Motion History Research Articles

Two-Stream Deep Learning Architecture-Based Human Action Recognition

Human action recognition (HAR) based on Artificial intelligence reasoning is the most important research area in computer vision. Big breakthroughs in this field have been observed in the last few years; additionally, the interest in research in this field is evolving, such as understanding of actions and scenes, studying human joints, and human posture recognition. Many HAR techniques are introduced in the literature. Nonetheless, the challenge of redundant and irrelevant features reduces recognition accuracy. They also faced a few other challenges, such as differing perspectives, environmental conditions, and temporal variations, among others. In this work, a deep learning and improved whale optimization algorithm based framework is proposed for HAR. The proposed framework consists of a few core stages i.e., frames initial preprocessing, fine-tuned pre-trained deep learning models through transfer learning (TL), features fusion using modified serial based approach, and improved whale optimization based best features selection for final classification. Two pre-trained deep learning models such as InceptionV3 and Resnet101 are fine-tuned and TL is employed to train on action recognition datasets. The fusion process increases the length of feature vectors; therefore, improved whale optimization algorithm is proposed and selects the best features. The best selected features are finally classified using machine learning (ML) classifiers. Four publicly accessible datasets such as Ut-interaction, Hollywood, Free Viewpoint Action Recognition using Motion History Volumes (IXMAS), and centre of computer vision (UCF) Sports, are employed and achieved the testing accuracy of 100%, 99.9%, 99.1%, and 100% respectively. Comparison with state of the art techniques (SOTA), the proposed method showed the improved accuracy.

Numerical Generation of Solitary Wave and Its Propagation Characteristics in a Step-Type Flume

This work concerns the numerical generation of stable solitary waves by using a piston-type wave maker and the propagation characteristics of a solitary wave in a step-type flume. The numerical generation of solitary waves was performed by solving N-S (Navier–Stokes) equations on the open source CFD (computational fluid dynamics) platform OpenFOAM. To this end, a new module of dynamic boundary conditions was programmed and can be applied to prescribe the horizontal linear motion of a paddle. Two kinds of paddle motions, based on both the first-order and ninth-order solutions of solitary waves, were first determined. The time history of paddle motion was restored in a file, which was then used as an input for the virtual wave maker. The solitary wave in water with a constant depth was generated by both numerical simulation and experiment in the wave flume installed with a piston wave maker. The results show that the amplitudes of trailing waves based on the first-order solution are larger than those based on the ninth-order solution and that wave height based on the first-order solution decays more quickly. The numerical wave profiles are in good agreement with the experimental ones. The propagation characteristics of a solitary wave in a step-type flume was numerically investigated as well. It was found that a part of the solitary wave is reflected when the solitary wave passes the step due to blockage effects, and the forward main wave collapses quickly when it enters shallow water. This work presents a very successful numerical study of stable solitary wave generation and reveals the phenomena when a solitary wave propagates in a step-type flume.

Simulation of strong earthquake characteristics of a scenario earthquake (MS7.5) based on the enlightenment of 2022 MS6.9 earthquake in Menyuan

The Menyuan area is an important transportation hub in the Hexi Corridor. The Menyuan MS6.9 earthquake that occurred on January 8, 2022 had a major impact on the local infrastructure and transportation of this region. Due to the high possibility of similar strong earthquakes occurring in this area in the future, preliminary assessment of the seismic intensity characteristics of destructive earthquakes in this region is essential for effective disaster control. This paper uses the empirical Green′s function (EGF) method as a numerical simulation tool to predict the ground motion intensity of Datong Autonomous County under the action of the scenario earthquake (MS7.5). Seismic records of aftershocks of the 2016 Menyuan MS6.4 earthquake were used as Green’s functions for this simulation. The uncertainties associated with various source parameters were considered, and 36 possible earthquake scenarios were simulated to obtain 72 sets of horizontal ground motions in Datong County. The obtained peak ground acceleration (PGA) vs. time histories of the horizontal ground motion were screened using the attenuation relationships provided by the fifth-edition of China's Seismic Ground Motion Parameter Zoning Map and the NGA-West2 dataset. Ultimately, 32 possible acceleration-time histories were selected for further analysis. The screened PGA values ranged from 78.8 to 153 cm/s2. The uncertainty associated with the initial rupture point was found to greatly affect the results of the earthquake simulation. The average acceleration spectrum of the selected acceleration-time history exceeded the expected spectrum of a intermediate earthquake, which means that buildings in Datong County might sustain some damage should the scenario earthquake occur. This research can provide reliable ground motion input for urban earthquake damage simulation and seismic design in Datong County. Growing the dataset of small earthquakes recorded in this region will facilitate the large-scale simulation of ground motions under different earthquake scenarios.

