Movement Patterns Research Articles

Intelligent rehabilitation assistant: Application of deep learning methods in sports injury recovery

In recent years, sports injury rehabilitation has developed into a specialized field that has forced the combination of an orthopedic surgeon, sports physiotherapist, and sports physician. Determining the appropriate time for an injured athlete to resume practice or competition is regarded as sports rehabilitation. Discovering the best solutions to avoid injuries, maximize recovery, and enhance performance is crucial for sports activities. The study introduced an intelligent rehabilitation assistant (IRA) that leverages advanced deep learning (DL) methods to enhance sports injury recovery. In this study, the IRA incorporates redefined prairie dog optimized bidirectional long-short-term memory (RPDO-Bi-LSTM) to enhance accuracy, predicting sports injury recovery. The study collected data on the state of rehabilitation, physiological parameters, and general health using wearable sensors and movement patterns. The data was preprocessed using a median filter to remove noise from sensor data. Region-based segmentation using segmented images from preprocessed data. Convolutional neural networks (CNN) using extracted features from obtained data. The IRA provides personalized recovery plans and real-time feedback. The framework consists of the components, suggested models to create quality scores for motions, measurements to quantify motion performance, and scoring of performance measurement elements into numerical quality scores. The proposed method is implemented using Python software. RPDO-Bi-LSTM presentation is evaluated by various metrics, such as accuracy 94.2% recall 98.2%, precision 96.5%, and specificity 95.2%, f1 score 95.6%, he planned technique attained good performance and improved the accuracy of sports injury recovery.

The effects of seasonal human mobility and Aedes aegypti habitat suitability on Zika virus epidemic severity in Colombia.

The Zika virus epidemic of 2015-16, which caused over 1 million confirmed or suspected human cases in the Caribbean and Latin America, was driven by a combination of movement of infected humans and availability of suitable habitat for mosquito species that are key disease vectors. Both human mobility and mosquito vector abundances vary seasonally, and the goal of our research was to analyze the interacting effects of disease vector densities and human movement across metapopulations on disease transmission intensity and the probability of super-spreader events. Our research uses the novel approach of combining geographical modeling of mosquito presence with network modeling of human mobility to offer a comprehensive simulation environment for Zika virus epidemics that considers a substantial number of spatial and temporal factors compared to the literature. Specifically, we tested the hypotheses that 1) regions with the highest probability of mosquito presence will have more super-spreader events during dry months, when mosquitoes are predicted to be more abundant, 2) regions reliant on tourism industries will have more super-spreader events during wet months, when they are more likely to contribute to network-level pathogen spread due to increased travel. We used the case study of Colombia, a country with a population of about 50 million people, with an annual calendar that can be partitioned into overlapping cycles of wet and dry seasons and peak tourism and off tourism seasons that drive distinct cyclical patterns of mosquito abundance and human movement. Our results show that whether the first infected human was introduced to the network during the wet versus dry season and during the tourism versus off tourism season profoundly affects the severity and trajectory of the epidemic. For example, Zika virus was first detected in Colombia in October of 2015. Had it originated in January, a dry season month with high rates of tourism, it likely could have infected up to 60% more individuals and up to 40% more super-spreader events may have occurred. In addition, popular tourism destinations such as Barranquilla and Cartagena have the highest risk of super-spreader events during the winter, whereas densely populated areas such as Medellín and Bogotá are at higher risk of sustained transmission during dry months in the summer. Our research demonstrates that public health planning and response to vector-borne disease outbreaks requires a thorough understanding of how vector and host patterns vary due to seasonality in environmental conditions and human mobility dynamics. This research also has strong implications for tourism policy and the potential response strategies in case of an emergent epidemic.

The cohesin complex: structure and principles of interaction with dna

Accurate duplication and separation of long linear genomic DNA molecules is associated with a number of purely mechanical problems. SMC complexes are key components of the cellular machinery that ensures decatenation of sister chromosomes and compaction of genomic DNA during division. Cohesin, one of the essential eukaryotic SMC complexes, has a typical ring structure with intersubunit pore through which DNA molecules can be threaded. The capacity of cohesin for such topological entrapment of DNA is crucial for the phenomenon of post-replicative association of sister chromatids better known as cohesion. Recently, it became apparent that cohesin and other SMC complexes are in fact motor proteins with a very peculiar movement pattern leading to the formation of DNA loops. This specific process was called loop extrusion. Extrusion underlies multiple cohesin’s functions beyond cohesion, but the molecular mechanism of the process remains a mystery. In this review, we have summarized data on the molecular architecture of cohesin, the influence of ATP hydrolysis cycle on this architecture, and the known modes of cohesin–DNA interactions. Many of the seemingly disparate facts presented here will probably be incorporated in a unified mechanistic model of loop extrusion in a not so far future.

Biomechanical factors influencing mental health in college students and the role of physical activity in cognitive resilience

The Mental Health (MH) of college students is increasingly becoming a public health concern, with rising rates of depression, anxiety, and stress. This study aims to explore the relationship between Biomechanical Factors (BF), Physical Activity (PA), and MH outcomes in college students, addressing gaps in current research that frequently overlook the biomechanical features of physical well-being. A cross-sectional observational design was employed, involving 200 college students aged 18–24. SP underwent comprehensive assessments, including postural analysis, movement pattern evaluation, and MH screening. Physical activity levels and cognitive resilience were also measured to evaluate their roles in mediating and moderating the relationships between BF and MH. Key findings revealed that poor biomechanical alignment, such as forward head posture and movement asymmetry, were significantly associated with higher levels of depression, anxiety, and stress. Correlation analysis showed that forward head posture correlated positively with depression (r = 0.52, p < 0.01) and anxiety (r = 0.47, p < 0.01). Movement asymmetry was also associated with MH disturbances (depression: r = 0.45, p < 0.01). PA mediated the relationship between BF and MH, with significant indirect effects via PA for forward head posture (0.18, p < 0.05). Cognitive resilience emerged as a significant moderator, buffering the negative impact of biomechanical inefficiencies on MH outcomes. Within-subject comparisons indicated improvements in BF and MH scores over a one-month follow-up, with decreases in forward head posture (−2.2 ± 1.5 degrees, p < 0.05) and depression scores (−1.5 ± 1.2, p < 0.01).

