=Paper=
{{Paper
|id=Vol-3628/short6
|storemode=property
|title=Cyber-physical systems at “Digital University”
|pdfUrl=https://ceur-ws.org/Vol-3628/short6.pdf
|volume=Vol-3628
|authors=Oleksandr Karnaukhov,Oleksii Duda,Serhii Martsenko,Vasyl Yatsyshyn
|dblpUrl=https://dblp.org/rec/conf/ittap/KarnaukhovDMY23
}}
==Cyber-physical systems at “Digital University”==
https://ceur-ws.org/Vol-3628/short6.pdf
Cyber-physical systems at “Digital University”
Oleksii Duda1, Oleksandr Karnaukhov1, Serhii Martsenko1 and Vasyl Yatsyshyn1
1
Ternopil Ivan Puluj National Technical University, Ruska str., 56, Ternopil, 46001, Ukraine
Abstract
The article is devoted to the theoretical analysis of the requirements for the study of the
university ecosystem development using information technology to achieve the concept of a
“digital university”, which is planned to be implemented in the future at Ternopil Ivan Puluj
National Technical University using artificial intelligence, the Internet of Things, cyber-
physical systems and “smart university” concept in different areas of “digital university”
infrastructure.
Keywords1
IoT, AI, university, education, cyber-physical systems, “digital university”, “smart
university”
1. Introduction
The concept of a “digital university” has gained popularity in recent years. This term has emerged
thanks to advances in artificial intelligence (AI), the Internet of Things (IoT), cyber-physical systems
(CPS) and “smart university” concept.
Artificial intelligence can be used to automate administrative tasks, provide personalized training,
analyze data for decision-making, and more.
IoT can be used to monitor audience occupancy, track resources, and monitor environmental
conditions.
Cyber-physical systems can include systems that monitor energy consumption in campus buildings
based on real-time occupancy data.
The idea of a “smart university” [1] combines these technologies to create an academic
environment where all aspects are interconnected, automated and intelligent. This includes not only
education, where technologies such as artificial intelligence can personalize the learning process and
IoT devices can create “smart classrooms”, but also extends to university management, financial
operations, and infrastructure in general.
For example, in university management, decision-making processes can be based on data analysis
using artificial intelligence, and real-time data is collected by IoT devices [2]. Financial operations
can be optimized with AI algorithms that can make accurate predictions and automate routine
tasks [3]. Infrastructure can be managed more efficiently with CPS and IoT, improving security,
saving energy, and optimizing resource utilization.
Thus, the concept of a “digital university” represents an evolution in higher education, utilizing
advances in AI, IoT, CPS and “smart university” to create an environment that is more efficient,
responsive, and conducive to learning and research. It is a comprehensive, holistic approach that
covers all aspects of university life, changing the way education is delivered and institutions are
1
Proceedings ITTAP’2023: 3rd International Workshop on Information Technologies: Theoretical and Applied Problems, November 22–24,
2023, Ternopil, Ukraine, Opole, Poland
EMAIL: oleksij.duda@gmail.com (A. 1); karnaukhov@live.com (A. 2); marcenko@cei.net.ua (A. 3); vyatcyshyn@gmail.com (A. 4)
ORCID: 0000-0003-2007-1271 (A. 1); 0009-0007-1432-5577 (A. 2); 0000-0003-2205-0204 (A. 3); 0000-0002-5517-6359 (A. 4)
©️ 2020 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
managed, and is proposed for research and implementation at Ternopil Ivan Puluj National Technical
University.
2. Analysis of the background and current state of research
The emergence of a “digital university” in higher education means a significant shift towards a
more receptive, adaptive and technologically advanced environment. Inspired by advances in
technologies such as artificial intelligence, the Internet of Things, and cyber-physical systems, the
concept of a “digital university” aims to integrate and optimize every aspect of university life. From
education to management, from financial operations to campus infrastructure, the “digital university”
seeks to harness the potential of these digital technologies to provide a more efficient workflow in
every sense for all members of the university community.
Research towards a “smart university” [4-14] cover a wide range of uses, including the potential of
artificial intelligence and cyber-physical systems to optimize and transform various aspects of
university life.
