BlazePose-Seq2Seq: Leveraging Regular RGB Cameras for Robust Gait Assessment.

Evaluation of human gait through smartphone-based pose estimation algorithms provides an attractive alternative to costly lab-bound instrumented assessment and offers a paradigm shift with real time gait capture for clinical assessment. Systems based on smart phones, such as OpenPose and BlazePose have demonstrated potential for virtual motion assessment but still lack the accuracy and repeatability standards required for clinical viability. Seq2seq architecture offers an alternative solution to conventional deep learning techniques for predicting joint kinematics during gait. This study introduces a novel enhancement to the low-powered BlazePose algorithm by incorporating a Seq2seq autoencoder deep learning model. To ensure data accuracy and reliability, synchronized motion capture involving an RGB camera and ten Vicon cameras were employed across three distinct self-selected walking speeds. This investigation presents a groundbreaking avenue for remote gait assessment, harnessing the potential of Seq2seq architectures inspired by natural language processing (NLP) to enhance pose estimation accuracy. When comparing BlazePose alone to the combination of BlazePose and 1D convolution Long Short-term Memory Network (1D-LSTM), Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), the average mean absolute errors decreased from 13.4° to 5.3° for fast gait, from 16.3° to 7.5° for normal gait, and from 15.5° to 7.5° for slow gait at the left ankle joint angle respectively. The strategic utilization of synchronized data and rigorous testing methodologies further bolsters the robustness and credibility of these findings.

Multi-task artificial neural networks and their extrapolation capabilities to predict full-body 3D human posture during one- and two-handed load-handling activities.

Machine-learning based human posture-prediction tools can potentially be robust alternatives to motion capture measurements. Existing posture-prediction approaches are confined to two-handed load-handling activities performed at heights below 120 cm from the floor and to predicting a limited number of body-joint coordinates/angles. Moreover, the extrapolating power of these tools beyond the range of the input dataset they were trained for (e.g., for underweight, overweight, or left-handed individuals) has not been investigated. In this study, we trained/validated/tested two posture-prediction (for full-body joint coordinates and angles) artificial neural networks (ANNs) using both 70%/15%/15% random-hold-out and leave-one-subject-out methods, based on a comprehensive kinematic dataset of forty-one full-body skin markers collected from twenty right-handed normal-weight (BMI = 18-26 kg/m2) subjects. Subjects performed 204 one- and two-handed unloaded activities at different vertical (0 to 180 cm from the floor) and horizontal (up to 60 cm lateral and/or anterior) destinations. Subsequently, the extrapolation capability of the trained/validated/tested ANNs was evaluated using data collected from fifteen additional subjects (unseen by the ANNs); three individuals in five groups: underweight, overweight, obese, left-handed individuals, and subjects with a hand-load. Results indicated that the ANNs predicted body joint coordinates and angles during various activities with errors of âˆ¼ 25 mm and âˆ¼ 10°, respectively; considerable improvements when compared to previous posture-prediction ANNs. Extrapolation errors of our ANNs generally remained within the error range of existing ANNs with obesity and being left-handed having, respectively, the most and least compromising effects on their accuracy. These easy-to-use ANNs appear, therefore, to be robust alternatives to common posture-measurement approaches.

Comparative Analysis of Preference in Contemporary and Earlier Texts Using Entropy Measures.

Research in computational textual aesthetics has shown that there are textual correlates of preference in prose texts. The present study investigates whether textual correlates of preference vary across different time periods (contemporary texts versus texts from the 19th and early 20th centuries). Preference is operationalized in different ways for the two periods, in terms of canonization for the earlier texts, and through sales figures for the contemporary texts. As potential textual correlates of preference, we measure degrees of (un)predictability in the distributions of two types of low-level observables, parts of speech and sentence length. Specifically, we calculate two entropy measures, Shannon Entropy as a global measure of unpredictability, and Approximate Entropy as a local measure of surprise (unpredictability in a specific context). Preferred texts from both periods (contemporary bestsellers and canonical earlier texts) are characterized by higher degrees of unpredictability. However, unlike canonicity in the earlier texts, sales figures in contemporary texts are reflected in global (text-level) distributions only (as measured with Shannon Entropy), while surprise in local distributions (as measured with Approximate Entropy) does not have an additional discriminating effect. Our findings thus suggest that there are both time-invariant correlates of preference, and period-specific correlates.

