Identifying stress scores from gait biometrics captured using a camera: A cross-sectional study.

BACKGROUND: Stress is a critical risk factor for various health issues, but an objective, non-intrusive and effective measurement approach for stress has not yet been established. Gait, the pattern of movements in human locomotion, has been proven to be a valid behavioral indicator for recognizing various mental states in a convenient manner. RESEARCH QUESTION: This study aims to identify the severity of stress by assessing human gait recorded through an objective, non-intrusive measurement approach. METHODS: One hundred and fifty-two participants with an average age of 23 years old (SD = 1.07) were recruited. The Chinese version of the Perceived Stress Scale with 10 items (PSS-10) was used to assess participants' stress levels. The participants were then required to walk naturally while being recorded with a regular camera. A total of 1320 time-domain and 1152 frequency-domain gait features were extracted from the videos. The top 40 contributing features, confirmed by dimensionality reduction, were input into models consisting of four machine-learning regression algorithms (i.e., Gaussian Process Regressor, Linear Regression, Random Forest Regressor, and Support Vector regression), to assess stress levels. RESULTS: The models that combined time- and frequency-domain features performed best, with the lowest RMSE (4.972) and highest validation (r = 0.533). The Gaussian Process Regressor and Linear Regression outperformed the others. The greatest contribution to model performance was derived from gait features of the waist, hands, and legs. SIGNIFICANCE: The severity of stress can be accurately detected by machine learning models using two-dimensional (2D) video-based gait data. The machine learning models used for assessing perceived stress were reliable. Waist, hand, and leg movements were found to be critical indicator in detecting stress.

Fabricating strong and tough aramid fibers by small addition of carbon nanotubes.

Synthetic high-performance fibers present excellent mechanical properties and promising applications in the impact protection field. However, fabricating fibers with high strength and high toughness is challenging due to their intrinsic conflicts. Herein, we report a simultaneous improvement in strength, toughness, and modulus of heterocyclic aramid fibers by 26%, 66%, and 13%, respectively, via polymerizing a small amount (0.05 wt%) of short aminated single-walled carbon nanotubes (SWNTs), achieving a tensile strength of 6.44 ± 0.11 GPa, a toughness of 184.0 ± 11.4 MJ m-3, and a Young's modulus of 141.7 ± 4.0 GPa. Mechanism analyses reveal that short aminated SWNTs improve the crystallinity and orientation degree by affecting the structures of heterocyclic aramid chains around SWNTs, and in situ polymerization increases the interfacial interaction therein to promote stress transfer and suppress strain localization. These two effects account for the simultaneous improvement in strength and toughness.

Using gait videos to automatically assess anxiety.

Background: In recent years, the number of people with anxiety disorders has increased worldwide. Methods for identifying anxiety through objective clues are not yet mature, and the reliability and validity of existing modeling methods have not been tested. The objective of this paper is to propose an automatic anxiety assessment model with good reliability and validity. Methods: This study collected 2D gait videos and Generalized Anxiety Disorder (GAD-7) scale data from 150 participants. We extracted static and dynamic time-domain features and frequency-domain features from the gait videos and used various machine learning approaches to build anxiety assessment models. We evaluated the reliability and validity of the models by comparing the influence of factors such as the frequency-domain feature construction method, training data size, time-frequency features, gender, and odd and even frame data on the model. Results: The results show that the number of wavelet decomposition layers has a significant impact on the frequency-domain feature modeling, while the size of the gait training data has little impact on the modeling effect. In this study, the time-frequency features contributed to the modeling, with the dynamic features contributing more than the static features. Our model predicts anxiety significantly better in women than in men (r Male = 0.666, r Female = 0.763, p < 0.001). The best correlation coefficient between the model prediction scores and scale scores for all participants is 0.725 (p < 0.001). The correlation coefficient between the model prediction scores for odd and even frame data is 0.801~0.883 (p < 0.001). Conclusion: This study shows that anxiety assessment based on 2D gait video modeling is reliable and effective. Moreover, we provide a basis for the development of a real-time, convenient and non-invasive automatic anxiety assessment method.

How social media expression can reveal personality.

