The Adoption of Artificial Intelligence-Based Systems in the Development of Public Transportation in Auckland

Full text

https://doi.org/10.34074/rere.00303
ADOPTION OF ARTIFICIAL INTELLIGENCE-BASED
SYSTEMS IN DEVELOPMENT OF PUBLIC
TRANSPORTATION SYSTEM IN AUCKLAND
Sheyda Baradar Razizadeh and Dr. Indrapriya Kularatne
OTAGO POLYTECHNIC AUCKLAND INTERNATIONAL CAMPUS
ABSTRACT
The concept of smart cities has gained signicant momentum with rapid advancements in Articial Intelligence-based
automation. Public mobility is a crucial component of modern cities, and its development signicantly impacts the level of
smartness of a city. The application of Articial Intelligence to the public transportation industry necessitates a continuous
reassessment of the factors inuencing the design, development, and implementation of the public transportation
infrastructure. This investigation aims to explore these factors, their implications for an effective transportation system in
Auckland, New Zealand and the signicant results that adopting Articial Intelligence would bring to the system. It includes
the integration of an Intelligent Transportation System, an Articial Intelligence-based real-time data collecting system,
and fully automated driverless vehicles that are connected to the Intelligent Transportation System.
Keywords: public transportation, infrastructure for public transportation, intelligent transportation systems, network
connectivity, travel time analysis
INTRODUCTION
Smart cities are characterised by their commitment to sustainability and efciency, utilising innovative technologies to
elevate the quality of life for their residents. Smart transportation is a critical component of smart cities, and it involves the
use of data analytics to optimise the movement of people and goods within a city (Macke et al., 2018). In Auckland, smart
public transportation (PT) systems have been proposed as a way of improving the city’s transportation network (Munjal et
al., 2020)
Smart PT signies the use of advanced technologies to promote the efciency and safety of the PT systems. Smart PT
systems use progressive technologies such as the Internet of Things (IoT), Articial Intelligence (AI) and Big Data Analytics
to optimise the ow of trafc, reduce congestion, and provide passengers with real-time information on routes, schedules
and delays. Such systems also incorporate other advanced technologies such as autonomous vehicles, electric buses, and
intelligent trafc management systems (Costa & Duran-Faundez, 2018).
Auckland Transport is a council-controlled corporation engaged with Auckland’s transport services, including roads, public
transport, cycling, and walking (Auckland Transport, 2022). Auckland Transport’s key priorities are to reduce congestion,
improve safety, and increase accessibility and sustainability (Radio New Zealand, 2022; Auckland Transport, 2022). Issues
that negatively impact the linkage between Auckland’s transportation system and smart PT systems include limited
coverage of AI-based smart technology implementation and challenges in data integration and utilisation (Wolken et al.,
2018).
The objective of this investigation is to understand the current state of PT in Auckland and what are the potential AI-based
solutions to optimise the existing system.
LITERATURE REVIEW
As one of the fastest-growing cities in New Zealand, Auckland’s PT system has faced challenges in accommodating
increasing demand, addressing congestion, and providing reliable and efcient services. In the process of this literature
review, it was discovered three distinct domains of issues concerning the Auckland PT system.
Article
19
Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

– Insufcient Infrastructure: Auckland’s PT system requires signicant investment in infrastructure to meet the increasing
demand for services including upgrading existing infrastructure, constructing new bus stations, and developing
integrated transport hubs (Auckland Rapid Transit Baseline, 2021)
– Poor Network Connectivity: Auckland’s PT network lacks seamless connectivity between different modes of transportation,
leading to reduced accessibility and convenience for users. This includes inadequate connections between buses, trains,
and ferries, and limited access to key destinations (Jacobson, 2018)
– Driver Shortage: Auckland’s PT system is facing a shortage of bus drivers, which impacts the reliability and efciency of
services (Scott, 2023)
Critical Evaluation of Public Transportation in Auckland
In modern infrastructure, a properly functioning PT system holds the utmost signicance. Evaluating a PT system
necessitates a thorough assessment of inuencing factors such as reliability, efciency, and safety (Atombo & Dzigbordi
Wemegah, 2021). The PT system in Auckland is a notable feature of the city’s urban infrastructure (Arora, 2023). Arora
stated that it is comprised of multiple modes of transportation, including buses, trains, and ferries, which provide people
with an array of options to navigate the urban landscape. The AT HOP card system is an addition to the PT system, which
enables passengers to conveniently pay for fares and transfer between modes of transportation (Arora, 2023). Auckland
Transport has been proactive in its efforts to improve the reliability and frequency of services, utilising initiatives such as bus
priority lanes and rail electrication as well as providing real-time features such as real-time bus and train arrival information
through the Auckland Transport website and app (Hyde & Smith, 2017). As Chowdhury et al. (2018) stated, the Auckland
City Rail Link, a substantial infrastructure project currently under construction, is expected to signicantly enhance the
efciency and capacity of the public mobility system.
