Human Movement Behavior Research Articles

Multifunctional Nano‐Conductive Hydrogels With High Mechanical Strength, Toughness and Fatigue Resistance as Self‐Powered Wearable Sensors and Deep Learning‐Assisted Recognition System

AbstractHigh mechanical strength, toughness, and fatigue resistance are essential to improve the reliability of conductive hydrogels for self‐powered sensing. However, achieving mutually exclusive properties simultaneously remains challenging. Hence, a novel directed interlocking strategy based on topological network structure and mechanical training is proposed to construct tough hydrogels by optimizing the network structure and modulating the orientation of molecular chains. Combining Zn2+ crosslinked cellulose nanofibers (CNFs) and a polyacrylamide‐poly(vinyl alcohol) double‐network, the unique interlocked‐network structure exhibits an enhanced toughening effect due to hydrogen bonding and metal‐ligand interactions. The aligned nanocrystalline domains achieved by training further contribute to an increase in the toughness and fatigue thresholds. This innovative approach synergistically enhances the mechanical properties of the nano‐conductive hydrogel, achieving a maximum tensile strength of 4.98 MPa and a toughness of 48 MJ m−3. Notably, the CNFs template with anchored polyaniline, when oriented through mechanical training, forms a unique directional conductive pathway, which significantly enhances the power output performance. Besides, a motion recognition system based on a self‐powered sensing device is designed with the assistance of deep learning techniques to accurately identify human motion behaviors. This work showcases a potentially transformative flexible electronic material for self‐powered sensing systems and intelligent recognition systems.

Flexible and robust polyaniline/cross-linked collagen sponge with fibrils network structure as a piezoresistive sensing material

The polyaniline/cross-linked collagen sponge (PANI/CCS) was synthesized by polymerizing PANI onto the collagen skeleton using mesoscopic collagen fibrils (CFs) as building blocks, serving as a piezoresistive sensing material. The structure and morphology of PANI/CCS were characterized using scanning electron microscopy (SEM), Fourier infrared spectroscopy (FTIR), X-ray photoelectron spectroscopy (XPS), and thermal analysis (TA). The mechanical properties of PANI/CCS could be controlled by adjusting the CFs content and polymerization conditions. PANI/CCS treated with pure water exhibited exceptional compressive elasticity under 1000 compression cycles, demonstrating a wide strain range (0–85 %), rapid response time (200 ms), recovery time (90 ms), and high sensitivity (6.72 at 40–50 % strain). The treatment of the ionic liquid further improved the elasticity and the strain sensing range (0–95 %). The presence of PANI nanoparticles and mesoscopic collagen fibrils imparted antibacterial properties, stability in solvents, and biodegradability to PANI/CCS. Utilizing PANI/CCS as a piezoresistive sensing material enabled monitoring human movement behavior through the assembled sensor, showing significant potential for flexible wearable devices.

Flexible and robust polypyrrole/cross-linked collagen sponge with collagen aggregates as building blocks for piezoresistive sensing

The polypyrrole/cross-linked collagen sponge (PPy/CCS) was synthesized through in-situ polymerization of PPy nanoparticles onto the collagen skeleton composed of mesoscopic collagen aggregates (CAs) as building blocks, which was employed as a sensing material. The structure and morphology of PPy/CCS were characterized using scanning electron microscopy (SEM), Fourier infrared spectroscopy (FTIR), X-ray photoelectron spectroscopy (XPS), and thermal analysis (TA). The conductivity and mechanical properties of PPy/CCS can be regulated by adjusting the polymerization conditions. The PPy/CCS treated with glycerin aqueous solution exhibits exceptional recovery performance under 10,000 compression stress cycles, with a short response time of 420 ms and recovery time of 400 ms, along with high sensitivity of 1.13 kPa−1 within a control pressure range of 0–43 kPa. The assembled PPy/CCS-based sensors enable monitoring of human movement behavior and achieving multi-touch control, thereby demonstrating significant potential in flexible wearable devices and human–machine interaction.