Effect of the core bone engaged length on the BASHTI fixation strength, an in-vitro study on bovine tendons using identical-density surrogate bones.

BACKGROUND: BASHTI is an implant-less anterior cruciate ligament (ACL) reconstruction technique, which resolves the problems caused by implants such as interference screws. This study aims to investigate the effect of the drill bit and tendon's diameter on the Core Bone Engaged Length (CBEL) and the fixation strength. CBEL is the length of core bone which has a full engagement with both tunnel and graft at the same time. METHODS: 60 in-vitro tests were conducted for 6, 7, 8, and 9 mm tendon sizes with a 10 mm bone tunnel. In this study bovine tendons and dummy bone blocks were used to model the fixation. Drill bits were used to extract the core bone for securing the auto-graft. A three-stage tensile test including a force-controlled cyclical preloading of 10-50 N with a frequency of 0.1 Hz for 10 cycles, followed by the main force-controlled cyclical loading of 50-200 N with a frequency of 0.5 Hz for 150 cycles, and immediately a displacement-controlled single cycle pull-out load with a rate of 20 mm/min were carried out to discover the fixation strength of each sample. RESULTS: The 6 mm group had the greatest CBEL. However, all cases in this group failed in loadings below 200 N, which is the minimum required strength after ACL reconstruction. The fixation strength of cases with more than 200 N fixation strength for 7, 8, and 9 mm tendon diameters were 275 ± 42, 330 ± 110, and 348 ± 93 N, respectively, showing insignificant difference between groups (P-value = 0.45). Nevertheless, CBELs for these groups were 16.6 ± 3.4, 9.6 ± 2.4, and 11.7 ± 3.8 mm, respectively, implying a significant increase in CBEL in the 7 mm group than that for 8 and 9 mm groups (P-value = 0.002 and 0.049, respectively). CONCLUSION: Results showed that CBEL could assess the quality of BASHTI technique. However, CBEL was an inverse function of tendon compression, so it was not an independent parameter to determine BASHTI strength. Also, the CBEL of 7 mm group which fulfilled the 200 N threshold was higher than that of 8 and 9 mm groups, so its healing process speed may be higher, which is recommended for a future study in this field.

Approximate Entropy in Canonical and Non-Canonical Fiction.

Computational textual aesthetics aims at studying observable differences between aesthetic categories of text. We use Approximate Entropy to measure the (un)predictability in two aesthetic text categories, i.e., canonical fiction ('classics') and non-canonical fiction (with lower prestige). Approximate Entropy is determined for series derived from sentence-length values and the distribution of part-of-speech-tags in windows of texts. For comparison, we also include a sample of non-fictional texts. Moreover, we use Shannon Entropy to estimate degrees of (un)predictability due to frequency distributions in the entire text. Our results show that the Approximate Entropy values can better differentiate canonical from non-canonical texts compared with Shannon Entropy, which is not true for the classification of fictional vs. expository prose. Canonical and non-canonical texts thus differ in sequential structure, while inter-genre differences are a matter of the overall distribution of local frequencies. We conclude that canonical fictional texts exhibit a higher degree of (sequential) unpredictability compared with non-canonical texts, corresponding to the popular assumption that they are more 'demanding' and 'richer'. In using Approximate Entropy, we propose a new method for text classification in the context of computational textual aesthetics.

Improved artificial neural networks for 3D body posture and lumbosacral moment predictions during manual material handling activities.