However, the quality of PT services has been the subject of complaints, with delays, cancellations, and overcrowding being
common issues (Horsnell, 2023). A lack of integration between different modes of transportation has also been noted
(Jacobson, 2018). There are concerns regarding accessibility, particularly for those residing in areas with limited PT options
or those with mobility issues. Furthermore, some suburbs and rural areas are underserved by the PT system, with limited
access available (Imran & Pearce, 2015). On the other hand, Campbell, (2023) identied the shortage of bus drivers in
Auckland which has emerged as a persistent issue in recent years.
Overall, Imran and Pearce (2015) stated that while the PT system in Auckland has various strengths, it is evident that there
is scope for improvement. They also identied that addressing issues such as reliability, accessibility, and coverage will be
vital for the system to cater effectively to the needs of Auckland residents, sustain growth, and promote the city’s
sustainability (Imran & Pearce, 2015).
The Issues
According to the report published by Fleming (2019), )Auckland has the world’s eleventh worst PT, based on scores in
accessibility, reliability, and affordability. Hence, this section will be followed by detailing the identied issues in relation to
insufcient infrastructure, poor connectivity, and the bus driver shortage.
– Insufcient Infrastructure
The contemporary issue of trafc congestion and air pollution caused by urban expansion and increased transportation
usage has garnered signicant attention from scholars and policymakers alike. Private vehicles, in particular, have been
identied as a major contributor to trafc congestion and air pollution in urban areas worldwide (Lu et al., 2021).
Cilliers (2023) quoted that “residents that rely on public transport are forced to endure atrocious trip lengths and infrequent
services” and also emphasised the necessity of PT development especially in Westgate, Auckland. Williams (2022) reported
a striking rise in trafc congestion in Auckland, which is believed to be primarily driven by population changes in the region.
Furthermore, it was also noted that the likelihood of an individual driving to work and the length of their commute increases
with distance from Auckland city centre. The author quoted that a report published in April 2022 by an Auckland Transport
spokesperson indicated that only 26% of morning trips to Downtown Auckland were made using PT, compared to 67%
using private transportation such as their own vehicle (Williams, 2022).
In addition to the environmental and logistical consequences of trafc congestion, Wild et al. (2021) have identied the
negative psychological impacts on drivers. Their study at the University of Auckland revealed that residents in Auckland are
excessively reliant on their vehicles, which has led to increased stress and anxiety among drivers. The authors represented
the ndings of a study in an urban planning programme at the University of Auckland, that argued addressing this issue
will require a shift in New Zealand’s socio-cultural values that have historically placed a high value on private vehicle
ownership (Wild et al., 2021).
Given the above information, it is evident that the efcient expansion of the PT infrastructure is critical to addressing the
transportation challenges facing Auckland. However, the infrastructure needs of PT systems can be complex and require
careful planning and resource allocation (Williams, 2022).
20 Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

– Poor Network Connectivity
Ceder (2009) argued that insufcient connectivity can be a deterrent to passengers utilising public transit network
connectivity refers to the degree to which different modes of PT, such as buses, trains, and subways, are integrated and
connected. To consider this issue, they proposed a methodology for measuring the performance of mass mobility
connectivity in Auckland. Their research found that the PT network in Auckland generally performs at a medium level in
terms of overall connectivity. However, certain areas exhibit lower connectivity to employment centres and universities.
Ceder (2009) suggest the use of a connectivity index to evaluate the number of potential journeys that can be made within
a certain travel time threshold, while also considering the frequency and reliability of services.
Chowdhury et al. (2018) asserted that integrating different modes of PT, such as buses, trains, and trams, can lead to a
seamless and efcient network that allows users to move from one mode to another without the need for additional tickets
or transfers between different transport providers. Nevertheless, they declared coordinating and integrating different
transport modes can be challenging, particularly in terms of ensuring that they are all running on time and that they are
connected in a way that is convenient for users. For instance, if a bus arrives late at a train station, it may cause users to miss
their connecting train, leading to frustration and inconvenience. It is important to ensure equitable access to integrated PT
systems, including accessibility for users with different mobility needs. For example, disabled individuals may require
additional accessibility features such as ramps or lifts to navigate the system (Chowdhury et al., 2018).
