Simulation of athlete gait recognition based on spectral features and machine learning

2020 ◽  
pp. 1-12
Author(s):  
Linuo Wang
Keyword(s):  
Machine Learning ◽  
Angular Velocity ◽  
Gait Recognition ◽  
Spectral Feature ◽  
Velocity Signal ◽  
Comparison Results ◽  
Computer Vision Technology ◽  
Feature Technology ◽  
Leg Movement ◽  
Recognition Efficiency

The current technology related to athlete gait recognition has shortcomings such as complicated equipment and high cost, and there are also certain problems in recognition accuracy and recognition efficiency. In order to improve the efficiency of athletes’ gait recognition, this paper studies the different recognition technologies of athletes based on machine learning and spectral feature technology and applies computer vision technology to sports. Moreover, according to the calf angular velocity signal, the occurrence of leg movement is detected in real time, and the gait cycle is accurately divided to reduce the influence of the signal unrelated to the behavior on the recognition process. In addition, this study proposes a gait behavior recognition method based on event-driven strategies. This method uses a gyroscope as the main sensor and uses a wearable sensor node to collect the angular velocity signals of the legs and waist. In addition, this study analyzes the performance of the algorithm proposed by this paper through experimental research. The comparison results show that the method proposed by this paper has improved the number of recognition action types and accuracy and has certain advantages from the perspective of computation and scalability.

scholarly journals Analysis of ergonomic and unergonomic human lifting behaviors by using Inertial Measurement Units

2017 ◽  
Vol 3 (1) ◽  
pp. 7-10 ◽  
Author(s):  
Jan Kuschan ◽  
Henning Schmidt ◽  
Jörg Krüger
Keyword(s):  
Quality Of Life ◽  
Machine Learning ◽  
Angular Velocity ◽  
Musculoskeletal System ◽  
Occupational Diseases ◽  
Inertial Measurement Units ◽  
Inertial Measurement ◽  
Measurement Units ◽  
Main Components

Abstract:This paper presents an analysis of two distinct human lifting movements regarding acceleration and angular velocity. For the first movement, the ergonomic one, the test persons produced the lifting power by squatting down, bending at the hips and knees only. Whereas performing the unergonomic one they bent forward lifting the box mainly with their backs. The measurements were taken by using a vest equipped with five Inertial Measurement Units (IMU) with 9 Dimensions of Freedom (DOF) each. In the following the IMU data captured for these two movements will be evaluated using statistics and visualized. It will also be discussed with respect to their suitability as features for further machine learning classifications. The reason for observing these movements is that occupational diseases of the musculoskeletal system lead to a reduction of the workers’ quality of life and extra costs for companies. Therefore, a vest, called CareJack, was designed to give the worker a real-time feedback about his ergonomic state while working. The CareJack is an approach to reduce the risk of spinal and back diseases. This paper will also present the idea behind it as well as its main components.

scholarly journals Burst Pressure Prediction of API 5L X-Grade Dented Pipelines Using Deep Neural Network

2020 ◽  
Vol 8 (10) ◽  
pp. 766
Author(s):  
Dohan Oh ◽  
Julia Race ◽  
Selda Oterkus ◽  
Bonguk Koo
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
Machine Learning Techniques ◽  
Burst Pressure ◽  
Comparison Results ◽  
Artificial Neural

Mechanical damage is recognized as a problem that reduces the performance of oil and gas pipelines and has been the subject of continuous research. The artificial neural network in the spotlight recently is expected to be another solution to solve the problems relating to the pipelines. The deep neural network, which is on the basis of artificial neural network algorithm and is a method amongst various machine learning methods, is applied in this study. The applicability of machine learning techniques such as deep neural network for the prediction of burst pressure has been investigated for dented API 5L X-grade pipelines. To this end, supervised learning is employed, and the deep neural network model has four layers with three hidden layers, and the neural network uses the fully connected layer. The burst pressure computed by deep neural network model has been compared with the results of finite element analysis based parametric study, and the burst pressure calculated by the experimental results. According to the comparison results, it showed good agreement. Therefore, it is concluded that deep neural networks can be another solution for predicting the burst pressure of API 5L X-grade dented pipelines.

scholarly journals An Investigation of Deep Learning Models for EEG-Based Emotion Recognition