Human action recognition based on smart sensors

Abstract This paper focuses on human activity recognition using LSTM (Long Short-Term Memory) for handling time series data issues. Because LSTM can better deal with the correlation and long-term correlation of time-series data, the model is utilized to build a human-computer interaction action recognition system. The experimental steps include the following: first, the bracelet sensor obtains the human body acceleration signal to obtain a data set containing a variety of motion postures and preprocesses the data. Then, LSTM is used to extract the features of the dataset, and the feature vector is utilized as the input to train the model iteratively. Finally, to improve the accuracy of recognition, a variety of machine learning models will be applied to compare the performance with the LSTM model. The experimental results indicate that the proposed model can better capture the acceleration changes of human motion in various life scenes, and can accurately distinguish various sudden action patterns of the human body in daily life. This also makes the human movement behavior recognition system proposed in this study more comprehensive.

GaitNet+ARL: A Deep Learning Algorithm for Interpretable Gait Analysis of Chronic Ankle Instability.

Chronic ankle instability (CAI) is a major public health concern and adversely affects people's mobility and quality of life. Traditional assessment methods are subjective and qualitative by means of clinician observation and patient self-reporting, which may lead to inaccurate assessment and reduce the effectiveness of treatment in clinical practice. Gait analysis becomes a commonly used approach for monitoring human motion behaviors, which can be applied to specific diagnosis and assessment of CAI. However, it is still challenging to recognize the pathological gait pattern for CAI subjects. In this paper, we propose an integrated deep learning framework to solve the CAI recognition problem using kinematic data. Specifically, inspired by the biomechanics of human body system, we create a simple graph neural network (GNN), termed GaitNet, that operates on a spatial domain and exploits interactions among 3-D joint coordinates. We also develop an attention reinforcement learning (ARL) model that determines attention weights of frames on a temporal domain, which is combined with GaitNet for prediction. The effectiveness of our method is validated on the kinematic NEU-CAI dataset which is collected in our institution using a stereophotogrammetric system. According to extensive experiments, we demonstrate that the selected key phases (i.e., sequences of frames with high attentions) significantly increase the predictability of the proposed biomechanics-based GNN model to differentiate between CAI cohort and control cohort. Moreover, we show a significant prediction accuracy improvement (20%-25%) by our approach compared to state-of-the-art machine learning and deep learning methods.

Design of Stretchable and Conductive Self-Adhesive Hydrogels as Flexible Sensors by Guar-Gum-Enabled Dynamic Interactions.

The limited elasticity and inadequate bonding of hydrogels made from guar gum (GG) significantly hinder their widespread implementation in personalized wearable flexible electronics. In this study, we devise GG-based self-adhesive hydrogels by creating an interpenetrating network of GG cross-linked with acrylic, 4-vinylphenylboronic acid, and Ca2+. With the leverage of the dynamic interactions (hydrogen bonds, borate ester bonds, and coordination bonds) between -OH in GG and monomers, the hydrogel exhibits a high stretchability of 700%, superior mechanical stress of 110 kPa, and robust adherence to several substrates. The adhesion strength of 54 kPa on porcine skin is obtained. Furthermore, the self-adhesive hydrogel possesses stable conductivity, an elevated gauge factor (GF), and commendable durability. It can be affixed to the human body as a strain sensor to obtain precise monitoring of human movement behavior. Our research offers possibilities for the development of GG-based hydrogels and applications in wearable electronics and medical monitoring.

Radiation synthesis of covalently/non-covalently coupled all ionic liquid-based Ionogels with rapid self-healing, environmental tolerance for multifunctional ionic skin

As novel artificial ion-conducting materials with skin-like functionalities, Ionic skins (I-Skins) have attracted wide attention in the field of smart wearables. Nonetheless, the crucial hurdle of maintaining their properties in extreme conditions, such as cold, hot or long-term storage, persists. Herein, ionic liquid monomers, ionic liquid solvents, and ionic liquid cross-linkers are employed to facilitate covalently/non-covalently coupled all ionic liquid-based Ionogel for multimodal artificial I-skin through electron beam irradiation under mild conditions at the first time. Profiting from the covalently/non-covalently interactions in the Ionogel, the Ionogel has tunable mechanical properties, excellent environmental adaptability (−60 to 150 °C), long-term stability (90 days), fast response time (0.1 s), rapid self-healing ability (120 s recovery to 90 % of original), and favorable adhesion properties. Moreover, Ionogel sensors possess the remarkable capability to accurately perceive external stimuli, including strain, temperature, and humidity, similar to human skin, which can effectively monitor human movement behavior, as well as fluctuations in ambient temperature and humidity. It is expected that this all ionic liquid-based Ionogel sensor can fill the gap of I-Skin in extreme conditions and realize multifunctional flexible sensing, thus expanding more application scenarios.