– Bus Driver Shortage
Campbell (2023) reported New Zealand’s largest cities were having difculty in managing the bus driver shortage, which is
making passengers impatient and late for work. Furthermore, cancelled buses, three years of impending rail closures, and
staff shortages on ferries are all contributing to the weakening of Auckland’s PT system.
Chandiran et al. (2023) mentioned that the bus driver shortage can result in several issues, such as delays and cancellations,
overworked drivers, increased costs, safety concerns, and decreased morale. The shortage can disrupt PT services, leading
to inconvenience and disruptions for users specially students and their parents who are taking them to schools. Overworked
drivers can compromise safety, increase the risk of accidents, and is a cause of fatigue and burnout due to the need to take
on extra routes. Chandiran et al. (2023) showed how higher transportation costs leads companies to invest in new
technology or equipment to improve efciency and reduce the need for drivers.
In light of the above, it is apparent that Auckland’s PT system is hampered by a cycle of interconnected problems. Increased
use of private vehicles as a result of inadequate infrastructure creates trafc congestion and ineffectiveness of PT due to
the weak network connectivity increasing people’s reliance on their private vehicle. On the other hand, the lack of bus
drivers raises the need for alternate modes of transportation. In order to increase the overall effectiveness, dependability,
and accessibility of PT in Auckland, it is imperative to address each of these problems in detail.
DISCUSSION
Urban mobility planning is a comprehensive process that involves analysing transportation demand, identifying gaps and
inefciencies in existing systems, developing policies and plans, and implementing and monitoring transportation systems
in urban areas (Ceder, 2021). It is a multifaceted and dynamic process that requires collaboration and coordination among
various stakeholders to create sustainable, efcient, and equitable transportation systems that can address the complex
social, economic, and environmental challenges faced by cities. The process utilises various tools, techniques, and
methodologies to inform decision-making and ensure the planning process is inclusive, participatory and transparent
(Ceder, 2021). However, according to Nieuwenhuijsen (2020) urban transport planning involves consideration of various
actionable factors depending on the context of the planning activity such as urban planning, business planning, strategic
planning, etc. that may interact with each other in complex ways, and planners must consider them carefully to develop
effective plans.
Gao & Zhu (2022) determined that the effectiveness of PT hinges on various city attributes that necessitate careful
consideration during the design and implementation of PT systems. Considering these factors, more efcient, accessible,
and dependable PT systems that cater to the needs of all users, regardless of their geographic location or socio-economic
status can be developed (Gao & Zhu, 2022).
On the other hand, the concept of AI-based automation has led to the development of powerful technology in various
elds able to carry out operations like sensing, thinking, and decision-making that ordinarily need human intellect (Kar et
al., 2019). Kar sated that the AI branch of machine learning is concerned with developing algorithms and statistical models
that can learn from data and improve over time. Therefore, Ang et al. (2022) suggested upgrading the urban mobility
planning of the cities is of great importance to adopt data analytics and machine learning in processing and interpreting
large volumes of transportation-related data, such as trafc patterns, travel behaviour, and road conditions.
21
Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

Recently, smart cities have been utilising Deep Learning (DL); a machine learning method to extract complex features
based on articial neural networks and Internet of Things (IoT) data analytics to support the development of smart cities
Atitallah et al. (2020). For instance, DL and IoT big data analytics can be used to analyse trafc patterns and optimise trafc
ow, reducing congestion and emissions (Heidari et al., 2022). Reis Da Silva (2023) examined how big data analytics would
enhance PT efciency in the city of Natal, Rio Grande do Norte (RN), Brazil. The same author published the applicable
outcomes that could signicantly enhance the efciency of PT in the target city by implementing big data analytics solutions
including DL and IoT (Reis Da Silva, 2023). However, there are several challenges associated with the use of DL and IoT big
data analytics in smart cities (Reis De Silva, 2023). These include concerns around data privacy and security, the need for
more interpretable and explainable DL models, and the development of more efcient and scalable DL algorithms. According
to Atitallah et al. (2020), big data analytics based on DL and IoT have enormous potential to aid in the creation of smart
cities and enhance residents’ quality of life in several ways including improvements to the PT system. However, further
research and innovation are needed to overcome the current challenges and fully realise the benets of these technologies.