2020 ◽  
Vol 14 ◽  
Author(s):  
Yaqing Zhang ◽  
Jinling Chen ◽  
Jen Hong Tan ◽  
Yuxuan Chen ◽  
Yunyi Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Emotion Recognition ◽  
Real Life ◽  
Learning Rate ◽  
Learning Models ◽  
Learning Methods ◽  
Time Frequency ◽  
Comparison Results

Emotion is the human brain reacting to objective things. In real life, human emotions are complex and changeable, so research into emotion recognition is of great significance in real life applications. Recently, many deep learning and machine learning methods have been widely applied in emotion recognition based on EEG signals. However, the traditional machine learning method has a major disadvantage in that the feature extraction process is usually cumbersome, which relies heavily on human experts. Then, end-to-end deep learning methods emerged as an effective method to address this disadvantage with the help of raw signal features and time-frequency spectrums. Here, we investigated the application of several deep learning models to the research field of EEG-based emotion recognition, including deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and a hybrid model of CNN and LSTM (CNN-LSTM). The experiments were carried on the well-known DEAP dataset. Experimental results show that the CNN and CNN-LSTM models had high classification performance in EEG-based emotion recognition, and their accurate extraction rate of RAW data reached 90.12 and 94.17%, respectively. The performance of the DNN model was not as accurate as other models, but the training speed was fast. The LSTM model was not as stable as the CNN and CNN-LSTM models. Moreover, with the same number of parameters, the training speed of the LSTM was much slower and it was difficult to achieve convergence. Additional parameter comparison experiments with other models, including epoch, learning rate, and dropout probability, were also conducted in the paper. Comparison results prove that the DNN model converged to optimal with fewer epochs and a higher learning rate. In contrast, the CNN model needed more epochs to learn. As for dropout probability, reducing the parameters by ~50% each time was appropriate.

scholarly journals A Novel Method for Estimating Knee Angle Using Two Leg-Mounted Gyroscopes for Continuous Monitoring with Mobile Health Devices

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2759 ◽  
Author(s):  
Eric Allseits ◽  
Kyoung Kim ◽  
Christopher Bennett ◽  
Robert Gailey ◽  
Ignacio Gaunaurd ◽  
...  
Keyword(s):  
Angular Velocity ◽  
Knee Joint ◽  
Convergent Validity ◽  
Continuous Monitoring ◽  
Joint Angle ◽  
Characteristic Point ◽  
Accelerometer Data ◽  
Knee Angle ◽  
Velocity Signal ◽  
Knee Joint Angle

Tele-rehabilitation of patients with gait abnormalities could benefit from continuous monitoring of knee joint angle in the home and community. Continuous monitoring with mobile devices can be restricted by the number of body-worn sensors, signal bandwidth, and the complexity of operating algorithms. Therefore, this paper proposes a novel algorithm for estimating knee joint angle using lower limb angular velocity, obtained with only two leg-mounted gyroscopes. This gyroscope only (GO) algorithm calculates knee angle by integrating gyroscope-derived knee angular velocity signal, and thus avoids reliance on noisy accelerometer data. To eliminate drift in gyroscope data, a zero-angle update derived from a characteristic point in the knee angular velocity is applied to every stride. The concurrent validity and construct convergent validity of the GO algorithm was determined with two existing IMU-based algorithms, complementary and Kalman filters, and an optical motion capture system, respectively. Bland–Altman analysis indicated a high-level of agreement between the GO algorithm and other measures of knee angle.

scholarly journals Fire Risk Assessment Models Using Statistical Machine Learning and Optimized Risk Indexing

2020 ◽  
Vol 10 (12) ◽  
pp. 4199
Author(s):  
Myoung-Young Choi ◽  
Sunghae Jun
Keyword(s):  
Machine Learning ◽  
Risk Assessment ◽  
Logistic Regression ◽  
Prediction Model ◽  
Fire Risk ◽  
Fire Occurrence ◽  
Statistical Machine Learning ◽  
Fire Insurance ◽  
Comparison Results ◽  
Fire Risk Assessment

