www.rsisinternational.org
Page 5828
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Sensor Technology in Intelligent Transportation Systems - Lane
Departure Warnings
Ahmed Oyeyemi
1
, Adebakin Osoja
2
, Olasunkanmi O. Olasokan
3
, Opeyemi Fadipe
4
1 2
Department of Transportation and urban infrastructure systems, Morgan State University,
Baltimore, Maryland, USA.
3
Registry Department, Lagos State University of Science and Technology, Ikorodu, Lagos, Nigeria
4
Department of Industrial Systems Engineering, Morgan State University, Baltimore, Maryland, USA.
DOI: https://dx.doi.org/10.47772/IJRISS.2025.910000479
Received: 02 November 2025; Accepted: 08 November 2025; Published: 17 November 2025
ABSTRACT
This study offers a thorough analysis of the vital role that mobility plays in economic growth, especially in
emerging nations where the proliferation of vehicles and the deterioration of infrastructure coexist. In order to
synthesise previous research on the topic and determine if Lane Departure Technology is beneficial in reducing
traffic accidents, the study used a scoping review methodology. In order to analyse the significance of the
technology adoption in the reduction of detrimental effects that transportation activities have on the
environment and society, the study emphasises the necessity of Smart Transportation Systems (STS),
sometimes referred to as Intelligent Transportation Systems (ITS). According to the study, a variety of
sensors—including infrastructure-, vehicle-, and device-based sensors—are critical to the efficiency of ITS.
These sensors gather data in real time for traffic control and safety enhancements. A key component of this
system is Lane Departure Warning Systems (LDWS), which use sensors like cameras, Lidar, or radar to track
lane locations and issue alarms, greatly enhancing road safety. However, the result points out a number of
obstacles to the broad use of ITS and LDWS, including sensor limitations, environmental considerations, high
prices, and privacy issues, especially in poor nations. Notwithstanding these difficulties, LDWS has been
demonstrated to improve overall vehicle performance and traffic flow by raising driver awareness and
lowering accident rates. Promising improvements in lane recognition accuracy and driver behaviour prediction
are possible with the incorporation of AI and machine learning into LDWS. In order to create safer and more
effective transport systems, this study emphasises the significance of ongoing investment and innovation in
ITS and LDWS.
Keywords: Intelligent Transportation System (ITS), Sensor, Artificial Intelligence (AI), Smart Transportation
System (STS), Transportation
INTRODUCTION
According to Osoja et al. (2022), transportation is the movement of products, services, or people from one
place (the origin) to another (the destination). This can be done by air, rail, sea, or road. Any economy needs
transport, which is also a typical tool for socioeconomic development (Oyeyemi et al., 2025). This is
significant in a global economy as the flow of people and things, including information and communication
technology, is related to economic possibilities (Olasokan and Toki, 2021). Vehicles are becoming
increasingly common in both urban and rural regions as emerging countries' populations grow rapidly and
living conditions improve.
The number of vehicles per capita (VpC) is a well-known metric used to track the progress of this
phenomenon. The development of transport networks has been critical to the economic growth of all countries.
This exceptional growth in Vehicles Per Capita (VpC), which is common in cities in developing nations
throughout the world and is linked to infrastructure decline in those countries, is out of date, and investment in
www.rsisinternational.org
Page 5829
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
its renewal lags far behind VpC. This problem is exacerbated by geopolitical factors because 10 of the 15 most
populous landlocked countries are in Africa; thus, they lack access to the sea, and with a total population of
300 million, the countries rely heavily on land and air transport to sustain economic growth (Casal and Selamé,
2015).
In today's linked world, the Smart Transportation System (STS) is critical for addressing the environmental
issues related to transportation operations. The STS is the standard for developing next-generation
technologies. Qureshi and Abdullah (2020) describe the STS as a distinct discipline that works in a variety of
fields, including the transportation industry, which encompasses operations, policy, control techniques, control
systems, and transportation management strategies. The remuneration paid for STS missions varies
substantially. The introduction of STS has the potential to drastically reduce risks linked with high accident
rates, traffic congestion, carbon emissions, and air pollution.
An Intelligent Transportation System (ITS) is one component of Smart City Transportation development. In
contrast, many developed economies throughout the world have used ITS to increase safety and dependability,
traffic flow, travel speeds, and passenger happiness across all forms of transportation. An intelligent transport
system is now widely employed in industrialised nations to avoid and decrease traffic accidents, thanks to
several research projects and efforts. In recent decades, as global urbanisation has progressed, an increasing
number of people have moved to cities. The expansion in city population has undoubtedly caused a number of
internal challenges, including land usage and supply-demand mismatch. In response to these concerns, smart
cities have received a lot of attention to explore sustainable development using sophisticated technology and
environmental principles to alleviate recognised issues.
Smart city development thus entails integrating Intelligent Transportation Systems (ITS) into the city
transportation system, to apply information, communication, and sensor technologies to vehicles and
transportation infrastructure in order to provide real-time information to road users and transportation system
operators to help them make better decisions (Meneguette et al., 2018). ITS utilises electronic information
technology to optimise traffic concerns. The notion of intelligent transport systems was initially proposed in
1991 (Bazzan & Klügl, 2022). Over ITS has grown rapidly over the last decade as a result of advances in
computer speed, mixed with sensors that capture a wide range of data from transportation infrastructure.
ITS enables the precise, real-time estimate of present and future traffic conditions, allowing for traffic
forecasting and prediction. ITS enhances transportation system mobility and efficiency by reducing congestion
while also boosting traveller information and convenience. Furthermore, ITS enhances public transit and
promotes sustainable development. ITS also increases road safety and security. The development of ITS surely
improves citizens' travel experiences while highlighting the advantages of smart travel.
A STS is made up of three major components: the transportation management system, which includes
regulatory bodies and traffic rules; the primary transportation infrastructure, which includes cars, buses, and
road networks; and, most importantly, the integration of information and communication technology (ICT),
which includes the Internet, cellular networks (4G/5G), cloud/edge computing, and the Global Positioning
System (GPS). These proposals all have one thing in common: they incorporate ICT into transportation
networks. The Internet of Things (IoT) enables the combination of data from roads, traffic controllers, and
cameras with real-time traffic movement information from various modes of transportation, including vehicles,
buses, boats, trains, and aeroplanes (Hilmani,2020).
