2025 International Conference on Pervasive Computational Technologies (ICPCT)

Adaptive Learning Systems: Integrating IoT Sensors

with Machine Learning for Dynamic Curriculum
Adjustment
2025 International Conference on Pervasive Computational Technologies (ICPCT) | 979-8-3315-0868-5/25/$31.00 ©2025 IEEE | DOI: 10.1109/ICPCT64145.2025.10939112

Mrudula kilaru1 Dr. S. Surya2 Mrs. Sindhu Boianapalli3

1 2 3
Assistant professor, Assistant Professor, Assistant Professor,
M.Tech, Siddhartha Academy of Sri Ramachandra Faculty of Department of CSE, CVR college of
Higher Education, Engineering & Technology (SRET), Sri Engineering
Velagapudi Ramakrishna Siddhartha Ramachandra Institute of Higher Vastunagar, Mangalpalli, I
School of Engineering Education & Research, brahimpatnam, Telangana - 501510
[email protected] Porur, Chennai - 600116 [email protected]
[email protected]
Dr. M. Kalyan Chakravarthi6
Dr. S. Vijaya Kumar4 Dr. Mamta Thakur5 6
Senior Lecturer,
4 5
Associate Professor, Assistant Professor, Department of Electronics and
English, B S Abdur Rahman Crescent Department of Mathematics, Chaitanya Communication Engineering,
Institute of Science and Technology, Bharathi Institute of Technology, University of Technology and Applied
Vandalur, Chennai, India Hyderabad -500075 Sciences, Muscat, Al Khuwair,
[email protected] [email protected] Muscat, Oman, PO Box 74
[email protected]
https://orcid.org/0000-0001-9913-8867

Abstract— The broad implementation of learning statistics [1]. Computerized innovation and web availability have
in different curriculum contexts is still difficult, despite empowered novel informative instruments, including ALS,
encouraging results in universities. Secondary and primary which show guarantee for working on the nature of instruction
institutions are hesitant to employ these technologies. By [2].
providing individualized education encounters catered to each
student's requirements, machine learning (ML) based adaptive Computerized reasoning (artificial intelligence) can
learning platforms have revolutionized learning by increasing possibly change advanced education by further developing
student involvement and results. Physical training can now be learning results across a few applications. Man-made
communicated through technology via the growth of the intelligence can make individualized schooling experiences in
Internet of Things (IoT), which links affordable, diverse gadgets view of remarkable training types, decisions, and capacities
and sensors to open, public spaces. This research investigates [3]. ALS naturally changes educational program intricacy and
the relationship between curriculum adjustment, a crucial speed contingent upon execution.
aspect of sports, and physical activities using a decision tree.
This platform gathers vital statistics from IoT-based wearable The Web of Things (IoT) implies a game-changing change
sensors, and by virtualization of the gadget, it interacts with the in how information is accumulated, handled, and utilized in
statistics in real time. Implementing and promoting physical different ventures, including schooling. IoT in schooling
education and learning curriculum in the real world and traverses a large number of purposes, including intuitive
building healthier atmosphere platforms to address the health homerooms and information driven administrative decisions
surveillance problems brought on by IoT sensors are the [4]. In these specific situations, web associated IoT devices
solutions suggested by the empirical evaluation. Research like sensors, contraptions, and computerized educational
results demonstrate the remarkable physical activity apparatuses give constant data about student cooperation,
surveillance accomplished by the suggested approach in homeroom discussions, and different elements. The utilization
comparison to the traditional technologies. With excellent of IoT innovation in school conditions is at this point not an
accuracy ratios (98.5%), estimation ratios (96.6%), unrealistic fantasy; it is rapidly turning into a basic instrument
communication ratios (94.5%), functioning ratios (95.3%), for working on both guidance and concentrating on
effectiveness ratios (93.4), F-values (92.3%), and lower error
experiences [5]. Several sectors have been reshaped by the
rates (17.6%), the computational evaluation of physical
education curriculum can assist learners and enhance the
association of AI and the IoTs, and education is no exception.
related facets of their physical skills. Educating learners in the quickly changing technology
environment requires teaching them about the advantages of
Keywords— Machine learning, Adaptive learning, incorporating cutting-edge technology [6].
Curriculum adjustment, Physical education, and Internet of IoT applications for educational institutions go beyond
things. simple administration duties and include customized
instruction [7]. The importance of ALS, which is made to
I. INTRODUCTION modify the exams and educational materials in response to
Contemporary technology breakthroughs have real-time statistics regarding a learner's functioning and
significantly transformed the schooling scene. The interest for degree of involvement, depends on this. Using complicated
individualized and versatile learning frameworks (ALS) is computations, these systems offer instantaneous, extremely
testing regular instructive methodologies that depend on customized input that takes into account each learner's distinct
customary educational procedures and fixed educational plans education route [8].

