Thesis topics (v2025)

The research involves proposing machine learning and deep learning models to classify a set of Activities of Daily Living (ADLs), integrating human motion data, recognized objects in the scene, and environmental sensor data.

• Lopez-Nava, I. H., & Muñoz-Meléndez, A. (2019). Human action recognition based on low-and high-level data from wearable inertial sensors. International Journal of Distributed Sensor Networks, 15(12), 1550147719894532.

The study focuses on automatically recognizing human emotions in discrete and continuous domains by integrating physiological signals, facial expressions, and voice. Classification models based on data collected in structured and naturalistic scenarios will be implemented and evaluated.

• Dzedzickis, A., Kaklauskas, A., & Bucinskas, V. (2020). Human emotion recognition: Review of sensors and methods. Sensors, 20(3), 592.

Development of a system based on inertial sensors and video keypoints for the measurement and evaluation of human gait. The approach includes the extraction of spatiotemporal and kinematic parameters to assess the progression of neuromuscular diseases and optimize rehabilitation strategies.

• López-Nava, I. H., Muñoz-Meléndez, A., Pérez Sanpablo, A. I., Alessi Montero, A., Quiñones Urióstegui, I., & Núñez Carrera, L. (2016). Estimation of temporal gait parameters using Bayesian models on acceleration signals. Computer methods in biomechanics and biomedical engineering, 19(4), 396-403.

Development of a system based on 2D video motion tracking to assess motor function and fall risk in individuals with neuromuscular conditions or older adults, integrating various scales, e.g., Fugl-Meyer, Berg Balance, Timed Up & Go.

• Steffen, T. M., Hacker, T. A., & Mollinger, L. (2002). Age- and gender-related test performance in community-dwelling elderly people: Six-Minute Walk Test, Berg Balance Scale, Timed Up & Go Test, and gait speeds. Physical therapy, 82(2), 128-137.

Proposing a computational model for the automatic segmentation and labeling of videos in which interpreters of Mexican Sign Language translate spoken or written discourse. The models will be implemented using deep learning techniques, and metrics for their evaluation will be investigated or proposed.

• Morfín-Chávez, R. F., Gortarez-Pelayo, J. J., & Lopez-Nava, I. H. (2023, November). Fingerspelling Recognition in Mexican Sign Language (LSM) Using Machine Learning. In Mexican International Conference on Artificial Intelligence (pp. 110-120). Cham: Springer Nature Switzerland.

This research explores the use of machine learning and natural language processing techniques to identify linguistic patterns linked to depression and anxiety. Its goal is the early detection of mental disorders through the analysis of multimodal data extracted from social networks.

• Le Glaz, A., Haralambous, Y., Kim-Dufor, D. H., Lenca, P., Billot, R., Ryan, T. C., ... & Lemey, C. (2021). Machine learning and natural language processing in mental health: systematic review. Journal of Medical Internet Research, 23(5), e15708.

Design and development of a digital platform that integrates interaction technologies, personalized monitoring, and adaptive recommendations to encourage healthy habits and social participation. Ubiquitous computing, data analysis, and accessibility approaches for the elderly population will be explored.

• López-Nava, I. H., Rodriguez, M. D., García-Vázquez, J. P., Perez-Sanpablo, A. I., ... & Favela, J. (2023). Current state and trends of the research in exergames for the elderly and their impact on health outcomes: a scoping review. Journal of Ambient Intelligence and Humanized Computing, 14(8), 10977-11009.

This research proposes the use of deep learning techniques for the classification, detection, and characterization of astronomical objects from large volumes of observational data. Neural network architectures and supervised and unsupervised learning strategies will be explored to optimize pattern identification.

• Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., ... & Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8, 1-74.

This thesis proposes the development of computational models for monitoring whale sharks using videos recorded by drones in Bahía de los Ángeles. Tasks include detection, tracking, identification, and size estimation of individuals. Segmentation, pattern recognition, and motion modeling techniques will be explored.

• Jenrette, J., Liu, Z. C., Chimote, P., Hastie, T., Fox, E., & Ferretti, F. (2022). Shark detection and classification with machine learning. Ecological Informatics, 69, 101673.

This interdisciplinary research proposes the development of a computer vision and machine learning-based system for the identification and density estimation of fish species in underwater videos. Segmentation, object detection, and species classification techniques will be explored to improve the accuracy and efficiency of ecological analysis in aquatic environments.

• Jalal, A., Salman, A., Mian, A., Shortis, M., & Shafait, F. (2020). Fish detection and species classification in underwater environments using deep learning with temporal information. Ecological Informatics, 57, 101088.