Article Open Access

Improving the Classification Performance of SVM, KNN, and Random Forest for Detecting Stress Conditions in Autistic Children

Melinda Melinda, Yunidar Yunidar, Rizka Miftahujjannah, Siti Rusdiana, Amalia Amalia, Lailatul Qadri Zakaria

Abstract


This paper addresses the critical challenges of managing stress in autistic children by introducing an innovative deployable system designed to detect signs of stress through continuous monitoring of physiological and environmental indicators. The system, implemented as a convenient portable detection system, measures key parameters such as heart rate, body temperature and skin conductance. The data is accessed in real-time and displayed on the Blynk application with an IoT system and viewed remotely via an Android device, allowing caregivers to receive instant notifications upon detection of potential stress symptoms. This timely alert system enables rapid intervention, potentially reducing stress intensity and providing peace of mind to caregivers. The study further compares three powerful data analysis methods namely Support Vector Machine (SVM), K-nearest neighbors (KNN) and Random Forest (RF) in interpreting the collected sensor data. The SVM-based system achieved a fairly good detection accuracy of 90%, KNN also showed excellent results of 92% while the Random Forest-based system showed superior performance with an impressive accuracy of 95%. These findings suggest that the Random Forest method exhibits a superior level of effectiveness in accurately predicting the onset of stress conditions., providing the importance for technological advancements that can be applied in supporting better management of autism-related behavioral defenses.


Keywords


Stress, Blynk, Support Vector Machine, K-nearest neighbors, Random Forest

References


M. Mousikou, A. Kyriakou, and N. Skordis, “Stress and growth in children and adolescents,” Hormone Research in Paediatrics,

vol. 96, no. 1, pp. 25–33, Mar. 2023, doi: 10.1159/000521074.

V. Codazzi, G. Frontino, L. Galimberti, et al., “Mechanisms and risk factors of metabolic syndrome in children and adolescents,”

Endocrine, vol. 84, pp. 16–28, 2024, doi: 10.1007/s12020-023-03642-x.

T. Yalim and S. Mohamed, “Meltdown in Autism: Challenges and Support Needed for Parents of Children with Autism,” Int. J. Acad. Res. Progress. Educ. Dev., vol. 12, no. 1, 2023, doi: 10.6007/ijarped/v12-i1/16184.

I. Y. Afif et al., “Effect of Short-Term Deep-Pressure Portable Seat on Behavioral and Biological Stress in Children with Autism Spectrum Disorders: A Pilot Study,” Bioengineering, vol. 9, no. 2, 2022, doi: 10.3390/bioengineering9020048

M. Lotan and M. Icht, “Diagnosing Pain in Individuals with Intellectual and Developmental Disabilities: Current State and Novel Technological Solutions,” Diagnostics, vol. 13, no. 3, 2023, doi: 10.3390/diagnostics13030401.

G. Ribeiro, O. Postolache and F. F. Martín, "A New Intelligent Approach for Automatic Stress Level Assessment Based on Multiple Physiological Parameters Monitoring," in IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1-14, 2024, Art no. 4001714, doi: 10.1109/TIM.2023.3342218

C. B. D. Kuncoro, A. Efendi, W.-J. Luo, M. M. Sakanti, and M. I. Ammarullah, “Wireless-based portable device heart rate measurement as biomedical devices for stress detection,” AIP Advances, vol. 14, no. 4, p. 045021, Apr. 2024, doi: 10.1063/5.0200619.

H. E. Semary, K. A. Al-Karawi, M. M. Abdelwahab, and A. M. Elshabrawy, “A Review on Internet of Things (IoT)-Related Disabilities and Their Implications,” J. Disabil. Res., vol. 3, no. 2, pp. 1–16, 2024, doi: 10.57197/jdr-2024-0012.

O. J. Adeyeye and I. Akanbi, “Artificial intelligence for systems engineering complexity: a review on the use of AI and machine learning algorithms,” Computer Science & IT Research Journal, vol. 5, no. 4, pp. 787–808, 2024, doi: 10.51594/csitrj.v5i4.1026.

M. M. Taye, “Understanding of machine learning with deep learning: Architectures, workflow, applications and future directions,” Computers, vol. 12, no. 5, p. 91, 2023, doi: 10.3390/computers12050091.

A. K. Rehn, V. R. Caruso, and S. Kumar, “The effectiveness of animal-assisted therapy for children and adolescents with autism spectrum disorder: A systematic review,” Complementary Therapies in Clinical Practice, vol. 50, p. 101719, 2023, doi: 10.1016/j.ctcp.2022.101719.

A. Khairah, Melinda, I. Hasanuddin, D. Asmadi, R. Arifin, and R. Miftahujjannah, “University students stress detection during final report subject by using NASA TLX method and logistic regression,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 3, pp. 215–226, 2025, doi: 10.29207/resti.v9i3.6401.

S. L. Stewart, G. K.C. King, J. N. Van Dyke, and J. W. Poss, “Predicting Service Urgency in Children and Youth with Autism Spectrum Disorder: The Development of an Algorithm,” J. Psychiatry Psychiatr. Disord., vol. 07, no. 06, pp. 210–222, 2023, doi: 10.26502/jppd.2572-519x0202.

