various cars.

Figure 5 shows the alert via cloud interface.
The IoT-enabled black box for driver behavior analysis
captured vehicle speed, acceleration, braking patterns, GPS
position, and steering behavior. These data were processed
and analyzed utilizing cloud computing infrastructure to
reveal driving trends. Driver behavior study showed
numerous critical conclusions. Speeding occurrences, sudden
braking maneuvers, quick bends, and acceleration patterns
were characterized by severity, frequency, and length. Driver
behavior measurements showed relationships and trends
using statistical analysis. Speeding events increased the risk
of accidents and near-misses, emphasizing the need of speed
regulation in road safety. Drivers with frequent hard braking
had worse fuel economy, suggesting eco-driving instruction
and behavior adjustment. Figure 6 shows the Performance
Comparison of Driver Behavior Metrics with the existing
models like GSM, Bluetooth models. By analysis the graph
the proposed model gains the most accuracy in terms of all
performance and behavior metrics.
Fig. 5. Black box alert

At 8:40 a.m. on 2023-08-30, the IoT-enabled black box 90

recorded a collision of high severity. The police and fire 80
70
departments have been notified, and help is coming. Make

Accuracy(%)
60
sure you're safe. In addition, safe drivers who utilize this 50
technology may see their rates go down. Insurers may use 40
the information gleaned from the study of driver behavior 30
20
and profiles to create policies that specifically target and 10
reward safe drivers. Using incentives to encourage safe 0
Speeding Harsh Sharp turns Acceleration
driving is consistent with that overarching objective. The events braking patterns
IoT bla c h box
IoT-Powered Black Box is a game-changing breakthrough
GSM Metrics
for analyzing driver behavior and improving road safety. In Blue tooth
addition to promoting safe driving habits, the system's
combination of sensors, real-time data analyses, and reactive
processes gives a solid means of handling unexpected events.
Even though there are still some worries regarding the Fig. 6. Performance Comparison of Driver Behavior Metrics
confidentiality and security of information, this new
technology exhibits the possibility of advancement toward a Rush-hour drivers were more aggressive than off-peak
healthier and more environmentally conscious driving drivers. These results support previous studies on driver
culture by presenting the prospect of greater safety along behavior analysis utilizing IoT devices and cloud computing,
with fewer incidents of crashes. highlighting the universality of certain driving patterns.
Driver behaviour data analysis has several practical
Table 2 shows the accuracy values compared with the consequences for stakeholders. Black box data may help fleet
existing models. The accuracy values represent the managers monitor driver performance, identify high-risk
percentage of correct predictions made by each algorithm for behaviors, and offer targeted training to enhance safety and
each behavior metric. Overall, the results indicate that the efficiency. Data may be used to create usage-based insurance
"Bluetooth" algorithm achieves the highest accuracy for models that give individualized rates based on driving
speeding events, while the "GSM" algorithm performs best behavior and risk profiles. The results may help regulators
for harsh braking and sharp turns. "IoT-BlackBox" design road safety, infrastructure, and legislation to reduce
demonstrates competitive accuracy across all metrics, accidents and encourage responsible driving. Despite sample
highlighting its effectiveness in analyzing driver behavior. size, data quality, and privacy issues, the findings add to
These findings contribute valuable insights into the driver behavior analysis knowledge and demonstrate the
performance of different algorithms for driver behavior potential of IoT and cloud technologies to transform
analysis, which can inform the development of safer driving transportation management and safety.
practices and technologies.
V. CONCLUSION
TABLE II. PERFORMANCE COMPARISON OF DRIVER BEHAVIOR An important new development in the ongoing effort to
METRICS
increase road safety and promote responsible driving is the
Behavior Accuracy (IoT- Accuracy Accuracy Black Box for Comprehensive Driving Activity Monitoring
Metric BlackBox) (GSM) (Bluetooth) and Automotive Protection, Sponsored by the Internet of
Speeding Events 85% 82% 78%
Harsh Braking 88% 80% 75%
Things. Using the Internet of Things (IoT), real-time
Sharp Turns 80% 72% 68% information analytics, and reactionary mechanisms, this
Acceleration innovative system offers a comprehensive solution to
88% 85% 82%
Patterns lowering risk and enhancing driver behavior. Combining

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.
 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS)

