Walking gait event detection based on electromyography signals using artificial neural network

Human walking is an important and intuitive operation in daily life, but it is different for people missing this ability. Recognizing human gait cycle portions during walking is very useful for understanding the biomechanics of the muscles, pre-disease’s diagnosis, and designing lower limb prosthetics. The normal gait cycle is divided into stance and swing phases. In this work, benchmarking of several classification techniques is performed, based on electromyography (EMG) data collected from seven lower limb muscles, with the gait cycle phase used as a target vector to label the EMG data. The dataset is split into a training set used to build a statistical model using a specified classification technique, and a test set for purpose of testing a pre-generated statistical model. EMG signals are unfortunately normally corrupted with noise, which drastically reduces their classification performance. A median filter and root mean square (RMS) filter were thus applied to the raw EMG signals, and the performance of the classification techniques calculated in all cases for the raw EMG, EMG with median filter, and EMG with RMS filters for comparison purposes. The use of filters offered good enhancement in the classification process. The median filtered EMG signal performed best and gave higher accuracy than the raw EMG and RMS filtered EMG signals due to the technique’s efficacy in removing outliers. This work also offers a simple explanation of each classifier algorithm used, and a graphical feature selection was also applied to all seven muscles of interest to identify the muscle with the most influence on the gait cycle. The Rectus Femoris muscle shows the best activity separation between swing and stance phases, working mainly during the swing phase; this higher activity during the swing phase thus caused it to be identified as the muscle with the most influence over the normal gait cycle.

We present a framework for the detection of swing and stance phases of gait cycle during walk on a perturbing platform, i.e., a slackline. The framework employs a time varying Kalman filter to reconstruct neural commands from the accelerometer data acquired from slackline perturbations that are generated by the participants. Electromyography (EMG) signals reconstructed from the estimated neural command were compared with surface EMG recordings during slackline walking. For four gait trials, the EMG signals were reconstructed with 92%-95% accuracy. These reconstructed signals were dimensionally reduced using principal component analysis (PCA) and classified using support vector machine (SVM), Decision Tree (DT), Naive Bayes (NB) classifiers. The stance and swing phases were discriminated, the performance of each classifiers was evaluated and classification accuracy was later enhanced with post processing. The DT algorithm outperformed others in detecting the stance and swing phases of gait cycle on slackline with 99.5% accuracy.

This study aims to detect gait events using a smartphone combined with deep learning and evaluate the remote effects and clinical significance of this method in different elderly populations and patients with cerebral small vessel disease (CSVD). In total, 150 healthy individuals aged 20-70 years were asked to attach a smartphone to their thighs and walk six gait cycles at self-selected low, normal, and high speeds, using an insole pressure sensor as the reference standard for gait events. A deep learning model was then established using BiTCN-BiGRU-CrossAttention, and two models (TCN-GRU and BiTCN-BiGRU) were compared. In total, 48 elderly (25 healthy, 12 with mild cognitive impairment, 11 with Parkinson's disease) participated in an online home assessment, completing single-task and cognitive dual-task walking. Overall, 35 CSVD patients participated in an offline clinical assessment, completing single-task, cognitive dual-task, and physical dual-task walking. The BiTCN-BiGRU-CrossAttention model had the lowest MAE for detecting gait events compared to the other models. All models had lower MAEs for detecting heel strikes than toe-offs, and the MAE for low and high walking was higher than for normal speed walking. There were significant differences (p < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Swing time, Stride length, and walking speed) between single-task and cognitive dual-task walking for all online elderly participants. CSVD patients showed significant differences (p < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Stride length, and walking speed) between single-task and cognitive dual-task and between single-task and physical dual-task walking.

The complex construction of the joint apparatus of the cat distal forelimb, which allows the paw three degrees of freedom, poses special requirements on the neural signals controlling the paw position. To understand the electromyography (emg) signals of the distal forelimb muscles during locomotion, it is necessary to know the kinematics of the forelimb joints in detail. As no such information is available, we used the pulsed X-ray technique in trained cats during treadmill locomotion to analyse the angular excursions of the wrist, the metacarpophalangeal (MCP) and the proximal interphalangeal (PIP) joints. X-ray illuminations were done in either the parasagittal or the frontal plane. At the beginning of the stance phase the wrist (WR) and the MCP joints extended slowly, and the PIP joints flexed. Whereas the WR and the PIP joints maintained a constant angular position of approximately 200 degrees and 60 degrees, respectively, throughout the stance phase, extension continued in the MCP joints from 240 degrees at touch-down to 300 degrees at the end of the stance phase. Slightly before lift-off (100 ms) the WR and the MCP joints flexed rapidly. This flexion changed approximately 150 ms after lift-off into a slow extension. The PIP joints extended rapidly at the beginning and at the end of the swing phase, during the interposed period of the swing phase they displayed a slow flexion. Rotatory movements of the forelimb in the radioulnar joints were present during the swing and stance phases. During the swing phase the limb first supinated (starting 100 ms after lift-off); pronation occurred immediately before ground contact. During the stance phase the supination angle was kept constant until 100 ms before lift-off, when a short pronation was found. The paw was kept in an ulnar deviated position throughout the complete step cycle. Ulnar deviation decreased at the end of the swing and stance phases. The results of this study increase our understanding of how the body weight is transmitted on to the ground. They suggest four main functions for the skeletomotor apparatus and the underlying neural commands to secure the forward movement of the animal during the stance phase: (i) preparation and stabilization of a force-transmitting platform; (ii) stabilization of the wrist and the carpal/metacarpal joints; (iii) stabilization of the supination angle; (iv) antigravity control of the extension in the MCP.

