Intelligent recognition of dance training movements based on machine learning and embedded system

2021 ◽  
pp. 1-13
Author(s):  
Dixin Zhang
Keyword(s):  
Real Time ◽  
Smart Home ◽  
Three Dimensional ◽  
Recognition Algorithm ◽  
Human Motion ◽  
Support Vector ◽  
Motion Recognition ◽  
Motion Data ◽  
Local Database ◽  
Error Recognition

Recognizing human movement is an important research topic in the field of human-computer interaction, and people expect it to be used in smart homes, virtual reality, and electronic games. Based on the interaction between humans and computers, more and more attention has been paid, especially in the field of smart home action recognition. Through observation, people can understand the intention of intelligent interaction is included in the main part. However, the current recognition algorithms still cannot meet the actual requirements of the accuracy, real-time and robustness of human motion recognition. Especially in order to recognize complex human movements in real time, it is imperative to solve several problems in motion capture and recognition. Establishing the feature parameter angle of the feature vector space of motion data, using the pre-recognition algorithm is based on multi-class support vector machines. The motion recognition algorithm takes advantage of the accurate and fast classification function of svm. Based on the structural differences of the motion data, most of the data can be correctly identified. The optimal motion recognition algorithm uses hmm to correct the svm error recognition result through the random constraint relationship between the error recognition data and the actual label. Based on data simulation and analysis, each variable determined by the grid search algorithm has the highest accuracy in the optimization of each variable of the support vector machine. Finally, a smart home simulation experiment interactive system was built, and a local database was created, including 1,300 processes. The real-time algorithm uses the data in the local database for training and testing. Experimental results show that the motion recognition algorithm in this paper improves the accuracy and robustness of complex motion recognition. While meeting the real-time recognition conditions, the correct answer rate of the final operation can reach 9.6%. The human motion trajectory recognition system uses the three-dimensional trajectory of gestures to recognize motion. The information in the three-dimensional space is more comprehensive, and the orbit recognition is more robust.

scholarly journals CSI-HC: A WiFi-Based Indoor Complex Human Motion Recognition Method

2020 ◽  
Vol 2020 ◽  
pp. 1-20
Author(s):  
Zhanjun Hao ◽  
Yu Duan ◽  
Xiaochao Dang ◽  
Tong Zhang
Keyword(s):  
Real Time ◽  
Human Motion ◽  
Detection Accuracy ◽  
Behavior Recognition ◽  
Motion Recognition ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Motion Data ◽  
Indoor Scenes ◽  
Human Motion Recognition

WiFi indoor personnel behavior recognition has become the core technology of wireless network perception. However, the existing human behavior recognition methods have great challenges in terms of detection accuracy, intrusion, and complexity of operations. In this paper, we firstly analyze and summarize the existing human motion recognition schemes, and due to the existence of the problems in them, we propose a noninvasive, highly robust complex human motion recognition scheme based on Channel State Information (CSI), that is, CSI-HC, and the traditional Chinese martial art XingYiQuan is verified as a complex motion background. CSI-HC is divided into two phases: offline and online. In the offline phase, the human motion data are collected on the commercial Atheros NIC and a powerful denoising method is constructed by using the Butterworth low-pass filter and wavelet function to filter the outliers in the motion data. Then, through Restricted Boltzmann Machine (RBM) training and classification, we establish offline fingerprint information. In the online phase, SoftMax regression is used to correct the RBM classification to process the motion data collected in real time and the processed real-time data are matched with the offline fingerprint information. On this basis, the recognition of a complex human motion is realized. Finally, through repeated experiments in three classical indoor scenes, the parameter setting and user diversity affecting the accuracy of motion recognition are analyzed and the robustness of CSI-HC is detected. In addition, the performance of the proposed method is compared with that of the existing motion recognition methods. The experimental results show that the average motion recognition rate of CSI-HC in three classic indoor scenes reaches 85.4%, in terms of motion complexity and indoor recognition accuracy. Compared with other algorithms, it has higher stability and robustness.

scholarly journals Human motion recognition based on SVM in VR art media interaction environment

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Fuquan Zhang ◽  
Tsu-Yang Wu ◽  
Jeng-Shyang Pan ◽  
Gangyi Ding ◽  
Zuoyong Li
Keyword(s):  
Genetic Algorithm ◽  
Dimensional Space ◽  
Dimensional Subspace ◽  
Recognition Algorithm ◽  
Human Motion ◽  
Support Vector ◽  
Motion Recognition ◽  
Linear Discriminant ◽  
Classification Feature ◽  
Human Motion Recognition