In ITS, the use of numerous sensors is the most fundamental instrument for building the overall framework.
The first phase in information collection is frequently to detect and analyse continuous or discrete data using
sensor recognition, followed by additional management and decision-making utilising communication
technology, electronic control technology, and so on. Designing and placing multiple sensors reasonably can
increase data collection accuracy while also lowering energy and maintenance expenses.
Scholars have used computer technology to enhance sensor safety and accuracy. Cao et al. (2021) were the
first to employ machine learning to investigate the safety of self-driving cars based on LiDAR perception.
However, the variety of in-vehicle sensors results in constantly rising data gathering, necessitating increasingly
www.rsisinternational.org
Page 5830
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
powerful computers and data processing technology. Furthermore, diverse sensor manufacturers' production
and application standards provide substantial challenges to sensor development; this requires close
communication and collaboration between investors and traffic administrators.
ITS coverage is determined by the deployment of sensors on roadways. Cameras and laser speed sensors can
be put in urban traffic networks to collect real-time road conditions for specific sections, allowing traffic
management to learn about traffic flow features and trends over time. In parking lots, numerous types of
sensors can monitor car identifying information and outwardly show the utilisation status. Road sensors can be
classified as environmental sensors or data sensors based on the type of data collected. Environmental sensors
are generally used to monitor road conditions such as weather, ice, and damage. They assist in cutting road
maintenance expenses and human resource usage.
Data sensors offer direct information about the traffic network to transportation management departments and
users, laying the groundwork for the development of intelligent transportation systems. Odat et al. (2017)
suggested a novel sensing device that combines passive infrared (PIR) sensors with ultrasonic rangefinders to
monitor vehicles, estimate speeds, and identify vehicle types. Researchers have significantly improved sensor
accuracy while substantially reducing mistakes. ITS still has a fundamental challenge, though, which includes
the effective integration of data from a variety of sensor types. Additionally, this study is important and will
likely necessitate future advances.
The hectic pace of many cities throughout the world makes people look for solutions to problems relating to
transportation. Intelligent transport systems have been put in place by a number of developed nations,
including the US, UK, Germany, and Singapore, to improve the speed and convenience of transit within their
borders. Nevertheless, STS is not widely accepted in underdeveloped nations, as the majority of them have not
yet completely embraced the idea. Only in their big cities have a few nations, like Nigeria and a few other
African nations, started to use this approach.
A range of technologies is used by Intelligent Transportation Systems (ITS) to enhance traffic efficiency,
lessen congestion, and improve road safety. Lane departure warning (LDW) systems are one of these
technologies that are essential for lowering accidents brought on by sleepiness or inattention on the part of
drivers. Thus, the purpose of this study is to investigate sensor technologies in intelligent transportation
systems, specifically focusing on Lane Departure Warning. To achieve the aim, underlisted objectives were
adopted:
1. To examine the type of sensors, technologies used in the Lane Departure Warning System (LDWS)
2. The effectiveness of the sensors, technologies in the mitigation of Road accidents
LITERATURE REVIEW
Evolution of Intelligent Transportation System (ITS)
The development of Intelligent Transportation Systems (ITS) is a reflection of technological breakthroughs
and a growing emphasis on enhancing the sustainability, safety, and efficiency of transportation. As a result,
the 1960s and 1980s are when this transformation began. Controlling traffic signals and a simple monitoring
system using timers and sensors were the main goals of the first attempt. Data challenges during the initial
acceptance period prompted the integration of electronics in the 1980s and 1990s, which in turn led to the
automated collection of traffic data, the development of computerised systems for incident management and
traffic signal control, and the installation of electronic signs to inform drivers in real time about road closures
and traffic conditions.
In order to enable automobiles to connect with traffic signals and other infrastructure, communication
technologies were integrated during the 1990s and 2000s as a result of the heavy traffic in Europe and the USA
at this time. This system employs GPS and mobile technologies to provide drivers with access to real-time
traffic information through applications and navigation systems. Advanced technology was introduced
www.rsisinternational.org
Page 5831
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
between the 2000s-2010s, popularly known as the Intelligent Transportation System (ITS), which integrates
information, communication, control, computer technology, and other modern technologies to deploy a real-
time, flexible, and efficient transportation management system. The concept was introduced by the United
States and Europe in the 20th century. However, the technology was confronted by some challenges in its
implementation, like integration of heterogeneous data from various sources, implementation cost,
unavailability of expertise in this area, and also the dissemination problem.
Nowadays, the technology has been globally accepted, and it has spread to other countries such as Japan,
Singapore, Korea, and some European countries. From 2010 to the present, the technology attention is now
more on sustainability and safety, which involves the integration with environmental monitoring to reduce
emissions and promote eco-friendly transportation. Autonomous Vehicle (AV) has also been introduced,
which allows the development of self-driving technology and its integration into existing transportation
systems. It promoted a shift towards integrating various transportation modes into a single accessible service
platform, enhancing user convenience. The growing use of cloud computing and next-generation cellular
networks, such as fifth generation (5G) or beyond 5G, have made this possible. These technologies are used
differently in different networks.
Sensors used by the Intelligent Transportation System
The relationship between the sensing capabilities of Intelligent Transportation Systems (ITS) and the range and
depth of services they offer is crucial for creating a comprehensive and effective transportation ecosystem. The
categorisations from the sensor level are as follows:
1. Vehicle-based sensors,
2. Infrastructure-based sensors, and
3. Device-based sensors.
Vehicle-based sensors: According to Guerrero-Ibanez, Zeadally, and Contreras-Castillo (2018), vehicle-based
sensors are a broad category of devices integrated into automobiles to gather and analyse different types of
data. These provide information on the environment around the vehicle, road conditions, and other
environmental factors. Examples of these include LiDAR, cameras, temperature, humidity, and air quality
sensors. They make it possible for functions like pollution tracking, weather monitoring, lane departure alarms,
and object detection. Speed, braking, engine, fuel consumption, pollution sensors, energy meters, cameras, and
LiDAR are examples of vehicle-specific sensors that track performance, energy efficiency, emissions, and
energy consumption. By enabling energy management, environmental compliance, fuel efficiency assessments,
and vehicle diagnostics, these sensors increase the uptake of zero-emission vehicles and lessen dependency on
fossil fuels.