According to Vision Indonesia, data on people with eye diseases in Indonesia in 2018-2019 were 3 million people or about 1.5% of the total population. So far, public information or knowledge about the recognition of eye disease disorders is still lacking. The problem in this study is how to educate the public about the introduction of eye diseases based on information on symptoms of the disease and how to apply the web-based Artificial Neural Network (ANN) algorithm for the introduction of eye diseases. The ANN algorithm in the eye disease recognition education system can conclude knowledge even though it does not have certainty and takes it into account sequentially so that the process is faster. In terms of educational content about eye disease recognition, this is a novelty to use. This research aims to create an educational system for introducing eye diseases based on information on symptoms of the disease and applying a web-based Artificial Neural Network (ANN) algorithm for the recognition of eye diseases. The method used is the Artificial Neural Network algorithm method. The work of ANN in the education system for the introduction of eye diseases is to make parameters of eye disease symptoms or indicators that will produce the type of eye disease. The research material used is data on types of eye diseases and symptoms of each type of eye disease. The research results are to create an education system that can help the public recognise eye diseases based on the symptoms of these eye diseases that can be run on a web platform. The Artificial Neural Network (ANN) algorithm can manage input analysis data from disease indicators and show the initial results of eye diseases that can be detected. suffered by someone based on Training Results Weights and Bias v11= 1.6769, v01= 0.4356, w11= -1.5233, w01= 0.3242. Based on white box testing, the test results are free from logical errors. The results of this study indicate that the use of the ANN algorithm for eye disease recognition shows accurate results based on eye disease symptom data.

Rapid disability patients increasing over time and need a solution in the future. Hand amputation is one form of disability that common in Indonesian society. A possible solution would be necessary at the moment is the development of prosthetic hand that has the ability as a human hand. The development of neuroscience has now reached the stage of the body's ability to use the signal as an input signal to operate a system. One of the applications of the science development is the use of electromyography (EMG) signals as an input to the control system to operate the prosthetic hand. This study is divided into two stages: a preliminary study and further research. Initial research focus in the process of EMG signal pattern recognition and advanced research focus in the development of a prototype prosthetic hand that is integrated with the controller system. Preliminary research indicates that the results of pattern recognition EMG signal using wavelet transform and Artificial Neural Network (ANN) classification has an accuracy rate of about 77.5 %. Based on these results, it can be concluded that the study results could be used as a signal input to program control of the prosthetic hand that will be developed in phase two.

Technical note: Validation of a semi-automated software tool to determine gait-cycle variables in dairy cows

Real-time detection of gait events can be applied as a reliable input to control drop foot correction devices and lower-limb prostheses. Among the different sensors used to acquire the signals associated with walking for gait event detection, the accelerometer is considered as a preferable sensor due to its convenience of use, small size, low cost, reliability, and low power consumption. Based on the acceleration signals, different algorithms have been proposed to detect toe off (TO) and heel strike (HS) gait events in previous studies. While these algorithms could achieve a relatively reasonable performance in gait event detection, they suffer from limitations such as poor real-time performance and are less reliable in the cases of up stair and down stair terrains. In this study, a new algorithm is proposed to detect the gait events on three walking terrains in real-time based on the analysis of acceleration jerk signals with a time-frequency method to obtain gait parameters, and then the determination of the peaks of jerk signals using peak heuristics. The performance of the newly proposed algorithm was evaluated with eight healthy subjects when they were walking on level ground, up stairs, and down stairs. Our experimental results showed that the mean F1 scores of the proposed algorithm were above 0.98 for HS event detection and 0.95 for TO event detection on the three terrains. This indicates that the current algorithm would be robust and accurate for gait event detection on different terrains. Findings from the current study suggest that the proposed method may be a preferable option in some applications such as drop foot correction devices and leg prostheses.