AbstractIn order to solve the problem of human motion recognition in multimedia interaction scenarios in virtual reality environment, a motion classification and recognition algorithm based on linear decision and support vector machine (SVM) is proposed. Firstly, the kernel function is introduced into the linear discriminant analysis for nonlinear projection to map the training samples into a high-dimensional subspace to obtain the best classification feature vector, which effectively solves the nonlinear problem and expands the sample difference. The genetic algorithm is used to realize the parameter search optimization of SVM, which makes full use of the advantages of genetic algorithm in multi-dimensional space optimization. The test results show that compared with other classification recognition algorithms, the proposed method has a good classification effect on multiple performance indicators of human motion recognition and has higher recognition accuracy and better robustness.

A Projection-based Human Motion Recognition Algorithm based on Depth Sensors

2021 ◽  
pp. 1-1
Author(s):  
Mu-Chun Su ◽  
Pang-Ti Tai ◽  
Jieh-Haur Chen ◽  
Yi-Zeng Hsieh ◽  
Shu-Fang Lee ◽  
...  
Keyword(s):  
Recognition Algorithm ◽  
Human Motion ◽  
Motion Recognition ◽  
Depth Sensors ◽  
Human Motion Recognition

scholarly journals A flexible motion tracking system based on inertial sensors

2018 ◽  
Vol 198 ◽  
pp. 04010
Author(s):  
Zhonghao Han ◽  
Lei Hu ◽  
Na Guo ◽  
Biao Yang ◽  
Hongsheng Liu ◽  
...  
Keyword(s):  
Motion Tracking ◽  
Data Transfer ◽  
Inertial Sensors ◽  
Tracking System ◽  
Calibration Procedure ◽  
Human Motion ◽  
The Body ◽  
Support Vector ◽  
Motion Data ◽  
Motion Tracking System

As a newly emerging human-computer interaction, motion tracking technology offers a way to extract human motion data. This paper presents a series of techniques to improve the flexibility of the motion tracking system based on the inertial measurement units (IMUs). First, we built a most miniatured wireless tracking node by integrating an IMU, a Wi-Fi module and a power supply. Then, the data transfer rate was optimized using an asynchronous query method. Finally, to simplify the setup and make the interchangeability of all nodes possible, we designed a calibration procedure and trained a support vector machine (SVM) model to determine the binding relation between the body segments and the tracking nodes after setup. The evaluations of the whole system justify the effectiveness of proposed methods and demonstrate its advantages compared to other commercial motion tracking system.

scholarly journals Genetic algorithm–optimized support vector machine for real-time activity recognition in health smart home

2020 ◽  
Vol 16 (11) ◽  
pp. 155014772097151
Author(s):  
Yan Hu ◽  
Bingce Wang ◽  
Yuyan Sun ◽  
Jing An ◽  
Zhiliang Wang
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Real Time ◽  
Activity Recognition ◽  
Smart Home ◽  
Feature Representation ◽  
Support Vector ◽  
Typical Application ◽  
Time Activity ◽  
Health Smart Home

Health smart home, as a typical application of Internet of things, provides a new solution for remote medical treatment. It can effectively relieve pressure from shortage of medical resources caused by aging population and help elderly people live at home more independently and safely. Activity recognition is the core of health smart home. This technology aims to recognize the activity patterns of users from a series of observations on the user’ actions and the environmental conditions, so as to avoid distress situations as much as possible. However, most of the existing researches focus on offline activity recognition, but not good at online real-time activity recognition. Besides, the feature representation techniques used for offline activity recognition are generally not suitable for online scenarios. In this article, the authors propose a real-time online activity recognition approach based on the genetic algorithm–optimized support vector machine classifier. In order to support online real-time activity recognition, a new sliding window-based feature representation technique enhanced by mutual information between sensors is devised. In addition, the genetic algorithm is used to automatically select optimal hyperparameters for the support vector machine model, thereby reducing the recognition inaccuracy caused by manual tuning of hyperparameters. Finally, a series of comprehensive experiments are conducted on freely available data sets to validate the effectiveness of the proposed approach.

