-- Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where precise identification of stance and swing phases is essential. This study evaluated the performance of seven kinematics-based methods and a Long Short-T erm Memory (LSTM) model for detecting heel strike and toe-off events across 4363 gait cycles from 588 able-bodied subjects. The results indicated that while the Zeni et al. method achieved the highest accuracy among kinematics-based approaches, other methods exhibited systematic biases or required dataset-specific tuning. The LSTM model performed comparably to Zeni et al., providing a data-driven alternative without systematic bias. Future research will explore the generalizability of these methods in pathological populations, such as individuals with post-stroke conditions and knee osteoarthritis, as well as their robustness across varied gait conditions and data collection settings to enhance their applicability in rehabilitation and exoskeleton control.

Accurate and rapid detection of gait phases is of utmost importance in achieving optimal performance of powered lower-limb prostheses and exoskeletons. With the increasing versatility and complexity of these robotic systems, there is a growing need to enhance the performance of gait detection algorithms. The development of reliable and functional gait detection algorithms holds the potential to enhance precision, stability, and safety in prosthetic devices and other rehabilitation technologies. In this systematic review, we delve into the extensive body of research and development in the domain of gait event detection methods, with a specific focus on their application to prosthetic devices. Our review critically assesses various proposed methods, aiming to identify the most effective approaches for gait phase classification in lower limb robotic systems. Through a comprehensive comparative analysis, we highlight the strengths and weaknesses of different algorithms, shedding light on their performance characteristics, applicability, and potential for further improvements. This comprehensive review was conducted by screening two databases, namely IEEE and Scopus. The search was limited to 204 papers published from 2010 to 2023. A total of 6 papers that focused on Heuristic, Thresholding, and Amplitude Zero Crossing involved techniques were identified and included in the review. 33.3% of implemented Algorithms used kinematic parameters such as joint angles, joint linear and angular velocity, and joint angular acceleration. This study purely focuses on threshold-based algorithms and thus paper focusing on other gait phase detection methods were excluded.

Analysis of runner's data will often examine gait variables with reference to one or more gait events. Two such representative events are the initial contact and toe off events. These correspond respectively to the moments in time when the foot makes the initial contact with the ground and when the foot leaves the ground again. These variables are traditionally measured with a force plate or motion capture system in a lab setting. However, thanks to recent evolutions in wearable technology, the use of accelerometers has become commonplace for prolonged outdoor measurements. Previous research has developed heuristic methods to identify the initial contact and toe off timings based on minima, maxima and thresholds in the acceleration profiles. A significant flaw of these heuristic-based methods is that they are tailored to very specific acceleration profiles, providing no guidelines on how to handle deviant profiles. Therefore, we frame the problem as a structured prediction task and propose a machine learning approach for determining initial foot contact and toe off events from 3D tibial acceleration profiles. With mean absolute errors of 2 ms and 4 ms for respectively the initial contact and toe-off events, our method significantly outperforms the existing heuristic approaches.