Experiments on the localized interaction at the interface fuel rod/spacer grid in pressurized water reactors

The release of fissile material into the coolant caused by fretting of the fuel rods at the interface with spacer grids is a significant safety issue and cause of financial losses in the operation of Pressurized Water Reactors (PWRs). Each fuel rod is kept in position inside spacer grids through friction from the preload exerted by retaining elements (springs and dimples). Fretting of the fuel rods occurs at the contact with the springs and dimples. In severe fretting cases the integrity of the fuel rod cladding is compromised and fission byproducts enter the primary coolant circuit. The reciprocating motion at the contact interface of the fuel rods and spacer grids resulting in material fretting is due to the Flow-Induced Vibrations (FIV) of fuel rods, caused by the unstable surrounding coolant flow, which in PWRs is predominantly parallel to the length of fuel rods (axial flow). Under specific flow conditions, fretting develops rapidly. The vibrations of fuel rods, as well as the relationship of fretting wear mechanisms with several factors associated with the fission process and coolant flow dynamics and stability (vibration amplitude, preload, oscillating loads, irradiation, axial slip, spring relaxation, temperature, oxidation, material of spacer grids and fuel rods), have been considered in the literature. However, direct experimental measurements of the contact force and axial slip during FIV have not been treated in the literature, likely because of the absence of suitable measurement methods. This gap in experimental measurement techniques is addressed in this work, specifically for the analysis of PWR fuel assemblies, by installing a piezoelectric stack and aiming laser Doppler vibrometers on a one-meter-long fuel rod, supported by two full-scale spacer grids, in-air or immersed in quiescent water. In the presence of small- and large- amplitude forced vibrations, the signal of the piezoelectric force transducer increases with the amplitude of vibration, but it is also affected by vibrations perpendicular to the excitation, which appear for large-amplitude excitations. The axial motion of the fuel rod at the spacer grid has a complex evolution and is significant for large-amplitude vibrations only. At any rate, the time histories of contact force and axial motion display the effects of impacts and slips, particularly during the tests in water. The measurement system shows that the severity of the interaction at the spacer grid interfaces is influenced strongly by the amplitude of the forced fuel rod vibrations. Since fuel rods and fuel assemblies are prone to several nonlinear phenomena, as demonstrated by recent studies, it follows that the usage of nonlinear models will be essential to numerically estimating the severity of fretting.

Estimation of top tensions in mooring lines by sensor fusion

The paper describes a sensor fusion method that provides reliable, uninterrupted and bias-free estimates of the top tension in a mooring line. The method exploits the geometric nonlinearity of mooring systems installed in shallow to moderate water depths: a change of line length (due to winching) affects the local dynamic stiffness of the mooring line. Based on measurements of fairlead displacements and of the dynamic part of the top tension, the line length and true (unbiased) mean tension can be inferred. The method combines the use of (1) a classical kinematic observer to derive fairlead motions, (2) the compression of the recent history of fairlead motions to a few parameters, (3) a bank of neural networks, each network modelling the response corresponding to a given line length/static tension, and (4) a heuristic approach to selecting the most promising model among the candidates. One major advantage of the method is its sparsity, making it computationally efficient so it can be applied both offline, on large sets of recorded historical data, and online running on lightweight embedded hardware. The paper presents in detail each component listed above, and the method as a whole is verified on a realistic case. Given that enough excitation is present, the estimator was found to converge towards the true value of the tension, and to cope well with transient conditions such as winching operations, and with the presence of oceanic current.