979-8-3315-0868-5/25/$31.00 ©2025 IEEE 900

Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.
 2025 International Conference on Pervasive Computational Technologies (ICPCT)

One significant component of the academic system is the ML approaches were picked for their ability to really deal
training impact of physical education, which is closely related with and grasp the different and overflowing information
to advancements in national wellness and academic provided by IoT sensors in instructive settings. DT is utilized
achievement [9]. Students gain competency and self- for characterization issues since it is straightforward and
assurance through physical education and exercise. proficient, making it fantastic for surveying understudy
Educational institution sports allow learners to develop a securing patterns and estimating instructive achievement
broad spectrum of skills and offer them novel strategies, relying upon quantifiable factors. These calculations are direct
tactics, and concepts for performance inside the house and in to get a handle on, which is basic in instructive settings where
the classroom. Physical education curricula at educational readings of framework decisions are expected for future
institutions are crucial for this purpose [10, 11]. The current educational getting sorted out. These frameworks continually
age in sports development is brought about by IoT and look at new information, changing the test, configuration, and
wearable technologies in sports, primarily for wellness substance of assessments continuously. For example, on the
assessments and effectiveness tracking. IoT gadgets, which off chance that a student prevails in a particular region, the
depend on sensor networks, are commonly used to perform framework could conform to give more troublesome questions
this. or change to new trains to ensure a balanced instructive
climate. This variation not just meets the specific scholastic
Hence this study integration of IoT and machine learning necessities of students yet in addition cultivates successful
(ML) algorithm decision tree (DT) is used to investigate the training method by coordinating resources where they are
physical education curriculum adjustment in ALS. generally required.