It is very difficult for us to accurately predict occurrence of a fire. But, this is very important to protect human life and property. So, we study fire hazard prediction and evaluation methods to cope with fire risks. In this paper, we propose three models based on statistical machine learning and optimized risk indexing for fire risk assessment. We build logistic regression, deep neural networks (DNN) and fire risk indexing models, and verify performances between proposed and traditional models using real investigated data related to fire occurrence in Korea. In general, fire prediction models currently in use do not provide satisfactory levels of accuracy. The reason for this result is that the factors affecting fire occurrence are very diverse and frequency of fire occurrence is very sparse. To improve accuracy of fire occurrence, we first build logistic regression and DNN models. In addition, we construct a fire risk indexing model for a more improved model of fire prediction. To illustrate comparison results between our research models and current fire prediction model, we use real fire data investigated in Korea between 2011 to 2017. From the experimental results of this paper, we can confirm that accuracy of prediction by the proposed method is superior to the existing fire occurrence prediction model. Therefore, we expect the proposed model to contribute to evaluating the possibility of fire risk in buildings and factories in the field of fire insurance and to calculate the fire insurance premium.

scholarly journals Mechanistic insights into the modulatory role of the mechanoreflex on central hemodynamics using passive leg movement in humans

2018 ◽  
Vol 125 (2) ◽  
pp. 545-552 ◽  
Author(s):  
Nicholas T. Kruse ◽  
William E. Hughes ◽  
Darren P. Casey
Keyword(s):  
Cardiac Output ◽  
Angular Velocity ◽  
Range Of Motion ◽  
Joint Angle ◽  
Feedback Mechanism ◽  
Fascicle Length ◽  
Percent Change ◽  
Muscle Fascicle ◽  
Angular Velocities ◽  
Leg Movement

The aim of this study was to examine the independent contributions of joint range of motion (ROM), muscle fascicle length (MFL), and joint angular velocity on mechanoreceptor-mediated central cardiovascular dynamics using passive leg movement (PLM) in humans. Twelve healthy men (age: 23 ± 2 yr, body mass index: 23.7 kg/m2) performed continuous PLM at various randomized joint angle ROMs (0°–50° vs. 50°–100° vs. 0°–100°) and joint angular velocities (“fast”: 200°/s vs. “slow”: 100°/s). Measures of heart rate (HR), cardiac output (CO), and mean arterial pressure (MAP) were recorded during baseline and during 60 s of PLM. MFL was calculated from muscle architectural measurements of fascicle pennation angle and tissue thickness (Doppler ultrasound). Percent change in MFL increased across the transition of PLM from 0° to 50° (15 ± 3%; P < 0.05) and from 0° to 100° knee flexion (27 ± 4%; P < 0.05). The average peak percent change in HR (increased, approx. +5 ± 2%; P < 0.05), CO (increased, approx. +5 ± 3%; P < 0.05), and MAP (decreased, approx. −2 ± 2%; P < 0.05) were similar between fast versus slow angular velocities when compared against shorter absolute joint ROMs (i.e., 0°–50° and 50°–100°). However, the condition that exhibited the greatest angular velocity in combination with ROM (0°–100° at 200°/s) elicited the greatest increases in HR (+13 ± 2%; P < 0.05) and CO (+12 ± 2%; P < 0.05) compared with all conditions. Additionally, there was a significant relationship between MFL and HR within 0°–100° at 200°/s condition ( r2 = 0.59; P < 0.05). These findings suggest that increasing MFL and joint ROM in combination with increased angular velocity via PLM are important components that activate mechanoreflex-mediated cardioacceleration and increased CO. NEW & NOTEWORTHY The mechanoreflex is an important autonomic feedback mechanism that serves to optimize skeletal muscle perfusion during exercise. The present study sought to explore the mechanistic contributions that initiate the mechanoreflex using passive leg movement (PLM). The novel findings show that progressively increasing joint angle range of motion and muscle fascicle length via PLM, in combination with increased angular velocity, are important components that activate mechanoreflex-mediated cardioacceleration and increase cardiac output in humans.

scholarly journals PID Control for Electric Vehicles Subject to Control and Speed Signal Constraints

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Amanda Danielle O. da S. Dantas ◽  
André Felipe O. de A. Dantas ◽  
João Tiago L. S. Campos ◽  
Domingos L. de Almeida Neto ◽  
Carlos Eduardo T. Dórea
Keyword(s):  
Angular Velocity ◽  
Electric Vehicles ◽  
Pid Control ◽  
Pid Controller ◽  
Dc Motor ◽  
Invariant Set ◽  
Velocity Signal ◽  
Tuning Parameters ◽  
Multiparametric Programming ◽  
Control Actions