Background: Personality psychology studies personality and its variation among individuals and is an essential branch of psychology. In recent years, machine learning research related to personality assessment has started to focus on the online environment and showed outstanding performance in personality assessment. However, the aspects of the personality of these prediction models measure remain unclear because few studies focus on the interpretability of personality prediction models. The objective of this study is to develop and validate a machine learning model with domain knowledge introduced to enhance accuracy and improve interpretability. Methods: Study participants were recruited via an online experiment platform. After excluding unqualified participants and downloading the Weibo posts of eligible participants, we used six psycholinguistic and mental health-related lexicons to extract textual features. Then the predictive personality model was developed using the multi-objective extra trees method based on 3,411 pairs of social media expression and personality trait scores. Subsequently, the prediction model's validity and reliability were evaluated, and each lexicon's feature importance was calculated. Finally, the interpretability of the machine learning model was discussed. Results: The features from Culture Value Dictionary were found to be the most important predictors. The fivefold cross-validation results regarding the prediction model for personality traits ranged between 0.44 and 0.48 (p < 0.001). The correlation coefficients of five personality traits between the two "split-half" datasets data ranged from 0.84 to 0.88 (p < 0.001). Moreover, the model performed well in terms of contractual validity. Conclusion: By introducing domain knowledge to the development of a machine learning model, this study not only ensures the reliability and validity of the prediction model but also improves the interpretability of the machine learning method. The study helps explain aspects of personality measured by such prediction models and finds a link between personality and mental health. Our research also has positive implications regarding the combination of machine learning approaches and domain knowledge in the field of psychiatry and its applications to mental health.

Electrically Modulated Nanofiltration Membrane Based on an Arch-Bridged Graphene Structure for Multicomponent Molecular Separation.

Tunable regulation of molecular penetration through porous membranes is highly desirable for membrane applications in the pharmaceutical and medical fields. However, in most previous reports additional reagents or components are usually needed to provide the graphene-based membranes with responsiveness. Herein, we report tunable arch-bridged reduced graphene oxide (rGO) nanofiltration membranes modulated by the applied voltage. Under a finite voltage of 5 V, the rGO membrane could completely reject organic/anionic molecules. With assistance of the voltage, the positive-charge-modified rGO membrane realized the universal rejection of both cationic and anionic dyes, also showing the valid modulation in harsh organic solvents. The efficient electrical modulation depended on the synergetic effects of Donnan repulsion and size exclusion, benefiting from the electric field enhancement in arch-bridged rGO structures. Furthermore, multicomponent separation was achieved by our electrically modulated rGO-based membranes, demonstrating their potential in practical applications such as pharmaceutical industries.

Sensing Psychological Well-being Using Social Media Language: Prediction Model Development Study.

BACKGROUND: Positive mental health is arguably increasingly important and can be revealed, to some extent, in terms of psychological well-being (PWB). However, PWB is difficult to assess in real time on a large scale. The popularity and proliferation of social media make it possible to sense and monitor online users' PWB in a nonintrusive way, and the objective of this study is to test the effectiveness of using social media language expression as a predictor of PWB. OBJECTIVE: This study aims to investigate the predictive power of social media corresponding to ground truth well-being data in a psychological way. METHODS: We recruited 1427 participants. Their well-being was evaluated using 6 dimensions of PWB. Their posts on social media were collected, and 6 psychological lexicons were used to extract linguistic features. A multiobjective prediction model was then built with the extracted linguistic features as input and PWB as the output. Further, the validity of the prediction model was confirmed by evaluating the model's discriminant validity, convergent validity, and criterion validity. The reliability of the model was also confirmed by evaluating the split-half reliability. RESULTS: The correlation coefficients between the predicted PWB scores of social media users and the actual scores obtained using the linguistic prediction model of this study were between 0.49 and 0.54 (P<.001), which means that the model had good criterion validity. In terms of the model's structural validity, it exhibited excellent convergent validity but less than satisfactory discriminant validity. The results also suggested that our model had good split-half reliability levels for every dimension (ranging from 0.65 to 0.85; P<.001). CONCLUSIONS: By confirming the availability and stability of the linguistic prediction model, this study verified the predictability of social media corresponding to ground truth well-being data from the perspective of PWB. Our study has positive implications for the use of social media to predict mental health in nonprofessional settings such as self-testing or a large-scale user study.

Ecological recognition of self-esteem leveraged by video-based gait.

Self-esteem is a significant kind of psychological resource, and behavioral self-esteem assessments are rare currently. Using ordinary cameras to capture one's gait pattern to reveal people's self-esteem meets the requirement for real-time population-based assessment. A total of 152 healthy students who had no walking issues were recruited as participants. The self-esteem scores and gait data were obtained using a standard 2D camera and the Rosenberg Self-Esteem Scale (RSES). After data preprocessing, dynamic gait features were extracted for training machine learning models that predicted self-esteem scores based on the data. For self-esteem prediction, the best results were achieved by Gaussian processes and linear regression, with a correlation of 0.51 (p < 0.001), 0.52 (p < 0.001), 0.46 (p < 0.001) for all participants, males, and females, respectively. Moreover, the highest reliability was 0.92 which was achieved by RBF-support vector regression. Gait acquired by a 2D camera can predict one's self-esteem quite well. This innovative approach is a good supplement to the existing methods in ecological recognition of self-esteem leveraged by video-based gait.