Infrastructure-based sensors: An Intelligent Transportation System (ITS) uses infrastructure-based sensors,
which are a group of gadgets positioned inside the infrastructure to carry out certain tasks (Soga and Schooling,
2016). These sensors may monitor road conditions; for example, pavement quality analysers and surface
temperature sensors are put immediately on the road to constantly analyse pavement conditions, detect cracks
and potholes, and track temperature swings. To gather vital vehicle data like identity, classification, speed, and
weight, vehicle presence and behaviour sensors—including weigh-in-motion systems, LiDAR, and license
plate recognition cameras—are positioned at traffic signals, overhead structures, or roadside gantries. These
sensors enable autonomous vehicle (AV) technology and enhance traffic enforcement and control.
Device-based sensors: Personal electronics like smartphones, wearables, and connected gadgets are equipped
with device-based sensors. These sensors gather a range of information, such as position from GPS sensors,
motion from gyroscopes and accelerometers, light and proximity data, and environmental data like humidity
and temperature. Visual data may be gathered using cameras and other image sensors. Real-time traffic
monitoring, travel analysis, personalised navigation, crowd sensing for road conditions, and incident reporting
are just a few of the applications for the data collected by these sensors in Intelligent Transportation Systems
(ITS). Device-based sensors can also record user-specific information, such as biometrics, for health and
driving monitoring. They make real-time data collection and personalised services possible.
www.rsisinternational.org
Page 5832
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Role of Data in Intelligent Transportation Systems
Travel behaviour patterns may be analysed using location data to improve transportation services, promote
shared mobility choices, and minimise the number of individual car journeys. Furthermore, through feedback
and recommendations, these sensors can encourage user involvement and behavioural change, resulting in
more energy-efficient transportation choices. An algorithm on an edge device, the cloud, or a central processor,
which might be a deterministic algorithm or artificial intelligence, examines the supplied data and returns
navigation suggestions for each car, while traffic lights get timing and management directives. Such a situation
might immediately pave the way for sophisticated traffic management tactics like cooperative adaptive cruise
control (CACC) and smart junction management, resulting in a large increase in EER.
Furthermore, intelligently changing traffic signal timings and vehicle routing recommendations can decrease
idle time at crossings (as seen in Figure 1). Reduced idle time results in lower fuel use and hence lower
pollution levels. Excessive braking and acceleration may be avoided with appropriate vehicle speed and
following distance adjustments based on current and anticipated traffic conditions. This improves traffic flow
and lowers fuel consumption. Emissions are quickly reduced when less gasoline is used. Additionally, by
removing the need for abrupt acceleration and stopping, which wastes fuel and worsens vehicle wear and tear,
these systems encourage more comfortable driving habits. By promoting smoother driving and more constant
speeds, these gadgets increase energy efficiency and reduce pollution.
Figure 1: Hybrid sensing collaboration.
Source: Omar Rinchi, Ahmad Alsharoa1 and Ibrahem Shatnawi, and Anvita Arora, 2024
Overview of Lane Departure Warning Systems
Lane Departure Warning Systems (LDWS) are cutting-edge safety features that notify drivers when their cars
inadvertently stray from their assigned lanes. This is especially critical to preventing accidents caused by
inattentive or sleepy drivers. LDWS usually alerts the driver by means of tactile, visual, or audible input.
Sensors, including lidar, radar, and cameras, are the main tools used by LDWS to keep an eye on road lane
markers. The system examines how the car is positioned in relation to these lane markers.
The evolution of LDWS over time is a reflection of improvements in safety regulations, driver aid systems,
and automotive technology. These developments initially surfaced in academic and research contexts in the
early 1980s, with an emphasis on the potential to improve vehicle safety. Its early usage is distinguished by the
use of basic image processing methods for lane marker recognition. The first commercial systems were
introduced in the 1990s as a result of additional technology advancements, mostly in luxury automobiles. For
the purpose of monitoring lane markers, these devices employed crude camera technology. In order to give the
driver input, it also resulted in the integration with the Anti-Braking System (ABS).
The 2000s saw more advancements, including better image processing algorithms that increased lane
recognition accuracy and enabled greater performance across a range of driving circumstances. Additionally,
there was a greater emphasis on car safety, which prompted regulatory agencies to look at lane departure
www.rsisinternational.org
Page 5833
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
warning systems and encourage automakers to use them. By the 2010s, Lane Departure Warning (LDWS) had
become a commonplace feature in many new cars, especially luxury and mid-range models. As the systems
developed, they added new features like lane keeping assistance, which helped drivers navigate their cars back
into their lanes while also warning them. Other advanced driving assistance systems (ADAS), such as adaptive
cruise control and collision avoidance systems, were further integrated with the LDWS.
Since the 2020s, LDWS has changed to include AI and machine learning. LDWS's capacity to precisely
identify lane markings and forecast driver behaviour is being improved by the application of AI and machine
learning. LDWS technologies are being included in autonomous driving systems as cars become more fully
automated, enabling smooth operation on both urban and interstate roadways. Putting more emphasis on
usability and driver experience while making sure that notifications are clear and unobtrusive.
Functionality of Lane Departure Warning Systems
LDWS has played a pivotal role in transportation management. The technology is often integrated with other
safety features, such as lane keeping provides comprehensive support to drivers in the following ways:
1. Accident Prevention: LDWS significantly reduces the risk of accidents caused by unintentional lane
departures. Research indicates that LDWS significantly reduces the likelihood of lane departure-related
accidents. Studies have shown that vehicles equipped with LDWS technology experience lower accident
rates compared to those without.
2. Increased Driver Awareness: The alerts encourage drivers to stay attentive and focused on the road.
3. Enhanced Safety for Vulnerable Road Users: By preventing lane drift, these systems help protect
pedestrians and cyclists.