Body posture measurement approaches, required in biomechanical models to assess risk of musculoskeletal injuries, are usually costly and/or impractical for use in real workplaces. Therefore, we recently developed three artificial neural networks (ANNs), based on measured posture data on several individuals, to predict whole body 3D posture (coordinates of 15 markers located on body's main joints), segmental orientations (Euler angles of 14 body segments), and lumbosacral (L5-S1) moments during static manual material handling (MMH) activities (ANNPosture, ANNAngle, and ANNMoment, respectively). These ANNs require worker's body height, body weight (only for ANNMoment), hand-load 3D position, and its mass as inputs to accurately predict 3D marker coordinates (RMSE = 7.0 cm), segmental orientations (RMSE = 29.9°) and L5-S1 moments (RMSE = 16.5 N.m) for various static MMH activities. The current work aims to further improve the accuracy of these ANNs by performing outlier elimination and data normalization (as effective tools to improve the accuracy of ANNs) as well as by introducing participant's knee flexion angle (i.e., lifting technique: stoop, semi-squat, and full-squat) and body weight as new inputs into these ANNs. Results indicate that the RMSE of the new ANNPosture, ANNAngle, and ANNMoment reduced by, respectively, ∼43%, 10%, and 29% (from 7.0 cm, 29.9°, and 16.5 Nm in the original ANNs to, respectively, 4.0 cm, 27.0°, and 11.8 Nm). Such significant improvements in the predictive power of our ANNs further confirm their effectiveness as alternative posture-prediction approaches requiring minimal in vivo data collection in real workplaces.

Effect of Geometry on the Fixation Strength of Anterior Cruciate Ligament Reconstruction Using BASHTI Technique.

The goal of this study is to investigate the effects of tendon and cannulated drill bit diameter on the strength of the bone and site hold tendon inside (BASHTI) fixation technique for an anterior cruciate ligament (ACL) reconstruction. Bovine digital tendons and Sawbones blocks were used to mimic the ACL reconstruction. Mechanical strength of the specimens was measured using a cyclic loading continued by a single cycle pullout load until failure to simulate the real postsurgical loading conditions. Finally, failure modes of specimens and ultimate failure load were recorded. The maximum possible tendon surface strain (i.e., tendon compression [TC]) for tendon diameters of 6, 7, 8, and 9 mm were 0.73, 0.8, 0.7, and 0.65, respectively. Eighty per cent of the specimens with tendon diameter of 6 mm and 20% of specimens with tendon diameter of 7 mm failed on the torn tendon. All samples with larger tendon diameters (i.e., 8 and 9 mm) failed on the fixation slippage. The maximum fixation strength according to the most suitable core bones for 6, 7, 8, and 9 mm tendons were 148 ± 47 N (core 9.5 mm), 258 ± 66 N (core 9.5 mm), 386 ± 128 N (core 8.5 mm), and 348 ± 146 N (core 8.5 mm), respectively. The mode of tendon failure was significantly influenced by the tendon diameter. Also, an increase in TC raised the fixation strength for all tendon diameters; however, tendon over compression decreased the fixation strength for the 8 mm tendon group. Finally, an empirical equation was proposed to predict BASHTI fixation strength.

Comparison of mechanical properties in interference screw fixation technique and organic anterior cruciate ligament reconstruction method: a biomechanical study.

BACKGROUND: Bone and Site Hold Tendon Inside (BASHTI) technique is an organic implant-less technique for anterior cruciate ligament (ACL) reconstruction with some clinical advantages, such as speeding up the healing process, over implantable techniques. The study aims to compare the mechanical properties of BASHTI technique with the conventional interference screw technique. METHODS: To investigate the mechanical properties, 20 in-vitro experimental tests were conducted. Synthetic dummy bone, along with fresh digital bovine tendons, as a graft, were used for experiments. Three loading steps were applied to all specimens, including a preconditioning, a main cyclic, and a pull-out loading. RESULTS: The mechanical characters of an interference screw technique using an 8 mm tendon diameter, including fixation strength, average cyclic stiffness (ACS), and average pull-out stiffness (APS) were found to be 439 ± 132 N, 10.3 ± 5.3 kN/mm, and 109 ± 40 N/mm, respectively. In the case of an interference screw using a 9 mm tendon, the fixation strength, ACS, and APS were obtained 549 ± 87 N, 10.3 ± 4.7 kN/mm, and 91 ± 13 N/mm, respectively. In parallel, the fixation strength, APS, and ACS of BASHTI technique using an 8 mm tendon were 360 ± 123 N, 3.3 ± 0.6 kN/mm, and 79 ± 27 N/mm, respectively, while, for 9 mm tendon 278 ± 103 N, 2.4 ± 1.2 kN/mm, and 111 ± 40 N/mm, were reported for fixation strength, APS, and ACS respectively when BASHTI technique was used. CONCLUSION: About 50% of interference screw samples showed superior mechanical properties compared to BASHTI technique, but in another half of the samples, the differences were not significant (N.S.). However, due to organic advantages of BASHTI technique and lower cost, it could be used as a substitute for interference screw technique, especially where fast recovery is expected.