Nevertheless, there are challenges associated with implementing emerging technologies in smart transportation systems.
According to Ang et al. (2022), rstly, data privacy and security are crucial issues that need to be addressed. Smart
transportation systems rely heavily on collecting, processing, and analysing large amounts of data, including personal and
sensitive information about individuals. Hence, it is crucial to make sure that data is gathered and utilised properly and that
the proper steps are taken to preserve people’s security and privacy. Secondly, the implementation of smart transportation
systems requires collaboration between different stakeholders, including government agencies, the private sector, and
citizens. The authors also state that, as smart transportation systems involve multiple components and systems, such as
trafc management, PT, and vehicle technology, collaboration between different stakeholders is necessary to ensure that
these systems work together seamlessly and that they meet the needs and expectations of all stakeholders.
Data Analytics and Articial Intelligence for Public Transportation Infrastructure Expansion
As discussed in previous sections, the enhancement of the PT infrastructure network constitutes a crucial aspect of urban
mobility planning, which can be effectively optimised through the utilisation of AI and data analytics (Ang et al., 2022). The
adoption of data analytics methodologies enables PT agencies to acquire and process large volumes of data, thereby
gaining invaluable insights that can facilitate informed decision-making regarding infrastructure design, optimisation, and
maintenance (Ang et al., 2022). Zou et al. (2014), stated that several key areas can be measured and analysed, such as user ow,
trafc patterns, travel time analysis, user behaviour analysis, and environmental factors in the design phase of PT infrastructure.
The utilisation of big data analytics allows the prediction of demand, optimisation of routes and schedules, and enhancement
of service quality through the analysis of user ow data. This data assists PT agencies in identifying high-demand routes
and allocating resources, such as additional vehicles or increased service frequency, to meet user needs (Welch & Widita,
2019). Furthermore, such insights can aid in the optimisation of transportation layouts to better align with user preferences
and requirements (Abduljabbar et al., 2019).
The Massachusetts Bay Transportation Authority in Boston, United States of America, uses data analytics to monitor user
ow in realtime, allowing the agency to optimise service frequency and capacity based on actual demand (Chen & Zegras,
2016). Public Transportation agencies use travel time analysis to evaluate PT performance and pinpoint areas for
improvement (Ang et al., 2022). By gathering data on travel times and comparing them to expected times, PT agencies can
identify and prioritise routes with frequent delays or bottlenecks, thus improving service reliability and reducing travel
times (von Mörner, 2017). Das et al. (2017) explained that infrastructure improvements like road widening or signal
optimisation can help alleviate congestion and reduce travel times, and using data analytics to identify areas where these
improvements would have the greatest impact can help PT agencies efciently allocate resources and provide better PT
services to the users.
The New York City Department of Transportation, United States of America, uses travel time data to evaluate the
performance of bus services and identify areas for improvement, such as bus lane prioritisation and signal optimisation
(Yazici et al., 2012). Liu et al. (2021), claimed the importance of user behaviour analysis for understanding the required PT
infrastructure. They noted the analysis help agencies identify improvement areas and meet the needs of their users. Finally,
the analysis of environmental data, such as weather patterns, natural disasters and topography of an area can improve the
resilience, effectiveness, and responsiveness of PT infrastructure (Liu et al., 2021).
In summary, the application of data analytics can provide valuable insights for PT agencies to make informed decisions
about infrastructure design, optimisation, and maintenance, thereby optimising their operations and improving user
experience in PT systems. Investment in data analytics methodologies is the recommendation of this study to address the
insufcient PT network issue in Auckland. The recommended approach involves the collection and analysis of data on user
ow, trafc patterns, travel time, user behaviour, and environmental factors to gain insights and facilitate informed decision-
making in PT infrastructure design, optimisation, and maintenance. Despite the potential benets of data analytics, concerns
exist over data privacy and security, and the possibility of biases in data collection and analysis. Additionally, cost and
feasibility issues may pose barriers for some transportation agencies.
22 Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

Data Analytics and Articial Intelligence for Network Connectivity
Transfer synchronisation plays a crucial role in providing the best possible travel experience for users by coordinating the
arrival and departure times of linked services (Ibarra-Rojas & Rios-Solis, 2012). Gkiotsalitis et al. (2023) have emphasised
that real-time control, a critical phase of transfer synchronisation, involves making timely adjustments to the timing of
services based on real-time data such as user demand, delays, and disruptions. Their predictive models and optimisation
algorithms to determine the best course of action and resulted successful implementation of real-time control for transfer
synchronisation. These models require accurate and timely data, reliable communication systems, and effective coordination
among stakeholders such as transport operators, trafc managers, and users.