R. Rahman, M. Samiun, N. Mohammad, M. Prabha, A. M. Zaman, R. Khan, and M. Hossain, “Wearable technology for real-time monitoring of stress and behavior in autistic individuals in the USA,” Journal of Management, vol. 2, pp. 70–77, 2025, doi: 10.53935/jomw.v2024i4.869.

P. Pergantis, V. Bamicha, A. Doulou, A. I. Christou, N. Bardis, C. Skianis, and A. Drigas, “Assistive and emerging technologies to detect and reduce neurophysiological stress and anxiety in children and adolescents with autism and sensory processing disorders: A systematic review,” Technologies, vol. 13, no. 4, p. 144, 2025, doi: 10.3390/technologies13040144.

M. Melinda, V. Setiawan, Y. Yunidar, G. Sakarkar, and N. Basir, “Portable stress detection system for autistic children using fuzzy logic,” Jurnal Nasional Teknik Elektro, vol. 13, no. 2, pp. 61–68, Jul. 2024, doi: 10.25077/jnte.v13n2.1203.2024.

C. Love, L. Sominsky, M. O’Hely, et al., “Prenatal environmental risk factors for autism spectrum disorder and their potential mechanisms,” BMC Medicine, vol. 22, p. 393, 2024, doi: 10.1186/s12916-024-03617-3.

A. Frolli, G. Savarese, F. Di Carmine, A. Bosco, E. Saviano, A. Rega, M. Carotenuto, and M. C. Ricci, “Children on the autism spectrum and the use of virtual reality for supporting social skills,” Children, vol. 9, no. 2, p. 181, 2022, doi: 10.3390/children9020181.

A. Roy and S. Chakraborty, “Support vector machine in structural reliability analysis: A review,” Reliability Engineering & System Safety, vol. 233, p. 109126, 2023, doi: 10.1016/j.ress.2023.109126.

I. Malashin, V. Tynchenko, A. Gantimurov, V. Nelyub, and A. Borodulin, “Support vector machines in polymer science: A review,” Polymers, vol. 17, no. 4, p. 491, 2025, doi: 10.3390/polym17040491.

H. Li, “K-nearest neighbor,” in Machine Learning Methods, Singapore: Springer, 2024, doi: 10.1007/978-981-99-3917-6_3.

R. K. Halder, M. N. Uddin, M. A. Uddin, et al., “Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications,” Journal of Big Data, vol. 11, p. 113, 2024, doi: 10.1186/s40537-024-00973-y.

H. A. Salman, A. Kalakech, and A. Steiti, “Random forest algorithm overview,” Babylonian Journal of Machine Learning, pp. 69–79, 2024, doi: 10.58496/BJML/2024/007.

Z. Sun, G. Wang, P. Li, H. Wang, M. Zhang, and X. Liang, “An improved random forest based on the classification accuracy and correlation measurement of decision trees,” Expert Systems with Applications, vol. 237, p. 121549, 2024, doi: 10.1016/j.eswa.2023.121549.

N. Jalal, A. Mehmood, G. S. Choi, and I. Ashraf, “A novel improved random forest for text classification using feature ranking and optimal number of trees,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 6, pp. 2733–2742, 2022, doi: 10.1016/j.jksuci.2022.03.012.

C. Avc?, M. Budak, N. Ya?mur, and F. Balç?k, “Comparison between random forest and support vector machine algorithms for LULC classification”, IJEG, vol. 8, no. 1, pp. 1–10, 2023, doi: 10.26833/ijeg.987605.

J. Kim, D. Yoon and H. -s. Kim, "Random Forest Approach in Prediction Workers' Stress from Personality Traits," 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, Republic of, 2022, pp. 2356-2358, doi: 10.1109/ICTC55196.2022.9952879.

K. Takahashi, K. Yamamoto, A. Kuchiba, et al., "Confidence interval for micro-averaged F1 and macro-averaged F1 scores,"Applied Intelligence, vol. 52, pp. 4961–4972, 2022. doi: 10.1007/s10489-021-02635-5.

M. Lotan and M. Icht, “Diagnosing Pain in Individuals with Intellectual and Developmental Disabilities: Current State and Novel Technological Solutions,” Diagnostics, vol. 13, no. 3, 2023, doi: 10.3390/diagnostics13030401. S. Mukodimah and C. Fauzi, "Comparison of tree implementation, regression logistics, and random forest to detect iris types," TAM (Technology Acceptance Model) Journal, vol. 12, no. 2, pp. 149–157, 2021.

R. V. Anand, A. Q. Md, S. Urooj, S. Mohan, M. A. Alawad, and A. C., “Enhancing diagnostic decision-making: Ensemble learning techniques for reliable stress level classification,” Diagnostics, vol. 13, no. 22, p. 3455, 2023, doi: 10.3390/diagnostics13223455




DOI: https://doi.org/10.52088/ijesty.v5i4.1206

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Melinda Melinda, Yunidar Yunidar, Rizka Miftahujjannah, Siti Rusdiana, Amalia Amalia, Lailatul Qadri Zakaria

International Journal of Engineering, Science, and Information Technology (IJESTY) eISSN 2775-2674