본 연구의 목적은 실외 보행 실험 시 사용하기에 간편한 가속도계를 이용하여 보행 이벤트를 자동으로 검출하는 알고리즘을 개발하고 검증하는 것이다. 개발된 알고리즘은 신발의 발등에 부착된 3축 가속도계의 가속도의 총합과 보행 진행 방향(x축) 가속도를 이용하였다. 가속도 총합은 착지 시점의 검출에, x축 가속도는 이지 시점의 검출에 각각 사용되었다. 7명의 피험자가 느린 보행 속도 선호 보행 속도 빠른 보행 속도로 보행 실험을 수행하였고, 개발된 알고리즘의 검증을 위해 지면반력기를 포함한 3차원동작분석시스템과 동시에 실시되었다. 지면반력기를 이용한 보행 시점을 기준으로, 기존에 발표된 동작 자료만을 이용한 알고리즘을 통하여 얻어진 보행 시점도 함께 비교 하였다. 그 결과, 고안된 알고리즘의 정확도는 지면반력기를 이용한 값에 평균, 착지시점은 <TEX>$22.33{\pm}17.45ms$</TEX>, 이지시점은 <TEX>$26.82{\pm}14.78ms$</TEX>의 차이가 났고, 그 오차의 패턴이 일관적으로 20ms가량 먼저 검출되는 경향이 있었다. 일반적으로 트레드밀 실험에서 많이 사용되는 동작데이터를 통한 보행 시점의 비교에서도 크게 차이를 보이지 않았다. 그러므로 개발된 알고리즘은 실외 실험의 보행 시점 검출에 이용할 수 있을 것으로 판단된다. 추후 연구로는 현재의 가속도계만으로 보행 시점뿐 만아니라, 중력가속도 성분을 제거하여 보행 공간변인의 추출이 필요할 것이다. The purpose of this study was to develop and automatic gait event detection algorithm using single accelerometer which is attached at the top of the shoe. The sinal vector magnitude and anterior-posterior(x-axis) directional component of accelerometer were used to detect heel strike(HS) and toe off(TO), respectively. To evaluate proposed algorithm, gait event timing was compared with that by force plate and kinematic data. In experiment, 7 subjects performed 10 trials level walking with 3 different walking conditions such as fast, preferred & slow walking. An accelerometer, force plate and 3D motion capture system were used during experiment. Gait event by force plate was used as reference timing. Results showed that gait event by accelerometer is similar to that by force plate. The distribution of differences were spread about <TEX>$22.33{\pm}17.45m$</TEX> for HS and <TEX>$26.82{\pm}14.78m$</TEX> for To and most error was existed consistently prior to 20ms. The difference between gait event by kinematic data and developed algorithm was small. Thus it can be concluded that developed algorithm can be used during outdoor walking experiment. Further study is necessary to extract gait spatial variables by removing gravity factor.

Segment-interaction and its relevance to the control of movement during sprinting

Kinematic Features of Rear-Foot Motion Using Anterior and Posterior Ankle-Foot Orthoses in Stroke Patients With Hemiplegic Gait

Artificial intelligence through deep neural networks is now widely used in a variety of applications that have profoundly altered human livelihoods in a variety of ways. People's daily lives have become much more convenient. Image recognition, smart recommendations, self-driving vehicles, voice translation, and a slew of other neural network innovations have had a lot of success in their respective fields. The authors present the ANN applied in weather forecasting. The prediction technique relies solely upon learning previous input values from intervals in order to forecast future values. And also, Convolutional Neural Networks (CNNs) are a form of deep learning technique that can help classify, recognize, and predict trends in climate change and environmental data. However, due to the inherent difficulties of such results, which are often independently identified, non-stationary, and unstable CNN algorithms should be built and tested with each dataset and system separately. On the other hand, to eradicate error and provides us with data that is virtually identical to the real value we need Artificial Neural Networks (ANN) algorithms or benefit from it. The presented CNN model's forecasting efficiency was compared to some state-of-the-art ANN algorithms. The analysis shows that weather prediction applications become more efficient when using ANN algorithms because it is really easy to put into practice.

Peak medial (but not lateral) hamstring activity is significantly lower during stance phase of running. An EMG investigation using a reduced gravity treadmill

The main objective of this work is to make an algorithm to detect onset and offset of stance and swing phase of human gait cycle. In order to proceed, the signal from the force sensors (placed underneath each foot) were first divided according to the fundamental period by auto-correlation. This ensures that each period contains a full stance phase and two fragmented swing phases. After this step, Short Time Fourier transform has been performed on each period of the signal to detect the initial search point (highest DC value) on the stance phase. Then by judging the width and slope of the straight line from changing search points on the signal to a changing destination point (starting from the minimum or maximum time value) of the graph the onset and offset of the stance and swing phase has been detected. The changing search point has small distance from the previous one, if the slope of the signal is small, but the distance increases with the increasing change of slope of the signal. The destination point changes with the change of slope of the straight line. This algorithm has been applied to the signals in the database of Parkinsons disease, which shows a success rate of more than 90%.

The computational cost of training artificial neural network (ANN) algorithms limits the use of large systems capable of processing complex problems. Implementing ANNs on a parallel or distributed platform to improve performance is therefore desirable. This work illustrates a method to predict and evaluate the performance of distributed ANN algorithms by analyzing the performance of the comparatively simple mathematical operations, which are used to construct the ANN. The ANN algorithms are divided into simple components: matrix and vector multiplication, matrix processed through a function, competition in a matrix. These basic operational parts are examined individually and it is demonstrated that the computation processes of distributed neural networks can be derived from the composition of these basic operations. Three popular network architectures are examined: multi-layer perceptrons with back-propagation learning, self-organizing map, and radial basis functions network.