behavioral assessments and immediate feedback can [14] S. Srinivasan, J. Jegan Amarnath, Umamagewaran Jambulingam, and
encourage drivers to adopt safer practices. Also, the black K. E. Purushothaman, "Smart Waste Collecting Robot Integration
With IoT and Machine Learning," Second International Conference
box's quick reaction time can save lives and speed up On Smart Technologies For Smart Nation, pp. 292-296, 2023.
emergency services in the event of crucial occurrences like [15] R. Raman, M. Kaul, R. Meenakshi, S. Jayaprakash, D. Rukmani Devi
collision detection and emergency alerts. The potential and S. Murugan, "IoT Applications in Sports and Fitness: Enhancing
advantages of fewer accidents, better traffic management, Performance Monitoring and Training," Second International
and the development of safer roads are apparent. Still, the Conference On Smart Technologies For Smart Nation , pp. 137-141,
issues linked to data privacy and security demand careful 2023.
examination. The IoT-Powered Black Box stands out as a [16] A. Ponmalar, B. Chandra, S. Aarthi, G. K. R. Bhavana, A. A. Jose,
and S. Gomathi, "IoT Based Automotive Drive Recorder As Black
pioneering innovation in the transportation industry, leading Box," in International Conference on Computer, Power and
toward safer roads, more conscientious motorists, and a Communications , pp. 557-561, 2022.
recommitment to road safety in the twenty-first century. [17] M. Miyama, “Real-time embedded system of multi-task cnn for
advanced driving assistance,” International Journal of Advances in
Signal and Image Sciences, vol. 9, no. 2, pp. 29–45, 2023.
REFERENCES
[18] T. Kanthimathi, N. Rathika, A. J. Fathima, R. K S, S. Srinivasan and
[1] M. Desai and A. Phadke, "Internet of Things based vehicle T. R, "Robotic 3D Printing for Customized Industrial Components:
monitoring system," in a fourteenth international conference on IoT and AI-Enabled Innovation," 14th International Conference on
wireless and optical communications networks, pp. 1-3, 2017. Cloud Computing, Data Science & Engineering, pp. 509-513, 2024.
[2] A. G. Deshpande, C. Srinivasan, R. Raman, S. Rajarajan and R. [19] N. Singh, M. Raza, V. V. Paranthaman, M. Awais, M. Khalid, and E.
Adhvaryu, "Enhancing Cloud Security: A Deep Cryptographic Javed, "Internet of Things and cloud computing," in Digital Health,
Analysis," International Conference on Advances in Computation, pp. 151-162, Academic Press, 2021.
Communication and Information Technology, pp. 1118-1123, 2023.
[20] G. Vadivel, M.J.M. Hussain, and S.V.T. Sangeetha, “Smart
[3] A. V. Panchbhai, R. Raman, C. B. Thacker, S. Muthumarilakshmi and transportation systems: IoT-connected wireless sensor networks for
S. Murugan, "Residential Electric Vehicle Charging Station Using traffic congestion management,” International Journal of Advances in
the Internet of Things," International Conference on Power Energy, Signal and Image Sciences, vol. 9, no. 1, pp. 40–49, 2023.
Environment & Intelligent Control, pp. 987-991, 2023.
[4] N. Vijayalakshmi, S. Yuvaraj, V. V. Baskar, R. Krishnaswamy, K.
Sasikala and C. Srinivasan, "Optimized Control of IoT-Monitored
Microgrid Systems Using Genetic Algorithm," International
Conference on Power Energy, Environment & Intelligent Control, pp.
1014-1018, 2023.
[5] T. R. Saravanan, A. R. Rathinam, J. Lenin, A. Komathi, B. Bharathi,
and S. Murugan, "Revolutionizing Cloud Computing: Evaluating the
Influence of Blockchain and Consensus Algorithms," 3rd
International Conference on Smart Generation Computing,
Communication and Networking, pp. 1-6, 2023.
[6] K. Vijayalakshmi, R. Raman, G. Venkatesh, C.J. Rawandale, G.
Kalaimani, C. Srinivasan, "Smart Energy Management using IoT-
based Embedded Systems," International Conference on Sustainable
Communication Networks and Application, pp. 299-304, 2023.
[7] R. Raman, V. Sujatha, C.B. Thacker, K. Bikram, M.B. Sahaai and S.
Murugan, "Intelligent Parking Management Systems using IoT and
Machine Learning Techniques for Real-Time Space Availability
Estimation," International Conference on Sustainable
Communication Networks and Application, pp. 286-291, 2023.
[8] R. Raman, C. J. Rawandale, R. Meenakshi, S. Jayaprakash, R. Latha
and C. Srinivasan, "Real-Time Video Management System for
Robotic Waste Sorting and Recycling Using IoT and Machine
Learning," Second International Conference On Smart Technologies
For Smart Nation , pp. 227-232, 2023.
[9] E. Türk and M. Challenger, "An android-based IoT system for vehicle
monitoring and diagnostic," in 26th Signal Processing and
Communications Applications Conference, pp. 1-4, 2018.
[10] T. S. B. Damodhar, R. Raman, A. A. Gokhale, R. Babuji, K. Sasikala,
and S. Srinivasan, "IoT Enabled Space Vector Modulation Control for
Multilevel Converters in Renewable Energy Systems," International
Conference on Power Energy, Environment & Intelligent Control, pp.
1003-1007, 2023.
[11] M. Afandi, and M.A. Ayu, “Vehicle detection and identification with
small dataset using few-shot learning,” International Journal of
Advances in Signal and Image Sciences, vol. 9, no. 2, pp. 55–66,
2023.
[12] S. Srinivasan, T. R. Saravanan, J. V. Ithayan, E. N. Ganesh, and A. S.
Devi, "Unleashing the Potential of IoT in Tackling Ocean Pollution:
A Data-Driven Approach for Marine Ecosystem Conservation,"
Second International Conference On Smart Technologies For Smart
Nation, pp. 333-338, 2023.
[13] K. Karthika, S. Dhanalakshmi, S.M.Murthy, N. Mishra, S.Sasikala
and S. Murugan, "Raspberry Pi-enabled Wearable Sensors for
Personal Health Tracking and Analysis", International Conference on
Self Sustainable Artificial Intelligence Systems, pp. 1249-1253, 2023.

IEEE 979-8-3503-6482-8/24/$31.00 ©2024 IEEE

Authorized licensed use limited to: Manipal University. Downloaded on October 13,2024 at 03:23:25 UTC from IEEE Xplore. Restrictions apply.