Sumalee & Ho (2018) examined the combination of AI with technological advances like the IoT, which has the potential to
transform PT systems. One of the key functions of AI in this domain is the development of Intelligent Transportation
Systems (ITS), which can optimise PT networks by analysing real-time data on user demand, trafc conditions, and route
schedules. This optimisation can reduce wait times and enhance operational efciency by allowing for the optimisation of
the routes and schedules of PT. Furthermore, the integration of emerging technologies can enable a more connected and
intelligent PT system, facilitating real-time monitoring and control of trafc ow, as well as predictive maintenance of
vehicles and infrastructure. Notably, explored ITS how can facilitate the development of smart cities, where PT is seamlessly
integrated with other aspects of urban life, such as energy management and public safety. However, they observed that
the implementation of ITS also presents signicant challenges, including data privacy and security, the digital divide, and
ethical implications (Sumalee & Ho, 2018).
This study endorses the realisation of the full potential of ITS requires collaborative efforts between industry, government,
and academia, as well as investment in research and development. Ultimately, the investigation offers insightful information
on the potential of cutting-edge technology to improve PT infrastructure.
The interconnection of rising technologies such as AI, big data analytics and IoT in the development of ITS are effective
strategies for enhancing the optimisation of PT networks. Given the increasing importance of transfer synchronisation in
PT operations and the potential benets of the integration of emerging technologies in the development of ITS, ndings
of this investigation indicate and highly recommended policymakers in the PT industry to practice the application of real-
time control in Auckland PT.
Data Analytics and Articial Intelligence for the Bus Driver Shortage
The use of AI in PT automation has expanded the idea of driverless vehicles in PT systems. Articial Intelligence-powered
driverless vehicles, such as buses or trains, can navigate and make decisions without human intervention, and optimise
routes based on real-time data on user demand and trafc conditions (Caballero Galeote et al., 2023). Articial Intelligence
algorithms can also analyse data on trafc patterns and predict congestion or other road hazards that may affect PT,
enabling PT agencies to adjust routes and schedules in realtime. Bharadiya, (2023) reported that AI can be used to monitor
the health of PT vehicles and predict when maintenance is required. By analysing data from sensors and diagnostic systems,
AI algorithms can identify potential issues and schedule maintenance before a breakdown occurs, thereby reducing
downtime and improve the overall reliability of PT services (Bharadiya, 2023).
Nikitas et al. (2021) explored the potential effects of driverless vehicles on employment in the urban PT industry and
identied three potential scenarios: job creation, job displacement, or a mix of both. They suggested that the impact of
driverless vehicles on employment will rely on a number of variables, including the rate of adoption, the type of vehicles
utilised, and the state of the labour market. While there is a lack of consensus in the literature on the topic, the authors
proposed policy recommendations, such as investing in skills and training programmes for employees, developing new
business models for the PT sector, and implementing policies that support job creation and the growth of new industries.
They stressed the need for proactive policy-making to ensure that the benets of driverless vehicles are maximised while
minimising potential negative consequences (Nikitas et al. 2021).
The EZ10 shuttle is a driverless vehicle that transfers users and has been undergoing testing on a medical university campus
in Toulouse, France since early 2021 (Bateman, 2021). It is the rst driverless vehicle in Europe to be authorised to operate
on a public road in mixed trafc without a human attendant, and operates at Level 4 autonomy, making it the most intelligent
driverless shuttle provider in the market. In contrast, Tesla’s Full Driving Feature Car is classied as a Level 2 Society of
Automotive Engineers (SAE) vehicle, which requires human supervision to some degree. The comparison highlights the
EZ10 shuttle’s technological advancements and potential for signicant changes in the PT industry (Bateman, 2021).
Consequently, this investigation recommends further research on the potential impact of AI-powered driverless vehicles
on employment, job creation and job displacement in the urban PT sector, particularly in the context of the scenarios
identied in the Nikitas et al. (2021) study. It is important to consider the various factors that can affect the impact of
driverless vehicles on employment, such as the speed of adoption, the type of vehicles used, and the labour market
conditions. This investigation may help to develop strategies to maximise the benets of driverless vehicles while
23
Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

minimising potential negative consequences. Additionally, investing in skills and training programmes for PT employees
and developing new business models for the PT sector could help mitigate any negative effects on employment and
support job creation and the growth of new industries. This could involve retraining PT drivers and other PT employees to
work in areas such as vehicle maintenance, data analysis, software development and customer service (Nikitas et al. 2021).