Operational Mechanism of LDW Systems
The operational mechanism of LDWS typically involves the following steps:
1. Data Acquisition: Data plays a significant role in the operation of LDWS; Sensors gather data about the
vehicle's position, speed, and the surrounding environment, which are then used for reference.
2. Lane Detection: The vehicles have sensors installed on them. The sensor processes available data to
identify lane markings and assess whether the vehicle is staying within its lane.
3. Driver Alert: The system detects an unintended lane departure; therefore, it activates an alert mechanism
on the vehicle, such as a visual warning on the dashboard, auditory signals, or steering wheel vibrations.
Types of Sensors in Lane Departure Warning System
Lidar Sensors
An alternative to camera-based detection in LDWS is the use of radar and Light Detection and Ranging (Lidar)
sensors. While the Radar Sensors can measure the distance and speed of adjacent cars and help detect lane
departures by studying vehicle movement patterns, the Lidar technology employs laser pulses to produce a 3D
image of the surroundings, providing great precision in lane boundary identification.
Camera-based systems
Camera-based sensors are one of the most common technologies used in LDW systems. Camera-based sensors
in LDWS are essential components that help monitor a vehicle's position relative to lane markings on the road.
Camera-based sensors in an LDWS use a front-mounted video camera to detect lane markings on the road.
Algorithms then analyse the camera's continuous video feed to monitor the vehicle's position within its lane. If
the system detects the vehicle drifting out of its lane unintentionally (without a turn signal), it provides a
warning to the driver, which can be visual, auditory, or a steering wheel vibration, prompting the driver to steer
back into the lane.
www.rsisinternational.org
Page 5834
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Radar Sensors
Radar uses radio waves to detect the proximity of the vehicle and the speed of the object. The system is less
common for LDWS; they can complement other sensor types in providing a more comprehensive detection
system.
Sensor Modalities for Lane Detection
1. Camera-Based Sensors: The camera-based sensor utilises optical imaging to capture road conditions and
lane markings. It works best under good weather conditions, as it enables it to capture high-resolution
images and provide detailed information about lane markings and the surrounding environment, and it is
cost-effective and widely available in consumer vehicles. However, one of the limitations of the sensor is
performance can degrade in low-light conditions, adverse weather (e.g., rain, fog), or when lane markings
are worn or obscured.
2. LIDAR (Light Detection and Ranging): LIDAR creates a three-dimensional map of the surroundings by
measuring the distances between objects using laser pulses. Because it can identify lane borders even in
situations when markers are not evident, it is incredibly precise, thorough, and efficient in a variety of
weather conditions. However, its usage is restricted due to its high cost and the complexity of integration
into automobiles.
3. Radar: Radar is more effective in low visibility situations (such as fog or rain) and is less impacted by
illumination than cameras since it employs radio waves to determine an object's position and speed. The
sensor's poorer resolution in comparison to cameras and LIDAR is its limitation. As a result, it is more
frequently employed for speed and distance measurements than for lane markers.
Lane Detection Methods
1. Convolutional Neural Networks (CNNs): A class of deep learning models specifically designed for
processing grid-like data, such as images. It can automatically learn features from raw pixel data,
improving accuracy in diverse conditions. It is effective for detecting complex lane shapes and occlusions.
Its limitation is that it requires large amounts of labelled data for training, and is computationally intensive
and may necessitate specialised hardware (e.g., GPUs).
2. Semantic Segmentation Networks (e.g., U-Net, SegNet): networks built for pixel-by-pixel classification
tasks, which provide a thorough comprehension of the picture. Distinguishes between various road
elements and offers accurate lane marker division. It works well in a range of weather and lighting
settings. Its training needs a variety of datasets and can be resource-intensive.
3. Recurrent Neural Networks (RNNs): Networks that are helpful for temporal analysis and can analyse
data sequences. It can improve tracking over time by taking temporal information into account for lane
detection. However, compared to feed-forward networks, it is longer to train and more complicated.
Current Lane Detection Methods
Recently, with the help of technological advancement and modelling, LDWS has evolved to include the
underlisted, just to mention a few:
1. Semantic Segmentation: i. The method allows for accurate lane marker recognition by giving each pixel
in an image a class label. U-Net is the name of the algorithm that is employed. Its design, which records
both spatial and contextual information, makes it useful for lane detection even though its primary use is
biological picture segmentation. Additionally, Deep Lab was released; it improves segmentation accuracy
by capturing multi-scale context using atrous convolution. The segmentation approach can distinguish
between lanes and other road characteristics because of its great accuracy in recognising lane markers,
including intricate curves and forms. The technique is computationally demanding and requires a sizable
dataset for training to maximise efficiency.
www.rsisinternational.org
Page 5835
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
2. Anchor-Based Detection: i. This method recognises lane lines in photos by using pre-established anchor
boxes. In order to forecast lane lines using the characteristics that are derived from the picture, the
approach necessitates dividing the images into a grid and placing anchors at certain locations. This
approach adapts quicker R-CNN algorithms for lane identification. The system can adjust to various lane
arrangements and is effective at recognising numerous lanes in a single pass. The approach may have
trouble with uneven lane shapes or missing markers since it heavily relies on the quality of anchor box
placement.
3. Curve-Based Line Models: i. These models represent lane borders as curves rather than straight lines by
using mathematical functions. Polynomial or spline functions are used to depict lane markers. To
accommodate different road geometries, the road curvature is computed. In comparison to linear models,
the approach may give smoother lane prediction and is hence more appropriate for curving roads and
complicated lane designs. When compared to a linear model, it can offer a smoother lane prediction.
However, for the model to work well, an accurate initial estimate of lane location is necessary. Higher-
order polynomials may become more computationally difficult.
4. Hough Transform: A traditional image processing method for identifying straight lines in pictures is the
Hough transform. These methods convert the image into a parameter space in which lines may be
recognised according to their distances and angles. The method has a minimal computing cost and is
straightforward and efficient for identifying distinct lane markers. The method is less successful for
curving lanes and has trouble detecting straight lines due to noise and abnormalities in lane markers.
