Quantifying Perceptual Uncertainty through Non-Invasive Kinematic Tracking: A Convolutional Neural Network-Based Approach for Digital Biomarker Development
DOI:
https://doi.org/10.61467/2007.1558.2026.v17i5.1306Keywords:
Computer Vision, Video Analysis, Kinematic Parameters, Human Motor Function, Perceptual Difficulty, visión por computador, función motora humana, dificultad perceptivaAbstract
The analysis of human motor function is considered fundamental in the biomedical and clinical fields, as it allows us to understand how sensory information is transformed into motor responses. In this study, we proposed an analytical design that combined a visual discrimination task with non-invasive tracking of hand trajectories, using convolutional neural networks (CNNs) applied to video analysis. Five young adults (aged 24 to 34) participated in a perceptual task in which they had to decide whether a pattern of static black bars was regular or irregular. The difficulty of the task was controlled by spatial variation, defined as controlled variations in the spacing between the bars. Behavioral variables, such as accuracy and reaction time, were recorded, along with kinematic parameters such as path length, linearity index, maximum velocity, and variability. The results showed that irregular stimuli were associated with lower accuracy, longer reaction times, and greater variability in motor performance compared to regular stimuli. These findings indicate that perceptual difficulty is reflected not only in behavioral performance but also in the fine structure of motor execution. This work highlights the potential of non-invasive tracking and computer vision for the development of kinematic biomarkers of confidence in decision-making, with applications in the early detection and monitoring of motor and chronic-degenerative disorders.
Spanish-language metadata / Metadatos en español
Título en español:
Cuantificación de la incertidumbre perceptiva mediante seguimiento cinemático no invasivo: un enfoque basado en redes neuronales convolucionales para el desarrollo de biomarcadores digitales
Resumen:
El análisis de la función motora humana se considera fundamental en los ámbitos biomédico y clínico, ya que permite comprender cómo la información sensorial se transforma en respuestas motoras. En este estudio se propuso un diseño analítico que combinó una tarea de discriminación visual con el seguimiento no invasivo de las trayectorias de la mano, mediante redes neuronales convolucionales (CNN) aplicadas al análisis de vídeo.
Participaron cinco adultos jóvenes, con edades comprendidas entre 24 y 34 años, en una tarea perceptiva en la que debían decidir si un patrón de barras negras estáticas era regular o irregular. La dificultad de la tarea se controló mediante variación espacial, definida como modificaciones controladas en el espaciado entre las barras.
Se registraron variables conductuales, como la exactitud y el tiempo de reacción, junto con parámetros cinemáticos como la longitud de la trayectoria, el índice de linealidad, la velocidad máxima y la variabilidad. Los resultados mostraron que los estímulos irregulares se asociaron con una menor exactitud, tiempos de reacción más prolongados y una mayor variabilidad en el rendimiento motor en comparación con los estímulos regulares.
Estos hallazgos indican que la dificultad perceptiva se refleja no solo en el rendimiento conductual, sino también en la estructura fina de la ejecución motora. Este trabajo pone de manifiesto el potencial del seguimiento no invasivo y de la visión por computador para el desarrollo de biomarcadores cinemáticos de la confianza en la toma de decisiones, con aplicaciones en la detección temprana y el seguimiento de trastornos motores y crónico-degenerativos.