Deep Learning-Based Recognition and Visualization of Human Motion Behavior

Human behavior recognition refers to the classification task of identifying the specific actions of human characters based on the characteristics of human body and the completed actions through a specific algorithm. It has a wide range of applications in intelligent surveillance, video retrieval and so on. The main challenge in this direction is to accurately extract the semantic information of each behavior to describe its dynamic changes in space and time. Therefore, this article introduces the latest research progress in the field of human behavior recognition. Through deep learning techniques, particularly convolutional neural networks and recurrent neural networks, human movements in video data can be effectively identified. However, deep learning models lack interpretability, which can be a challenge in practical applications. The researchers also introduce the application of traditional methods and deep learning-based methods to human behavior recognition, and explore the advantages of deep learning models in processing multi-time scale information and introducing attention mechanisms. Finally, the paper summarizes the potential of deep learning technology combined with multimodal data in behavioral analysis, and provides prospects for applications in smart fitness, health care and other fields.

Exploring Human Movement Behavior in The Central Garden of Zuwara City– Libya

Urban spaces provide a suitable place to social communicate, as these urban spaces provide a variety of physical and social benefits. Human behavior is the sum of the psychological, physical, physiological and verbal activity of a person who deals with and interacts with his environment. It represents all kinds of activities that a person undertakes while dealing with and adapting to the environment and includes several aspects: cognitive, movement and emotional.The paper aims to determine the effect of human movement behavior in the central garden of Zuwara. the methodology used is qualitative research, through personal observation of the behavior of the visitors, monitoring them using video camera, recording comments and signing them on the tracking maps. and the interviews were used to gather opinions of the users about the reasons for the behaviors used within the garden, and explore the users' satisfaction with the garden's components, services and the ease of movement within it. The results showed some unplanned movement behaviors in the garden, such as walking on the grass instead of walking in the paths designated for that. The study presented a set of recommendations for the study area, along with a proposal that includes the visitors' requirements and some services that contribute to increasing the efficiency of the garden.

Retracted: Feature Recognition of Human Motion Behavior Based on Depth Sequence Analysis

Retracted: Feature Recognition of Human Motion Behavior Based on Depth Sequence Analysis

STGlow: A Flow-Based Generative Framework With Dual-Graphormer for Pedestrian Trajectory Prediction.

The pedestrian trajectory prediction task is an essential component of intelligent systems. Its applications include but are not limited to autonomous driving, robot navigation, and anomaly detection of monitoring systems. Due to the diversity of motion behaviors and the complex social interactions among pedestrians, accurately forecasting their future trajectory is challenging. Existing approaches commonly adopt generative adversarial networks (GANs) or conditional variational autoencoders (CVAEs) to generate diverse trajectories. However, GAN-based methods do not directly model data in a latent space, which may make them fail to have full support over the underlying data distribution. CVAE-based methods optimize a lower bound on the log-likelihood of observations, which may cause the learned distribution to deviate from the underlying distribution. The above limitations make existing approaches often generate highly biased or inaccurate trajectories. In this article, we propose a novel generative flow-based framework with a dual-graphormer for pedestrian trajectory prediction (STGlow). Different from previous approaches, our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors. Besides, our method has clear physical meanings for simulating the evolution of human motion behaviors. The forward process of the flow gradually degrades complex motion behavior into simple behavior, while its reverse process represents the evolution of simple behavior into complex motion behavior. Furthermore, we introduce a dual-graphormer combined with the graph structure to more adequately model the temporal dependencies and the mutual spatial interactions. Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches.

The Human Motion Behavior Recognition by Deep Learning Approach and the Internet of Things

The Human Motion Behavior Recognition by Deep Learning Approach and the Internet of Things

Multidimensional Biomimetic Construction of Highly Sensitive Wrinkled Gels Based on the Transformation of Multiple Supramolecular Interactions Induced by Dual‐Solvent Strategy