Cyber-physical systems are a combination of computing, networks, and physical processes. These
systems harness the power of data and connectivity to provide automated and intelligent solutions. In
the context of a “digital university”, CPS impacts numerous areas, changing the way they work. In
parallel with CPS, AI is increasingly becoming a cornerstone in the automation of various processes
due to its ability to learn from data and make predictions, recommendations, and detect anomalies.
The use of artificial intelligence in the concept of a “digital university” can significantly change work
processes in general.
One of the important aspects of a “digital university” is management. With the help of artificial
intelligence, cyber-physical systems and “smart university” management goes beyond traditional
human capabilities, creating a more dynamic and intelligent system in “digital university”.
Administrative tasks are transformed into automated processes, resource allocation is optimized, and
predictive models are used for strategic planning and decision-making. By processing data in real time
from various management sources, a “digital university” can achieve unsurpassed efficiency, accuracy
and flexibility. Therefore, artificial intelligence is widely used in the field of administration. Here, it
can automate and optimize numerous tasks that traditionally required significant manual labor. CPS
can significantly contribute to the efficient operation of a university. By comparing real-time data
from various sources on campus [13,15], CPS can provide comprehensive information about various
processes. This information can help university management make informed decisions, optimize
processes, improve services, and ultimately improve all workflows at the university.
Financial operations is another area where CPS can lead to transformation. Financial
operations [16,17], from student payment management, payroll processing, and budget allocation can
be optimized with CPS. It can help automate these processes, reduce errors, increase transparency,
and save time and effort.
The student admission process, in a conventional system, involves significant human involvement
and manual routine work, which is time-consuming and error-prone. However, using AI, universities
can automate the process. AI algorithms can be programmed to evaluate application materials such as
grades, test scores, and other documents, making the process more streamlined and efficient. The
system can be trained to rank applicants based on university admission criteria, thus ensuring fairness
and transparency.
Another practical application of artificial intelligence in a “digital university” is timetabling.
Traditionally, scheduling has been a complex task that requires taking into account numerous
variables, such as classroom availability [18], teachers’ schedules, the number of classrooms, and the
needs of students. However, AI can greatly simplify this process. Machine learning algorithms can
analyze all these variables, identify patterns, and propose an optimal schedule that meets all the
requirements. This not only ensures efficient use of resources, but also minimizes schedule conflicts,
which contributes to a more rational learning process.
Resource allocation is another area that benefits from CPS and AI. With real-time data and
predictive analytics, universities can make informed decisions about how best to allocate their
resources, from classrooms to faculty time to financial resources. This optimization not only leads to
cost savings, but also ensures that resources are used in the most efficient way, contributing to the
overall efficiency of the university.
At the infrastructure level, a “digital university” uses CPS to automatically control buildings,
classrooms, libraries, dormitories, and more. It’s not just about turning lights on and off automatically,
but also about creating an infrastructure that “thinks” and “reacts”. “Smart buildings” in a “digital
university” use sensor networks and artificial intelligence algorithms to monitor and control
environmental parameters, optimize energy consumption [19,20], managing the use of workspace and
maintaining safety. They are designed to adapt to a variety of needs, increasing comfort while
ensuring sustainability. IoT sensors [21] can monitor energy consumption in real time, enabling
energy-saving measures to be implemented. AI can also be used to predict when maintenance will be
required, preventing costly breakdowns. The integration of AI and CPS can lead to the development
of smart infrastructure. For example, smart parking systems can direct drivers to available spaces,
reducing congestion, smart lighting and heating systems [22-24] can be adjusted depending on the
number of people and time of day, saving energy. Video surveillance systems can improve security.
In education, the introduction of CPS and AI can lead to the creation of “digital
classrooms” [21,25]. Such classrooms are not just rooms with advanced technology; they are adaptive
environments that facilitate personalized learning [26-28]. IoT devices in these rooms collect data in
real time, while AI processes this data to create an adaptive teaching and learning environment. These
systems use artificial intelligence to analyze student performance in real time, dynamically adjusting
the pace and complexity of content to match individual learning styles and abilities. This
personalization can greatly enhance learning outcomes by ensuring that the learning material is
neither too easy nor too difficult. Smart learning environments equipped with interactive technologies
can create a more engaging learning experience. For example, AI-powered chatbots can provide
instant responses to student queries, while smart classrooms can offer immersive and interactive
learning experiences through augmented reality and virtual reality technologies.