The Relationship of Risk Factors With The Incidence Of Postoperative Nausea And Vomiting In Patients who underwent surgery with General Anesthesia at Rsi Siti Rahmah

General anesthesia is a medical procedure that aims to relieve pain, lose consciousness, and be predictable. General anesthesia has side effects in the form of PONV which cancause dehydration, electrolyte imbalance, re-open wounds, pulmonary aspiration and delay in discharge from the hospital. To know the characteristics of general anesthesia patients, to know the degree of PONV, and to know the relationship between patient, intraoperative, and postoperative risk factors who experience PONV in patients undergoing surgery under anesthesia general.The type of this research used is analytic observational with a cross-sectional approach. The affordable population in this study were all general anesthesia patients at Siti Rahmah Hospital Padang with 65 samples using a consecutive sampling technique. Analysis of univariate and bivariate data presented in the form of frequency and percentage distributions, data processing using the Kolgomorov Smirnov test statistical test. General anesthesia patients aged 26-35 years (24.6%), female (56.9%), no smoking history (89.2%), surgical oncology (47.7%), 60 minutes duration (67.7%), mild pain (38.5%), opioid use (92.3%). Grade 0 PONV (87.6%). The relationship of risk factors for patients experiencing PONV with age p = 0.288, gender p = 0.997, motion sickness p = 0.443, smoking history p = 0.958. Relationship of intraoperative risk factors for PONV with type of surgery p = 1,000, duration of surgery p = 0,978. The relationship between postoperative risk factors for experiencing PONV with opioid use p = 1,000, pain degree p = 1,000. Most general anesthesia patients were aged 26-35 years, most gender was female, most motion history was no history, most smoking history ie no history, the most type of surgery is oncology, the most duration is 60 minutes, the most opioid use is using, the highest degree of pain is mild.

Video Object Segmentation using Point-based Memory Network

Recent years have witnessed the prevalence of memory-based methods for Semi-supervised Video Object Segmentation (SVOS) which utilise past frames efficiently for label propagation. When conducting feature matching, fine-grained multi-scale feature matching has typically been performed using all query points, which inevitably results in redundant computations and thus makes the fusion of multi-scale results ineffective. In this paper, we develop a new Point-based Memory Network, termed as PMNet, to perform fine-grained feature matching on hard samples only, assuming that easy samples can already obtain satisfactory matching results without the need for complicated multi-scale feature matching. Our approach first generates an uncertainty map from the initial decoding outputs. Next, the fine-grained features at uncertain locations are sampled to match the memory features on the same scale. Finally, the matching results are further decoded to provide a refined output. The point-based scheme works with the coarsest feature matching in a complementary and efficient manner. Furthermore, we propose an approach to adaptively perform global or regional matching based on the motion history of memory points, making our method more robust against ambiguous backgrounds. Experimental results on several benchmark datasets demonstrate the superiority of our proposed method over state-of-the-art methods.

Conglomeration of Symptomatic Crohn’s Disease and Celiac Sprue: a Case Report from Western India and Review of the Literature

Background: Background: Celiac diseases are found to be associated with other autoimmune diseases such as autoimmune thyroiditis, type I diabetes, Addison’s disease, primary biliary cirrhosis, and inflammatory bowel disease (IBD). In literature, only a few cases were described simultaneously presenting both conditions in the same patient. Case Presentation:: A 23-year-old Indian male presented with a one-month history of loose motion 10-12 times per day, having watery stool, and nocturnal diarrhea. The patient had pallor, weakness, fatigability, and anorexia/weight loss. The patient also had a history of periumbilical pain abdomen and black-colored stools. In our study, both conditions are clinically symptomatic in the same patient, as proved by endoscopic changes and histopathologically. Esophagogastroduodenoscopy (EGD) examination shows severe scalloping of duodenal folds and nodularity, indicating celiac disease changes. A colonoscopy examination was performed, which revealed multiple linear longitudinal ulcerations, friability, erosions and absent vascularity, which indicates Crohn’s disease. Duodenal biopsy shows celiac disease (Marsh IIIa), and Colonic biopsy shows Crohn’s disease. The patient was treated with improvement in abdominal pain, weight, and anemia. Conclusion: Celiac and Crohn’s both conditions are clinically symptomatic in the same patient, as proved by endoscopic and histopathological changes.

