Motion Recognition Research Articles

Application of gaming robot based on gait recognition algorithm in sports training and assistance system

At present, game sports robots have become a new type of sports assistance technology, which can achieve more natural and smooth motion trajectory analysis under continuous training, and provide a gamified user experience for sports training. This article analyzes the application of game motion robots based on gait recognition algorithms in sports training and motion assistance systems, which can more accurately obtain information data of the athlete during the movement process and has good results in preventing sports injuries. We combine gait recognition algorithms with video feature aggregation to integrate high-level and low-level network features, achieving effective extraction of multi-level image features. Finally, complete action recognition, review, and analysis. Through experimental comparison, it can be seen that the feature aggregation modules designed in this article at different levels are very effective, and combined with gait recognition algorithms, they can effectively improve the accuracy of motion recognition and have excellent robustness. The motion assistance system designed in this article can automatically determine the movements during exercise, allowing athletes to self-evaluate their movements and correct incorrect movements without the need for professional guidance, achieving healthy and effective exercise results.

Exploration of deep learning-driven multimodal information fusion frameworks and their application in lower limb motion recognition

Research on Lower Limb Motion Recognition (LLMR) based on various wearable sensors has been widely applied in exoskeleton robots, exercise rehabilitation, etc. Typically, employing multimodal information tends to yield higher accuracy and stronger robustness compared to using unimodal information. Due to the inevitable reliance on feature engineering in shallow machine learning-based LLMR methods, this study leverages the powerful non-linear feature mapping capability of deep learning (DL) to construct several end-to-end LLMR frameworks, including: Convolutional Neural Networks (CNNs), CNN-Recurrent Neural Networks (RNNs) and CNN-Graph Neural Networks (GNNs). The effectiveness of the proposed frameworks is verified in distinct tasks, including the recognition of seven types of lower limb motions in healthy subjects and three types of motions in patients with stroke, as well as the phase recognition task during the sit-to-stand (SitTS) process in patients with stroke, achieving the highest mean accuracy of 95.198 %, 99.784 %, and 99.845 %, respectively. Further research and integration of two transfer learning techniques, adaptive Batch Normalization (BN) and model fine-tuning, significantly enhance the applicability of the proposed frameworks in inter-subject prediction. Additionally, systematic analyses are conducted to assess the strengths and weaknesses of different models in terms of recognition performance, complexity, and adaptability to variations in the number of modalities and sensor channels. Experimental results indicate that the proposed frameworks hold promise in providing potential support for the development of human-robot collaborative lower limb exoskeletons or rehabilitation robots.

Shifted and Weighted LFCC Features for Hand Movements Recognition Using EEG Signals

Shifted and Weighted LFCC Features for Hand Movements Recognition Using EEG Signals

Applying deep learning in brain-computer interfaces for motion recognition

Applying deep learning in brain-computer interfaces for motion recognition

A Highly Durable and UV‐Resistant Graphene‐Based Knitted Textile Sensing Sleeve for Human Joint Angle Monitoring and Gesture Differentiation

Flexible strain sensors based on textiles have attracted extensive attention owing to their light weight, flexibility, and comfort when wearing. However, challenges in integrating textile strain sensors into wearable sensing devices include the need for outstanding sensing performance, long‐term monitoring stability, and fast, convenient integration processes to achieve comprehensive monitoring. The scalable fabrication technique presented here addresses these challenges by incorporating customizable graphene‐based sensing networks into knitted structures, thus creating sensing sleeves for precise motion detection and differentiation. The performance and real‐world application potential of the sensing sleeve are evaluated by its precision in angle estimation and complex joint motion recognition during intra‐ and intersubject studies. For intra‐subject analysis, the sensing sleeve only exhibits a 2.34° angle error in five different knee activities among 20 participants, and the sensing sleeves show up to 94.1% and 96.1% accuracy in the gesture classification of knee and elbow, respectively. For inter‐subject analysis, the sensing sleeve demonstrates a 4.21° angle error, and it shows up to 79.9% and 85.5% accuracy in the gesture classification of knee and elbow, respectively. An activity‐guided user interface compatible with the sensing sleeves for human motion monitoring in home healthcare applications is presented to illustrate the potential applications.