This adaptive approach to learning creates a more engaging and effective educational environment
by offering students individualized paths to achieve their academic goals. AI has also been used to
assess [5,29,30]. Traditional assessments can be time-consuming and biased or inconsistent. AI can
automate this process, ensuring speed, accuracy, and fairness. Specifically, AI can be used to grade
multiple-choice questions or even more complex tasks such as essays by training algorithms on a
large portion of the work being graded.
In the case of academic advising, AI can help by providing personalized recommendations to
students based on their academic history [31], personal interests, career goals, etc. An AI-powered
academic advising system can monitor a student’s progress, notify them if they are not up to date with
certain events, offer relevant courses, and even recommend potential career paths [32]. This level of
personalized guidance can greatly enhance a student’s academic experience and help them make
informed decisions about their education and future.
Thus, “digital university” research is changing the way universities operate. It is not only about
improving the learning process, but also about making the entire university ecosystem more efficient,
responsive, and sustainable. CPS is a vital component of the “digital university” concept. It helps to
create an interconnected, intelligent and efficient environment that benefits students, faculty and staff
alike. From personalized learning to effective management and sustainable operations.
To summarize, the benefits of implementing CPS and AI in universities are multidimensional,
encompassing not only improved operational efficiency and educational personalization, but also
better resource allocation, increased student engagement, and an overall improved student experience.
3. Research on the implementation of “digitalization” in the world’s leading
universities
At this stage, many leading universities have begun to implement solutions related to the “digital
university” paradigm. These innovative solutions represent a shift towards a more intelligent,
engaging, interconnected and sustainable learning environment. Nevertheless, this is only the
beginning of the journey towards the comprehensive realization of “digital universities”, and there is
still plenty of room for improvement and expansion. Here is a brief selection of common global
achievements:
1. Massachusetts Institute of Technology uses IoT-enabled platform to monitor energy
consumption of university facilities in real time [33]. Also, together with Harvard University,
research on online learning is being conducted [34].
2. Stanford’s energy management and control system uses IoT to optimize energy use, including
campus lighting and air conditioning systems [35].
3. Harvard is using its campus as a “living laboratory” for climate change research, using IoT
technology to monitor the environment [36]. Also, together with Massachusetts Institute of
Technology, research on online learning is being conducted [34].
4. Nanyang Technological University is known for its Smart Campus initiative, which involves
the use of digital technology and big data to improve learning. This includes using IoT
sensors to monitor and improve energy efficiency and AI to personalize learning [37].
5. Tsinghua University has introduced “smart building technology”. For example, Tsinghua’s
iCenter uses a building management system (BMS) that utilizes IoT technology for energy
efficiency and comfort [20].
6. The University of Hong Kong [38], and University of New South Wales [39] have their own
implementations of “smart campuses”.
7. University of Melbourne, Australia: The university has implemented an IoT-enabled energy
management system on campus.
8. Campinas University uses information technology to manage energy efficiency [40].
4. Prospects for the implementation of a “digital university” in the Ternopil
Ivan Puluj National Technical University
In the concept of a “digital university”, the key is the harmonious interaction between various
elements such as AI, CPS, IoT, “smart university”, core infrastructure, students, staff, management,
and physical elements such as buildings and resources. Each of these components plays a crucial role
in the overall operation and efficiency of the university. According to the figure 1 are the following
elements:
1. AI plays an important role in managing numerous processes in a “digital university”. For
example, in the context of adaptive learning, AI algorithms analyze student data to understand
individual learning patterns and adapt teaching methodologies accordingly. These can range
from determining the pace of teaching, creating personalized learning plans, to automating
assessment systems.
2. CPS essentially bridges the gap between the physical and digital worlds. In a “digital
university”, these systems can monitor and control physical components such as energy
consumption, ventilation, heating, etc. in real time. This leads to higher levels of efficiency
and optimized use of resources.
3. IoT serves as the senses of a “digital university”, providing real-time data on various aspects.
This can be the occupancy rate in different parts of the university, current energy
consumption, server load, or even tracking the movement of assets within the university.
4. The basic infrastructure of a “digital university” includes servers, databases, network devices,
etc. These components ensure the uninterrupted flow, storage, and processing of data, which
allows for real-time decision-making and control.
5. Students are the main beneficiaries of a “digital university”. Adaptive learning with AI
provides them with a personalized learning experience. The IoT-enabled infrastructure
provides a comfortable, safe, and supportive environment for their academic and
extracurricular activities.