5. Optical Flow: ii. This technique tracks lane markers by analysing object motion between successive
frames. It is capable of estimating lane continuity by computing the displacement of lane characteristics
over time. The technique improves resilience to occlusions and transient impediments and works well in
dynamic contexts where lane markers may be altered. The technique needs favourable starting
circumstances and is sensitive to changes in illumination. In situations where speed is high, performance
may suffer.
6. Machine Learning Approaches: To categorise pixels or picture areas as lane or non-lane, the method
uses conventional machine learning techniques, including Support Vector Machines (SVM) and Random
Forests. Compared to deep learning techniques, it may be learnt on fewer datasets and is frequently
simpler to use and comprehend. In complicated contexts, the method is less precise than deep learning
techniques, and feature engineering—which can be labour-intensive—is necessary.
Lane Detection Algorithm
Classical vs. Deep Learning
1. Performance: Deep learning algorithms generally outperform classical methods in complex
environments, particularly in varied lighting and weather conditions.
2. Data Requirements: Classical algorithms require less data and are easier to implement, while deep
learning methods require large datasets for effective training.
3. Robustness: Deep learning models show greater robustness to variations in lane markings and
environmental conditions.
4. Computational Resources: Classical algorithms are less resource-intensive, while deep learning models
typically require significant computational power.
LDWS Integration Approaches
LDWS can be integrated into a vehicle safety system to enhance overall safety and driving experience,
adopting the following approaches:
1. Lane Keeping Assist (LKA): This method improves lane-keeping reliability by sharing data from the
same sensor (camera), resulting in a smooth experience. When the car veers out of its lane, it alerts the
driver. By automatically guiding the car back into place (the lane) if the driver does not react, LKA goes
one step further.
www.rsisinternational.org
Page 5836
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
2. Adaptive Cruise Control (ACC): When LDWS is combined with ACC, the system may automatically
adapt to the speed of the car in front of it while modifying the speed based on traffic flow and lane
position. This keeps the car in its lane and at a safe distance.
3. Collision Avoidance Systems (CAS): CAS integrates collision avoidance with LDWS data. The car can
react quickly and more accurately in circumstances where veering out of the lane may result in an accident.
When the system detects possible crashes, it applies the brakes or sounds a warning as a preventative
measure.
4. Blind Spot Monitoring (BSM): BSM improves lane change safety by warning drivers of cars in their
blind areas when they try to change lanes while LDWS is engaged. In order to stop dangerous moves, it
may also send out extra alerts if a car is in the blind spot.
5. Traffic Jam Assist (TJA): In traffic bottlenecks, LDWS can help by making sure the car stays in its lane.
By automatically regulating direction and speed, the device assists drivers in navigating through heavy
traffic.
6. Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) Communication: Vehicles may
connect with infrastructure (such as traffic lights) and with each other thanks to V2V and V2I
technologies. By offering data about impending road conditions, lane closures, or traffic patterns, the
technological integration can improve LDWS's efficacy.
7. Driver Monitoring Systems: These systems keep an eye on drivers' conduct and attentiveness, warning if
they exhibit any indications of inattention or tiredness. The driver monitoring system can take control by
triggering additional safety features or sending out more intense warnings if the driver is not responding to
LDWS notifications.
Impact on overall vehicle performance and safety
Lane Departure Warning Systems (LDWS) have a significant impact on overall vehicle performance and
safety. Here’s an overview of their effects:
1. Improved Driver Awareness: By giving drivers visual and audio warnings when they inadvertently stray
from their lane, LDWS improves driver visual awareness and helps them maintain concentration on the
road, which makes our roadways safer. It also helps minimise distraction; LDWS enables the driver to
concentrate better on driving responsibilities, particularly during lengthy trips or in boring situations.
Accident Prevention: Lane-Drift Accidents are less common because of LDWS. According to studies,
lane-departure accidents—which are frequently brought on by driver weariness or distraction—can be
considerably decreased by LDWS (Riexinger et al., 2019).
2. Complementing Other Safety Systems: LDWS can offer a multi-layered safety strategy, significantly
reducing the chance of accidents when combined with other safety features like blind spot monitoring and
collision avoidance.
Better Vehicle Control: LDWS aids in maintaining vehicle stability and control, particularly in inclement
weather, and it helps notify drivers of lane deviations. The car may actively direct itself back into the lane
when equipped with desired technology, such as Lane Keeping Assist (LKA), improving control and
lowering the chance of losing it.
3. Greater Driving Confidence: LDWS also boosts driving confidence, which can help novice and
inexperienced drivers by giving them more encouragement and certainty when they're behind the wheel.
Therefore, knowing that the technology may help maintain lane position increases driver confidence while
doing longer trips.
4. Data Collection and Analysis: Manufacturers and researchers may evaluate driver behaviour and
enhance future safety systems by using LDWS to gather data on driving trends. The input from LDWS
may be used to improve algorithms and the system's efficacy, which will support continued advancements
in car safety technology.
5. Notable Decrease in Traffic Congestion: Lane departure incidents are less common due to LDWS. This
can help improve traffic flow and lessen accident-related congestion. Consequently, traffic efficiency and
safety will increase, and there will be less downtime on the roads.
www.rsisinternational.org
Page 5837
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
METHODOLOGY
Framework for Data Gathering and Scope
The study used Arkey and O'Malley's scoping review methodological framework, which served as a guide for
creating protocols for scoping reviews and meta-analyses. Examining articles and other resources that are
suitable for the study project requires a methodical approach. Relevant potential sources were looked up
between 2010 and 2025. The researchers created a thorough search strategy in order to simplify and streamline
the search procedure. The following keywords were incorporated into the search strategy: lane departure
technology, transportation, intelligent transportation system, and sensor technology.
Framework for the Analysis
Using Arksey and O'Malley's Framework, the researchers conducted a scoping assessment of sensor
technologies in intelligent transportation systems (ITS), with a special emphasis on lane departure warnings
(LDWs). The framework offers a methodical way to carry out scoping evaluations. There are four phases to
this study. Below is a breakdown of the stages:
1. Identifying the Research Question: Clearly define what you want to explore regarding sensor
technology and LDWs. The purpose of this research is the analyse the effectiveness and adoption of the
technology.
2. Identifying Relevant Literature: Use databases to gather a comprehensive range of literature on the
topic.