Towards Multi-Classification of Human Motions Using Micro IMU and SVM Training Process

2009 ◽  
Vol 60-61 ◽  
pp. 189-193 ◽  
Author(s):  
Guang Yi Shi ◽  
Yue Xian Zou ◽  
Wen J. Li ◽  
Yu Feng Jin ◽  
Pei Guan
Keyword(s):  
Optimal Parameter ◽  
Recognition Rate ◽  
Three Dimensional ◽  
Human Motion ◽  
Measurement Unit ◽  
Support Vector ◽  
Training Process ◽  
Motion Feature ◽  
Novel Approach ◽  
Multi Classification

This paper introduces a novel approach for human motion recognition via motion feature vectors collected by A Micro Inertial Measurement Unit (µIMU). First, µIMU that is 56x23x15mm3 in size was built. The unit consists of three dimensional MEMS accelerometers, gyroscopes, a Bluetooth module and a Micro Controller Unit (MCU), which can transmit human motion information through a serial port to a computer. Second, a human motion database was setup by recording the motion data from the µIMU. The motions include fall, walk, stand, run and step upstairs. Third, Support Vector Machine (SVM) training process was used for human motion multi-classification. FFT was used for feature generation and optimal parameter searching process was done for the best SVM kernel function. Experimental results showed that for the given 5 different motions, the total correct recognition rate is 92%, of which the fall motion can be classified from others with 100% recognition rate.

scholarly journals A Flexible and Stretchable Self-Powered Nanogenerator in Basketball Passing Technology Monitoring

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2584
Author(s):  
Changjun Jia ◽  
Yongsheng Zhu ◽  
Fengxin Sun ◽  
Tianming Zhao ◽  
Rongda Xing ◽  
...  
Keyword(s):  
Real Time ◽  
Inorganic Salt ◽  
Rapid Development ◽  
Human Motion ◽  
Small Scale ◽  
New Approach ◽  
Motion Data ◽  
Fifth Generation ◽  
Self Powered ◽  
Generation Technology

The rapid development of the fifth generation technology poses more challenges in the human motion inspection field. In this study, a nanogenerator, made by PVDF, ionic hydrogel, and PDMS, is used. Furthermore, a transparent, stretchable, and biocompatible PENG (TSB-PENG) is presented, which can be used as a self-powered sensor attached to the athlete’s joints, which helps to monitor the training and improve the subject’s performance. This device shows the ability to maintain a relatively stable output, under various external environments (e.g., inorganic salt, organic matter and temperature). Additionally, TSB-PENG can supply power to small-scale electronic equipment, such as Bluetooth transmitting motion data in real time. This study can provide a new approach to designing lossless, real-time, portable, and durable self-powered sensors in the sports motoring field.

scholarly journals Real-Time Prediction of Joint Forces by Motion Capture and Machine Learning

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6933
Author(s):  
Georgios Giarmatzis ◽  
Evangelia I. Zacharaki ◽  
Konstantinos Moustakas
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Motion Capture ◽  
Human Motion ◽  
Contact Forces ◽  
Skeletal Structure ◽  
Mathematical Representation ◽  
Support Vector ◽  
Optical Motion ◽  
Training Schemes

Conventional biomechanical modelling approaches involve the solution of large systems of equations that encode the complex mathematical representation of human motion and skeletal structure. To improve stability and computational speed, being a common bottleneck in current approaches, we apply machine learning to train surrogate models and to predict in near real-time, previously calculated medial and lateral knee contact forces (KCFs) of 54 young and elderly participants during treadmill walking in a speed range of 3 to 7 km/h. Predictions are obtained by fusing optical motion capture and musculoskeletal modeling-derived kinematic and force variables, into regression models using artificial neural networks (ANNs) and support vector regression (SVR). Training schemes included either data from all subjects (LeaveTrialsOut) or only from a portion of them (LeaveSubjectsOut), in combination with inclusion of ground reaction forces (GRFs) in the dataset or not. Results identify ANNs as the best-performing predictor of KCFs, both in terms of Pearson R (0.89–0.98 for LeaveTrialsOut and 0.45–0.85 for LeaveSubjectsOut) and percentage normalized root mean square error (0.67–2.35 for LeaveTrialsOut and 1.6–5.39 for LeaveSubjectsOut). When GRFs were omitted from the dataset, no substantial decrease in prediction power of both models was observed. Our findings showcase the strength of ANNs to predict simultaneously multi-component KCF during walking at different speeds—even in the absence of GRFs—particularly applicable in real-time applications that make use of knee loading conditions to guide and treat patients.

Sign in / Sign up

Export Citation Format

Share Document