AbstractTraditional artificial skin gels often only focuses on a single perspective and overlooks the necessity of multidimensional synergistic design for sensitivity enhancement. To address these problems, the innovative introduction of dual solvents on the surface of polyacrylamide/sodium alginate gel induces to the transformation of supramolecular interactions including ion coordination, crystalline alcohol, and phase separation, synergistically achieving adjustable wrinkle wavelengths (304.2 ± 19.9 to 2393.5 ± 95.9 µm) and modulated chemical compositions with tunable moduli (87.5 ± 3.3 to 157.6 ± 3.7 kPa). This flexible strategy allows the construction of long‐range ordered wrinkled microstructures of three‐dimensional surfaces and complex morphologies. Meanwhile, the bridge effect induced by crystalline alcohols directs the insertion of ethanol molecules into the polymer chains, effectively reducing intramolecular friction. Benefiting from the small wavelength and low modulus dominated by crystalline alcohol, the wrinkled gel exhibits extremely high sensitivity of 164 kPa−1 (<0.5 kPa) and wide detection range (44.3 kPa). The wrinkled gel remains stable high sensitive to detect micro‐ and large stress, tactile perception, and human motion behaviors. This work proposes a new strategy for constructing highly sensitive bioinspired skin from multiple dimensions, showing broad application prospects in the fields of bioengineering and behavioral cognition.

An intrinsic phase change elastomer with superior stretchability and reparable capabilities for self-thermal managing stretchable electronics

In recent years, phase change materials (PCMs) are gradually developed and utilized for thermal management in wearable electronics due to their autonomous heat absorption ability during the phase change process. However, the high rigidity (elastic modulus ＞ 100 MPa) and stiffness (yield strain ＜ 15%) severely limited the thermal management application of the reported PCMs in stretchable electronics. Herein, we present an intrinsic phase change elastomer (IPCE) combining the function of PCM and elastomer by introducing crystalline polyethylene glycol segments and amorphous polypropylene glycol segments into an elaborately designed chemical cross-linked networks. The fabricated IPCE merges excellent softness (elastic modulus ＜ 20 MPa), stretchability of 900%, elastic mechanical behavior (without yield phenomenon), fantastic thermal management ability, and outstanding thermal repairable capability. Eventually, we fabricated a simple strain sensor with IPCE as substrate by spraying gold nanoparticles on both sides of the IPCE film. The stable sensing ability that repeatedly monitoring the subtle human motion and autonomous thermal management behavior of the strain sensor demonstrated the appealing practicability of our IPCE. This work paved an avenue for fabricating stretchable and self-thermal managing elastomer for stretchable electronics.

Abnormal Behavior Recognition for Human Motion Based on Improved Deep Reinforcement Learning

Recognizing abnormal behavior recognition (ABR) is an important part of social security work. To ensure social harmony and stability, it is of great significance to study the identification methods of abnormal human motion behavior. Aiming at the low accuracy of human motion ABR method, ABR method for human motion based on improved deep reinforcement learning (DRL) is proposed. First, the background image is processed in combination with the Gaussian model; second, the background features and human motion trajectory features are extracted, respectively; finally, the improved DRL model is constructed, and the feature information is input into the improvement model to further extract the abnormal behavior features, and the ABR of human motion is realized through the interaction between the agent and the environment. The different methods were examined based on UCF101 data set and HiEve data set. The results show that the accuracy of human motion key point acquisition and posture estimation accuracy is high, the proposed method sensitivity is good, and the recognition accuracy of human motion abnormal behavior is as high as 95.5%. It can realize the ABR for human motion and lay a foundation for the further development of follow-up social security management.

Simulating Smart Cities Under Different Scenarios and Factors

In this research, we suggest building or utilizing a virtual environment of a smart city where fixed and mobile sensors are arranged in a certain way, using particular movement models and techniques for transmitting and sharing data via the virtual city. This proposal proposes to carry out several experiments for various movement models, such as:(Individual Mobility Model,Exponential movement model and Rayleigh Flight movement model), A specific data distribution (Gaussian, Littice, Power-law, Exponential) and a certain data routing methodology (Spray and Wait, Probabilistic Flooding, and Epidemic) were used to examine the impact of this on the use of network resources. In this proposal, we also want to look at the usage of various resources, including electricity and data. A movement model, an item distribution strategy, and a data routing protocol were all combined to create each experiment that was intended to be conducted in this proposal. All submitted experiments will ultimately be compared to one another, and recommendations that assist the research and design community in conserving network resources will be made. the findings show that the traffic models that were used with mobile nodes are considered one of the important factors in determining the consumption of network resources. In addition to the influence of traffic models on the consumption of network resources, algorithms and methods of routing data also have an impact. The Human Mobility Model, which accurately expresses human movement behavior, is considered one of the most stable models in terms of performance.