Palabras Claves:
visión por computador, análisis de vídeo, parámetros cinemáticos, función motora humana, dificultad perceptiva
Smart citations:
References
Abasıyanık, Z., & Kahraman, T. (2022). Effect of dual-task training on cognitive functions in persons with multiple sclerosis: A systematic review and meta-analysis. Multiple Sclerosis and Related Disorders, 62, Article 103801. https://doi.org/10.1016/j.msard.2022.103801
Cieślik, K., & Łopatka, M. J. (2022). Research on speed and acceleration of hand movements as command signals for anthropomorphic manipulators as a master-slave system. Applied Sciences, 12(8), Article 3863. https://doi.org/10.3390/app12083863
Cui, C., Sunar, M. S., & Su, G. E. (2024). A dataset of egocentric and exocentric view hands in interactive senses. Data in Brief, 57, Article 111003. https://doi.org/10.1016/j.dib.2024.111003
Deutsch, K. M., & Newell, K. M. (2005). Noise, variability, and the development of children’s perceptual-motor skills. Developmental Review, 25(2), 155–180. https://doi.org/10.1016/j.dr.2004.09.001
di Biase, L., Di Santo, A., Caminiti, M. L., De Liso, A., Shah, S. A., Ricci, L., & Di Lazzaro, V. (2020). Gait analysis in Parkinson’s disease: An overview of the most accurate markers for diagnosis and symptoms monitoring. Sensors, 20(12), Article 3529. https://doi.org/10.3390/s20123529
di Biase, L., Raiano, L., Caminiti, M. L., Pecoraro, P. M., & Di Lazzaro, V. (2022). Parkinson’s disease wearable gait analysis: Kinematic and dynamic markers for diagnosis. Sensors, 22(22), Article 8773. https://doi.org/10.3390/s22228773
El Iskandarani, M., Bolton, M., & Riggs, S. L. (2025). Examining dual-task interference effects of visual and auditory perceptual load in virtual reality. International Journal of Human-Computer Studies, 205, Article 103619. https://doi.org/10.1016/j.ijhcs.2025.103619
Gold, J. I., & Shadlen, M. N. (2007). The neural basis of decision making. Annual Review of Neuroscience, 30, 535–574. https://doi.org/10.1146/annurev.neuro.29.051605.113038
Gorniak, S. L. (2019). The relationship between task difficulty and motor performance complexity. Attention, Perception, & Psychophysics, 81(1), 12–19. https://doi.org/10.3758/s13414-018-1634-4
Kristensen, S. B., Bødkergaard, K., & Bibby, B. M. (2025). Analysing the bias introduced by adaptive designs to estimates of psychometric functions. Journal of Mathematical Psychology, 124, Article 102899. https://doi.org/10.1016/j.jmp.2025.102899
Labuguen, R., Bardeloza, D. K., Negrete, S. B., Matsumoto, J., Inoue, K., & Shibata, T. (2019). Primate markerless pose estimation and movement analysis using DeepLabCut. In 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR) (pp. 297–300). IEEE. https://doi.org/10.1109/ICIEV.2019.8858533
Lee, M.-F. R., Chen, Y.-C., & Tsai, C.-Y. (2022). Deep learning-based human body posture recognition and tracking for unmanned aerial vehicles. Processes, 10(11), Article 2295. https://doi.org/10.3390/pr10112295
Li, J., Kang, F., Zhang, Y., Liu, Y., & Yu, X. (2023). Research on tracking and identification of typical protective behavior of cows based on DeepLabCut. Applied Sciences, 13(2), Article 1141. https://doi.org/10.3390/app13021141
Lin, L. P. Y., Plack, C. J., & Linkenauger, S. A. (2021). The influence of perceptual-motor variability on the perception of action boundaries for reaching in a real-world setting. Perception, 50(9), 783–796. https://doi.org/10.1177/03010066211038406
Lucia, S., & Di Russo, F. (2025). Identification of anticipatory brain activity in a time discrimination task. Brain and Cognition, 183, Article 106243. https://doi.org/10.1016/j.bandc.2024.106243
Mathis, A., Mamidanna, P., Cury, K. M., Abe, T., Murthy, V. N., Mathis, M. W., & Bethge, M. (2018). DeepLabCut: Markerless pose estimation of user-defined body parts with deep learning. Nature Neuroscience, 21(9), 1281–1289. https://doi.org/10.1038/s41593-018-0209-y
Moro, M., Marchesi, G., Hesse, F., Odone, F., & Casadio, M. (2022). Markerless vs. marker-based gait analysis: A proof of concept study. Sensors, 22(5), Article 2011. https://doi.org/10.3390/s22052011
Nath, T., Mathis, A., Chen, A. C., Patel, A., Bethge, M., & Mathis, M. W. (2019). Using DeepLabCut for 3D markerless pose estimation across species and behaviors. Nature Protocols, 14(7), 2152–2176. https://doi.org/10.1038/s41596-019-0176-0
Ofir, N., & Landau, A. N. (2025). A drift-diffusion model of temporal generalization outperforms existing models and captures modality differences and learning effects. Behavior Research Methods, 57(12), Article 334. https://doi.org/10.3758/s13428-025-02819-8