II. LITERATURE REVIEW The consolidation of IoT measurements with ML

calculations is a significant part of this review, empowering a
The study [12] presented an approach that uses several smooth and dynamic educational plan assessment stage. IoT
IoT detection devices connected to the physical activity sensors in the instructive setting continually accumulate
identification and surveillance system (PAISS), which is information, which is accordingly integrated into continuous
considered a key concept for intelligent medical care, to ML calculations. Information standardization, tending to
continuously track a safe environment. Learners may be blunders, and removing highlights are a couple of the
capable of tracking their body temperature, heart rate, blood preliminary techniques taken to guarantee the information's
pressure, and temperatures in real time because of this. Based exactness and materialness for ML. This strategy guarantees
on PAISS, an experiment was verified to address the novel that the frameworks are exact and current all through the term,
problems of the IoT context for efficient health surveillance addressing the latest scholarly examples and understudy
for university students. correspondence. The input circle framed by IoT devices and
The study [13] evaluated the deployment, adoption, and ML calculations is basic for the continuous improvement of
effect of exercise circulation as a component of the the assessment structure, making it more delicate to both
PECM method, which aims to enhance the teaching understudy prerequisites and academic points.
profession's physical education curriculum model in
urbanized schools. PECM was embraced by educators and the B. System Design
administration. As a result, physical training was included in The framework design of the IoT-based actual schooling
the regular curriculum and outside sports training activities. observing stage is expected to integrate progressed
The paper [14] describes an innovative human action advancement into normal instructive tasks without upsetting
identification method (HAIM) that uses inertia sensors to the typical course of preparing and advancing without a hitch.
detect physical exercises in continual phases. The study Each part is planned to work pair, in this manner ensuring the
focused on portable sensors that constantly track human whole construction is both successful and usable. The
wellness through various postures and actions, enabling reasonable format of the IoT-driven assessment system
prompt and efficient management. The recommended method portrays a multi-layered procedure intended to further develop
was examined on 3 tasks to determine its practicality. the two information stream and design execution. The
establishment is the information gathering layers, which
The study [15] found that older individual attitudes and comprise of various IoT devices and sensors dissipated across
perspectives were related to their engagement with Free-time the actual training setting. These devices assemble different
physical conduct (FTPC), providing an understanding of information sorts, including relevant and association inputs.
physical exercise development. A few examinations have Past this, the edge calculation level restricts information
been directed to evaluate the perspectives and impression of investigation to limit postponement and weight on unified
more established people in different spaces. frameworks. This layer utilizes smaller ML strategies to lead
beginning assessments and separating insights prior to
III. MATERIALS AND METHODS sending it to the cloud.
The cloud calculation level is the underpinning of the
A. Adoption of ML Methods framework, giving solid handling capacity to putting away
The utilization of ML approaches in the setting of IoT- information, more extensive information investigation, and
based ALS is a vital part of this review, which centers around more muddled ML exercises. This layer incorporates the key
working on the versatility and customization of actual datasets and ML stages, which handle most of information
schooling checking. This part frames the picking and thinking assessment and dependable protection. It furthermore helps
for specific ML strategies, the versatile techniques utilized, the application layer, which creates and keeps up with the
and the consolidation of IoT sensors into these systems, framework's projects and administrations. These applications
showing how these pieces cooperate to upset actual work return broke down information to clients, actually finishing
assessments. the circle of correspondence. Its UI and client skill format are

901
Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.
 2025 International Conference on Pervasive Computational Technologies (ICPCT)

