SavedAdd your journal

Journals / Firat University Journal of Experimental and Computational Engineering / 2026 / Cilt: 5 Sayı: 3

LBP-Moment: A Lightweight and Interpretable EEG Framework for Automated ADHD Detection

LBP-Moment: Otomatik DEHB Tespiti için Hafif ve Yorumlanabilir Bir EEG Modeli

İrem Taşcı(FIRAT UNIVERSITY)0000-0001-7069-769X
Ömer Faruk Göktaş(ANKARA YILDIRIM BEYAZIT ÜNİVERSİTESİ)0000-0002-2021-4052
Kübra Yıldırım(FIRAT UNIVERSITY)0000-0002-4738-2777
Abdul Hafeez Baig(University of Southern Queensland)0000-0003-3848-8008
Mehmet Bayğın(ERZURUM TEKNİK ÜNİVERSİTESİ)0000-0001-6449-8950
Burak Tasci(FIRAT ÜNİVERSİTESİ)0000-0002-4490-0946
Sengul Dogan(FIRAT UNIVERSITY)0000-0001-9677-5684
Türker Tuncer(FIRAT UNIVERSITY)0000-0002-5126-6445
Pages
827–847
Publication Date
2026-10-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These findings support a transparent, CPU-based feature-engineering approach, but participant-wise and external validation are required before clinical interpretation.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder.
📊
Key Findings & Data:Each 5-s segment was represented by a 256-dimensional local binary pattern histogram and 40 statistical features (IST40).
💡
Conclusion & Impact:These findings support a transparent, CPU-based feature-engineering approach, but participant-wise and external validation are required before clinical interpretation.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:DEHB tespiti · EEG sınıflandırması · Yerel ikili örüntü

Abstract

Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder. Here we present LBP-Moment, a lightweight and interpretable framework for automated ADHD classification from electroencephalography (EEG). Each 5-s segment was represented by a 256-dimensional local binary pattern histogram and 40 statistical features (IST40). Iterative Chi-square selection reduced the resulting 296-dimensional space to 132 features. A k-nearest-neighbour classifier (k=1; Manhattan distance) was evaluated by segment-level 10-fold cross-validation. The model achieved 97.65% accuracy, a 97.65% F1-score, a Cohen's kappa of 0.9527 and an area under the receiver operating characteristic curve of 0.9762. Ablation analysis showed complementary contributions from LBP and IST40; feature selection removed 55.4% of the features and increased accuracy by 0.35 percentage points. These findings support a transparent, CPU-based feature-engineering approach, but participant-wise and external validation are required before clinical interpretation.

Özet

Dikkat eksikliği hiperaktivite bozukluğu (DEHB), yaygın bir nörogelişimsel bozukluktur. Bu çalışmada, elektroensefalografi (EEG) sinyallerinden DEHB'nin otomatik tespiti için hafif ve yorumlanabilir bir makine öğrenmesi çerçevesi sunulmuştur. Her 5 saniyelik segmentten 256 “ yerel ikili örüntü (LBP) histogramı ile 40 boyutlu IST40 istatistiksel özellik vektörü çıkarılmış ve 296 boyutlu bir temsil elde edilmiştir. Yinelemeli Ki-kare seçimi bu uzayı 132 özelliğe indirmiştir. Manhattan uzaklığına dayalı k-en yakın komşu sınıflandırıcısı (k=1), segment düzeyinde 10 katlı çapraz doğrulama ile değerlendirilmiştir. Model %97,65 doğruluk, %97,65 F1 puanı, 0,9527 Cohen kappa ve 0,9762 AUC üretmiştir. Ayrıştırma analizi, LBP ve IST40 özelliklerinin tamamlayıcı katkısını ve özellik seçiminin boyutu %55,4 azaltırken doğruluğu 0,35 yüzde puanı artırdığını göstermiştir. Bulgular, sınırlı donanımda çalışabilen saydam bir EEG özellik mühendisliği yaklaşımını desteklemektedir. Bununla birlikte, katılımcı düzeyinde ve bağımsız veri setlerinde doğrulama klinik yorumdan önce gereklidir.