6. Management and finance: management can use AI, IoT, and CPS to make strategic decisions,
allocate resources, and make forecasts. Predictive models can provide information about
potential future trends, enabling proactive measures. The finance department can also
optimize budget planning, track expenses in real time, and improve financial efficiency with
these technologies.
7. Buildings and resources: “digital university” buildings are not just physical structures, but
also embedded with numerous sensors that are monitored by the CPS. This allows for real-
time monitoring and control of various aspects such as energy, gas, heating, ventilation, and
even security systems, leading to efficient resource management.
8. Security systems: the use of artificial intelligence and the Internet of Things in security
systems helps create a safe and secure environment for students and staff. From AI-powered
video surveillance systems for threat detection to IoT-enabled access control systems, security
is improved on multiple levels.
9. Adaptive learning and teaching processes: AI-driven adaptive learning and teaching processes
form the backbone of the academic environment in a “digital university”. It provides
personalized learning paths for students, helping them to better understand and improve
outcomes.
Figure 1: “Digital university” concept
In a “digital university”, all these elements are interconnected and constantly communicate with
each other, creating an ecosystem that is constantly learning, adapting, and evolving. This results in
higher education that is much more efficient, flexible, and beneficial for all stakeholders.
In the context of a “digital university”, the harmonious integration of AI, CPS, IoT, “smart
university” and other technologies brings numerous benefits that radically change the traditional
educational environment.
One of the most significant improvements is in the area of personalized learning [41-43]. With the
help of artificial intelligence, the university can offer an individualized learning journey for each
student, taking into account their unique learning pace, strengths, and areas for improvement. This
makes learning more productive, improving overall academic performance and student
satisfaction [22,44-47]. In addition, resource management in a “digital university” is extremely
efficient. Cyber-Physical Systems (CPS) allow you to monitor and optimize a variety of resources in
real time, including energy, gas, ventilation, heating, etc. This ability to monitor and manage
resources can significantly reduce the university’s operating costs.
IoT infrastructure further supports this efficiency. From tracking asset movements to monitoring
occupancy rates in different parts of the university, the real-time data provided by IoT devices allows
for efficient management and utilization of physical resources.
In addition, in a “digital university”, the role of leadership becomes much more strategic and data-
driven. AI, IoT, and CPS allow management to make proactive decisions based on predictive models
and real-time data. This capability also extends to the finance department, where budget planning,
cost tracking, and financial efficiency have been significantly improved.
The safety of students and staff is also significantly improved by smart security systems. AI and
IoT technologies make threat detection and access control much more reliable and efficient, ensuring
a safe environment for everyone on campus.
But perhaps one of the most profound impacts of these improvements is how they are transforming
the university into an adaptive, evolving system. Because all elements are interconnected and
constantly communicating with each other, the university as a whole can learn, adapt, and evolve in
real time to better serve its community.
In fact, the introduction of these technologies in a “smart university” leads to a fundamental shift
in higher education, which, using the example of the Ternopil Ivan Puluj National Technical
University, will allow us to demonstrate the effectiveness of increasing competitiveness, quality of
services and productivity. From increased academic performance to efficient resource management,
improved security, and data-driven decision-making, the benefits are diverse and transformative.
5. Conclusions
The future of the Ternopil Ivan Puluj National Technical University lies in the implementation of
the concept of a “digital university” that uses the capabilities of artificial intelligence, cyber-physical
systems and the Internet of Things to adapt to the changing needs of students, faculty and staff.
Universities can optimize their operations and resources to create a more engaging, personalized, and
efficient workflow. With the constant progress of digital technologies, the transition to a “digital
university” is becoming inevitable.
Through the integration of advanced technologies such as AI, CPS, IoT, universities can improve
their operations, from education to management, from financial operations to infrastructure. This
paves the way for an improved, efficient, and interconnected higher education system.
In addition to traditional administrative processes, managing a “digital university” with AI and
CPS will allow optimizing administrative tasks and resource allocation in the future. Strategic
planning and decision-making will be based on predictive models. Using real-time data from various
sources, universities can achieve an unparalleled level of efficiency, accuracy, and flexibility.
