Capture Data Research Articles

Important pollinator species for conserving rare plant species endemic to San Clemente Island, California

Much effort has been spent on the conservation of rare, threatened, and endangered plants in the biodiversity hotspot of the California Floristic Province, however little is known about the identity of their pollinators. In this study we provide the first formal study on the identity of the invertebrate pollinators of five rare endemic island plant species from San Clemente Island, the southernmost of the California Channel Islands: Delphinium variegatum ssp kinkiense, Lithophragma maximum, Malacothamnus clementinus, Malva assurgentiflora ssp glabra, and Sibara filifolia. We surveyed plant-pollinator interactions at populations of each focal plant species using timed sweep-netting. We used pollinator capture data to compile bipartite interaction networks for each plant population, and calculated centrality indices (degree, betweenness centrality, and closeness centrality) of pollinators to identify species important to network stability. We found a significant effect of pollinator taxonomic group (fly, bee, wasp, or Lepidopteran) on some indices of pollinator centrality in interaction networks, and variation in pollinator centrality between different locations. Hoverflies, moths, and butterflies were important generalists with higher network centrality across all plant populations, while bees tended to be more specialists within their networks, except for the Malva assurgentiflora ssp glabra network, where bees were on average of higher centrality than flies. We recommend targeted restoration practices for future study that could support pollination both directly and indirectly to focal rare plant species of conservation interest across plant populations. These practices could augment general pollinator conservation best practices such as reducing pesticide use and planting native plant species to provide increased pollination to endangered plants.

Social networks reveal sex- and age-patterned social structure in Butler's gartersnakes (Thamnophis butleri).

Sex- and age-based social structures have been well documented in animals with visible aggregations. However, very little is known about the social structures of snakes. This is most likely because snakes are often considered non-social animals and are particularly difficult to observe in the wild. Here, we show that wild Butler's Gartersnakes have an age and sex assorted social structure similar to more commonly studied social animals. To demonstrate this, we use data from a 12-year capture-mark-recapture study to identify social interactions using social network analyses. We find that the social structures of Butler's Gartersnakes comprise sex- and age-assorted intra-species communities with older females often central and age segregation partially due to patterns of study site use. In addition, we find that females tended to increase in sociability as they aged while the opposite occurred in males. We also present evidence that social interaction may provide fitness benefits, where snakes that were part of a social network were more likely to have improved body condition. We demonstrate that conventional capture data can reveal valuable information on social structures in cryptic species. This is particularly valuable as research has consistently demonstrated that understanding social structure is important for conservation efforts. Additionally, research on the social patterns of animals without obvious social groups provides valuable insight into the evolution of group living.

Utilizing the Clustering Techniques using Distance-Based Similarity Measures of SVNS in Medical Diagnosis

The clustering techniques, combined with distance-based similarity measures of Single Valued Neutrosophic Sets (SVNS) are studied and applied in medical diagnosis. The study starts with reviewing SVNS' theoretical foundations, emphasising its ability to capture and handle ambiguous data. This study focuses on integrating distance-based similarity measurements to improve the clustering process, which has seen limited implementation thus far. The set of data includes three patients with five symptoms and three diagnoses. To deal with the data in medical diagnosis, each patient is diagnosed with a disease based on distance-based similarity measures. The disease with the highest similarity measure value indicates the recognized disease for that patient. Then, the diseases are clustered into different categories depend on the values of confidence level. The obtained results show that the suggested method enhances the precision of medical diagnosis significantly, especially in cases with ambiguity and uncertainty.

High-density EMG, IMU, kinetic, and kinematic open-source data for comprehensive locomotion activities

Novel sensor technology enables new insights in the neuromechanics of human locomotion that were previously not possible. Here, we provide a dataset of high-density surface electromyography (HDsEMG) and high-resolution inertial measurement unit (IMU) signals, along with motion capture and force data for the lower limb of 10 healthy adults during multiple locomotion modes. The participants performed level-ground and slope walking, as well as stairs ascent/descent, side stepping gait, and stand-to-walk and sit-to-stand-to-walk, at multiple walking speeds. These data can be used for the development and validation of locomotion mode recognition and control algorithms for prosthetics, exoskeletons, and bipedal robots, and for motor control investigations.