CONCLUSIONS AND RECOMMENDATIONS
Based on the information provided, it is recommended that PT agencies in Auckland invest in data analytics methodologies
to optimise the design, maintenance, and performance of PT infrastructure networks as a solution to address the insufcient
PT network issues. The use of data analytics can provide PT agencies with valuable insights to make informed decisions
about infrastructure design, optimisation, and maintenance. This would involve the collection and analysis of data on user
ow, trafc patterns, travel time, user behaviour, and environmental factors to gain insights that could facilitate informed
decision-making.
Correspondingly, the development of ITS can benet from the incorporation of cutting-edge technologies like AI, big data,
and IoT, which could improve the optimisation of PT networks through the analysis of real-time data. This article discusses
information on the integration of emerging technologies in the development of ITS providing valuable insights into the
application of real-time control and emerging technologies in increasing the operational quality of public transportation.
It is recommended that scholars, practitioners, and policymakers in the PT industry consider this investigation to inform
their decision-making and strategies.
Finally, another important development that could be used to improve the public transportation levels of Auckland PT users
is the use of driverless vehicles. These vehicles are fully automated and connected to a real-time database, enabling them
to make the best decision dependent on time and cost. This technology can further enhance the efciency of PT systems by
reducing the need for bus or train drivers, minimising human error, and allowing for more effective route planning and scheduling.
There is also a need for further research on the potential impact of AI-powered driverless vehicles on employment in the
urban PT sector. This should focus on the three scenarios identied in the present study namely job creation, job
displacement, or a mix of both. Various factors can affect the impact of driverless vehicles on employment, such as the
speed of adoption, the type of vehicles used, and the labour market conditions. It is recommended that policymakers use
the results of this investigation to develop strategies that maximise the benets of driverless vehicles while minimising
potential negative consequences. It is suggested that policymakers invest in skills and training programmes for PT employees
and develop new business models for the PT sector to mitigate any negative effects on employment and support job
creation and the growth of new industries. This could involve retraining bus and train drivers and other PT employees to
work in areas such as vehicle maintenance, data analysis, and software development. Additionally, new business models
might also be established to open new job prospects in sectors like eet management and customer service.
REFERENCES
1 Abduljabbar, R., Dia, H., Liyanage, S., & Bagloee, S. A. (2019). Applications of Articial Intelligence in Transport: An Overview. Sustainability,
11(1), Article 1. https://doi.org/10.3390/su11010189
2 Ang, K. L.-M., Seng, J. K. P., Ngharamike, E., & Ijemaru, G. K. (2022). Emerging Technologies for Smart Cities’ Transportation: Geo-
Information, Data Analytics and Machine Learning Approaches. ISPRS International Journal of Geo-Information, 11(2), Article 2. https://doi.
org/10.3390/ijgi11020085
3 Arora, S. (2023, January 19). Digital, contactless payments for Auckland Transport to be introduced in 2024 | Stuff.co.nz. https://www.stuff.