basic since they straightforwardly affect the openness and as bodily temperature, pulse level, and the growth of smart and
adequacy of electronic gadgets in schooling. digital gadgets. Table I displays the sequence in which the
physical action surveillance statistics for the IoT-PECA model
The backend methods of the IoT-based actual instructive variables are represented.
observing stage are where most of the innovative intricacies
lie. These activities incorporate information examination,
framework preparing, and the continuous update of the ML TABLE I. SURVEILLANCE OF LEARNER PHYSICAL ACTIVITIES WITH
strategy. Information assembled from IoT sensors is first pre- IOT-PAMD
handled at the edge, which includes purifying, normalizing, IoT-
Variables PAISS PECM HAIM FTPC
and extricating highlights. These pre-handled insights are then PECA
shipped off the cloud, where further developed information Accuracy 58.4
64.5 73.2 82.7 98.5
handling tasks are completed. These obligations include Percentage
Estimation 55.2
conglomerating information from different sources, leading Percentage
65.6 71.3 83.8 96.6
definite investigations to determine more prominent Communication 56.3
comprehension, and getting ready information for joining into 66.4 75.5 86.6 94.5
Percentage
ML calculations. Functioning
59.5 70.6 78.5 90 95.3
Percentage
Recreation is a ceaseless movement in the framework that Effectiveness
57.3 68.5 76.4 88.7 93.4
utilizes both unaided and regulated learning draws near. ML Percentage
calculations are first prepared on authentic information to F-Value
60.5 72.3 80 90.2 92.3
make principles and determining abilities. As the framework Percentage
continues working, slow preparation approaches are utilized Lower Error
88.4 74.6 66 44.8 17.6
Percentage
to refresh the calculations with new information. This
technique ensures that the reproductions change in accordance A. Accuracy Proportion
with vacillations in educational patterns while staying Accuracy is increased and notable adjustments in learner
proficient over the long run. The backend additionally physical exercise are shown by the RL algorithm. Employing
incorporates solid security systems to save information a multiple-sensor gadget strategy reduces the mean error and
privacy and validness. This includes involving complex increases the accuracy of classifying physical exercise rather
encryption calculations for communicating information, than relying on a surveillance gadget for gathering statistics.
leading occasional wellbeing assessments, and following Employing a single sensing gadget with many sensors and
worldwide information security necessities. These security combining statistics to offer more trustworthy data on
techniques are pivotal for holding client trust and guaranteeing physical exercise in meditation decisions is linked to the
the framework's wellbeing from assaults, everything being ability to improve classification accuracy and estimation. By
equal. integrating surveillance sensors like the neck, foot, chest, and
hand, the workout database generates an altimeter in a variety
IV. RESULT AND DISCUSSION of locations, including the leg, chest, and hand. The accuracy
Supporting ALS transformation proactively and of the 3 models framework, category, and reverse fusion is
improving the quality of education created by digital systems computed. Fig. 1 shows the suggested physical exercise
in schools may constitute an important technological option to surveillance system's mean accuracy. The outcomes
raise the curriculum and efficient degree of physical education demonstrate that the recommended method for merging
curriculum in schools. The implementation possibilities of IoT gadgets provides exceptional accuracy.
sensors in the physical education setting are examined in this
research. Accuracy Percentage
The IoT gadgets gather necessary data and
120
communicate in real-time with the IoT while the system goes
through a virtualized system. Digital systems for establishing 100
a real-time database, academic benchmark structure, and 80
innovative technological systems can be provided by IoT
60
wearables. Initially, the IoTs are used to study and identify
different physical activity tracking sensors. The smart 40
wearable sensors serve as the foundation for the 20
learner's health service offered. It gathers the 0
learner's temperatures and pulse and alerts educators to
PAISS PECM HAIM FTPC IoT-PECA
immediate information access. This study used a non-invasive
physical action surveillance technique to demonstrate the Accuracy Percentage
potential of leveraging sensing statistics from IoT wearable
sensors as an asset for continuous surveillance. The empirical
Fig. 1. Average Accuracy Percentage
findings show that tracking physical action efficiently records
students' motions and actions for use in medical applications. In summary, this research emphasizes the critical role that
The purpose of physical action surveillance is to continually smart technology plays in providing an educational platform
gather learner physical statistics using wearable technology. for more thorough adoption and automated innovations. The
According to certain research, the number of wearable gadgets advantages of traditional physical education curricula are
that gather vital biological and physical learner statistics has combined with smart technological innovations to increase the
grown. These seek to track learners' routine exercise while precision of physical education and provide learners with a
creating innovation to track and assist physical ailments, such

902
Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.
 2025 International Conference on Pervasive Computational Technologies (ICPCT)

more personalized curriculum. The higher accuracy of

the physical education program is represented in the selection Communication Percentage
of academic result measurements by contrasting the various
signals leading to the impact and analysis. 100
80
B. Communication and Functioning Proportion
60
The team conducted a study to analyze the correlation
between physical exercise and academic functionality. 40
Research suggests that physical exercise is linked to improved 20
academic functionality, whether specialized or general. The
0
study found a substantial difference in academic functioning
for lower-level students in physical exercise at university. PAISS PECM HAIM FTPC IoT-PECA
Coaches can employ physical activity surveillance to enhance
Communication Percentage
team performance by swiftly analyzing individual player
functioning and team organization. For tracking all the athletic
events, it's ideal to employ an IoT-based sensor gadget for Fig. 3. Average Communication Proportion
data basis, as trainers may only identify half of them. Sports
activities may employ gadget regression to gauge and enhance
skills for learners while avoiding damage. Fig.2 and 3 show Estimation Percentage
the average functioning and communication proportion. 120
100
Functioning Percentage 80
120 60
40
100
20
80 0
PAISS PECM HAIM FTPC IoT-PECA
60