Reliability and validity analysis of personality assessment model based on gait video.

Personality affects an individual's academic achievements, occupational tendencies, marriage quality and physical health, so more convenient and objective personality assessment methods are needed. Gait is a natural, stable, and easy-to-observe body movement that is closely related to personality. The purpose of this paper is to propose a personality assessment model based on gait video and evaluate the reliability and validity of the multidimensional model. This study recruited 152 participants and used cameras to record their gait videos. Each participant completed a 44-item Big Five Inventory (BFI-44) assessment. We constructed diverse static and dynamic time-frequency features based on gait skeleton coordinates, interframe differences, distances between joints, angles between joints, and wavelet decomposition coefficient arrays. We established multidimensional personality trait assessment models through machine learning algorithms and evaluated the criterion validity, split-half reliability, convergent validity, and discriminant validity of these models. The results showed that the reliability and validity of the Gaussian process regression (GPR) and linear regression (LR) models were best. The mean values of their criterion validity were 0.478 and 0.508, respectively, and the mean values of their split-half reliability were all greater than 0.8. In the formed multitrait-multimethod matrix, these methods also had higher convergent and discriminative validity. The proposed approach shows that gait video can be effectively used to evaluate personality traits, providing a new idea for the formation of convenient and non-invasive personality assessment methods.

Superelastic graphene aerogel-based metamaterials.

Ultralight, ultrastrong, and supertough graphene aerogel metamaterials combining with multi-functionalities are promising for future military and domestic applications. However, the unsatisfactory mechanical performances and lack of the multiscale structural regulation still impede the development of graphene aerogels. Herein, we demonstrate a laser-engraving strategy toward graphene meta-aerogels (GmAs) with unusual characters. As the prerequisite, the nanofiber-reinforced networks convert the graphene walls' deformation from the microscopic buckling to the bulk deformation during the compression process, ensuring the highly elastic, robust, and stiff nature. Accordingly, laser-engraving enables arbitrary regulation on the macro-configurations of GmAs with rich geometries and appealing characteristics such as large stretchability of 5400% reversible elongation, ultralight specific weight as small as 0.1 mg cm-3, and ultrawide Poisson's ratio range from -0.95 to 1.64. Additionally, incorporating specific components into the pre-designed meta-structures could further achieve diversified functionalities.

Carbonene Fibers: Toward Next-Generation Fiber Materials.

The development of human society has set unprecedented demands for advanced fiber materials, such as lightweight and high-performance fibers for reinforcement of composite materials in frontier fields and functional and intelligent fibers in wearable electronics. Carbonene materials composed of sp2-hybridized carbon atoms have been demonstrated to be ideal building blocks for advanced fiber materials, which are referred to as carbonene fibers. Carbonene fibers that generally include pristine carbonene fibers, composite carbonene fibers, and carbonene-modified fibers hold great promise in transferring the extraordinary properties of nanoscale carbonene materials to macroscopic applications. Herein, we give a comprehensive discussion on the conception, classification, and design strategies of carbonene fibers and then summarize recent progress regarding the preparations and applications of carbonene fibers. Finally, we provide insights into developing lightweight, high-performance, functional, and intelligent carbonene fibers for next-generation fiber materials in the near future.

Vertical Graphene Arrays as Electrodes for Ultra-High Energy Density AC Line-Filtering Capacitors.

High-frequency responsive electrochemical capacitor (EC), as an ideal lightweight filtering capacitor, can directly convert alternating current (AC) to direct current (DC). However, current electrodes are stuck in limited electrode area and tortuous ion transport. Herein, strictly vertical graphene arrays (SVGAs) prepared by electric-field-assisted plasma enhanced chemical vapour deposition have been successfully designed as the main electrode to ensure ions rapidly adsorb/desorb in richly available graphene surface. SVGAs exhibit an outstanding specific areal capacitance of 1.72 mF cm-2 at Φ120 =80.6° even after 500 000 cycles, which is far better than that of most carbon-related materials. Impressively, the output voltage could also be improved to 2.5 V when using organic electrolyte. An ultra-high energy density of 0.33 µWh cm-2 can also be handily achieved. Moreover, ECs-SVGAs can well smooth arbitrary AC waveforms into DC signals, exhibiting excellent filtering performance.