Transformer language model for mapping construction schedule activities to uniformat categories

Creating consistency among project schedule data, BIM, and payment applications requires activities in a construction schedule to be mapped with the most relevant ASTM Uniformat classifications. To do so, we introduce UniformatBridge, a new transformer-based natural language processing model, that automatically labels activities in a project schedule with Uniformat classification. Our model introduces construction sequencing tokens that capture logistically-constrained predecessor and successor activities into BERT architecture. We also introduce a dataset of real-world construction project schedules with their ground-truth Uniformat classifications for validation. Experimental results using this dataset achieve F1-scores of 0.93 and 0.87 when matching unstructured schedule data to Uniformat Level 2 and 3 classifications, respectively. We share how our method unlocks development of new techniques to (1) automatically create 4D BIM, and (2) computer-vision progress monitoring to tie semantic segmentation of reality capture data based on Uniformat classes against schedule or payment application data structures, with/without BIM.

Examination of 2D frontal and sagittal markerless motion capture: Implications for markerless applications.

This study examined if occluded joint locations, obtained from 2D markerless motion capture (single camera view), produced 2D joint angles with reduced agreement compared to visible joints, and if 2D frontal plane joint angles were usable for practical applications. Fifteen healthy participants performed over-ground walking whilst recorded by fifteen marker-based cameras and two machine vision cameras (frontal and sagittal plane). Repeated measures Bland-Altman analysis illustrated that markerless standard deviation of bias and limits of agreement for the occluded-side hip and knee joint angles in the sagittal plane were double that of the camera-side (visible) hip and knee. Camera-side sagittal plane knee and hip angles were near or within marker-based error values previously observed. While frontal plane limits of agreement accounted for 35-46% of total range of motion at the hip and knee, Bland-Altman bias and limits of agreement (-4.6-1.6 ± 3.7-4.2˚) were actually similar to previously reported marker-based error values. This was not true for the ankle, where the limits of agreement (± 12˚) were still too high for practical applications. Our results add to previous literature, highlighting shortcomings of current pose estimation algorithms and labelled datasets. As such, this paper finishes by reviewing methods for creating anatomically accurate markerless training data using marker-based motion capture data.

A pelvic kinematic approach for calculating hip angles for active hip disarticulation prosthesis control

BackgroundControl system design for a microprocessor-controlled hip–knee–ankle–foot (HKAF) prosthesis is a challenge since hip disarticulation amputees lack the entire leg and, therefore, only have pelvis movement as user-guided input. This research proposes a method for determining hip joint angles from pelvis movement in a control system for the next generation of powered prostheses.MethodThree-dimensional pelvic motion and stance time of 10 transfemoral (TF) prosthetic users were used to identify important features and to develop an algorithm to calculate hip angles from pelvis movement based on correlation and linear regression results. The algorithm was then applied to a separate (independent) TF group to validate algorithm performance.ResultsThe proposed algorithm calculated viable hip angles during walking by utilizing pelvic rotation, pelvic tilt, and stance time. Small angular differences were found between the algorithm results and motion capture data. The greatest difference was for hip maximum extension angle (2.5 ± 2.0°).ConclusionsSince differences between algorithm output and motion data were within participant standard deviations, the developed algorithm could be used to determine the desired hip angle from pelvis movements. This study will aid the future development of gait control systems for new active HKAF prostheses.

Abstract 371: Physiological Predictors of Cerebral Oxygenation During Hemorrhage in Swine

Introduction: Measurements of cerebral oxygenation (rSO 2 ) using near-infrared spectroscopy (NIRS) have been used to predict survival in retrospective clinical studies. However, the physiology underlying changes in rSO 2 during critical states such as hemorrhage is not completely understood. This analysis examined the effect of blood pressures, intracranial pressure, and heart rate on rSO 2 . Methods: Eight swine were instrumented with invasive pressure catheters in the aorta, right atrium, and cerebrum and underwent a pressure-targeted arterial hemorrhage protocol. Animals were bled at a rate of 20mL/min to a target diastolic pressure of 35 mmHg. Brief periods of increased baseline airway pressure (15 cm H 2 O) were introduced to cause transient drops in arterial blood pressure. The aortic pressure waveform was used to identify individual heartbeats. The first 100 heartbeats represent baseline data, while heart beats 4900-5000 (time from start of bleed; 40±7 min) capture data late into the bleed for all animals. Data from 53,315 heart beats were entered into a regression model: rSO 2 = mean diastolic aortic pressure + mean diastolic right atrial pressure + intracranial pressure + heart rate + animal. Results: The hemorrhage reduced diastolic aortic pressure from 61.7±9.6 (heart beats 1-100) to 35.0±9.2 mmHg (heart beats 4900-5000), increased right atrial pressure from 4.1±3.6 to 4.9±6.9 mmHg, reduced intracranial pressure from 33.6±23.2 mmHg to 16.3±2.5 mmHg, and increased heart rate from 101±14 to 144±40 beats/min. Output from the regression model (Table 1) shows that mean diastolic aortic pressure, but not right atrial pressure, intracranial pressure or heart rate, is a significant predictor of rSO 2 . Conclusions: rSO 2 values are largely driven by arterial blood pressure and may serve as a useful non-invasive tool as a surrogate for arterial blood pressure during hemorrhage. Further work should investigate the use of this technology to provide real-time feedback.