3. Charting the Data: The data collected was later charted into the following categories: Types of sensors,
technologies used in LDWs, and the effectiveness in mitigating accidents.
4. Collating, Summarising, and Reporting Results: The analysis and summation of the findings,
highlighting trends and gaps in the literature.
Data Charting Process
According to the JBI Manual for Evidence Synthesis, charting the results is an iterative process in which the
charting table is constantly updated using a template designed for ease of reference and tracking. The
important information graphic in each source comprises the following, as taken from JBI and revised by the
researcher:
Authors and year of publication
Type of sensor technology used
Study design/ methodology
Effectiveness of the technology
Limitations mentioned by the authors
Recommendations
Synthesis of Results
A scoping review study is not considered complete until all materials have been effectively synthesised and
presented in an understandable format. Thus, results synthesis is the act of arranging and summarising the
findings from the included research. The study mapped existing literature and identified essential themes,
ideas, and knowledge gaps. The synthesis process entails repetitive study of the literature and continuous
refining of themes and concepts as new articles are evaluated. The method gives a wide overview and
comprehension of the available literature, which may be used to drive future research, policy formation, and
practice.
www.rsisinternational.org
Page 5838
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Presentation of Findings
The researcher synthesises the various sample data using the JBI Manual for Evidence Synthesis, focusing on
the topic of "Sensor Technology in Intelligent Transportation Systems - Lane Departure Warnings." This
synthesis summarises the findings from hypothetical studies and organises them into a structured format
presented below:
S/No
Author(s)
Study
Design
Sensor
Tech.
Limitation
Recommendations
1.
Tochukwu et
al, 2024
Systematic
Review
Camera-
based
sensor
Challenges of
implementing
the technology
in poor nations
There is a need for
legislative
frameworks and
infrastructure
investment.
2.
Guerrero-Ibáñez
et al., 2018
Field
survey/
Quantitative
survey
Camera-
based
sensor
Inability to
detect damaged
infrastructure,
such as blurry
or erased
transit lines
Inadequate or,
in some cases,
inexistent
traffic signals,
fast object
detection
There is a need to
integrate other
technologies and
devices, such as
data analytics,
automated
operation tools,
decision-making
tools, and social
and mobile
networks
3.
Orie, 2022
Quantitative
approach
LIDAR
Inability to
monitor or
sense devices’
ranges located
on roads,
vehicles, and
transportation
infrastructures.
Recommend the
possible creation of
numerous next-
generation smart
applications to
enhance traffic
management and
safety in both
current and future
transportation
systems.
4.
Balashanmugam
et al., 2015
Observation
study
LIDAR
Their
performance
strongly
depends on
illumination
conditions.
In areas proposed
for adoption, there
should be proper
illumination.
5.
Ankit Singh et
al., 2025
Quantitative
approach
Camera
Based
The efficiency
of these
systems under
critical
distracted
The findings from
the study highlight
the positive
influence of lane
departure warning
www.rsisinternational.org
Page 5839
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
driving
conditions is a
matter of
concern.
systems on driver
behaviour under
distracted driving
conditions.
The study
supported the idea
of installing LDW
systems in vehicles
to enhance road
safety.
6.
Scanlon et al.,
2016
Field
Survey
LIDAR
The
effectiveness of
these systems
is highly
dependent on
roadway
characteristics,
such as lane
markings and
shoulder width.
The results suggest
that modifying all
roadway
infrastructures to
include lane
markings and
expanding roadway
shoulder width.
7.
Sultana et al.,
2016
Simulation
study
Camera-
based/
Radar
This system is
robust against
noise and a
high-speed
algorithm.
The driver
assist system,
which is used,
is very
efficient, low-
cost cost and
robust against
noise.
Proposes a video-
based driver assist
system that alerts
the driver with an
audio alarm and
visual message
about lane
departure, as well
as tracks the
specific vehicle
using license plate
extraction.
Source: Researchers' Output, 2025
A study by Tochukwu et al, 2024, a study on the integration of Advanced Sensors in Smart Transportation
Systems: Enhancing Efficiency and Safety. The study involves a systematic review of various literature. The
study examined the effectiveness of camera-based sensors on the efficiency and safety of motorists. The study
adjudged that the technology was effective for traffic management assistance, and it helped to improve safety
by 65%. The researchers identified the challenges of implementing the technology in poor nations because of
their financial constraints. The research recommends a legislative framework and infrastructural investment in
the technology for its effectiveness. Guerrero-Ibáñez et al. (2018) examined Sensor Technologies for
intelligent transportation Systems. The study involves a field survey and a quantitative approach, where
camera camera-based sensor was used. The authors acknowledged the ability of the camera to detect lane
departure on roads with good lane marking, but have difficulty in detecting damaged infrastructure, such as
blurry or erased transit lines. It also has challenges in cases where there are nonexistent traffic signals, fast
object detection. The researchers recommend the need to integrate the technology with other devices such as
data analytics, automated operation tools, decision-making tools, and social and mobile networks to aid
effectiveness.
www.rsisinternational.org
Page 5840
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
A study by Orie (2022) examined Sensor Technologies Perception for Intelligent Vehicle Movement Systems
on the Nigerian Road Network. The researcher adopted a quantitative approach in his study using LIDAR. The
study established the effectiveness of the technology in monitoring lane departure at 75% effectiveness. The
researcher identified the inability of the technology to monitor or sense devices located on roads, vehicles, and
transportation. The researcher recommends the possible creation of numerous next-generation smart
applications to enhance traffic management and safety in both current and future transportation systems. In the
same vein, Balashanmugam et al. (2015) studied the development of a lane departure warning traffic system
using an observation study, and camera camera-based sensor. The study established the ability of the
technology to detect lane marking under well-illuminated conditions, effective of 85%. The study identifies its
inability to perform under poor lighting conditions. The study, therefore, recommends better illumination in
proposed areas of installation.