co.nz/national/300908558/digital-contactless-payments-for-auckland-transport-to-be-introduced-in-2024
4 Atitallah, S. B., Driss, M., Boulila, W., & Ghézala, H. B. (2020). Leveraging Deep Learning and IoT big data analytics to support the smart cities
development: Review and future directions. Computer Science Review, 38, 100303. https://doi.org/10.1016/j.cosrev.2020.100303
5 Atombo, C., & Dzigbordi Wemegah, T. (2021). Indicators for commuter’s satisfaction and usage of high occupancy public bus transport
service in Ghana. Transportation Research Interdisciplinary Perspectives, 11, 100458. https://doi.org/10.1016/j.trip.2021.100458
6 Auckland Rapid Transit Baseline Working Doc.pdf. (2021). Retrieved May 24, 2023, from https://fyi.org.nz/request/17720/response/68301/
attach/5/Auckland%20Rapid%20Transit%20Baseline%20Working%20Doc.pdf
7 Bateman, T. (2021, December 1). Europe’s rst fully autonomous bus hits the road in France. Euronews. https://www.euronews.com/
next/2021/12/01/france-approves-fully-autonomous-bus-for-driving-on-public-roads-in-a-european-rst
8 Bharadiya, J. (2023). Articial Intelligence in Transportation Systems A Critical Review. American Journal of Computing and Engineering, 6(1),
Article 1. https://doi.org/10.47672/ajce.1487
9 Caballero Galeote, L., Molinillo-Jiménez, S., Ruiz Montañez, M., & Liébana Cabanillas, F. (2023). An overview of the scientic production on
the application of AI in public transport. https://riuma.uma.es/xmlui/handle/10630/27051
10 Campbell, G. (2023, May 22). Auckland’s bus driver shortage almost halved. NZ Herald. https://www.nzherald.co.nz/nz/aucklands-bus-
driver-shortage-halved-kinetic-reports-559-recruits-across-nz/WILQB22QXNF5RHZOOEPOEAOVZY/
11 Ceder, A. (2021). Urban mobility and public transport: Future perspectives and review. International Journal of Urban Sciences, 25(4),
455–479. https://doi.org/10.1080/12265934.2020.1799846
12 Chandiran, P., Ramasubramaniam, M., Venkatesh, V. G., Mani, V., & Shi, Y. (2023). Can driver supply disruption alleviate driver shortages? A
systems approach. Transport Policy, 130, 116–129. https://doi.org/10.1016/j.tranpol.2022.10.002
24 Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023

13 Chen, S., & Zegras, C. (2016). Rail Transit Ridership: Station-Area Analysis of Boston’s Massachusetts Bay Transportation Authority.
Transportation Research Record, 2544(1), 110–122. https://doi.org/10.3141/2544-13
14 Chowdhury, S., Hadas, Y., Gonzalez, V. A., & Schot, B. (2018). Public transport users’ and policy makers’ perceptions of integrated public
transport systems. Transport Policy, 61, 75–83. https://doi.org/10.1016/j.tranpol.2017.10.001
15 Costa, D. G., & Duran-Faundez, C. (2018). Open-Source Electronics Platforms as Enabling Technologies for Smart Cities: Recent
Developments and Perspectives. Electronics, 7(12), Article 12. https://doi.org/10.3390/electronics7120404
16 Das, S., Kamenica, E., & Mirka, R. (2017). Reducing congestion through information design. 2017 55th Annual Allerton Conference on
Communication, Control, and Computing (Allerton), 1279–1284. https://doi.org/10.1109/ALLERTON.2017.8262884
17 Fleming, Z. (2019, November 16). Auckland one of the worst cities in the world for public transport, road taxes according to new data |
Newshub. https://www.newshub.co.nz/home/new-zealand/2019/11/auckland-one-of-the-worst-cities-in-the-world-for-public-transport-
road-taxes-according-to-new-data.html
18 Gao, Y., & Zhu, J. (2022). Characteristics, Impacts and Trends of Urban Transportation. Encyclopedia, 2(2), Article 2. https://doi.org/10.3390/
encyclopedia2020078
19 Gkiotsalitis, K., Cats, O., & Liu, T. (2023). A review of public transport transfer synchronisation at the real-time control phase. Transport
Reviews, 43(1), 88–107. https://doi.org/10.1080/01441647.2022.2035014
20 Heidari, A., Navimipour, N. J., & Unal, M. (2022). Applications of ML/DL in the management of smart cities and societies based on new trends
in information technologies: A systematic literature review. Sustainable Cities and Society, 85, 104089. https://doi.org/10.1016/j.
scs.2022.104089
21 Horsnell, J. (2023, March 14). North Shore commuters frustrated with cancelled, overcrowded buses. https://www.1news.co.nz/2023/03/14/
north-shore-commuters-frustrated-with-cancelled-overcrowded-buses/
22 Hyde, R., & Smith, D. (2017). Assessing the value of public transport as a network May 2017.
23 Ibarra-Rojas, O. J., & Rios-Solis, Y. A. (2012). Synchronization of bus timetabling. Transportation Research Part B: Methodological, 46(5),
599–614. https://doi.org/10.1016/j.trb.2012.01.006
24 Imran, M., & Pearce, J. (2015). Discursive Barriers to Sustainable Transport in New Zealand Cities. Urban Policy and Research, 33(4), 392–415.
https://doi.org/10.1080/08111146.2014.980400
25 Jacobson, A. (2018, January 25). Auckland ranks lowest in public transport accessibility out of sister cities, study nds | Stuff.co.nz.
https://www.stuff.co.nz/auckland/local-news/central-leader/100723290/auckland-ranks-lowest-in-public-transport-accessibility-out-of-
sister-cities-study-nds
26 Kar, U., Dash, R., McMurtrey, M., & Rebman, C. (2019). Application of Articial Intelligence in Automation of Supply Chain Management.
