2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 19 , Issue 2 , PP: 211-223, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Maddala Kranthi 1 , Saswati Debnath 2 , Priyadharsini 3 , R. Venkatesan 4 *
Doi: https://doi.org/10.54216/FPA.190216
Identifying Autism early in children is vital for ensuring more precise developmental support and effective therapeutic interventions. Traditional diagnostic approaches are frequently delayed, and data privacy concerns limit the availability of broad, multi-institutional datasets required for effective machine learning models. To address these limitations, this study proposes a CNN-LSTM-based autism detection model for children using Federated Learning (FL). In the model, temporal and spatial information is extracted from the facial CNNs are highly adept at using convolutional filters to extract spatial features from images. LSTM networks are a specific type of Recurrent Neural Network (RNN) that is ideal for processing time-series or sequences because it can identify long-term relationships in sequential data. This architecture uses CNN layers to extract spatial information from important indications that are important for detecting ASD, like eye patterns, gestures, and facial expressions. After that, these features are sent to LSTM layers, which examine the time-dependent and sequential behavioral patterns associated with autism. Federated Learning allows the locally to train the model on its own dataset locally, sharing only model updates with a central server, thereby preserving data privacy while promoting diverse data contributions. According to experimental results using the proposed techniques, the federated CNN-LSTM model performs 4.3% better than the conventional centralized models because it has less overfitting and is more resilient to a range of data distributions. The model’s performance metrics further highlight its reliability, accuracy, precision, recall, and F1-Score values reaching 98.90%, 97.80%, 98.05%, and 98%, respectively, showing its potential for reliable ASD detection in children across diverse populations.
Autism , Convolutional Neural Networks , Long Short-Term Memory , Children , Federated Learning
[1] M. Alsaidi, N. Obeid, N. Al-Madi, H. Hiary, and I. Aljarah, "A Convolutional Deep Neural Network Approach to Predict Autism Spectrum Disorder Based on Eye-Tracking Scan Paths," Information, vol. 15, no. 3, p. 133, 2024, doi: 10.3390/info15030133.
[2] A. Amirbay et al., "Development of an algorithm for identifying the autism spectrum based on features using deep learning methods," Int. J. Electr. Comput. Eng., vol. 14, no. 5, pp. 2088–8708, 2024, doi: 10.11591/ijece.v14i5.pp5513-5523.
[3] Autism Spectrum Disorder Facial Image Dataset (ASD-FID), [Online]. Available: https://drive.google.com/drive/folders/1XQU0pluL0m3TIlXqntano12d68peMb8A?usp=sharing. [Accessed: 14-Nov-2024].
[4] Autistic Children Facial Image Data Set, [Online]. Available: https://www.kaggle.com/datasets/imrankhan77/autistic-children-facial-data-set. [Accessed: 14-Nov-2024].
[5] J. Baio, L. Wiggins, and D. L. Christensen, "Prevalence of Autism Spectrum Disorder Among Children Aged 8 Years — Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2014," MMWR Surveill. Summ., vol. 67, no. SS-6, pp. 1–23, 2018, doi: 10.15585/mmwr.ss6706a1.
[6] R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, and N. Elhadad, "Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission," in Proc. 21st ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 2015, pp. 1721–1730, doi: 10.1145/2783258.278861.
[7] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic minority over-sampling technique," J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002, doi: 10.1613/jair.953.
[8] S. Chen, M. Jiang, and Q. Zhao, "Deep Learning to Interpret Autism Spectrum Disorder Behind the Camera," IEEE Trans. Cogn. Dev. Syst., 2024, doi: 10.1109/tcds.2024.3386656.
[9] P. Gelmez, T. E. Karakoc, and O. Ulucan, "Autism Spectrum Disorder and Atypical Brain Connectivity: Novel Insights from Brain Connectivity-Associated Genes by Combining Random Forest and Support Vector Machine Algorithm," OMICS: J. Integr. Biol., 2024, doi: 10.1089/omi.2024.016.
[10] S. Gupta et al., "Enhancing Autism Spectrum Disorder Classification with Lightweight Quantized CNNs and Federated Learning on ABIDE-1 Dataset," Mathematics, vol. 12, no. 18, p. 2886, 2024, doi: 10.3390/math12182886.
[11] S. B. Jugunta et al., "Unleashing the Potential of Artificial Bee Colony Optimized RNN-Bi-LSTM for Autism Spectrum Disorder Diagnosis," Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 11, 2023, doi: 10.14569/IJACSA.2023.0141173.
[12] K. Khan and R. Katarya, "WS-BiTM: Integrating White Shark Optimization with Bi-LSTM for Enhanced Autism Spectrum Disorder Diagnosis," J. Neurosci. Methods, vol. 110319, 2024, doi: 10.1016/j.jneumeth.2024.110319.
[13] C. Li et al., "Multimodal foundation models: From specialists to general-purpose assistants," Found. Trends® Comput. Graph. Vis., vol. 16, no. 1-2, pp. 1–214, 2024, doi: 10.1561/0600000110.
[14] C. Lord et al., "The Autism Diagnostic Observation Schedule (ADOS): A Standard Measure of Social and Communication Deficits Associated with the Spectrum of Autism," J. Autism Dev. Disord., vol. 30, no. 3, pp. 205–223, 2020, doi: 10.1023/A: 1005379700087.
[15] K. Mittal, K. S. Gill, D. Upadhyay, S. Dangi, and G. R. Kumar, "Applying Machine Learning and the Gradient Boosting Classification Method for Evaluating the Probability of Autism," in Proc. IEEE 9th Int. Conf. Converg. Technol. (I2CT), 2024, pp. 1–5, doi: 10.1109/I2CT61223.2024.10544362.
[16] L. Qiu and J. Zhai, "A hybrid CNN-SVM model for enhanced autism diagnosis," PLoS One, vol. 19, no. 5, p. e0302236, 2024, doi: 10.1371/journal.pone.0302236.
[17] R. A. Rasul et al., "An evaluation of machine learning approaches for early diagnosis of autism spectrum disorder," Healthc. Anal., vol. 5, p. 100293, 2024, doi: 10.1016/j.health.2023.100293.
[18] Stanford Children’s Health Facial Imaging Dataset, [Online]. Available: https://aimidatasetindex.stanford.edu/datasets-home. [Accessed: 14-Nov-2024].
[19] A. Valizadeh et al., "Automated diagnosis of autism with artificial intelligence: State of the art," Rev. Neurosci., vol. 35, no. 2, pp. 141–163, 2024, doi: 10.1515/revneuro-2023-0050.
[20] World Health Organization (WHO), "Autism Spectrum Disorders," [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/autism-spectrum-disorders. [Accessed: 2022].
[21] F. L. Zhu et al., "A multimodal machine learning system in early screening for toddlers with autism spectrum disorders based on the response to name," Front. Psychiatry, vol. 14, p. 1039293, 2023, doi: 10.3389/fpsyt.2023.1039293.
[22] N. K. Kumar et al., "Enhanced Alzheimer’s disease Prediction through Advanced Imaging: A Study of Machine Learning and Deep Learning Approaches," in Proc. 5th Int. Conf. Smart Electron. Commun. (ICOSEC), Trichy, India, 2024, pp. 1177–1182, doi: 10.1109/ICOSEC61587.2024.10722116.
