Prediction of bad postures based on Machine Learning models - 8th IESTEC

Aug 5, 2026

Advances in internet and mobile computing enable data-driven applications, yet increased technology use can create health discomfort, particularly when the spine is affected by poor posture. This work proposes a prototype system that detects and helps correct bad posture during daily activities using three inertial sensors and a monitoring framework with three posture risk factors. Feedback is delivered through an application that alerts users when posture exceeds an established threshold to prevent chronic problems such as neck and back pain. Experiments across machine learning algorithms show strong discrimination of improper head posture, with neural networks achieving the best results.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduccion

Text neck and health impact

IoT sensors and data analysis

Planteamiento del problema

Origins and definition of text neck

Relationship between device use and neck pain

System approach (inferred)

2022 8th International Engineering, Sciences and Technology Conference (IESTEC) Prediction of“bad postures” based on Machine Learning models Luis Fernando Gómez Mendoza Universidad Nacional de Ingeniería Grupo de Sensado Multidisciplinario Lima, Perú [lgomezm@uni.pe](lgomezm@uni.pe)[ ](lgomezm@uni.pe)[https://orcid.org/0000-0002-2727-8972](https://orcid.org/0000-0002-2727-8972) Sofía Huamán Vizconde Universidad Nacional de Ingeniería Grupo de Sensado Multidisciplinario Lima, Perú [s.huaman@ieee.org](s.huaman@ieee.org)[ ](s.huaman@ieee.org)[https://orcid.org/0000-0002-7865-1255](https://orcid.org/0000-0002-7865-1255) Jimmy Aurelio Rosales Huamaní Universidad Nacional de Ingeniería Grupo de Sensado Multidisciplinario Lima, Perú [jrosales@uni.edu.pe](jrosales@uni.edu.pe)[ ](jrosales@uni.edu.pe)[https://orcid.org/0000-0002-3737-8694](https://orcid.org/0000-0002-3737-8694) José Luis Castillo Sequera Universidad de Alcalá Departamento de Computer Science Madrid, España[jluis.castillo@uah.es](jluis.castillo@uah.es)[ ](jluis.castillo@uah.es)[https://orcid.org/0000-0002-9131-1618](https://orcid.org/0000-0002-9131-1618) Abstract—The advances of the Internet, mobile communications and computing have opened new frontiers fora society that is increasingly focused on data analysis. New applications increasingly rely on machine-to-machine communications, which in turn create workloads that demand innovative systems, as network devices, sensors, and intelligent systems now generate vast amounts of data that can be processed to solve everyday problems, there is no doubt that new technologies have made our lives easier. However, despite all the advantages they bring, they have also brought some discomfort to our health. Especially, behind our back, which can be harmful to the spine. For these reasons, the purpose of this work was to design and build a prototype system that "detects and corrects bad posture" of a person when performing their daily activities. To do this, we use a prediction system with the help of three inertial sensors. The developed device consists of a monitoring system that includes 3 risk posture factors and is capable of providing feedback, through an application that alerts the user in order to prevent poor posture or inadequate posture that can become chronic. , causing neck pain, back pain, etc. In this way, a message is sent in case the posture of the human subject is outside the established threshold. The experimental results carried out with various machine learning algorithms demonstrate the abilities of the system to distinguish an improper head posture from a correct one. Different algorithms were applied, finding that by applying Neural Networks Artificial (ANN) we obtain better results. Keywords—Machine Learning, Neural Networks Artificial, bad posture, neck text, prediction. I. INTRODUCCION Los dispositivos de red, los sensores, los sistemasinteligentes generan grandes cantidades de datos que puedenser procesados para solucionar problemas cotidianos. Lautilización de los móviles va más allá que la comunicación, cumpliendo otras funciones como entretenimiento, educacióne incluso como sistema para captación y recopilación de datos aplicados a temas de salud. Debido a esto, cada vez más sedesarrollan nuevos dispositivos con una gran variedad de sensores en el ámbito tecnológico de IoT, que hace posible laintegración de éstos dispositivos con el interés de medirdistancias, velocidad, aceleración, etc. La complejidad de estas nuevas herramientas, así como las innovaciones en inteligencia artificial, aprendizaje automático y análisis de datos posibilitan su aplicación a diversas áreas. Por otro lado, según estudios recientes se demuestra que lainserción de las nuevas tecnologías en las escuelas y en la vida cotidiana ha ocasionado que el tiempo estimado en lautilización de ordenadores, móviles, tablets o algún otrodispositivo se incremente considerablemente. El síndrome“text neck” daña el apar

FAQs

What is the main goal of the proposed work?

To design and build a prototype system that detects and helps correct bad posture during daily activities.

How does the system detect posture?

It uses three inertial sensors to collect acceleration data and applies machine learning models to predict improper vs. correct head posture.

Which machine learning approach performed best in the experiments?

Neural Networks Artificial (ANN) provided better results compared with other tested algorithms.

Aug 5, 2026

Upload by Theodore