Ankit Singh et al. (2025) researched improving power quality in electric cars and battery energy storage
systems with multiple inverter topologies. The study took a quantitative approach, utilising a camera-based
sensor. The study demonstrated the usefulness of the technology while the driver is fully active, allowing for a
quick swing into action, since the system's efficiency during crucial distracted driving conditions is a source of
worry. Therefore, the data demonstrated a favourable impact of lane departure warning systems on driver
conduct under distracted driving situations, but care is advised. The study supports the notion of putting an
LDW system in automobiles to improve road safety.
Furthermore, Scanlon et al. (2016) investigated the impact of roadway characteristics on the potential safety
benefits of lane departure warning and prevention systems in the United States vehicle fleet. Field surveys
were conducted using LIDAR technology and were found to be 70% successful. The study found that the
efficacy is greatly dependent on route parameters such as lane markers and shoulder width. As a result, it
advises that the highway infrastructure be modified to incorporate lane markings and an increase in roadway
shoulder width. Finally, Sultana et al. (2016) investigated LDW using message and alarm systems, as well as
vehicle position tracking. The study includes a field survey, which necessitates the use of a camera-based
sensor. In various environments, the system detects lanes with an accuracy of over 96%. The research suggests
a video-based driving assistance system that would inform the driver with an aural alarm and a visual message
regarding lane deviation, as well as the capacity to follow car license plate extraction.
Types of Sensor Technologies
Camera-based Systems: The study reveals that camera-based sensor is widely embraced by most of the
studies and found to be effective but sensitive to environmental conditions like fog and rain.
LIDAR Systems: The various studies reveal LIDAR possesses a high accuracy and reliability reported,
though cost remains a hurdle for widespread adoption, and its effectiveness greatly depends on the road
characteristics.
Radar Systems: Effective in various weather conditions but with fewer studies by the studied by the
various researchers.
Effectiveness
Studies indicate a range of accuracy from 80% to 92% depending on the technology and environmental
factors.
Multi-sensor systems tend to outperform single-sensor solutions.
LIMITATIONS
High prices, system complexity, and performance problems in low-visibility situations are all examples of the
technology's drawbacks. Additionally, because its efficacy is dependent on lighting, it is unable to identify
damaged infrastructure, such as transportation lines that are obscured or indistinct. Numerous studies
emphasise the necessity for further long-term dependability data.
www.rsisinternational.org
Page 5841
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
SUMMARY, RECOMMENDATIONS, AND CONCLUSION
Summary
The study offers a thorough examination of how transportation contributes to economic growth, highlighting
the development and importance of lane departure warning systems (LDWS) and intelligent transportation
systems (ITS). Economic growth depends heavily on transportation, particularly in emerging nations with
inadequate infrastructure. Although it makes it easier for people, products, and services to move about, it also
presents social issues that call for the use of Smart Transportation Systems (STS) in order to lessen adverse
effects. From simple traffic control to complex systems combining control, communication, and sensor
technologies, STS has come a long way. For real-time data gathering necessary for traffic management and
safety enhancements, effective STS depends on a variety of sensors, including infrastructure-, vehicle-, and
device-based sensors. In order to reduce accidents brought on by inadvertent lane exits, LDWS is essential.
These systems improve road safety by raising driver awareness and warning them of lane positioning by using
sensors like cameras and LIDAR. Environmental restrictions, high expenses, integration difficulties, and
privacy issues are some of the difficulties that both ITS and LDWS must overcome, especially in developing
nations. These elements impede efficacy and broad adoption.
Sensor Technologies Effectiveness
Camera-based Systems: Widely used and effective, but sensitive to environmental conditions like fog and
rain.
LIDAR Systems: High accuracy and reliability noted, though costly. Effectiveness is influenced by road
characteristics.
Radar Systems: Effective across various weather conditions but less frequently studied.
Effectiveness Metrics: Studies report effectiveness ranging from 80% to 92%, with multi-sensor systems
generally outperforming single-sensor solutions.
Limitations Identified: Common limitations include performance issues in low visibility, high costs, and
complexity. Specific challenges were noted in detecting damaged infrastructure and reliance on illumination
conditions for accurate functioning.
Recommendation
Based on the findings of the study regarding the evolution and impact of Intelligent Transportation Systems
(ITS) and Lane Departure Warning Systems (LDWS), the following recommendations are proposed:
1. Legislative Framework: Legislative frameworks and infrastructural investments are necessary to
enhance the effectiveness of sensor technologies.
2. Integration with other technology: Integration with data analytics and automated tools is recommended
to improve overall system performance.
3. Enhance Infrastructure Investment: Governments should prioritise investment in transportation
infrastructure to support the integration of ITS. This includes upgrading existing roads, signals, and
communication networks to accommodate advanced technologies.
4. Promote Smart Transportation Systems (STS): Encourage the adoption of STS by providing
incentives for municipalities and the private sector to invest in intelligent transportation solutions. This
could include subsidies for technology implementation and training programs for staff.
5. Strengthen Sensor Integration: Develop standardised protocols for the integration of various sensor
types (vehicle-based, infrastructure-based, and device-based) to ensure seamless communication and data
sharing. This will enhance the effectiveness of ITS and LDWS.
www.rsisinternational.org
Page 5842
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
6. Address Environmental Challenges: Invest in research to improve sensor reliability under adverse
weather conditions. Implementing robust algorithms that can compensate for environmental factors will
enhance the performance of LDWS.
7. Focus on Affordability and Accessibility: To facilitate wider adoption, develop cost-effective ITS and
LDWS solutions tailored for developing countries. This may involve partnerships with technology
providers to lower implementation costs.
8. Enhance Public Awareness and Education: Conduct public awareness campaigns to educate drivers
about the benefits of ITS and LDWS. Understanding these systems will encourage acceptance and proper
usage.
9. Implement Data Privacy Measures: Establish clear regulations and guidelines to protect user privacy
while collecting data for ITS and LDWS. Transparency in data handling will build public trust and
encourage participation.
10. Leverage Artificial Intelligence (AI): Invest in advancements in AI and machine learning to
continuously improve the capabilities of LDWS. Enhanced algorithms can provide better lane detection
and predict driver behaviour, further reducing accident risks.
11. Encourage Collaborative Efforts: Foster collaboration among government agencies, private companies,
and academic institutions to share knowledge and resources. Collaborative efforts can lead to innovative
solutions and a more effective implementation of ITS.