Panconi, G., Grasso, S., Guarducci, S., Mucchi, L., Minciacchi, D., & Bravi, R. (2025). DeepLabCut custom-trained model and the refinement function for gait analysis. Scientific Reports, 15, Article 2364. https://doi.org/10.1038/s41598-025-85591-1
Papaioannidis, C., Mademlis, I., & Pitas, I. (2023). Fast CNN-based single-person 2D human pose estimation for autonomous systems. IEEE Transactions on Circuits and Systems for Video Technology, 33(3), 1262–1275. https://doi.org/10.1109/TCSVT.2022.3209160
Pecoraro, P. M., Marsili, L., Espay, A. J., Bologna, M., & di Biase, L. (2025). Computer vision technologies in movement disorders: A systematic review. Movement Disorders Clinical Practice, 12(9), 1229–1243. https://doi.org/10.1002/mdc3.70123
Przybyszewski, A. W., Śledzianowski, A., Chudzik, A., Szlufik, S., & Koziorowski, D. (2023). Machine learning and eye movements give insights into neurodegenerative disease mechanisms. Sensors, 23(4), Article 2145. https://doi.org/10.3390/s23042145
Ryu, J., Nejatbakhsh, A., Torkashvand, M., Gangadharan, S., Seyedolmohadesin, M., Kim, J., Paninski, L., & Venkatachalam, V. (2024). Versatile multiple object tracking in sparse 2D/3D videos via deformable image registration. PLOS Computational Biology, 20(5), Article e1012075. https://doi.org/10.1371/journal.pcbi.1012075
Säfström, D. (2025). The multisensory control of sequential actions. Experimental Brain Research, 243(1), Article 13. https://doi.org/10.1007/s00221-024-06962-0
Schaffelhofer, S., Agudelo-Toro, A., & Scherberger, H. (2015). Decoding a wide range of hand configurations from macaque motor, premotor, and parietal cortices. Journal of Neuroscience, 35(3), 1068–1081. https://doi.org/10.1523/JNEUROSCI.3594-14.2015
Sihn, D., Kim, J., Kim, M. J., & Kim, S.-P. (2025). The intrinsic propagation directionality of fMRI infra-slow activity during visual tasks. Neuroscience, 564, 52–59. https://doi.org/10.1016/j.neuroscience.2024.11.041
Spindler, P., Alzoobi, Y., Truckenmüller, P., Hahn, S., Manzoni, Y. N., Feldmann, L., Hermann, K.-G., Kühn, A. A., Faust, K., Schneider, G.-H., Vajkoczy, P., & Schmidt, H. (2022). A noninvasive method to quantify the impairment of spinal motion ability in Parkinson’s disease. European Spine Journal, 31(12), 3316–3323. https://doi.org/10.1007/s00586-022-07401-w
Sternad, D., Abe, M. O., Hu, X., & Müller, H. (2011). Neuromotor noise, error tolerance and velocity-dependent costs in skilled performance. PLOS Computational Biology, 7(9), Article e1002159. https://doi.org/10.1371/journal.pcbi.1002159
Vidal, P.-P., & Lacquaniti, F. (2021). Perceptual-motor styles. Experimental Brain Research, 239(5), 1359–1380. https://doi.org/10.1007/s00221-021-06049-0
Villalonga, M. B., & Sekuler, R. (2023). Keep your finger on the pulse: Better rate perception and gap detection with vibrotactile compared to visual stimuli. Attention, Perception, & Psychophysics, 85(6), 2004–2017. https://doi.org/10.3758/s13414-023-02736-y
Villalonga, M. B., Noyce, A. L., & Sekuler, R. (2025). Dynamic modulation of spatial selection: Online and anticipatory adjustments in the flanker task. Attention, Perception, & Psychophysics, 87(3), 794–814. https://doi.org/10.3758/s13414-025-03026-5
Visser, Y. F., Medendorp, W. P., & Selen, L. P. J. (2025). Corticomuscular and intermuscular coherence during evidence accumulation in sensorimotor decision-making. Physiological Reports, 13(6), Article e70237. https://doi.org/10.14814/phy2.70237
Wong, A. L., & Haith, A. M. (2017). Motor planning flexibly optimizes performance under uncertainty about task goals. Nature Communications, 8, Article 14624. https://doi.org/10.1038/ncomms14624
Xiang, L., Wang, A., Gu, Y., Zhao, L., Shim, V., & Fernandez, J. (2022). Recent machine learning progress in lower limb running biomechanics with wearable technology: A systematic review. Frontiers in Neurorobotics, 16, Article 913052. https://doi.org/10.3389/fnbot.2022.913052
Zadid, T. H., Tanim, S. A., & Mridha, M. F. (2025). A dataset of exocentric images capturing hand gestures in multiplayer games. Data in Brief, 63, Article 112182. https://doi.org/10.1016/j.dib.2025.112182
Zhan, W., Ke, Z., Wang, C., Pan, Y., Sun, Y., & Yin, X. (2025). Application of the Deeplabcut for the analysis and study on the crawling behavior of Henosepilachna vigintioctopunctata (Fabricius). IEEE Access, 13, 44024–44040. https://doi.org/10.1109/ACCESS.2025.3543311
Zhang, H., Xiong, G., Cai, S., & Wu, S. (2024). A causal role of right temporoparietal junction in prosocial learning: A transcranial direct current stimulation study. Neuroscience, 538, 59–67. https://doi.org/10.1016/j.neuroscience.2023.12.008
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Combinatorial Optimization Problems and Informatics

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.