A Flexible Triboelectric Nanogenerator Based on MXene for Jumping Motion Monitoring

Recently, owing to the development of artificial intelligence technology, human posture recognition has aroused great interest in the academic community. Thus, we designed a triboelectric nanogenerator based on PDMS layer and MXene/PDMS layer (PM-TENG) to obtain mechanical energy and sense human posture. According to the results, the open-circuit voltage ([Formula: see text] of PM-TENG can arrive at 372 V, and the short-circuit current ([Formula: see text] of PM-TENG can reach 16.21 [Formula: see text]A, respectively. Due to its highly sensitive sensor to complex human motor states like folding, stretching, squeezing, and tapping, it can not only be used to harvest mechanical energy from its surroundings, but also to monitor human movement and behavior. Thus, human motion behaviors like walking, leg lifting, and light and high jumps may be tracked and identified by reading pulse electrical signal production. This research will provide a new idea for human motion posture monitoring.

Explainable human activity recognition based on probabilistic spatial partitions for symbiotic workplaces

ABSTRACT In recent years, smart workplaces that adapt to human activity and motion behavior have been proposed for cognitive production systems. In this respect, methods for identifying the feelings and activities of human workers are being investigated to improve the cognitive capability of smart machines such as robots in shared working spaces. Recognizing human activities and predicting the possible next sequence of operations may simplify robot programming and improve collaboration efficiency. However, human activity recognition still requires explainable models that are versatile, robust, and interpretative. Therefore, recognizing and analyzing human action details using continuous probability density estimates in different workplace layouts is essential. Three scenarios are considered: a standalone, a one-piece flow U-form, and a human-robot hybrid workplace. This work presents a novel approach to human activity recognition based on a probabilistic spatial partition (HAROPP). Its performance is compared to the geometric-bounded activity recognition method. Results show that spatial partitions based on probabilistic density contain 20% fewer data frames and 10% more spatial areas than the geometric bounding box. The approach, on average, detects human activities correctly for 81% of the cases for a pre-known workplace layout. HAROPP has scalability and applicability potential for cognitive workplaces with a digital twin in the loop for pushing the cognitive capabilities of machine systems and realizing human-centered environments.

Empirical Study on Linear, Non-linear, and System Dynamics: Oriented Human Motor Behavior

Human movement and motor behavior science involve various theoretical frameworks and methodologies. This study describes the force control of motor phenomenon, processes of linear or nonlinear dynamics, and proposes a system approach as an additional potential aspect. Thus far, issues regarding these motor control and learning paradigms were critically examined, and their respective mechanisms were compared using descriptive analysis. Elaborate simulations based on the transitions and development flow of each component at issue contributed to the linear approach, laid concrete emphasis on the advantages of the nonlinear approach, and empirically derived the rationale for the indispensable application of system dynamics. Sports science can benefit from system dynamics associated with human motor behavior, as demonstrated in this study.

A dynamic supercritical carbon dioxide foaming method for fabricating wrinkled surface to enhance triboelectric nanogenerator performance

AbstractTriboelectric nanogenerator (TENG) is a promising energy harvester to overcome the energy depletion issue. The surface structure has been considered as an effective way to enhance the triboelectric performance. Herein, a dynamic supercritical carbon dioxide (scCO2) foaming method, which introduced a scCO2 flow field during scCO2 saturation, was proposed to fabricate thermoplastic polyurethane (TPU) foams with surface wrinkly structures. The size of the surface wrinkles could be regulated in the range of 1.8–10 μm by varying the foaming pressure. The surface wrinkled TPU film with wrinkle wave length of 2.4 μm demonstrated an excellent enhancement in output voltage (130%), current (180%), and maximum transfer charge (130%) when paired with surface structured polydimethylsiloxane film in a TENG. Due to the excellent durability and flexibility of the composing materials, the developed TENG showed outstanding stability in long‐term continuous operation. With a high power density of 0.5 W/m2 achieved on a 107 Ω external load, the flexible TENG could be used to charge capacitors, power light‐emitting‐diodes, and served as a self‐powered sensor to detect various human movement behaviors. This work provides a new path for the fabrication of surface wrinkled films for the sustainable development of high performance TENGs.