🔖

Cite This Article

Taşcı, İ., Göktaş, Ö. F., Yıldırım, K., Baig, A. H., Bayğın, M., Tasci, B., Dogan, S., Tuncer, T. (2026). LBP-Moment: A Lightweight and Interpretable EEG Framework for Automated ADHD Detection. Firat University Journal of Experimental and Computational Engineering, Cilt: 5 Sayı: 3, 827–847. https://doi.org/10.62520/fujece.1950290

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (38)

  1. T. E. Wilens and T. J. Spencer, “Understanding attention-deficit/hyperactivity disorder from childhood to adulthood,” Postgrad. Med., vol. 122, no. 5, pp. 97–109, 2010.
  2. G. Antolini and M. Colizzi, “Where do neurodevelopmental disorders go? Casting the eye away from childhood towards adulthood,” Healthcare, vol. 11, no. 7, Art. no. 1015, 2023.
  3. T. Banaschewski, K. Becker, M. Döpfner, M. Holtmann, M. Rösler, and M. Romanos, “Attention-deficit/hyperactivity disorder: A current overview,” Dtsch. Arztebl. Int., vol. 114, no. 9, p. 149, 2017.
  4. L. Furman, “What is attention-deficit hyperactivity disorder (ADHD)?” J. Child Neurol., vol. 20, no. 12, pp. 994–1002, 2005.
  5. E. Cormier, “Attention deficit/hyperactivity disorder: A review and update,” J. Pediatr. Nurs., vol. 23, no. 5, pp. 345–357, 2008.
  6. C. Colomer, C. Berenguer, B. Roselló, I. Baixauli, and A. Miranda, “The impact of inattention, hyperactivity/impulsivity symptoms, and executive functions on learning behaviors of children with ADHD,” Front. Psychol., vol. 8, Art. no. 540, 2017.
  7. R. Drechsler, S. Brem, D. Brandeis, E. Grünblatt, G. Berger, and S. Walitza, “ADHD: Current concepts and treatments in children and adolescents,” Neuropediatrics, vol. 51, no. 5, pp. 315–335, 2020.
  8. J. M. Halperin, A.-C. V. Bédard, and J. T. Curchack-Lichtin, “Preventive interventions for ADHD: A neurodevelopmental perspective,” Neurotherapeutics, vol. 9, no. 3, pp. 531–541, 2012.
  9. E. J. Sonuga-Barke, J. Koerting, E. Smith, D. C. McCann, and M. Thompson, “Early detection and intervention for attention-deficit/hyperactivity disorder,” Expert Rev. Neurother., vol. 11, no. 4, pp. 557–563, 2011.
  10. S. K. Loo and S. Makeig, “Clinical utility of EEG in attention-deficit/hyperactivity disorder: A research update,” Neurotherapeutics, vol. 9, no. 3, pp. 569–587, 2012.
  11. A. Lenartowicz and S. K. Loo, “Use of EEG to diagnose ADHD,” Curr. Psychiatry Rep., vol. 16, no. 11, Art. no. 498, 2014.
  12. D. P. Subha, P. K. Joseph, R. Acharya U, and C. M. Lim, “EEG signal analysis: A survey,” J. Med. Syst., vol. 34, no. 2, pp. 195–212, 2010.
  13. M. Maniruzzaman, M. A. M. Hasan, N. Asai, and J. Shin, “Optimal channels and features selection based ADHD detection from EEG signal using statistical and machine learning techniques,” IEEE Access, vol. 11, pp. 33570–33583, 2023.
  14. M. Bakhtyari and S. Mirzaei, “ADHD detection using dynamic connectivity patterns of EEG data and ConvLSTM with attention framework,” Biomed. Signal Process. Control, vol. 76, Art. no. 103708, 2022.
  15. M. Maniruzzaman, J. Shin, M. A. M. Hasan, and A. Yasumura, “Efficient feature selection and machine learning based ADHD detection using EEG signal,” Comput. Mater. Contin., vol. 72, no. 3, 2022.
  16. L. Li et al., “ADHD detection from EEG signals using GCN based on multi-domain features,” Front. Neurosci., vol. 19, Art. no. 1561994, 2025.
  17. B. Latifi, A. Amini, and A. M. Nasrabadi, “Siamese based deep neural network for ADHD detection using EEG signal,” Comput. Biol. Med., vol. 182, Art. no. 109092, 2024.
  18. R. Catherine Joy, S. Thomas George, A. Albert Rajan, and M. Subathra, “Detection of ADHD from EEG signals using different entropy measures and ANN,” Clin. EEG Neurosci., vol. 53, no. 1, pp. 12–23, 2022.