Development of a Motion Controller for the Electric Wheelchair of Quadriplegic Patients Using Head Movements Recognition

The robotic wheelchair is designed to allow independent movement for patients with severe musculoskeletal and neuromuscular disorders that interfere with normal wheelchair propulsion by hands. Control of the movement of the wheelchair necessities residual motion of the upper extremity which was not applicable for patients with upper extremity disability as in Quadriplegic patients. Several research efforts have been proposed to help quadriplegic patients independently use the robotic wheelchair. However, the proposed solutions had many problems with accuracy, simplicity, and cost. The current work aims to build an accurate, simple, and low-cost control system for robotic wheelchairs using head movement. The proposed system was based on the use of the MEMs Inertial measurement unit (IMU) to sense the head movement gestures and transfer the gestures into signals to control the wheelchair movements. A new lightweight algorithm for the detection of head gestures was proposed to improve the system’s accuracy. The proposed system has been applied and tested on volunteers. The results revealed that the accuracy of the proposed method in recognizing head movement was 97% on average.

Self-powered porous polymer sensors with high sensitivity for machine learning-assisted motion and rehabilitation monitoring

Muscle contraction and relaxation inherently contains valuable information crucial for monitoring physical states, rehabilitation, and injury prevention. However, the majority of flexible wearable devices struggle to offer customizable sensors with high sensitivity, durability, and stability, resulting in suboptimal biofeedback performance. Herein, the machine learning-assisted smart motion and rehabilitation monitoring system (SMRMS) is demonstrated for full-body motion recognition and rehabilitation assessment using a designed porous triboelectric nanogenerator (TENG) array. A theoretical model of porous materials is built to demonstrate the effect mechanism of porosity on TENG output. Through pore design on the tribolayer, theoretical simulation and experimental are performed to determine the key features of porous TENG sensors with high sensitivity (1.76 kPa−1), fast response time (50 ms) and high durability (over 100,000 cycles). A ring-shaped TENG (RS-TENG) is fabricated based on the porous TENG sensor, enabling real-time recording of leg/arm force without additional attachment. By integrating the RS-TENG array with a multichannel signal acquisition system, an SMRMS is designed to capture motion information during human subjects’ exercise and rehabilitation training. These data are then fused for machine learning analytics, resulting in significantly improved accuracy in motion pattern recognition (98.75 %) and rehabilitation monitoring (100 %). The simple, precise and durable porous sensors could help mitigate the risk of excessive exercise-induced muscle injuries, expanding self-powered wearable functionalities and adaptabilities.

Usability Evaluation pada Aplikasi Taspen Otentikasi Berbasis System Usability Scale: Studi Kasus pada Pensiunan PNS

The Taspen Otentikasi application is a self-authentication service for retirees that uses combined biometric technology, which includes voice, face, and movement recognition from PT Taspen Persero. The aim of digitizing the authentication service into self-authentication is to make it easier for PT Taspen customers who are retirees and most of whom have entered old age so that they do not need to come to the Taspen payment partner office to carry out authentication at the counter and to avoid document forgery. To find out how easy a system can be used, usability testing can be carried out. One method that can be used in usability testing is the System Usability Scale (SUS). The total number of respondents used was 34 respondents. From this test, a score of 68.3 was obtained, which indicates that the system that has been built still needs to be refined so that it can be well received by users, especially elderly people.

Multistage Microstructured Ionic Skin for Real‐Time Vital Signs Monitoring and Human‐Machine Interaction

Skin‐like electronics research aiming to mimic even surpass human‐like specific tactile cognition by operating perception‐to‐cognition‐to‐feedback of stimulus to build intelligent cognition systems for certain imperceptible or inappreciable signals was so attractive. Herein, we constructed an all‐in‐one tri‐modal pressure sensing wearable device to address the issue of power supply by integrating multistage microstructured ionic skin (MM i‐skin) and thermoelectric self‐power staffs, which exhibits high sensitivity simultaneously. The MM i‐skin with multi‐stage “interlocked” configurations achieved precise recognition of subtle signals, where the sensitivity reached up to 3.95 kPa−1, as well as response time of 46 ms, cyclic stability (over 1500 cycles), a wide detection range of 0–200 kPa. Furthermore, we developed the thermoelectricity nanogenerator, piezoelectricity nanogenerator, and piezocapacitive sensing as an integrated tri‐modal pressure sensing, denoted as P‐iskin, T‐iskin, and C‐iskin, respectively. This multifunctional ionic skin enables real‐time monitoring of weak body signals, rehab guidance, and robotic motion recognition, demonstrating potential for Internet of things (IoT) applications involving the artificial intelligence‐motivated sapiential healthcare Internet (SHI) and widely distributed human‐machine interaction (HMI).

