Gait event detection is important for diagnosis and evaluation. This is a challenging endeavor due to subjectivity, high amount of data, among other problems. ANFIS (Artificial Neural Fuzzy Inference Systems), ARX (Autoregressive Models with Exogenous Variables), OE (Output Error models), NARX (Nonlinear Autoregressive Models with Exogenous Variables) and models based on NN (neural networks) were developed in order to detect gait events without the problems mentioned. The objective was to compare developed models' performance and determinate the most suitable model for gait events detection. Knee joint angle, heel foot switch and toe foot switch during normal walking in a treadmill were collected from a healthy volunteer. Gait events were classified by three experts in human motion. Experts' mean classification was obtained and all models were trained and tested with the collected data and experts' mean classification. Fit percentage was obtained to evaluate models performance. Fit percentages were: ANFIS: 79.49%, ARX: 68.8%, OE: 71.39%, NARX: 88.59%, NNARX: 67.66%, NNRARX: 68.25% and NNARMAX: 54.71%. NARX had the best performance for gait events classification. For ARX and OE, previous filtering is needed. NN's models showed the best performance for high frequency components. ANFIS and NARX were able to integrate criteria from three experts for gait analysis. NARX and ANFIS are suitable for gait event identification. Test with additional subjects is needed.

Gait event detection is important for diagnosis and evaluation. This is a challenging endeavor that can be addressed with Computational Intelligence (CI). Four different CI models were developed and compared. Spatio-temporal parameters during normal walking in a treadmill were collected from a healthy volunteer. Gait events were classified by three experts in human motion. All identification systems were trained and tested with the collected data and experts' mean classification. Fit percentage was obtained to evaluate models performance. Nonlinear Autoregressive Models with Exogenous Variables (NARX) had the best performance for gait events classification with a fit percentage of 88.59%. High frequency components were the main source of error for classical models. NARX was able to integrate criteria from the three experts for gait event detection. NARX models are suitable for gait event identification. Future work will include implementation of supervisory systems and additional data.

Introduction: Daily volume loss of residual limb is a condition that most prosthetic users face, negatively affecting their life. One of the consequences is the loss of contact between the residual limb and the socket, which modifies internal pressures. Objective: The aim of this study was to study how the loss of volume of the residual limb affects socket adjustment through measuring pressures inside the socket. Study design: The study design is prospective longitudinal. Materials and Methods: Four subjects with unilateral transtibial amputation, with at least 1 year of prosthetic use, and walking with a comfortable prosthesis participated in this study. The pressure between the socket and the subject's residual limb was measured with an FSocket System (Tekscan). Residual limb volume was measured before and after each test with two different methods: optical scanning (Structure Sensor, Occipital) and conical frustum model. Sanders' protocol for volume loss was followed (Sanders et al. J Rehabil Res Dev. 2012;49:1467-1478. Volume changes in the residual limb and socket internal pressures were analyzed. Results/Discussion: The pressure graph obtained is consistent with Sanders' volume graphs. The pressure distribution inside the socket is lost after 5 hours of use of the prosthetic device; this can be related to volume loss and alignment. The only area where the pressure increases is in the distal zone, given that once the prosthetic fit is lost, weight bearing is transferred to the socket's distal section (mean volume loss, intrasession −3%; mean pressure loss, intrasession −39%). Conclusions:The study suggests that a small change in the volume can cause a change in the distribution of pressures inside the socket, indicating that the prosthetic fit may be compromised. For patient follow-up, measuring pressure inside the socket could be a useful indicator of socket misfit. Clinical Relevance: Daily volume changes in the prosthesis can produce pressures that lead to pain, injuries, an inefficient gait, and prosthesis abandonment. Consequently, it is important to understand the behavior of the pressures inside the socket and the influence of the daily changes of volume on the socket adjustment to design better strategies and techniques of daily volume changes management. (

No abstract