Pristine Titanium Carbide MXene Hydrogel Matrix.

The hydrogel matrix normally forms via covalent or noncovalent interactions that make the matrix resistant to hydration and disassembly. Herein this type of chemical transition is demonstrated in titanium carbide MXene (Ti3C2Tx), in which the exchange of intercalated Li+ with hydrated protons triggers significantly suppressed hydration in stacked Ti3C2Tx. Based on this intercalation chemistry behavior, pristine Ti3C2Tx hydrogel matrices with an arbitrary microstructures are fabricated by freezing-induced preassembly and a subsequent specially designed thawing process in protic acids. The absence of extrinsic components maximizes the materials performance of the resultant pristine Ti3C2Tx hydrogel, which produces a compressive modulus of 2.4 MPa and conductivity of 220.3 ± 16.8 S/m at 5 wt % solid content. The anisotropic Ti3C2Tx hydrogel also delivers a promising performance in solar steam generation by facilitating rapid water transport inside vertical microchannels.

An intelligent film actuator with multi-level deformation behaviour.

Smart materials with simply reversible deformation or reconfigurability have shown great potential in artificial muscles, robots, controlled displays, etc. However, the combination of reversible and reconfigured functions in responsive materials, which can endow them with mature and complex actuation performance similar to that of living things, is still a great challenge. In this regard, we report an intelligent graphene oxide (GO)/polyvinylidene fluoride (PVDF) film with reconfigured structures resulting from inner plastic deformation after treatment at elevated temperature (40-80 °C), which simultaneously expresses basically and secondarily reversible deformation ability of its original and reconfigured states in response to external stimuli (e.g. IR light and moisture), respectively. As a result, this film achieves unique multi-level actuation behaviour by combining reversible and reconfigured functions. Based on this, an "Artificial Pupil" with two switchable light penetration modes under the different reconfigured states was designed and developed. Furthermore, many special and reconfigured 3D structures (e.g. cubic boxes, pyramids) have been well explored, which is promising for applications in future materials engineering and biomimetic devices.

Chemically modified graphene films with tunable negative Poisson's ratios.

Graphene-derived macroscopic assemblies feature hierarchical nano- and microstructures that provide numerous routes for surface and interfacial functionalization achieving unconventional material properties. We report that the microstructural hierarchy of pristine chemically modified graphene films, featuring wrinkles, delamination of close-packed laminates, their ordered and disordered stacks, renders remarkable negative Poisson's ratios ranging from -0.25 to -0.55. The mechanism proposed is validated by the experimental characterization and theoretical analysis. Based on the understanding of microstructural origins, pre-strech is applied to endow chemically modified graphene films with controlled negative Poisson's ratios. Modulating the wavy textures of the inter-connected network of close-packed laminates in the chemically modified graphene films also yields finely-tuned negative Poisson's ratios. These findings offer the key insights into rational design of films constructed from two-dimensional materials with negative Poisson's ratios and mechanomutable performance.

Chemical Approach to Ultrastiff, Strong, and Environmentally Stable Graphene Films.

Reduced graphene oxide (rGO) sheets prepared by a modified Hofmann method (Ho-rGO) have large graphitic domains with few structural defects, facilitating the dense packing between rGO sheets to enhance the mechanical performances of the resultant graphene films. Graphene films are fabricated by the filtration of the aqueous dispersions of Ho-rGO sheets and further treated by thermal annealing. They display high moduli (stiffness) of 54.6 ± 1.4 GPa and high tensile strengths of 521 ± 19 MPa. They also exhibit high toughness and good electrical properties. The intact structure of Ho-rGO sheets narrows the nanochannels in the film matrices, greatly reducing the water infiltration into films and providing the graphene films with excellent environmental stability. These graphene films are attractive for practical applications because of their light weights and ultrastiff and ultrastrong mechanical properties.

Topological Design of Ultrastrong and Highly Conductive Graphene Films.

Nacre-like graphene films are prepared by evaporation-induced assembly of graphene oxide dispersions containing small amounts of cellulose nanocrystal (CNC), followed by chemical reduction with hydroiodic acid. CNC induces the formation of wrinkles on graphene sheets, greatly enhancing the mechanical properties of the resultant graphene films. The graphene films deliver an ultrahigh tensile strength of 765 ± 43 MPa (up to 800 MPa in some cases), a large failure strain of 6.22 ± 0.19%, and a superior toughness of 15.64 ± 2.20 MJ m-3 , as well as a high electrical conductivity of 1105 ± 17 S cm-1 . They have a great potential for applications in flexible electronics because of their combined excellent mechanical and electrical properties.