Journal of Strategic Innovation and Sustainability, 14. https://doi.org/10.33423/jsis.v14i3.2105
27 Liu, T., Cats, O., & Gkiotsalitis, K. (2021). A review of public transport transfer coordination at the tactical planning phase. Transportation
Research Part C: Emerging Technologies, 133, 103450. https://doi.org/10.1016/j.trc.2021.103450
28 Lu, J., Li, B., Li, H., & Al-Barakani, A. (2021). Expansion of city scale, trafc modes, trafc congestion, and air pollution. Cities, 108, 102974.
https://doi.org/10.1016/j.cities.2020.102974
29 Macke, J., Casagrande, R. M., Sarate, J. A. R., & Silva, K. A. (2018). Smart city and quality of life: Citizens’ perception in a Brazilian case study.
Journal of Cleaner Production, 182, 717–726. https://doi.org/10.1016/j.jclepro.2018.02.078
30 Munjal, R., Liu, W., Jun Li, X., & Gutierrez, J. (2020, December 10). A Neural Network-Based Sustainable Data Dissemination through Public
Transportation for Smart Cities. https://www.mdpi.com/2071-1050/12/24/10327
31 Nieuwenhuijsen, M. J. (2020). Urban and transport planning pathways to carbon neutral, liveable and healthy cities; A review of the current
evidence. Environment International, 140, 105661. https://doi.org/10.1016/j.envint.2020.105661
32 Nikitas, A., Vitel, A.-E., & Cotet, C. (2021). Autonomous vehicles and employment: An urban futures revolution or catastrophe? Cities, 114,
103203. https://doi.org/10.1016/j.cities.2021.103203
33 Reis Da Silva, B. (2023). Use of Big Data Analytics for Public Transport Efciency:Evidence from Natal, (RN), Brazil. https://urn.kb.se/
resolve?urn=urn:nbn:se:ltu:diva-95620
34 RNZ, Auckland Transport. (2022, October 19). [News]. RNZ. https://www.rnz.co.nz/news/national/477000/auckland-mayor-wayne-brown-
calls-for-auckland-transport-to-change-approach
35 Scott, M. (2023, May 24). Auckland Fights the Bus Driver Shortage with Safety Glass | Newsroom. https://www.newsroom.co.nz/auckland-
ghts-the-bus-driver-shortage-with-safety-glass
36 Sumalee, A., & Ho, H. W. (2018). Smarter and more connected: Future intelligent transportation system. IATSS Research, 42(2), 67–71.
https://doi.org/10.1016/j.iatssr.2018.05.005
37 von Mörner, M. (2017). Application of Call Detail Records—Chances and Obstacles. Transportation Research Procedia, 25, 2233–2241.
https://doi.org/10.1016/j.trpro.2017.05.429
38 Welch, T. F., & Widita, A. (2019). Big data in public transportation: A review of sources and methods. Transport Reviews, 39(6), 795–818.
https://doi.org/10.1080/01441647.2019.1616849
39 Wild, K., Woodward, A., Tiatia-Seath, J., Collings, S., Shaw, C., Ameratunga, & Shanthi. (2021, March 11). The relationship between transport
and mental health in Aotearoa New Zealand. https://researchspace.auckland.ac.nz/handle/2292/54817
40 Williams, C. (2022, May 27). Auckland trafc congestion at an all-time high in 2021. Stuff. https://www.stuff.co.nz/national/trafc-
updates/128777165/auckland-trafc-congestion-at-an-alltime-high-in-2021
41 Wolken, A., Smith, M., Kaye-Blake, W., Curry, K., Dickson, M., & Drummond, C. (n.d.). Driving change: Technology diffusion in the transport
sector.
42 Yazici, M. A., Kamga, C., & Mouskos, K. C. (2012). Analysis of Travel Time Reliability in New York City Based on Day-of-Week and Time-of-Day
Periods. Transportation Research Record, 2308(1), 83–95. https://doi.org/10.3141/2308-09
43 Zou, L., Dai, H., Yao, E., Jiang, T., & Guo, H. (2014). Research on Assessment Methods for Urban Public Transport Development in China.
Computational Intelligence and Neuroscience, 2014, 941347. https://doi.org/10.1155/2014/941347
25
Rere Āwhio – Journal of Applied Research & Practice: Issue 3, 2023