Analysis of Fringescale Sardine Fishing Grounds (Sardinella fimbriata) Based on Sea Surface Temperature and Chlorophyll-A in Tegal Waters, Indonesia

An alternative that can be done in determining the fishing area is to use remote sensing technology through the approach of sea surface temperature distribution and chlorophyll-a. The purpose of this study was to determine the value of the distribution of sea surface temperature and chlorophyll-a, as well as analyze the relationship between sea surface temperature and chlorophyll-a on Fringescale sardine (Sardinella fimbriata). The research method used is the descriptive method. The research data taken are in-situ data and SNPP Viirs satellite imagery data, as well as capture data from 2018 – 2022. Data analysis used multiple linear regression methods and Pearson correlation analysis. The results showed that the sea surface temperature distribution value ranged from 29.5°C – 29.9°C and chlorophyll-a ranged from 0.0545 mg m-3 – 0.4022 mg m-3. The value of sea surface temperature and chlorophyll-a in Tegal waters on land tends to have a higher value compared to high seas waters. Analysis conducted between sea surface temperature and chlorophyll-a on catches found a coefficient of determination of 0.74 or 74% affecting the total catch. The partial correlation between sea surface temperature and catch is 0.81 or 81%. The correlation between chlorophyll-a and catch is 0.86 or 86% where this value is included in the very strong category in influencing the catch of Sardinella fimbriata. Fishermen no longer rely on instinct to predict potential fishing zone each season, but it has taken advantage of variables that affect the presence of S. fimbriata using potential fishing zone map.

Integrated Genomic Analysis Identifies a Downstream Regulatory Element Oncogenically Activating Hematopoietically Expressed Homeobox ( HHEX) in ETP-ALL

Hematopoietically-expressed Homeobox ( HHEX) is required for the maintenance of hematopoietic stem cells (HSPCs) and common lymphoid progenitor cells. HHEX is also the second most frequent integration site in retroviral insertional mutagenesis screens of leukemias and lymphomas arising in AKXD recombinant inbred mouse strains, implying that it is an important oncogene. Enforced expression of HHEX induces T-cell acute lymphoblastic leukemias (T-ALL) in murine bone marrow transplantation models. In human studies, HHEXmRNA expression is upregulated in human T-ALL studies, especially in Early T-cell Precursor (ETP-) ALL subtypes where it is concordantly expressed with LMO2. The HHEX locus is not rearranged in ETP-ALL where it is upregulated so the mechanism of HHEX activation is not clear. We analyzed T-ALL induced by retroviral mutagenesis and found an intergenic site of frequent integration, 65kb 3‘ of the Hhex coding exons. Integrations clustered within a 3 kb genomic area that is also an open chromatin region (OCR) by ATAC-seq analysis and that induced Hhex upregulation. The syntenic human region was highly enriched for H3K27 acetylation and for occupancy by multiple transcription factors, notably GATA1 and TAL1, per ENCODE. Our prior data had shown that HHEX was a downstream target of the LMO2 complex comprised of GATA1/2, TAL1 or LYL1, and nucleated by the scaffolding protein, LIM domain binding protein 1 (LDB1). We had previously shown by ChIP-PCR that the LMO2 complex was bound to the intron 1 enhancer. Thus, we performed ChIP-exonuclease analysis of LDB1 in the human ETP-ALL model cell line, LOUCY. We confirmed its occupancy at the intron 1 enhancer but we also observed LDB1 occupancy 68kb 3‘ of the HHEX coding exons, in the exact region syntenic to the murine common insertion sites. ChIP-exo analysis allowed us to pinpoint a core element with composite GATA/E box sites that was highly conserved across multiple mammalian species. LDB1 occupancy at intron 1 and at +68kb of the HHEX locus was reminiscent of LDB1's occupancy at the beta globin locus where LDB1's occupancy and homodimerization mediates chromatin looping between composite E box/GATA sites in the locus control region (LCR) and the beta globin proximal promoters. To test whether a similar interaction was occurring at the HHEX locus, we analyzed virtual 4C (chromatin conformation capture) data. We confirmed looping between the +68kb element and the proximal promoter of HHEX in human ETP-ALL primary samples and in human HSPCs. The experiments showed that looping occurs in certain developmental contexts in HSPCs and is recapitulated in ETP-ALL and mediated by the LMO2/LDB1 protein complex. HHEX is a downstream oncogene of the LMO2/LDB1 complex and is activated through this distal +68kb regulatory element. Our studies raise the possibility that dissection of this regulatory element and interference with chromatin looping are potential therapeutic mechanisms that could disrupt oncogene expression.