12. Monitor and Evaluate Progress: Establish monitoring frameworks to evaluate the performance of ITS
and LDWS continuously. This will help in identifying areas for improvement and ensuring that systems
are meeting safety and efficiency goals.
13. Further exploration: Future research should focus on developing next-generation smart applications to
enhance traffic management and safety.
Conclusion
According to the study, transportation plays a crucial role in economic development by facilitating the
movement of people, goods, and services, especially in developing countries with limited infrastructure. The
development of Intelligent Transportation Systems (ITS) and Lane Departure Warning Systems (LDWS) is a
major step towards mitigating the adverse effects of transportation activities on the environment and society.
ITS improves operational efficiency, safety, and sustainability by integrating many technologies, whereas
LDWS is essential for preventing accidents by improving driver awareness and providing real-time
notifications. In the end, improving traffic flow, promoting sustainable urban growth, and improving road
safety all depend on the effective deployment of Smart Transportation Systems and Lane Departure Warning
Systems. In order to remove current obstacles and optimise the advantages of these cutting-edge transportation
technologies, sustained investment, cooperation, and innovation will be essential.
REFERENCES
1. Ankit Singh, Vibhu Jately, Peeyush Kala B, Yongheng Yang (2025). Enhancing power quality in electric
vehicles and battery energy storage systems using multilevel inverter topologies – A review, Journal of
Energy Storage, Volume 110,115274, ISSN 2352-
152X,https://doi.org/10.1016/j.est.2024.115274.(https://www.sciencedirect.com/science/article/pii/S235
2152X24048606)
2. Balashanmugam, P., & Kalaichelvan, P. T. (2015). Biosynthesis characterisation of silver nanoparticles
using Cassia roxburghii DC. Aqueous extract and coated on cotton cloth for effective antibacterial
activity. International journal of nanomedicine, 10(sup2), 87-97.
3. Bazzan, A. L., & Klügl, F. (2022). Introduction to intelligent systems in traffic and transportation.
Springer Nature.
4. Cao, M., Wang, R., Chen, N., & Wang, J. (2021). A learning-based vehicle trajectory-tracking approach
for autonomous vehicles with lidar failure under various lighting conditions. IEEE/ASME transactions
on mechatronics, 27(2), 1011-1022.
5. Casal, P., & Selamé, N. (2015). Sea for the landlocked: a sustainable development goal?. Journal of
Global Ethics, 11(3), 270-279.
www.rsisinternational.org
Page 5843
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
6. Guerrero-Ibáñez, J., Zeadally, S., & Contreras-Castillo, J. (2018). Sensor technologies for intelligent
transportation systems. Sensors, 18(4), 1212.
7. Meneguette, R. I., De Grande, R., & Loureiro, A. A. (2018). Intelligent transport system in smart cities.
Cham: Springer International Publishing, 1, 182.
8. Nafrees, A. C. M., Sujah, A. M. A., & Mansoor, C. (2021, December). Smart Cities: Emerging
technologies and Potential solutions to the cybersecurity threats. In 2021 5th International Conference on
Electrical, Electronics, Communication, Computer Technologies and Optimisation Techniques
(ICEECCOT) (pp. 220-228). IEEE.
9. Odat, E., Shamma, J. S., & Claudel, C. (2017). Vehicle classification and speed estimation using
combined passive infrared/ultrasonic sensors. IEEE transactions on intelligent transportation systems,
19(5), 1593-1606.
10. Olasokan, O. O., & Toki, E. O. (2021). A Spatiotemporal Analysis of the Incidence of Road Traffic
Accidents Along Lagos/Abeokuta Expressway.
11. Omar R., Alsharoa, A., Shatnawi, I., & Arora, A. (2024). The role of intelligent transportation systems
and artificial intelligence in energy efficiency and emission reduction. arXiv preprint arXiv:2401.14560.
12. Orie, M. J. (2022). Availability and application of information and communication technology for
educational research in the post-COVID-19 era. In The Colloquium (Vol. 10, No. 1, pp. 39-48).
13. Osoja, A. O., Opeyemi, A. M., Olasokan, O. O., & Toki, O. E. (2022). An Assessment of factors
influencing commuters' travel behaviour on the Mile 2-Badagry Expressway, Lagos, Nigeria. GSJ, 10(1).
14. Oyeyemi, A., Osoja, A., Fadipe, O., & Olasokan, O. O. (2025). Evaluating the impact of urbanisation on
road traffic accidents: Insights from Lagos, Nigeria. SSR Journal of Arts, Humanities and Social
Sciences, 2(8), 42-52.
15. Qureshi, K. N., & Abdullah, A. H. (2020). The evolution of smart working and sustainability in a socio-
technical perspective: A scientometrics technology analysis. Journal of Engineering Science and
Technology, 15(3), 1868-1882
16. Rinchi, O., Assaid, S. A., & Khasawneh, H. J. (2021, November). Accurate Android-Based Navigation
using Fuzzy Adaptive Extended Kalman Filter. In 2021, IEEE Jordan International Joint Conference on
Electrical Engineering and Information Technology (JEEIT) (pp. 234-239). IEEE.
17. Sarker, A. R., Sultana, M., Mahumud, R. A., Sheikh, N., Van Der Meer, R., & Morton, A. (2016).
Prevalence and health care–seeking behaviour for childhood diarrheal disease in Bangladesh. Global
pediatric health, 3, 2333794X16680901.
18. Scanlon, B. R., Reedy, R. C., Faunt, C. C., Pool, D., & Uhlman, K. (2016). Enhancing drought resilience
with conjunctive use and managed aquifer recharge in California and Arizona. Environmental Research
Letters, 11(3), 035013.
19. Soga, K., & Schooling, J. (2016). Infrastructure sensing. Interface focus, 6(4), 20160023.
20. Tochukwu, N., Ahmed, A., Oluomachi, E., & Abdullah, A. (2024). Enhancing Data Privacy In Wireless
Sensor Networks: Investigating Techniques And Protocols To Protect Privacy Of Data Transmitted Over
Wireless Sensor Networks In Critical Applications Of Healthcare And National Security. arXiv preprint
arXiv:2404.11388.