Quantifying the Link Between the Detrital Zircon Record and Tectonic Settings

AbstractFull‐plate reconstructions describe the history of past continental motions and how plate boundaries have evolved to accommodate these motions. Traditionally, tectonic reconstructions relied on geophysical data from the oceans and paleomagnetism as the primary quantitative constraints. However, these data do not directly constrain the paths of subduction zones or other plate boundaries, so reconstructing the complete configurations of tectonic plates in the past must rely on alternative methods. Here, we investigate the applicability of detrital zircon age spectra to characterize tectonic settings in deep time using a much larger data set than previously considered. We analyzed the proximity between reconstructed plate boundaries and sample sites assigned to different tectonic categorizations based on the proportion of zircon ages close to the depositional age and found that the categorization has an ∼70% success rate in distinguishing convergent settings. Results are not strongly influenced by factors such as the number of zircon grains available within each detrital sample or uncertainty in the depositional age of the sample. The ability of the categorization to define extensional settings, such as rift basins, is less clear. Nonetheless, the broader pattern of results at the scale of Pangea shows that categorized zircon samples form a coherent pattern, where samples with dominantly young zircons lie at the supercontinent periphery while samples in the core of Pangea are dominated by grains much older than the age of deposition. This result suggests that zircon data could help to quantify uncertainties in full‐plate reconstructions and discriminate between competing models for Proterozoic supercontinents.

Structure and Evolution of Northern Juan de Fuca Crust and Uppermost Mantle Over the Last 8 Ma From an Active‐Source Seismic Tomography Study

AbstractWe present results from a two‐dimensional wide‐angle controlled source seismic transect designed to characterize the velocity structure of the oceanic crust and uppermost mantle spanning the northern Juan de Fuca (JdF) plate from near Endeavor ridge to the Cascadia margin. Reflection and refraction travel time inversion is used to derive a tomographic Vp model of sediments, crust, and upper mantle. Velocity model results are compared to baseline reference Vp values for unaltered crustal and upper mantle rocks at temperatures assuming plate cooling. Effective medium theory is used to infer the degree of hydration of the crust and mantle. Results indicate a somewhat fractured and hydrated upper crust (≤2.5 wt% water), a near dry lower crust (≤0.7 wt%) and upper mantle (≤0.5 wt%) west of the deformation front, and an ∼75 km wide region of modestly lower velocity in the mid‐plate. Comparison with prior results from a complementary transect offshore Oregon indicates significant differences in Vp of the upper crust, with lower Vp‐inferred porosity along most of the Washington transects that may reflect different extents of fault‐related alteration and sediment burial histories. Approaching the deformation front, Washington transect Vp structure indicates dryer conditions than offshore Oregon, consistent with differences in extent of subduction bend faulting found in reflection imaging studies. On both transects, quasi‐abrupt changes in plate properties at ages of 8, 6, and 3.4/4 Ma are found. Distinct crustal accretion modes are recognized, aligning with changes in JdF plate motion and recent history of Cobb‐Eickelberg hotspot influence on crustal accretion at the JdF ridge.