In addition, “digital universities” offer ample opportunities for automated infrastructure
management. Thanks to CPS, a university becomes not just a static structure, but an intelligent
infrastructure (augmented university) that adapts to the needs and behavior of its residents. “Smart
buildings” use sensor networks and artificial intelligence algorithms to monitor and control
environmental parameters, optimize energy consumption, manage space use, and ensure the safety of
students and staff.
A “digital university” is more than the sum of its parts. It represents a holistic approach to higher
education where every aspect of university life is interconnected and optimized. It emphasizes a future
where universities are not just educational institutions, but complex, adaptive systems that can evolve
in real time to better serve their communities.
While significant progress has been made in the field of “digital universities”, the journey is far
from over. Future research on these issues at Ternopil Ivan Puluj National Technical University
should continue to address the issues surrounding the implementation of technology, ensuring that it is
applied ethically, effectively and sustainably.
6. References
[1] Christian M. Stracke, Michael Shanks, Oddgeir Tveiten, Smart universities education’s digital
future. Logos Verlag Berlin GmbH, 2017.
[2] Xiao Nie, “Research on smart campus based on cloud computing and internet of things”,
Applied Mechanics and Materials, vol. 380–384, pp. 1951–1954, 2013, doi:
10.4028/www.scientific.net/AMM.380-384.1951.
[3] Innocent Chiawa Igbokwe, “Application of artificial intelligence (AI) in educational
management”, International Journal of Scientific and Research Publications (IJSRP), vol. 13, no. 3, p.
13536, 2023, doi: 10.29322/IJSRP.13.03.2023.p13536.
[4] A. S. Seitbatkalova, Zh.P. Smailova, “Creating smart universities as a challenge to
modernity”, Reports of the national academy of sciences of the republic of kazakhstan, vol. 4, no.
326, pp. 151–158, 2019, doi: 10.32014/2019.2518-1483.130.
[5] Olha I. Potapchuk, Iryna B. Lutsyk, Ihor V. Hevko, Bogdan B. Buyak, “Implementation of
the concept of a smart university in terms of distance education”, Information Technologies and
Learning Tools, №6, vol. 92, pp. 140–153, 2022.
[6] Dewar Rico-Bautista, César D. Guerrero, César A. Collazos, Gina Maestre-Góngora, Julio A.
Hurtado-Alegría, Yurley Medina-Cárdenas, Jose Swaminathan, “Smart university: A vision of
technology adoption”, Revista Colombiana de Computación, vol. 22, no. 1, pp. 44–56, 2021, doi:
10.29375/25392115.4153.
[7] Owoc L. Mieczysław, Marciniak Katarzyna, “Knowledge management as foundation of smart
university”, pp. 1267–1272, 2013.
[8] Aliya Seitbatkalova, Saltanat Tamenova, Bulent Tarman, Saken Mukan, Elmira Yeralina,
“Assessment of implementation of smart university management system: The case of kazakh ablai
khan university of international relations and world languages”, Problems and Perspectives in
Management, vol. 14, pp. 504–514, 2023, doi: 10.21511/ppm.21(1).2023.43.
[9] Liqiao Nong, Geping Liu, Changhui Tang, Ying Chen, “The design and implementation of
campus informatization in chinese universities: A conceptual framework”, Sustainability, vol. 15, no.
6, 2023, doi: 10.3390/su15064732.
[10] Francisco Maciá Pérez, José Vicente Berna Martínez, Iren Lorenzo Fonseca, “Modelling and
implementing smart universities: An IT conceptual framework”, Sustainability, vol. 13, no. 6, 2021,
doi: 10.3390/su13063397.
[11] D W Rico-Bautista, “Conceptual framework for smart university”, Journal of Physics:
Conference Series, vol. 1409, no. 1, Nov. 2019, doi: 10.1088/1742-6596/1409/1/012009.
[12] Anne Bakupa Mbombo, Nadire Cavus, “Smart university: A university in the technological
age”, TEM Journal, vol. 10, no. 1, pp. 13–17, 2021, doi: 10.18421/TEM101-02.
[13] Thanchanok Sutjarittham, Hassan Habibi Gharakheili, Salil Kanhere, Vijay Sivaraman,
“Realizing a smart university campus: Vision, architecture, and implementation”, Dec. 2018, pp. 1–6.
doi: 10.1109/ANTS.2018.8710084.X
[14] Rania Abed Moneim, “Towards a smart university in the light of 21st century skills”, Najah
Univ. J. Res. (Humanities)., vol. 34, pp. 1109–1132, 2020.