Fractality and Variability in Canonical and Non-Canonical English Fiction and in Non-Fictional Texts.

This study investigates global properties of three categories of English text: canonical fiction, non-canonical fiction, and non-fictional texts. The central hypothesis of the study is that there are systematic differences with respect to structural design features between canonical and non-canonical fiction, and between fictional and non-fictional texts. To investigate these differences, we compiled a corpus containing texts of the three categories of interest, the Jena Corpus of Expository and Fictional Prose (JEFP Corpus). Two aspects of global structure are investigated, variability and self-similar (fractal) patterns, which reflect long-range correlations along texts. We use four types of basic observations, (i) the frequency of POS-tags per sentence, (ii) sentence length, (iii) lexical diversity, and (iv) the distribution of topic probabilities in segments of texts. These basic observations are grouped into two more general categories, (a) the lower-level properties (i) and (ii), which are observed at the level of the sentence (reflecting linguistic decoding), and (b) the higher-level properties (iii) and (iv), which are observed at the textual level (reflecting comprehension/integration). The observations for each property are transformed into series, which are analyzed in terms of variance and subjected to Multi-Fractal Detrended Fluctuation Analysis (MFDFA), giving rise to three statistics: (i) the degree of fractality ( H ), (ii) the degree of multifractality ( D ), i.e., the width of the fractal spectrum, and (iii) the degree of asymmetry ( A ) of the fractal spectrum. The statistics thus obtained are compared individually across text categories and jointly fed into a classification model (Support Vector Machine). Our results show that there are in fact differences between the three text categories of interest. In general, lower-level text properties are better discriminators than higher-level text properties. Canonical fictional texts differ from non-canonical ones primarily in terms of variability in lower-level text properties. Fractality seems to be a universal feature of text, slightly more pronounced in non-fictional than in fictional texts. On the basis of our results obtained on the basis of corpus data we point out some avenues for future research leading toward a more comprehensive analysis of textual aesthetics, e.g., using experimental methodologies.

Global Image Properties Predict Ratings of Affective Pictures.

Affective pictures are widely used in studies of human emotions. The objects or scenes shown in affective pictures play a pivotal role in eliciting particular emotions. However, affective processing can also be mediated by low-level perceptual features, such as local brightness contrast, color or the spatial frequency profile. In the present study, we asked whether image properties that reflect global image structure and image composition affect the rating of affective pictures. We focused on 13 global image properties that were previously associated with the esthetic evaluation of visual stimuli, and determined their predictive power for the ratings of five affective picture datasets (IAPS, GAPED, NAPS, DIRTI, and OASIS). First, we used an SVM-RBF classifier to predict high and low ratings for valence and arousal, respectively, and achieved a classification accuracy of 58-76% in this binary decision task. Second, a multiple linear regression analysis revealed that the individual image properties account for between 6 and 20% of the variance in the subjective ratings for valence and arousal. The predictive power of the image properties varies for the different datasets and type of ratings. Ratings tend to share similar sets of predictors if they correlate positively with each other. In conclusion, we obtained evidence from non-linear and linear analyses that affective pictures evoke emotions not only by what they show, but they also differ by how they show it. Whether the human visual system actually uses these perceptive cues for emotional processing remains to be investigated.

Teaching ethics using games: Impact on Iranian nursing students' moral sensitivity.

This study seeks to develop a method of teaching ethics to nursing students using games. We used the one-group pretest-posttest design with 30 undergraduate nursing students as participants. Professional ethics education was provided for 17 weeks in 90-minute sessions. The Lutzen ethical sensitivity questionnaire and a checklist of the satisfaction levels of games used measured the effects of training. Repeated-measures ANOVA and the Greenhouse-Geisser correction were used to measure ethics game satisfaction. After training, total moral sensitivity questionnaire scores increased significantly (p = 0.02). The score on awareness of the relationship with the patient and the application of ethics concepts in ethical decisions from the subdomain of moral sensitivity increased significantly. Card sorting and drawing or art production earned the highest scores of satisfaction. The results show that playing games is a useful approach to developing moral sensitivity among nursing students to make them more sensitive toward ethics issues in their professional environment.