Sensorized insoles have been used as a wearable instrument to study human gait and can be a great source of identifying and predicting pathologies and injuries. However, most of these sensorized insoles are being statically calibrated only, using a scale and known weights to establish a relationship between electrical signals and the load applied on laboratory benches, ignoring the dynamic interaction between person and instrument. The present study proposes and verifies a calibration method complementary to static calibration to compensate for different dynamic interactions between the insole and the individual during gait. Were used an experimental resistive sensorized insole (SI), a double-belt instrumented treadmill (Bertec, 1000Hz, USA), and 32 participants (18 men and 14 women). The SI data was compared with the treadmill force plate and adjusted using a machine learning algorithm to create a dynamic coefficient to complement and optimize the results. This study also verifies the impact of the method considering three different types of gait: pronated, neutral and supinated. The improvement after applying the method achieved up to 12%, considering the correlation between the sensorized insole and the treadmill with a force plate (considered another standard for measuring the ground reaction force).

No abstract

Human gait analysis can provide an excellent source for identifying and predicting pathologies and injuries. In this respect, sensorized insoles also have a great potential for extracting gait information. This, combined with mathematical techniques based on machine learning (ML), can potentialize biomechanical analyses. The present study proposes a proof-of-concept of a system based on vertical ground reaction force (vGRF) acquisition with a sensorized insole that uses an ML algorithm to identify different patterns of vGRF and extract biomechanical characteristics that can help during clinical evaluation. The acquired data from the system was clustered by an immunological algorithm (IA) based on vGRF during gait. These clusters underwent a data mining process using the classification and regression tree algorithm (CART), where the main characteristics of each group were extracted, and some rules for gait classification were created. As a result, the system proposed was able to collect and process the biomechanical behavior of gait. After the application of IA and CART algorithms, six groups were found. The characteristics of each of these groups were extracted and verified the capability of the system to collect and process the biomechanical behavior of gait, offering verification points that can help focus during a clinical evaluation.

No abstract

Purpose Currently, several studies have been published using sensorized insoles for estimating ground reaction force using plantar pressure. However, information on design parameters, manufacturing techniques and guidelines for developing insoles is scarce, often leaving gaps that do not allow reproducing the insole. This study aims to empirically investigate the main parameters of constructing a sensorized insole for application in human gait. Design/methodology/approach Two devices were built to evaluate the force sensors. The first focuses on the construction of the sensors with different settings: the density of the sensor’s conductive trails (thickness and distance of the trails) and the inertia of the sensors (use of spacers to prevent unwanted readings). The second device focuses on the data capture and processing system: resolution of the analog–digital converter, acquisition rate and sensor activation level. Findings The resolution increase of the analog–digital converter and acquisition rate do not contribute to noise increase. Reducing the sensors’ coverage area can increase sensorized insole capacity. The inertia of the sensors can be adjusted using spacers without changing the electrical circuit and acquisition system. Originality/value Most sensorized insoles use commercial sensors. For this reason, it is not possible a full customization. This paper maps the main variables to manufacture custom sensors and data acquisition systems. This work also presents a case study where it is possible to see the influence of the parameters in the correlation between the sensorized insole and an instrumented treadmill with a force platform.