Sloshing dynamics of liquid tank with built-in buoys for wave energy harvesting

This paper proposes a novel design of liquid tank with built-in buoys for wave energy harvesting, named the ’sloshing wave energy converter (S-WEC)’. When the tank is oscillated by external loads (such as ocean waves), internal liquid sloshing is activated, and the mechanical energy of sloshing waves can be absorbed by the power take-off (PTO) system attached to these buoys. A fully-nonlinear numerical model is established based on the boundary element method for a systematic investigation on dynamic properties of the proposed S-WEC. A motion decoupling algorithm based on auxiliary functions is developed to solve the nonlinear interaction of sloshing waves and floating buoys in the tank. An artificial damping model is introduced to reflect viscous effects of the sloshing liquid. Physical experiments are carried out on a scaled S-WEC model to validate the mathematical and numerical methodologies. Natural frequencies of the S-WEC system are first investigated through spectrum analyses on motion histories of the buoy and sloshing liquid. The viscous damping strength is identified through comparisons with experimental measurements. Effects of the PTO damping on power generation characteristics of S-WEC is further explored. An optimal PTO damping can be found for each excitation frequency, leading to the maximisation of both the power generation and conversion efficiency of the buoy. To determine a constant PTO damping for engineering design, a practical approach based on diagram analyses is proposed, where the averaged conversion efficiency can reach 70%. Effects of the buoy’s geometry on power generation characteristics of the S-WEC are also investigated. The geometry factors including the draught-to-width ratio (DWR) and inclination bottom angle of the buoys are investigated. For cases under consideration, the conversion efficiency of the S-WEC can even reach over 90%. In engineering practice, the present design of S-WEC can be a promising technical solution of ocean wave energy harvesting, based on its comprehensive advantages on survivability enhancement, metal corrosion or fouling organism inhibition, power generation stability and efficiency, and so on.

Vehicle trajectory prediction on highways using bird eye view representations and deep learning

This work presents a novel method for predicting vehicle trajectories in highway scenarios using efficient bird’s eye view representations and convolutional neural networks. Vehicle positions, motion histories, road configuration, and vehicle interactions are easily included in the prediction model using basic visual representations. The U-net model has been selected as the prediction kernel to generate future visual representations of the scene using an image-to-image regression approach. A method has been implemented to extract vehicle positions from the generated graphical representations to achieve subpixel resolution. The method has been trained and evaluated using the PREVENTION dataset, an on-board sensor dataset. Different network configurations and scene representations have been evaluated. This study found that U-net with 6 depth levels using a linear terminal layer and a Gaussian representation of the vehicles is the best performing configuration. The use of lane markings was found to produce no improvement in prediction performance. The average prediction error is 0.47 and 0.38 meters and the final prediction error is 0.76 and 0.53 meters for longitudinal and lateral coordinates, respectively, for a predicted trajectory length of 2.0 seconds. The prediction error is up to 50% lower compared to the baseline method.

Towards automatic finite-element methods for geodynamics via Firedrake

Abstract. Firedrake is an automated system for solving partial differential equations using the finite-element method. By applying sophisticated performance optimisations through automatic code-generation techniques, it provides a means of creating accurate, efficient, flexible, easily extensible, scalable, transparent and reproducible research software that is ideally suited to simulating a wide range of problems in geophysical fluid dynamics. Here, we demonstrate the applicability of Firedrake for geodynamical simulation, with a focus on mantle dynamics. The accuracy and efficiency of the approach are confirmed via comparisons against a suite of analytical and benchmark cases of systematically increasing complexity, whilst parallel scalability is demonstrated up to 12 288 compute cores, where the problem size and the number of processing cores are simultaneously increased. In addition, Firedrake's flexibility is highlighted via straightforward application to different physical (e.g. complex non-linear rheologies, compressibility) and geometrical (2-D and 3-D Cartesian and spherical domains) scenarios. Finally, a representative simulation of global mantle convection is examined, which incorporates 230 Myr of plate motion history as a kinematic surface boundary condition, confirming Firedrake's suitability for addressing research problems at the frontiers of global mantle dynamics research.

Internal deformation of the Gorda plate and its tectonic significance within the Cascadia subduction zone

In this review paper, we compile observations that have been made over decades of research on the Cascadia convergent boundary and re-examine the deformation using structural kinematic models, thereby providing new insights. Deformation in the subducting Juan de Fuca slab and the overriding North American plate is primarily accommodated by fracturing. We show that the along-strike deformation patterns are a function of fracture density and activity, which influences coupling with the overriding North American plate and the underlying mantle wedge. We analyze the deformation within a fracture kinematics framework and show that the orientations of the fractures and motion history follow expected empirical fracture mechanics models and are used to provide a more detailed kinematic history of the Cascadia convergent boundary. We focus on the Gorda plate of the Juan de Fuca subducting slab and show that it is intensely fractured with curved magnetic anomalies such that the brittle deformation is collectively expressed macroscopically as a deforming continuum. The Gorda plate has changed shape via NS shortening and clockwise rotation without losing cohesion at the plate-scale, which suggests that the fractures form an interlocking network to accommodate ductile deformation via cataclastic flow. In the forearc, the fracture and velocity patterns suggest that deformation is accommodated by a continental-scale right-lateral shear zone, trending 320°/140° and is assisted via crustal-scale cataclastic flow. We suggest that ETS activity is strongly correlated to deformation in the over-riding plate. The Gorda plate is also used to better understand larger-scale plate dynamics. We demonstrate that the Gorda plate acts as a ductile deformation zone to assist global plate mobility. Additionally, details of the magnetic lineation patterns in the Gorda plate indicate that slab pull overtakes plate rotation post-subduction. This suggests that plate behavior is strongly influenced by its internal deformation and coupling with the mantle post-subduction.