Instruction transmission of combat robotic arm based on neck muscles surface electromyography signals

This paper introduces a novel method for instructing wearable robotic arms based on neck movements to enhance user control. By capturing head movements representing four aiming directions and analysing surface electromyography (sEMG) signals from specific muscles, the study employs the random forest algorithm for movement recognition. Results show that utilising sEMG signals from six muscles improve classification accuracy, and applying the variational mode decomposition (VMD) algorithm enhances feature extraction. Notably, right-side muscles, particularly the sternocleidomastoid muscles, significantly impact movement classification. These findings provide theoretical support for better recognition of neck movements.

All-Textile Piezoelectric Nanogenerator Based on 3D Knitted Fabric Electrode for Wearable Applications.

Flexible, air permeable and elastic self-powered sensors for human motion monitoring and assisted medical rehabilitation have recently become a hot research topic. However, most current piezoelectric sensors can not account for many characteristics. Addressing this challenge, an all-textile piezoelectric sensor (ATPS) based on 3D structured knitted fabric electrodes is reported. The ATPS consists of a piezoelectric element polyvinylidene fluoride nanofiber membrane, flexible knitted fabric electrodes, and an elastic self-adhesive bandage. Based on the flexible and efficient knitting technology, the sensor has the advantages of low cost, flexibility, simple structure, and convenient large-area manufacturing. Experimental and finite element simulation results show that the knitting pattern of fabric electrodes can enhance the piezoelectric output of ATPS. The optimal ATPS has a high voltage response sensitivity of up to 0.68 V/kPa. The proposed ATPS responds to a wide range of input forces from 0.098 to 724 N in self-powered mode, verifying its feasibility as a tactile sensor for human motion detection and recognition (throat swallowing, wrist bending, elbow bending, knee bending, walking slowly, running fast) and as a pressure sensor (Morse code, digit recognition) and demonstrating its potential for motion tracking, medical rehabilitation, and human-computer interaction.

Head Gesture Recognition Combining Activity Detection and Dynamic Time Warping.

The recognition of head movements plays an important role in human-computer interface domains. The data collected with image sensors or inertial measurement unit (IMU) sensors are often used for identifying these types of actions. Compared with image processing methods, a recognition system using an IMU sensor has obvious advantages in terms of complexity, processing speed, and cost. In this paper, an IMU sensor is used to collect head movement data on the legs of glasses, and a new approach for recognizing head movements is proposed by combining activity detection and dynamic time warping (DTW). The activity detection of the time series of head movements is essentially based on the different characteristics exhibited by actions and noises. The DTW method estimates the warp path distances between the time series of the actions and the templates by warping under the time axis. Then, the types of head movements are determined by the minimum of these distances. The results show that a 100% accuracy was achieved in the task of classifying six types of head movements. This method provides a new option for head gesture recognition in current human-computer interfaces.

Self-supervised motor imagery EEG recognition model based on 1-D MTCNN-LSTM network

Objective. Aiming for the research on the brain–computer interface (BCI), it is crucial to design a MI-EEG recognition model, possessing a high classification accuracy and strong generalization ability, and not relying on a large number of labeled training samples. Approach. In this paper, we propose a self-supervised MI-EEG recognition method based on self-supervised learning with one-dimensional multi-task convolutional neural networks and long short-term memory (1-D MTCNN-LSTM). The model is divided into two stages: signal transform identification stage and pattern recognition stage. In the signal transform recognition phase, the signal transform dataset is recognized by the upstream 1-D MTCNN-LSTM network model. Subsequently, the backbone network from the signal transform identification phase is transferred to the pattern recognition phase. Then, it is fine-tuned using a trace amount of labeled data to finally obtain the motion recognition model. Main results. The upstream stage of this study achieves more than 95% recognition accuracy for EEG signal transforms, up to 100%. For MI-EEG pattern recognition, the model obtained recognition accuracies of 82.04% and 87.14% with F1 scores of 0.7856 and 0.839 on the datasets of BCIC-IV-2b and BCIC-IV-2a. Significance. The improved accuracy proves the superiority of the proposed method. It is prospected to be a method for accurate classification of MI-EEG in the BCI system.