A PID control for electric vehicles subject to input armature voltage and angular velocity signal constraints is proposed. A PID controller for a vehicle DC motor with a separately excited field winding considering the field current constant was tuned using controlled invariant set and multiparametric programming concepts to consider the physical motor constraints as angular velocity and input armature voltage. Additionally, the integral of the error, derivative of the error constraints, and λ were considered in the proposed algorithm as tuning parameters to analyze the DC motor dynamic behaviors. The results showed that the proposed algorithm can be used to generate control actions taking into account the armature voltage and angular velocity limits. Also, results demonstrate that a controller subject to constraints can improve the electric vehicle DC motor dynamic; and at the same time it protects the motor from overvoltage.

scholarly journals Transient Stability Control Based on Kinetic Energy Changes Measured by Synchronized Angular Velocity

Energies ◽  
2021 ◽  
Vol 14 (21) ◽  
pp. 6893
Author(s):  
A. F. Diaz-Alzate ◽  
John E. Candelo-Becerra ◽  
Albert Deluque-Pinto
Keyword(s):  
Kinetic Energy ◽  
Angular Velocity ◽  
Power Systems ◽  
Real Time ◽  
Transient Stability ◽  
Stability Control ◽  
Area Measurement ◽  
Velocity Signal ◽  
Large Power ◽  
Time Operation

Real-time transient stability studies are based on voltage angle measures obtained with phasor measurement units (PMUs). A more precise calculation to address transient stability is obtained when using the rotor angles. However, these values are commonly estimated, which leads to possible errors. In this work, the kinetic energy changes in electric machines are used as a criterion for evaluating and correcting transient stability, and to determine the precise time of insertion of a special protection system (SPS). Data from the PMU of the wide-area measurement system (WAMS) are used to construct the SPS. Furthermore, it is assumed that a microcontroller can be located in each generation unit to obtain the synchronized angular velocity. Based on these measurements, the kinetic energy of the system and the respective control action are performed at the appropriate time. The results show that the proposed SPS effectively corrects the oscillations fast enough during the transient stability event. In addition, the proposed method has the advantage that it does not depend on commonly proposed methods, such as system models, the identification of coherent machine groups, or the structure of the network. Moreover, the synchronized angular velocity signal is used, which is not commonly measured in power systems. Validation of the method is carried out in the New England power system, and the findings show that the method is helpful for real-time operation on large power systems.

scholarly journals Comparative analysis of multiple classification models to improve PM10 prediction performance

2021 ◽  
Vol 11 (3) ◽  
pp. 2500
Author(s):  
Yong-Jin Jung ◽  
Kyoung-Woo Cho ◽  
Jong-Sung Lee ◽  
Chang-Heon Oh
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Particulate Matter ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Occurrence Rate ◽  
Classification Models ◽  
Comparison Results ◽  
Multiple Classification

With the increasing requirement of high accuracy for particulate matter prediction, various attempts have been made to improve prediction accuracy by applying machine learning algorithms. However, the characteristics of particulate matter and the problem of the occurrence rate by concentration make it difficult to train prediction models, resulting in poor prediction. In order to solve this problem, in this paper, we proposed multiple classification models for predicting particulate matter concentrations required for prediction by dividing them into AQI-based classes. We designed multiple classification models using logistic regression, decision tree, SVM and ensemble among the various machine learning algorithms. The comparison results of the performance of the four classification models through error matrices confirmed the f-score of 0.82 or higher for all the models other than the logistic regression model.

scholarly journals Research and Application of Computer Control System Based on Complex Neural Network

2018 ◽  
Vol 227 ◽  
pp. 02009
Author(s):  
Rui Yang
Keyword(s):  
Machine Learning ◽  
Control System ◽  
Objective Function ◽  
Probabilistic Models ◽  
Computer Control ◽  
Stochastic Theory ◽  
Computer Control System ◽  
Computer Vision Technology ◽  
Learning Machine ◽  
Control System Model

In recent years, many researchers have carried out extensive research on this issue, and some research results have been widely applied to the practice of machine learning. Machine learning essentially uses a function to transform the problem of machine learning into a function problem, and then implement machine learning by solving the objective function. The most important tool in solving the objective function is the optimization algorithm. In this paper, based on computer vision technology and stochastic theory, a computer control system model based on ARTMAP network is proposed. Based on this model, we validate the performance of the system by performing system simulations and compare it with traditional computer control systems. And randomized algorithms, which embodies the compelling principles of theory. In this position paper we use probabilistic models to disconfirm that the infamous interposable algorithm for the evaluation.

Sign in / Sign up

Export Citation Format

Share Document