40 Estimation Percentage

20 Fig. 4. Average Estimation Proportion

0
PAISS PECM HAIM FTPC IoT-PECA D. Effectiveness Proportion
The evaluation of learner wellness data gathered through
Fig. 2. Average Functioning Percentage physical education tracking of the extremely effective usage
of exercise equipment in learners' physical education. It
Good physical wellness can be attributed to good training emphasizes how very effective the data-driven framework of
experiences and communication among learners. For each contemporary physical exercise technology is for learner
outcome and characteristic, connections are investigated using education. Surveillance of healthcare procedures and other
datasets and linear regression. Concurrently documented are health aspects greatly lowers wellness and error levels while
learner operations, classes, and communications that also enhancing system uniformity and reliability. The findings
contribute to their growth. The study focused on a small group supported the examination of exercise and the influence of
of learners from various locations due to the time-consuming sports on efficiency, health, physical education, job
nature of physically managing and evaluating such data. alternatives, and success metrics in several research. The
Inadequate VR technological advances on campuses limit the exercise list, which is accomplished through motion
use of auto-monitoring equipment in collaborative sports. innovations, takes an identical strategy to increase pupils'
Athletes are known for their ability to quickly adjust to various physical action effectiveness. Among other things, it rises
settings that need agility and adaptability. with regular training and falls with ineffective and undesirable
training. In physical education and other subjects,
C. Estimation and Lower Error Proportion concentration is crucial, and the level of emphasis is essential
The curriculum prioritizes wellness and fitness when it for efficiently obtaining data [16]. Creating a university-level
comes to exercise involvement. The accuracy of this training curriculum, motivating instructors to develop a fresh
clarification is dubious and scarcely explored. Physical set of capabilities for exercise classes, and utilizing highly
education focuses on improving students' involvement in effective educational facilities and physical education are all
routine tasks. This paper examines the relationship between part of maximizing the physical training curriculum. Learners
student wellness rates, expected conduct, mediation who have the capacity for efficient physical exercise should
circumstances, and restrictions. The study indicates that lower perform better in rigorous and intense training. The
error rates estimate a self-identified pattern, but learners effectiveness proportion is displayed in Table II.
greatly minimize this impact. Figure 8a displays the
mean estimated proportion.

903
Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.
 2025 International Conference on Pervasive Computational Technologies (ICPCT)