Influence of VR-Assisted College Dance on College Students' Physical and Mental Health and Comprehensive Quality

With the development and the popularization of sports dance, sports dance teaching has become a required elective course in universities. Sports dance can not only improve students' comprehensive quality, but also affect college students' healthy psychology. The use of VR (Virtual Reality) technology in dance education will definitely develop and promote dance education. This paper studies an effective feature extraction method for the characteristics of dance movements based on VR. The edge features of all video images in each segment are accumulated into one image, and the directional gradient histogram features are extracted from it. The results show that compared with the current robust regression method and cascade regression method, our method has higher positioning accuracy on the pollution test set, and more than 75% of the sample errors in this method are within 0.1. This also verifies the effectiveness of this motion recognition algorithm for dance motion recognition. Dance can effectively resist the psychological barriers of college students and improve their comprehensive quality.

A Biologically Inspired Movement Recognition System with Spiking Neural Networks for Ambient Assisted Living Applications.

This study presents a novel solution for ambient assisted living (AAL) applications that utilizes spiking neural networks (SNNs) and reconfigurable neuromorphic processors. As demographic shifts result in an increased need for eldercare, due to a large elderly population that favors independence, there is a pressing need for efficient solutions. Traditional deep neural networks (DNNs) are typically energy-intensive and computationally demanding. In contrast, this study turns to SNNs, which are more energy-efficient and mimic biological neural processes, offering a viable alternative to DNNs. We propose asynchronous cellular automaton-based neurons (ACANs), which stand out for their hardware-efficient design and ability to reproduce complex neural behaviors. By utilizing the remote supervised method (ReSuMe), this study improves spike train learning efficiency in SNNs. We apply this to movement recognition in an elderly population, using motion capture data. Our results highlight a high classification accuracy of 83.4%, demonstrating the approach's efficacy in precise movement activity classification. This method's significant advantage lies in its potential for real-time, energy-efficient processing in AAL environments. Our findings not only demonstrate SNNs' superiority over conventional DNNs in computational efficiency but also pave the way for practical neuromorphic computing applications in eldercare.

Human Motion Recognition Based on Integrate Interval Grey Association Degree With Pyroelectric Sensors Node

Human Motion Recognition Based on Integrate Interval Grey Association Degree With Pyroelectric Sensors Node

Amoeba‐Inspired Self‐Healing Electronic Slime for Adaptable, Durable Epidermal Wearable Electronics

AbstractEpidermal electronics has garnered significant research attention due to its promising applications in wearable human‐machine interfaces and intelligent healthcare sensing. However, their widespread use faces challenges due to complex manufacturing processes, high material costs, inadaptability to different skin surfaces, and inadequate reusability. Herein, inspired by the biological reshapability and environmental adaptability of amoeba, an ultra‐deformable (≈2600% strain), bioadhesive (adhesive strength ≈3 kPa), strong self‐healing (fastest recovery time ≈1s, maximum wound distance ≈5 mm), and electromechanical‐durable wearable electronic slime (E‐slime) is proposed, which can instantaneously form on‐skin electronics in situ to detect body motion and physiological signals. E‐slime demonstrates desired sensing performance with high sensitivity (gauge factor 2.95), wide sensing range (up to 400% strain), and low detection limit (≈1% strain), which can seamlessly adhere to the skin and can be easily reused multiple times (≈100 cycles usage). E‐slime also enables on‐the‐fly deployment of motion monitoring tasks at various body locations, showcasing its versatility and reliability for body motion recognition and personal health monitoring. This study holds potential for next‐generation green electronics, motion sensing devices, and wearable human‐machine interfaces, ultimately helping to ensure healthy lives and promote well‐being.