[15] Chaoman Xie, “Construction of smart campus cloud service platform based on big data
computer system”, Procedia Computer Science, vol. 208, pp. 583–589, 2022, doi:
10.1016/j.procs.2022.10.081.
[16] Ken Polin, Tan Yigitcanlar, Mark Limb, Tracy Washingto, “The making of smart campus: A
review andConceptual framework”, Buildings, vol. 13, no. 4, 2023, doi: 10.3390/buildings13040891.
[17] Noémie Chagnon-Lessard, Louis Gosselin, Simon Barnabé, Tunde Bello-Ochende, Sebastian
Fendt, Sebastian Goers, Luiz Carlos Pereira Da Silva, Benedikt Schweiger, Richard Simmons,
Annelies Vandersickel, Peng Zhang, “Smart campuses: Extensive review of the last decade of
research and current challenges”, IEEE Access, vol. 9, pp. 124200–124234, 2021, doi:
10.1109/ACCESS.2021.3109516.
[18] Yusuf Kalınkara, Tarık Talan, “Role of the internet of things in education system”, 1st
International Conference on Innovative Academic Studies, pp. 194–198, Sep. 2022.
[19] Seongju Chang, Ardeshir Mahdavi, “A hybrid system for daylight responsive lighting
control”, Journal of The ACM - JACM, vol. 31, Jan. 2001, doi: 10.1080/00994480.2002.10748379.
[20] Xi Yang, Qing Tong, Xunmin Ou, “Analysis of technical energy conservation potential of
china’s energy consumption sectors”, Open Journal of Energy Efficiency, vol. 3, pp. 93–97, Jan.
2014, doi: 10.4236/ojee.2014.34010.
[21] Senny Luckyardi, Ratih Jurriyati, D. Disman, Puspo Dewi Dirgantari, “A systematic review
of the IoT in smart university: Model and contribution”, Indonesian Journal of Science & Technology
7(3) (2022) 529-550, pp. 529–550, 2022, doi: 10.17509/ijost.v7i3.51476.X
[22] Lasse Rouhiainen, “How AI and data could personalize higher education.”
https://hbr.org/2019/10/how-ai-and-data-could-personalize-higher-education (accessed Aug. 03,
2023).X
[23] Jonathan Williams, “Media lab MIT.” https://www.media.mit.edu/about/ (accessed Aug. 03,
2023).X
[24] Tammy Xu, “These simple changes can make AI research much more energy efficient”,
2022, Available: https://www.technologyreview.com/2022/07/06/1055458/ai-research-emissions-
energy-efficient/
[25] Rashid A Saeed, Xiaolin Xia, Xiaojun Li, “Artificial intelligence for higher education
development and teaching skills”, Wireless Communications and Mobile Computing, vol. 2022, pp.
300–307, 2022, doi: 10.1155/2022/7614337.
[26] Behdad Bakhshinategh, Gerasimos Spanakis, Osmar Zaiane, Samira ElAtia, “A course
recommender system based on graduating attributes.” INSTICC; SciTePress, pp. 347–354, 2017. doi:
10.5220/0006318803470354.
[27] Minchuan Huang, Hsianglin Huang, Iping Chen, Ke Chen, Aiguo Wang, “Artificial
intelligence aided course scheduling system”, Journal of Physics: Conference Series, vol. 1792, no. 1,
p. 012063, Feb. 2021, doi: 10.1088/1742-6596/1792/1/012063.
[28] Zhenxing Ge, Ying Hu, “Innovative application of artificial intelligence (AI) in the
management of higher education and teaching”, Journal of Physics: Conference Series, vol. 1533, no.
3, p. 032089, Apr. 2020, doi: 10.1088/1742-6596/1533/3/032089.
[29] Suvojit Dhara, Sheshadri Chatterjee, Ranjan Chaudhuri, Adrijit Goswami, Soumya Kanti
Ghosh, Artificial intelligence in higher education: A practical approach, 1st ed. Taylor; Francis, 2022,
pp. 153–167. doi: 10.1201/9781003184157-8.
[30] Víctor González-Calatayud, Paz Prendes-Espinosa, Rosabel Roig-Vila, “Artificial
intelligence for student assessment: A systematic review”, Applied Sciences, vol. 11, no. 12, 2021,
doi: 10.3390/app11125467.