Oklo natural fission reactors and dynamical models of dark energy.

Bounds on the cosmological variation of the fine structure constant α inferred from Oklo neutron capture dataare sometimes taken cum grano salis. It is possible to quantify uncertainties related to the treatment of excitation, deformation and the Coulomb interaction. On the basis of this analysis, it is concluded that Oklo data imply the relative change in α over the last 1.9 billion years is < 0.01ppm (95% CL). Accommodation of this constraint represents a challenge to dark energy models that predict that fundamental constants do change.

Design and preliminary evaluation of a low-cost three-dimensional biomechanical force plate

Abstract Objective: The three-dimensional (3D) force plate is a widely used device in biomechanical research, capable of measuring the ground reaction force (GRF) exerted on the sole of the foot. The forces of human joints are calculated by combining GRF with motion capture data. In the field of nursing and rehabilitation, evaluation of joint pressure can inform further therapy. However, its high cost often limits its application to a small population. Therefore, we aimed to design and manufacture a low-cost 3D force plate to address this issue, which will advance the evaluation of joint pressure in nursing practices. Methods: Through mechanical derivation and finite element method simulation, the feasibility of this 3D force plate was tested. We proposed a method based on simulation results to assist in calibration. Furthermore, we collected the GRF data of the author using the 3D force plate designed in this study. Then we imported this GRF data and the data obtained from motion capture into OpenSim. Results: The 3D force plate consisted of two 3D force sensors and a 600 300 mm board. The 3D force plate could measure the 3D reaction force between the sole of a subject’s foot and the ground. The 3D force plate was validated the usability in this study through theoretical calculation and a complete musculoskeletal analysis process. Conclusion: We have completed the design and practicality verification of this low-cost 3D force plate and provided a calibration method based on finite element method simulation assistance. Low-cost 3D force plates can accelerate the popularization and application of musculoskeletal analysis in the field of nursing and rehabilitation, which is helpful for precision health.

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

Accurate and reliable human motion reconstruction is crucial for creating natural interactions of full-body avatars in Virtual Reality (VR) and entertainment applications. As the Metaverse and social applications gain popularity, users are seeking cost-effective solutions to create full-body animations that are comparable in quality to those produced by commercial motion capture systems. In order to provide affordable solutions though, it is important to minimize the number of sensors attached to the subject’s body. Unfortunately, reconstructing the full-body pose from sparse data is a heavily under-determined problem. Some studies that use IMU sensors face challenges in reconstructing the pose due to positional drift and ambiguity of the poses. In recent years, some mainstream VR systems have released 6-degree-of-freedom (6-DoF) tracking devices providing positional and rotational information. Nevertheless, most solutions for reconstructing full-body poses rely on traditional inverse kinematics (IK) solutions, which often produce non-continuous and unnatural poses. In this article, we introduce SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from a reduced set of six tracking devices. Our system incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses by learning the human motion manifold from motion capture data. Then, we employ a learned IK component, made of multiple lightweight feed-forward neural networks, to adjust the hands and feet toward the corresponding trackers. We extensively evaluate our method on publicly available motion capture datasets and with real-time live demos. We show that our method outperforms state-of-the-art techniques using IMU sensors or 6-DoF tracking devices, and can be used for users with different body dimensions and proportions.