  19. M. Y. Esas and F. Latifoğlu, “Detection of ADHD from EEG signals using new hybrid decomposition and deep learning techniques,” J. Neural Eng., vol. 20, no. 3, Art. no. 036028, 2023.
  20. B. TaghiBeyglou, A. Shahbazi, F. Bagheri, S. Akbarian, and M. Jahed, “Detection of ADHD cases using CNN and classical classifiers of raw EEG,” Comput. Methods Programs Biomed. Update, vol. 2, Art. no. 100080, 2022.
  21. P. D. Barua et al., “TMP19: A novel ternary motif pattern-based ADHD detection model using EEG signals,” Diagnostics, vol. 12, no. 10, Art. no. 2544, 2022.
  22. J. Sanchis, S. García-Ponsoda, M. A. Teruel, J. Trujillo, and I.-Y. Song, “A novel approach to identify the brain regions that best classify ADHD by means of EEG and deep learning,” Heliyon, vol. 10, no. 4, 2024.
  23. H. W. Loh et al., “ADHD/CD-NET: Automated EEG-based characterization of ADHD and CD using explainable deep neural network technique,” Cogn. Neurodyn., vol. 18, no. 4, pp. 1609–1625, 2024.
  24. A. R. Singh, G. Singh, and N. Saluja, “Automated detection of ADHD: A machine learning approach with EEG signals,” in Proc. 2024 IEEE 3rd World Conf. Appl. Intell. Comput. (AIC), 2024, pp. 67–70.
  25. R. Holker and S. Susan, “Computer-aided diagnosis framework for ADHD detection using quantitative EEG,” in Proc. Int. Conf. Brain Inform., 2022, pp. 229–240.
  26. N. Arunkumar, B. Nagaraj, and M. R. Keziah, “RESNET34 with synchrosqueezing transform for ADHD disorder detection using EEG signals,” Fluct. Noise Lett., vol. 23, no. 5, Art. no. 2450054, 2024.
  27. M. Pietikäinen, “Local binary patterns,” Scholarpedia, vol. 5, no. 3, Art. no. 9775, 2010.
  28. M. Steinbach and P.-N. Tan, “kNN: k-nearest neighbors,” in The Top Ten Algorithms in Data Mining. Boca Raton, FL, USA: Chapman and Hall/CRC, 2009, pp. 165–176.
  29. N. K. Ahire, “Attention-driven deep learning framework for EEG analysis in ADHD detection,” Appl. Neuropsychol. Child, pp. 1–11, 2025.
  30. A. Alim and M. H. Imtiaz, “Automatic identification of children with ADHD from EEG brain waves,” Signals, vol. 4, no. 1, pp. 193–205, 2023.
  31. D. Tanko et al., “EPSPatNet86: Eight-pointed star pattern learning network for detection ADHD disorder using EEG signals,” Physiol. Meas., vol. 43, no. 3, Art. no. 035002, 2022.
  32. A. Nouri and Z. Tabanfar, “Detection of ADHD disorder in children using layer-wise relevance propagation and convolutional neural network: An EEG analysis,” Front. Biomed. Technol., vol. 11, no. 1, pp. 14–21, 2024.
  33. T. Sindhu and S. Sujatha, “Common spatial pattern based feature extractor with hybrid LinkNet-SqueezeNet for ADHD detection from EEG signal,” Prog. Eng. Sci., vol. 2, no. 4, Art. no. 100172, 2025.
  34. P. Shahmohamadi, S. Amini, S. Khanbabaee, N. Tavakoli, S. Molaei, and N. Teimoori, “Advanced ADHD detection using multivariate variational mode decomposition and deep learning: A novel EEG-based framework,” InfoScience Trends, vol. 2, no. 6, pp. 42–56, 2025.
  35. E. Sathiya, T. Rao, and T. S. Kumar, “Gabor filter-based statistical features for ADHD detection,” Front. Hum. Neurosci., vol. 18, Art. no. 1369862, 2024.
  36. M. Maniruzzaman, M. A. M. Hasan, T. Suzuki, and J. Shin, “Identification of children with ADHD from EEG signals based on entropy measures and support vector machine,” in Proc. 2023 11th Eur. Workshop Vis. Inf. Process. (EUVIP), 2023, pp. 1–6.
  37. U. Hassan and A. Singhal, “ADHD detection using artificial neural network,” Procedia Comput. Sci., vol. 260, pp. 570–575, 2025.
  38. D. V. Salazar-Dubois, A. M. Álvarez-Meza, and G. Castellanos-Dominguez, “T-GARNet: A transformer and multi-scale Gaussian kernel connectivity network with Alpha-Rényi regularization for EEG-based ADHD detection,” Mathematics, vol. 13, no. 24, Art. no. 4026, 2025.