TABLE II. OUTCOME OF EFFECTIVENESS Employing ALS corresponds with environmentally friendly
No. of IoT- objectives, fostering open and fair quality studies. This
PAISS PECM HAIM FTPC strengthens the school's image as innovative and
Learners PECA
10 50.2 62.4 70.2 80.2 87.7 environmentally accountable. These observations highlight
20 52.4 62.5 71.3 80.6 88.4 the importance of utilizing ALS to achieve long-term learning
30 53.7 63.6 72.8 81.6 90 achievement.
40 54.6 65.6 73.9 82.7 90.5
50 55.7 68 74.7 83.5 91.2 According to this research, DT can be used to
60 56.9 68.4 75.8 84.6 92.8 adjust physical education curriculum while acknowledging
70 57.8 69.9 76.9 85.7 94 the importance of IoT sensors for physical activity to IoT
80 59 70 79.6 86 94.2
issues. A comprehensive approach for resolving such
90 59.6 70.3 80.2 86.2 94.6
challenges has been devised and examined by learners with
100 60.3 71 81 87 93.4 various degrees of physical and functioning ability. The two
main contributions of the data evaluation are: tracking
E. F-Value different physical actions in learners studying physical
Table III displays the F-value evaluation of exercise wellness employing IoT sensors, such as daily strolling,
employing a database that includes sensors and sets of jogging, and resting to practice activity regularly. Employing
surveillance gadgets. The model instrument assesses the IoT-PECA approaches, the difficulties are overcome by the
different actions such as strolling, sitting, standing, lying, etc. work necessary to supply portable IoT sensors to track
that are suggested in the database. For the ankle, chest, and students' exercise routines with a functioning proportion. With
hand combos of detectors, exercises are produced, and the excellent accuracy ratios (98.5%), estimation ratios (96.6%),
outcomes are analyzed and presented. The findings show that communication ratios (94.5%), functioning ratios (95.3%),
students' functioning during exercises increases involvement effectiveness ratios (93.4), F-values (92.3%), and lower error
when gadgets are connected. The various gadget places, such rates (17.6%), the computational evaluation of physical
as the ankle and hand, may be investigated for model education curriculum can assist learners and enhance the
evaluation [17]. As an outcome, when the two sensors' related facets of their physical skills. Ultimately, the findings
functioning is combined, exercise has the greatest F-value. For support the suggested approach to determine the physical
instance, the foot, wrist, and chest sensor is utilized to wellness of the learners for further observation. The suggested
combine the data of learners' physical exercise analysis. The framework's safety features will be included in the future to
data above display the mean F-score once it has been boost reliability and functionality.
computed. The findings blend gadgets with physical exercise
forecasts and show that physical exercise functions best. In REFERENCES
Table III, the F-value outcome is displayed. [1] W S. Wang, C. Christensen, W. Cui, R. Tong, L. Yarnall, L. Shear,
and M. Feng, "When adaptive learning is effective learning:
comparison of an adaptive learning system to teacher-led instruction,"
TABLE III. OUTCOME OF F-VALUE Interactive Learning Environments, vol. 31, no. 2, pp. 793–803, Feb.
2023.
No. of IoT-
PAISS PECM HAIM FTPC [2] H. Khosravi, S. Sadiq, and D. Gasevic, "Development and adoption of
Learners PECA
10 52.4 66.8 76.1 80.4 89.6 an adaptive learning system: Reflections and lessons learned," in Proc.
20 55.5 67.8 76.2 81.5 90 51st ACM Tech. Symp. Computer Science Educ., Feb. 2020, pp. 58–64.
30 59.1 69 77.3 82.6 85.2 [3] W. Holmes and I. Tuomi, "State of the art and practice in AI in
40 61.1 70.1 77.4 83.5 86.3 education," Eur. J. Educ., vol. 57, no. 4, pp. 542–570, Dec. 2022.
50 64.9 71.2 77.8 85.2 87.6 [4] M. Al-Emran, S. I. Malik, and M. N. Al-Kabi, "A survey of Internet of
60 66.9 72.3 78.2 86 88.4 Things (IoT) in education: Opportunities and challenges," in Toward
70 67.8 73.3 78.6 86.4 89.4 Social Internet of Things (IoT): Enabling Technologies, Architectures,
80 61 74.6 9 87.5 90.1 and Applications: Emerging Technologies for Connected and Smart
90 60.6 75.7 79.4 88.6 91.4 Social Objects, 2020, pp. 197–209.
100 65.3 75.8 80.2 89.2 92.3 [5] A. Felicia, W. K. Wong, W. N. Loh, and F. H. Juwono, "The increasing
role of IoT in the education sector: A review of Internet of educational
things (IoT)," in Proc. 2021 Int. Conf. Green Energy, Computing, and
When contrasted to PAISS, the PECM, the HAIM, and the Sustainable Technology (GECOST), Jul. 2021, pp. 1–6.
FTPC techniques, the suggested structure IoT-PECA exhibits [6] A. Kumar, M. Rani, D. R. Sisodia, Y. Perwej, A. C. Kakde, and F. M.
excellent accuracy ratios, estimation ratios, communication Rakhimjonovna, "Transforming education through IoT and AI:
ratios, functioning ratios, effectiveness ratios, F-scores, and Opportunities and challenges," Educational Administration: Theory
lowered error rates. The investigation highlights DT in and Practice, vol. 30, no. 5, pp. 11610–11622, May 2024.
physical education that acknowledges the value of exercising [7] M. Chanthiran, A. B. Ibrahim, and M. H. Rahman, "A systematic
to wearable IoT sensor issues. literature review with bibliometric meta-analysis of IoT and AI
technology adoption in education," Evaluation Studies in Social
Sciences, vol. 2, pp. 7–13, Oct. 2021.
V. CONCLUSION AND FUTURE SCOPE [8] K. Osadcha, V. Osadchyi, H. Chemerys, and A. Chorna, "The review
of the adaptive learning systems for the formation of individual
To improve student achievement, physical education educational trajectory," Educational Administration: Theory and
management can benefit greatly from the incorporation of ML Practice, vol. 30, no. 5, pp. 11728–11744, 2024.
and IoT-sensors ALS. These technologies provide customized [9] P. Rocliffe, M. Adamakis, B. T. O’Keeffe, L. Walsh, A. Bannon, L.
educational opportunities that increase learner involvement García-González, F. Chambers, M. Stylianou, I. Sherwin, P. Mannix-
and educational achievement, potentially leading to increased McNamara, and C. MacDonncha, "The impact of typical school
registration. Using ML and IoT in education allows for real- provision of physical education, physical activity and sports on
adolescent mental health and wellbeing: A systematic literature
time monitoring and assessment of learner advancement, review," Adolescent Research Review, vol. 9, no. 2, pp. 339–364, Jun.
leading to more successful and satisfying learning activities. 2024.