Knee kinematics are primarily determined by implant alignment but knee kinetics are mainly influenced by muscle coordination strategy

Implant malalignment has been reported to be a primary reason for revision total knee arthroplasty (TKA). In addition, altered muscle coordination patterns are commonly observed in TKA patients, which is thought to alter knee contact loads. A comprehensive understanding of the influence of surgical implantation and muscle recruitment strategies on joint contact mechanics is crucial to improve surgical techniques, increase implant longevity, and inform rehabilitation protocols. In this study, a detailed musculoskeletal model with a 12 degrees of freedom knee was developed to represent a TKA subject from the CAMS-Knee datasets. Using motion capture and ground reaction force data, a level walking cycle was simulated and the joint movement and loading patterns were estimated using a novel technique for concurrent optimization of muscle activations and joint kinematics. In addition, over 12′000 Monte Carlo simulations were performed to predict knee contact mechanics during walking, considering numerous combinations of implant alignment and muscle activation scenarios. Validation of our baseline simulation showed good agreement between the model kinematics and loading patterns against the in vivo data. Our analyses reveal a considerable impact of implant alignment on the joint kinematics, while variation in muscle activation strategies mainly affects knee contact loading. Moreover, our results indicate that high knee compressive forces do not necessarily originate from extreme kinematics and vice versa. This study provides an improved understanding of the complex inter-relationships between loading and movement patterns resulting from different surgical implantation and muscle coordination strategies and presents a validated framework towards population-based modelling in TKA.

Identifying treatment non-responders based on pre-treatment gait characteristics - A machine learning approach

BackgroundPaediatric movement disorders such as cerebral palsy often negatively impact walking behaviour. Although clinical gait analysis is usually performed to guide therapy decisions, not all respond positively to their assigned treatment. Identifying these individuals based on their pre-treatment characteristics could guide clinicians towards more appropriate and personalized interventions. Using routinely collected pre-treatment gait and anthropometric features, we aimed to assess whether standard machine learning approaches can be effective in identifying patients at risk of negative treatment outcomes. MethodsObservational data of 119 patients with movement disorders were retrospectively extracted from a local clinical database, comprising sagittal joint angles and spatiotemporal parameters, derived from motion capture data pre- and post-treatment (physiotherapy, orthosis, botulin toxin injections, or surgery). Participants were labelled based on their change in gait profile score (GPS, non-responders with a decline in GPS of <1.6° vs. responders). Their pre-treatment features (sagittal joint angles, spatiotemporal parameters, anthropometrics) were used to train a support vector machine classifier with 5-fold cross-validation and Bayesian optimization within a MATLAB-based Classification Learner App. ResultsAn average accuracy of 88.2 ± 0.5 % was achieved for identifying participants whose gait will not respond to treatment, with 64 % true negative rate and an area under the curve of 88 %. ConclusionOverall, a classical machine learning model was able to identify patients at risk of not responding to treatment, based on gait features and anthropometrics collected prior to treatment. The output of such a model could function as a warning signal, notifying clinicians that a certain individual might not respond well to the standard of care and that a more personalized intervention might be needed.

Neuromechanics of finger hangs with arm lock-offs: analyzing joint moments and muscle activations to improve practice guidelines for climbing.

Climbing imposes substantial demands on the upper limbs and understanding the mechanical loads experienced by the joints during climbing movements is crucial for injury prevention and optimizing training protocols. This study aimed to quantify and compare upper limb joint loads and muscle activations during isometric finger hanging exercises with different arm lock-off positions. Seventeen recreational climbers performed six finger dead hangs with arm lock-offs at 90° and 135° of elbow flexion, as well as arms fully extended. Upper limb joint moments were calculated using personalized models in OpenSim, based on three-dimensional motion capture data and forces measured on an instrumented hang board. Muscle activations of upper limb muscles were recorded with surface electromyography electrodes. Results revealed that the shoulder exhibited higher flexion moments during arm lock-offs at 90° compared to full extension (p = 0.006). The adduction moment was higher at 135° and 90° compared to full extension (p < 0.001), as well as the rotation moments (p < 0.001). The elbows exhibited increasing flexion moments with the increase in the arm lock-off angle (p < 0.001). Muscle activations varied across conditions for biceps brachii (p < 0.001), trapezius (p < 0.001), and latissimus dorsi, except for the finger flexors (p = 0.15). Our findings indicate that isometric finger dead hangs with arms fully extended are effective for training forearm force capacities while minimizing stress on the elbow and shoulder joints. These findings have important implications for injury prevention and optimizing training strategies in climbing.