[31] Amer Al-Badarenah, Jamal Alsakran, “An automated recommender system for course
selection”, International Journal of Advanced Computer Science and Applications, vol. 7, no. 3, 2016,
doi: 10.14569/IJACSA.2016.070323.
[32] Shadi Atalla, Mohammad Daradkeh, Amjad Gawanmeh, Hatim Khalil, Wathiq Mansoor,
Sami Miniaoui, Yassine Himeur, “An intelligent recommendation system for AutomatingAcademic
advising based on curriculum analysisand performance modelin”, Mathematics, vol. 15, no. 1098,
2023, doi: 10.3390/math11051098.
[33] “MIT energy initiative.” https://energy.mit.edu/
[34] Isaac Chuang, Andrew Ho, “HarvardX and MITx: Four years of open online courses – fall
2012-summer 2016”, Dec. 2016, doi: 10.2139/ssrn.2889436.
[35] “Stanford energy and climate initiatives.” https://sustainable.stanford.edu/energy-
climate/energy-initiatives
[36] “Harvard strengthens living laboratory to help mitigate climate impact.”
https://news.harvard.edu/gazette/story/2016/10/harvard-strengthens-living-laboratory-to-help-
mitigate-climate-impact/
[37] “NTU smart campus.” https://www.ntu.edu.sg/about-us/smart-campus
[38] Yuchen Zhang, Z. Y. Dong, Christine Yip, Sharon Swift, “Smart campus: A user case study
in hong kong”, IET Smart Cities, vol. 2, pp. 146–154, Sep. 2020, doi: 10.1049/iet-smc.2020.0047.
[39] “Melbourne uni connects 700 apps in smart campus drive.”
https://www.itnews.com.au/news/melbourne-uni-connects-700-apps-in-smart-campus-drive-522720
[40] Mauro Berni, Paulo Manduca, Sergio Bajay, J. Pereira, J. Fantinelli, “Energy efficiency and
renewable energy technologies using smart grids: Study case on NIPE building at UNICAMP
campus”, Smart Grid and Renewable Energy, vol. 5, pp. 193–197, Jan. 2014, doi:
10.4236/sgre.2014.58018.
[41] Nhi N. Y. Vo, Quang T. Vu, Nam H. Vu, Tu A. Vu, Bang D. Mach, Guandong Xu, “Domain-
specific NLP system to support learning path and curriculum design at tech universities”, Computers
and Education: Artificial Intelligence, vol. 3, p. 100042, 2022, doi: 10.1016/j.caeai.2021.100042.
[42] Pat Pataranutaporn, Valdemar Danry, Joanne Leong, Parinya Punpongsanon, Dan Novy,
Pattie Maes, Misha Sra, “AI-generated characters for supporting personalized learning and well-
being”, Nature Machine Intelligence, vol. 3, no. 12, pp. 1013–1022, 2021, doi: 10.1038/s42256-021-
00417-9.
[43] Emma Sabzalieva, Arianna Valentini, ChatGPT and artificial intelligence in higher education
quick start guide. UNESCO, 2023.
[44] Shaikh Rezwan Rahman, Md. Asfiul Islam, Pritidhrita Paul Akash, Masuma Parvin, Nazmun
Nessa Moon, Fernaz Narin Nur, “Effects of co-curricular activities on student’s academic
performance by machine learning”, Current Research in Behavioral Sciences, vol. 2, p. 100057, 2021,
doi: 10.1016/j.crbeha.2021.100057.
[45] Deepani B. Guruge, Rajan Kadel, Sharly J. Halder, “The state of the art in methodologies of
course recommender systems—a review of recent research”, Data, vol. 6, no. 2, 2021, doi:
10.3390/data6020018.
[46] A. Esteban, A. Zafra, C. Romero, “Helping university students to choose elective courses by
using a hybrid multi-criteria recommendation system with genetic optimization”, Knowledge-Based
Systems, vol. 194, p. 105385, 2020, doi: 10.1016/j.knosys.2019.105385.
[47] F. O. Isinkaye, Y. O. Folajimi, B. A. Ojokoh, “Recommendation systems: Principles, methods
and evaluation”, Egyptian Informatics Journal, vol. 16, no. 3, pp. 261–273, 2015, doi:
10.1016/j.eij.2015.06.005.