Gait analysis is a prosperous tool for the clinical evaluation and diagnosis. In this article, portable gait system based on foot-mounted inertial sensors established. A threshold-free method using long short-term memory recurrent neural network constructed to segment four typical phases in sequence temporal parameters analysis. Segmentation accuracy reaches over 95% across recruited subjects with distinct patterns, which significantly superior when compared traditional machine learning...

A correct riding posture is essential for a good performance in equestrian. This paper proposes method of equestrian analysis based on body sensor networks. First all, raw data corresponding to professional (PRO) riders and beginners (BEGs) under different horse gaits were collected by inertial nodes. Then, after an initial alignment with the reduced error, kind motion reconstruction gradient descent was used fuse constantly update rider's attitude information. In addition, evaluate tracking...

Motion capture based on wearable inertial sensors is a promising technique for swimmers' training. To apply motion techniques properly, swimming evaluation method technology proposed. Our proposed uses multisensor data fusion algorithm attitude estimation, and the posture reconstructed in combination with human biomechanical model. Furthermore, comparative experiment between our system NDI tracking shows that performs reliably accurately, estimation errors are well controlled. In addition,...

For the purpose of quantitative analysis, this paper proposes a wearable gait analysis method for Parkinson's disease (PD) to evaluates motor ability. The error state Kalman filter (ESKF) is used attitude estimation, and parameters are modified by phase segmentation zero velocity update (ZUPT) algorithm. In addition, study uses as classifier features recognize abnormal gait, compares recognition effect with statistical features. our system verified comparison OptiTrack system, mean absolute...

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they be used as input for the to predict body’s movement intention. In this paper, OpenSim software is determine muscle sites measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps lateral gastrocnemius, and tibial anterior. The surface (sEMG) inertial data are collected from lower limbs while human body walking, going...

Swimming is a worldwide popular sports whose performance highly correlated to the posture.To analyze and recognize posture in swimming, monitoring system (SwimSense) for human swimming training based on wearable inertial sensors established. In this paper, one sensor node arranged surface of lumbar, raw data concerning four styles was collected. Through fusion method statistical analysis, features information were extracted. Subsequently, we proposed an action recognition HMM. According...

Evaluation of the motor ability children with cerebral palsy (CP) based on International Classification Functioning, Disability and Health for Children Youth (ICF-CY) framework is an effective way to evaluate exercise rehabilitation therapy at present. Spastic diplegia (SD) a common symptom in CP, which can cause movement disorders physical disability lower limbs. To rehabilitate these children, it important assess their level different treatment stages. In this study, method motion...

Deadlift is one of the most common weight training exercises that can help build waist muscles. However, many trainers with less experience may not receive expected effect or even damage themselves. To exercise in a healthier way, portable and quantifiable deadlift evaluation system proposed this article. The employs body sensor network (BSN), including inertial surface electromyography (sEMG) information, to reconstruct human motion segment into certain phases realize detailed analysis. A...

The development of activity recognition based on multi-modal data makes it possible to reduce human intervention in the process monitoring. This paper proposes an efficient and cost-effective sensing framework for monitoring, can automatically identify activities data, provide help patients with moderate disabilities. monitoring relies parallel processing videos inertial data. A new supervised adaptive fusion method (AMFM) is used Spatio-temporal graph convolution network loss function...

Tremor is one of the earliest signs Parkinson's disease (PD), which seriously disrupts patients' daily lives. It important to study upper limb tremors quantitatively control PD progression. In this study, surface electromyography (sEMG) signals from wearable devices are used recognize rest, posture, and kinetic tremor action six clinical actions quantify features tremors. A multivariable time-series classification model (MTSCM) based on fully convolutional networks a long short-term memory...

Injury duo to falling has accounted for a significant portion of accident. In order provide prompt first-aid service the victims, automatic and wearable devices are necessary report accident as soon it occurs. This paper presents an intelligent shoe system which can not only detect fall, but also classify fall direction, especially serious backward fall. prototype, eight pairs force sensing resistors (FSRs) acquire forces in different location insole. To reduce computational cost power...

This study proposed a wearable inertial motion capture (Mocap) method for Parkinson's lower limb reconstruction and analysis. To eliminate the error accumulation caused by sensor noise, state Kalman filter is used attitude estimation. The Mocap in this compared with OptiTrack system to verify tracking effect. accuracy of different phase-detection methods compared, highest recognition 99.11% using long short-term memory (LSTM) method. In addition, collected subjects healthy control (HC),...

The domestic and foreign status of terahertz wireless communication is introduced, the paper analyzes feasibility ultra high speed short range long inter-satellite communication.The capacity system under ideal additive white Gaussian noise (AWGN) channel studied.It simulates link calculates gain antenna design parameter requirements by analyzing more than 100Gbps 2.5Gbps communication.

Horse-rider interaction analysis by wearable sensors is a promising tool for monitoring equestrian training. In this paper, body sensor network (BSN) based motion system developed, which combines bespoke inertial measurement units (IMU) and MindWave electroencephalography (EEG) acquisition equipment. To fuse the mechanical EEG signals collected from system, emotional attitude information can be obtained to analyze between rider horse in For data fusion, novel method, exercise intensity...

Objective and quantitative physical fitness assessment is the basis of pre-rehabilitation treatment for cancer patients, which can speed up process reduce adverse effects after treatment. In this study, in order to make shortcomings traditional by oncologists according scale, a method using multi-model decision fusion based on multi-source data proposed. After fully considering weakness novel experimental paradigm designed. The physiological 201 patients suffer from cancers have been...

Combining the current development of high-gain antenna technology, inter-satellite terahertz communication system's demand for acquisition pointing and tracking (Acquisition Pointing Tracking, APT) technology are analyzed based on application. The tracking-pointing error has a major influence received power system by simulating calculating APT subsystem. higher wave frequency, greater error. vibration satellite platform simulation calculation. There is almost no when frequency 0.34THz, while...

Quantitative gait research is an effective auxiliary means to provide clinic diagnosis and surgery guidance for patients mobility. The traditional analysis carried out in the laboratory cannot be easily applied into clinical medicine due its complexity high operating costs. To overcome this limitation, inertial sensors fixed on ankle could perform out-of-lab measurements subjects walking patterns. In paper, a low-cost intelligent wearable system based proposed, which can measure...

For the special meteorological condition of high altitude transmission,first,the influence atmospheric turbulence on Terahertz wireless communication is analyzed, and constants model with increase in height given. On this basis, relationship between flicker index horizon transmission distance wave analyzed by simulation. Then, through analysis path loss noise, link built. Finally, budget given according to current device parameters, bit error rate (BER) performance on-off keyed modulation...

Accelerometer is a motion sensor, which can sense change in any of its three axes. It known that accelerometers inevitably suffer from multiple noise effects, and hence six-position calibration method usually applied to estimate the deterministic sensor errors. However, for traditional method, high-precision turntable needed, relatively expensive fixed place, thus not available many research groups use as portable tool. Therefore, this paper improves by introducing rotation matrix achieve...