Probabilistic Traffic Motion Labeling for Multi-Modal Vehicle Route Prediction.

The prediction of the motion of traffic participants is a crucial aspect for the research and development of Automated Driving Systems (ADSs). Recent approaches are based on multi-modal motion prediction, which requires the assignment of a probability score to each of the multiple predicted motion hypotheses. However, there is a lack of ground truth for this probability score in the existing datasets. This implies that current Machine Learning (ML) models evaluate the multiple predictions by comparing them with the single real trajectory labeled in the dataset. In this work, a novel data-based method named Probabilistic Traffic Motion Labeling (PROMOTING) is introduced in order to (a) generate probable future routes and (b) estimate their probabilities. PROMOTING is presented with the focus on urban intersections. The generation of probable future routes is (a) based on a real traffic dataset and consists of two steps: first, a clustering of intersections with similar road topology, and second, a clustering of similar routes that are driven in each cluster from the first step. The estimation of the route probabilities is (b) based on a frequentist approach that considers how traffic participants will move in the future given their motion history. PROMOTING is evaluated with the publicly available Lyft database. The results show that PROMOTING is an appropriate approach to estimate the probabilities of the future motion of traffic participants in urban intersections. In this regard, PROMOTING can be used as a labeling approach for the generation of a labeled dataset that provides a probability score for probable future routes. Such a labeled dataset currently does not exist and would be highly valuable for ML approaches with the task of multi-modal motion prediction. The code is made open source.

Real-Time Multi-Modal Human–Robot Collaboration Using Gestures and Speech

Abstract As artificial intelligence and industrial automation are developing, human–robot collaboration (HRC) with advanced interaction capabilities has become an increasingly significant area of research. In this paper, we design and develop a real-time, multi-model HRC system using speech and gestures. A set of 16 dynamic gestures is designed for communication from a human to an industrial robot. A data set of dynamic gestures is designed and constructed, and it will be shared with the community. A convolutional neural network is developed to recognize the dynamic gestures in real time using the motion history image and deep learning methods. An improved open-source speech recognizer is used for real-time speech recognition of the human worker. An integration strategy is proposed to integrate the gesture and speech recognition results, and a software interface is designed for system visualization. A multi-threading architecture is constructed for simultaneously operating multiple tasks, including gesture and speech data collection and recognition, data integration, robot control, and software interface operation. The various methods and algorithms are integrated to develop the HRC system, with a platform constructed to demonstrate the system performance. The experimental results validate the feasibility and effectiveness of the proposed algorithms and the HRC system.

Deep reinforcement learning coupled with musculoskeletal modelling for a better understanding of elderly falls.