Effects of high-profile crossover feet on gait biomechanics in 2 individuals with Syme amputation.

Prosthetic treatment options for people with ankle disarticulation (i.e., Syme amputation) are limited. Prosthetic feet designed for people with Syme amputation are often low profile to accommodate build-height restrictions, resulting in decreased energy return during gait. High-profile crossover feet that attach to the posterior proximal aspect of the prosthetic socket can bypass these restrictions and may promote a more physiologic gait pattern. To compare level-ground gait biomechanics and patient-reported outcomes between crossover and traditional energy-storing feet in people with Syme amputation. Within-participant pilot study. Both participants were fit with energy-storing and crossover feet and were randomized to the order they used the feet. Participants used each foot for 2 weeks before assessment. Step length symmetry, prosthetic ankle range of motion, prosthetic-side energy return, and peak sound-side loading were determined from motion capture data obtained in a laboratory. Mobility and balance confidence were measured using standardized patient-reported outcome measures. Foot preference was assessed with an ad hoc survey. Two participants with Syme amputations completed the study. Prosthetic ankle peak dorsiflexion and push-off power increased with the crossover foot compared with the energy-storing foot for both participants. Both participants reported an overall preference of the crossover foot. Changes in patient-reported outcomes did not exceed published minimum detectable change values. Crossover feet increased prosthetic ankle range of motion and energy return compared with traditional energy-storing feet in this pilot investigation of 2 participants. Crossover feet seem to promote physiologic gait and may be a promising alternative to traditional low-profile feet for people with Syme amputation.

Low-Cost Hyperspectral Imaging Device for Portable Remote Sensing

Hyperspectral imaging has revolutionized various scientific fields by enabling a detailed analysis of objects and materials based on their spectral signatures. However, the high cost and complexity of commercial hyperspectral camera systems limit their accessibility to researchers and professionals. In this paper, a do-it-yourself (DIY) hyperspectral camera device that offers a cost-effective and user-friendly alternative to hyperspectral imaging is presented. The proposed device leverages off-the-shelf components, commercially available hardware parts, open-source software, and novel calibration techniques to capture and process hyperspectral imaging data. The design considerations, hardware components, and construction process are discussed, providing a comprehensive guide for building the device. Furthermore, the performance of the DIY hyperspectral camera is investigated through experimental evaluations with a multi-color 3D-printed box in order to validate its sensitivities to red, green, blue, orange and white colors.

Structural equation modeling of female gait attractiveness using gait kinematics

In our social lives, movement’s attractiveness greatly affects interpersonal cognition, and gait kinematics mediates walkers’ attractiveness. However, no model using gait kinematics has so far predicted gait attractiveness. Thus, this study constructed models of female gait attractiveness with gait kinematics and physique factors as explanatory variables for both barefoot and high-heel walking. First, using motion capture data from 17 women walking, including seven professional runway models, we created gait animations. We also calculated the following gait kinematics as candidate variables to explain walking’s attractiveness: four body-silhouette-related variables and six health-related variables. Then, 60 observers evaluated each gait animation’s attractiveness and femininity. We performed correlation analysis between these variables and evaluation scores to obtain explanatory variables. Structural equation modeling suggested two models for gait attractiveness, one composed of trunk and head silhouette factors and the other of physique, trunk silhouette, and health-related gait factors. The study’s results deepened our understanding of mechanisms behind nonverbal interpersonal cognition through physical movement and brought us closer to realization of artificial generation of attractive gait motions.

Interactive Locomotion Style Control for a Human Character based on Gait Cycle Features

AbstractThis article introduces a data‐driven locomotion style controller for full‐body human characters using gait cycle features. Based on gait analysis, we define a set of gait features that can represent various locomotion styles as spatio‐temporal patterns within a single gait cycle. We compute the gait features for every single gait cycle in motion capture data and use them to search for the desired motion. Our real‐time style controller provides users with visual feedback for the changing inputs, exploiting the Motion Matching algorithm. We also provide a graphical controller interface that visualizes our style representation to enable intuitive control for users. We show that the proposed method is capable of retrieving appropriate locomotions for various gait cycle features, from simple walking motions to single‐foot motions such as hopping and dragging. To validate the effectiveness of our method, we conducted a user study that compares the usability and performance of our system with those of an existing footstep animation tool. The results show that our method is preferred over the baseline method for intuitive control and fast visual feedback.