Lower Limb Motion Recognition with Improved SVM Based on Surface Electromyography.

During robot-assisted rehabilitation, failure to recognize lower limb movement may efficiently limit the development of exoskeleton robots, especially for individuals with knee pathology. A major challenge encountered with surface electromyography (sEMG) signals generated by lower limb movements is variability between subjects, such as motion patterns and muscle structure. To this end, this paper proposes an sEMG-based lower limb motion recognition using an improved support vector machine (SVM). Firstly, non-negative matrix factorization (NMF) is leveraged to analyze muscle synergy for multi-channel sEMG signals. Secondly, the multi-nonlinear sEMG features are extracted, which reflect the complexity of muscle status change during various lower limb movements. The Fisher discriminant function method is utilized to perform feature selection and reduce feature dimension. Then, a hybrid genetic algorithm-particle swarm optimization (GA-PSO) method is leveraged to determine the best parameters for SVM. Finally, the experiments are carried out to distinguish 11 healthy and 11 knee pathological subjects by performing three different lower limb movements. Results demonstrate the effectiveness and feasibility of the proposed approach in three different lower limb movements with an average accuracy of 96.03% in healthy subjects and 93.65% in knee pathological subjects, respectively.

Tunable porous fiber-shaped strain sensor with synergistic conductive network for human motion recognition and tactile sensing

With the rapid development of portable electronic products, smart wearable devices show great application potential in personalized motion monitoring, health monitoring and even in human-machine interaction. In particular, high-performance flexible fiber-shaped strain sensors are receiving more and more attention because they can be well integrated with clothes or human skin for real-time human activities monitoring. However, achieving improved sensitivity, wide detection range, diverse applications and easy operation of them remains a challenge. Here, we adopt a simple wet-spinning technique to prepare a porous fiber-shaped carbon nanotubes (CNTs)/silver nanoparticles (AgNPs)/thermoplastic polyurethane (TPU) fiber (CATF) for high-performance strain sensor, of which the synergistic conductive network of CNTs and AgNPs enables a wide detection range (∼248 %), high sensitivity (GF > 4295), fast response/recovery time (120 ms/140 ms) and excellent stability. Interestingly, strain sensing range and sensitivity of the sensor can be tuned by changing the AgNPs loading to make it suitable for different application scenarios. All the merits of the sensor make it capable for diverse human movements monitoring, pronunciation recognition, and gesture recognition. More importantly, our prepared CATF strain sensor can be easily weaved into wearable smart textiles, showing great potential for tactile sensing to realize multi-touch and pressure tracking. Finally, the CATF also displays efficient photothermal conversion capability even under different tensile strains up to 150 %, showing great potential in human body thermal management to improve the wearing comfort of wearable electronic fabric.

A bioinspired MXene-based flexible sensory neuron for tactile near-sensor computing

Multifunctional near-sensor computing sensory neurons based on the integration of flexible sensors and memristors hold promise to achieve unprecedented development in large-scale neuromorphic perception circuits and human-machine interaction systems. However, the traditional sensory-memory integrated systems are based on the integration of different device modules, which are subjected to redundant analog-to-digital conversion circuits and poor flexibility. Here, an all MXene-based flexible sensory neuron fabricated by a room temperature energy-efficient, and controllable oxidation preparation technique is reported. The near-sensor computing system is seamlessly integrated a MXene-based pressure sensor array for acquisition of tactile signals with a flexible MXene-based memristor array for simulating the implementation of perceived behavior. The tactile sensor array shows a wide range (0.1–100 kPa), high linear sensitivity (23.9 kPa−1), and the memristor array exhibits repeatable and stable bipolar resistive switching behavior (retention >100 cycles, endurance >103 s) and excellent flexibility (R=1.0 mm). As a conceptual demonstration, our devices realize high-precision recognition of handwritten digit recognition (93.21%) and human motion (97.96%), which demonstrate the feasibility for real-time health monitoring based on signals collected by sensors and artificial neural networks constructed by the memristors. The MXene-based sensor-memristor system offers a prominent contribution towards advanced application of intelligence in electronic skin and wearable electronic equipment.