Reinforcement learning (RL) has been used to study human locomotion learning. One of the current challenges in healthcare is our understanding of and ability to slow the decline due to muscle ageing and its effect on human falls. The purpose of this study was to investigate reinforcement learning for human movement strategies when modifying muscle parameters to account for age-related changes. In particular, human falls with modified physiological factors were modelled and simulated to determine the effect of muscle descriptors for ageing on kinematic behaviour and muscle force control.A 3D musculoskeletal model (8 DoF and 22 muscles) of the human body was used. The deep deterministic policy gradient (DDPG) method was implemented. Different muscle descriptors for ageing were integrated, including changes in maximum isometric force, contraction velocity, the deactivation time constant and passive muscle strain. Additionally, the effects of isometric force reductions of 10, 20 and 30% were also considered independently. An environment for the simulation was developed using the opensim-rl package for Python with the training process completed on Google Compute Engine. The simulation outcomes for healthy young adult and elderly falls under modified muscle behaviours were compared to experimental observations for validation.The result of our elderly simulation for multiple ageing-related factors (M_all) produced a walking speed of 0.26m/s for the two steps taken prior to the fall. The over activation of the hip extensors and inactivation of knee extensors led to a backward fall for this elderly simulation. The inactivated rectus femoris and right tibialis are main actors of the forward fall. Our simulation outcomes are consistent with experimental observations through the comparison of kinematic features and motion history evolution.We showed in the present study, for the first time, that RL can be used as a strategy to explore the effect of ageing muscle physiological factors on kinematics and muscle control during falls. Our findings show that the elderly fall model for the M_all condition more closely resembles experimental elderly fall data than our simulations which considered age-related reductions of force alone. As future perspectives, the behaviour preceding a fall will be studied to establish the strategies used to avoid falls or fall with minimal consequence, leading to the identification of patient-specific rehabilitation programmes for elderly people.

A unified theory of slender wings in asymmetric motion, with an application to a swimming sea snake

Abstract The slender body theory is extended to accommodate cases where a wing, in generally non-uniform motion, sideslips at sufficiently large angle to make the flow separate from one of its long edges but not from any part of the other. In those cases, an approximately triangular wake forms to the side of the wing, rendering the pressure loads on the wing not only asymmetrical, but also dependent on the history of the wing's motion. The theory can have a wide range of possible applications, from estimating lift and drag of a slender wing in pronouncedly asymmetric flight, through analysing an aero-elastic stability of that wing, to estimating thrust, lift and power of a sea snake that swims at an angle to its body axis. Coherence of the theory is demonstrated through numerous numerical simulations.

Gravitational radiation from a binary system in odd-dimensional spacetime

We explore possible manifestations of an odd number of extra dimensions in gravitational radiation, which are associated with violation of Huygens' principle in flat odd-dimensional spacetime. Our setup can be regarded as the limit of an infinite compactification radius in ADD model and is not viable as realistic cosmology, but it still may be useful as a simple analytically solvable model catching certain features of more realistic scenarios. The model consists of two point masses moving inside a flat three-dimensional brane, embedded in a five-dimensional Minkowski space and interacting only through a massless scalar field localized on the same brane, while gravitational radiation is emitted into the bulk. This setup avoids the difficulties associated with taking into account the gravitational stresses binding the system, which require the cubic terms in the perturbative gravitational Lagrangian, and permits to limit ourselves to linearized theory. We calculate radiation in a linearized five-dimensional gravity generalizing the Rohrlich-Teitelboim approach to extract the emitted part of the retarded gravitational field. The source term consists of a local contribution from point particles and a non-local contribution from scalar field stresses, which is calculated using the DIRE approach to post-Newtonian expansions. In the nonrelativistic limit, we find an analog of the quadrupole formula containing an integral over the history of the particles' motion preceding the retarded time. We also show that, for an observer on the brane, the radiation contains a third polarization: the breathing mode.

Recognition of Human Body Feature Changes in Sports Health Based on Deep Learning.

With the rapid development of social economy and the extensive and in-depth development of national fitness activities, national physical fitness monitoring and research work has achieved rapid development. In recent years, the application of deep learning technology has also achieved research breakthroughs in the field of computer vision. How deep learning technology can effectively capture motion information in sample data and use it to realize the recognition and classification of human actions is currently a research hot spot. Today's popularization of various shooting devices such as mobile phones and portable action cameras has contributed to the vigorous growth of image data. Therefore, through computer vision technology, image data is widely used in practical application scenarios of human feature recognition. This paper proposes a deep learning network based on the recognition of human body feature changes in sports, improves the recognition method, and compares the recognition accuracy with the original method. The experimental results of this paper show that the result of this paper is 1.68% higher than the original recognition method, the accuracy rate of the improved motion history image is increased by 14.8%, and the overall recognition rate is higher. It can be seen from the above experimental results that this method has achieved good results in human body action recognition.