904
Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.
 2025 International Conference on Pervasive Computational Technologies (ICPCT)

[10] R. Burgueño, Á. Abós, J. Sevil-Serrano, L. Haerens, K. De Cocker, and primary schools," Physical Education and Sport Pedagogy, vol. 26, no.
L. García-González, "A circumplex approach to (de) motivating styles 1, pp. 79–96, Jan. 2021.
in physical education: Situations-in-school–physical education [14] A. Jalal, M. Batool, and K. Kim, "Stochastic recognition of physical
questionnaire in Spanish students, pre-service, and in-service activity and healthcare using tri-axial inertial wearable sensors," Appl.
teachers," Measurement in Physical Education and Exercise Science, Sci., vol. 10, no. 20, p. 7122, Oct. 2020.
vol. 28, no. 1, pp. 86–108, Jan. 2024.
[15] S. Lee, C. Lee, and J. An, "Psycho-social correlates of leisure-time
[11] A. Oudah, R. Abbood, S. Shabib, L. Aldewan, and M. Ghazi, physical activity (LTPA) among older adults: A multivariate analysis,"
"Developing physical education curricula within the framework of Eur. Rev. Aging Phys. Act., vol. 17, pp. 1–7, Dec. 2020.
digital transformation to achieve sustainable development," Teacher
Education and Curriculum Studies, vol. 9, no. 3, pp. 86–102, 2024. [16] S. B. Rajoli and G. Manoharan, "Gender perception of talent
management practices among IT professionals in Hyderabad," in Proc.
[12] C. L. Zhong, "Internet of Things sensors assisted physical activity 2024 3rd Int. Conf. Comput. Model. Simul. Optim. (ICCMSO), Phuket,
recognition and health monitoring of college students," Measurement, Thailand, 2024, pp. 182–187, doi:
vol. 159, p. 107774, Jul. 2020. 10.1109/ICCMSO61761.2024.00046.
[13] R. M. Telford, L. S. Olive, R. J. Keegan, S. Keegan, and R. D. Telford, [17] K. Subramani and G. Manoharan, "Humanizing the role of artificial
"Teacher and school outcomes of the Physical Education and Physical intelligence in revolutionizing emotional intelligence," in Proc. 2024
Literacy (PEPL) approach: a pragmatic cluster randomized controlled 3rd Int. Conf. Comput. Model. Simul. Optim. (ICCMSO), Phuket,
trial of a multicomponent intervention to improve physical literacy in Thailand, 2024, pp. 237–242, doi:
10.1109/ICCMSO61761.2024.00056

905
Authorized licensed use limited to: HCT Muscat. Downloaded on April 06,2025 at 07:36:53 UTC from IEEE Xplore. Restrictions apply.