Dance as mindful movement:a perspective from motor learning and predictive coding.

Defining "dance" is challenging, because many distinct classes of human movement may be considered dance in a broad sense. Although the most obvious category is rhythmic dancing to a musical beat, other categories of expressive movement such as dance improvisation, pantomime, tai chi, or Japanese butoh suggest that a more inclusive conception of human dance is needed. Here we propose that a specific type of conscious awareness plays an overarching role in most forms of expressive movement and can be used to define dance (in the broad sense). We can briefly summarize this broader notion of dance as "mindful movement." However, to make this conception explicit and testable, we need an empirically verifiable characterization of "mindful movement." We propose such a characterization in terms of predictive coding and procedural learning theory: mindful movement involves a "suspension" of automatization. When first learning a new motor skill, we are highly conscious of our movements, and this is reflected in neural activation patterns. As skill increases, automatization and overlearning occurs, involving a progressive suppression of conscious awareness. Overlearned, habitual movement patterns become mostly unconscious, entering consciousness only when mistakes or surprising outcomes occur. In mindful movement, this automatization process is essentially inverted or suspended, reactivating previously unconscious details of movement in the conscious workspace, and crucially enabling a renewed aesthetic attention to such details. This wider perspective on dance has important implications for potential animal analogs of human dance and leads to multiple lines of experimental exploration.

Associations Between Sprint Mechanical Properties and Change of Direction Ability and Asymmetries in COD Speed Performance in Basketball and Volleyball Players

This study aimed to assess the associations between sprint force–velocity profile variables with change of direction (COD) performance and to investigate the impact of these variables on asymmetries in COD speed performance. Ninety-nine participants (volleyball players: n = 44, basketball players: n = 55) performed 40 m sprints for Fv relationship calculation, two COD tests (Modified Agility T-test and 505 test). A partial least squares (PLS) regression analysis was conducted to determine the relationships between the variables. The V0 was the most influential variable; it was negatively associated with COD performance variables (β = −0.260, −0.263 and −0.244 for MAT, 505-D and 505-ND, respectively), and F0 (β = 0.169, 0.163) was associated with the COD performance variables (COD deficit D and COD deficit ND, respectively), slightly larger than the effects of Fvslope (β = −0.162, −0.146), DRF (β = −0.159, −0.142) and Pmax (β = −0.162, −0.146). For COD deficit imbalance, the DRF (β = −0.070) was the most influential variable followed by Fvslope (β = −0.068), F0 (β = 0.046) and gender (β = 0.031). V0 and RFmax were the critical variables for improving COD performance that includes linear sprints, while DRF, Fvslope, F0 and Pmax collectively influence 180° COD performance. Meanwhile, DRF and Fvslope were important factors for asymmetries in COD speed performance. It is recommended to use the Fv profile to diagnose different COD movement patterns and then develop training plans accordingly for team sports played on smaller courts, such as basketball and volleyball.

Decoding Motor Skills: Video Analysis Unveils Age-Specific Patterns in Childhood and Adolescent Movement

Motor skill development is crucial in human growth, evolving with the maturation of the nervous and musculoskeletal systems. Quantifying these skills, especially coordinative abilities, remains challenging. This study aimed to assess the performance of five motor tasks in children and adolescents using high-speed video analysis, providing data for movement and health professionals. Seventy-two volunteers were divided into three age groups: 27 first-grade primary school students (19 males and 8 females, aged 6.5 ± 0.5 years), 35 fourth-grade primary school students (16 males and 19 females, aged 9.2 ± 0.4 years), and 28 s-year middle school students (16 males and 12 females, aged 13.0 ± 0.3 years). Participants performed five motor tasks: standing long jump, running long jump, stationary ball throw, running ball throw, and sprint running. Each task was recorded at 120 frames per second and analyzed using specialized software to measure linear and angular kinematic parameters. Quantitative measurements were taken in the sagittal plane, while qualitative observations were made using a dichotomous approach. Statistical analysis was performed using the Kruskal–Wallis and Mann–Whitney tests with Bonferroni correction. Significant differences were observed across age groups in various parameters. In the standing long jump, older participants exhibited a longer time between initial movement and maximum loading. The running long jump revealed differences in the take-off angle, with fourth-grade students performing the best. Ball-throwing tests indicated improvements in the release angle with age, particularly in females. Sprint running demonstrated the expected improvements in time and stride length with age. Gender differences were notable in fourth-grade students during the running long jump, with females showing greater knee flexion, while males achieved better take-off angles. Video analysis effectively identified age-related and gender-specific differences in motor skill performance. The main differences were measured between first-grade primary school and second-year middle school students while gender differences were limited to all age groups. This method provides valuable insights into motor development trajectories and can be used by professionals to objectively assess and monitor the technical aspects of motor skills across different age groups.

Eye Movement Patterns in Russian-Speaking Adolescents with Differing Reading Comprehension Proficiency: Exploratory Scanpath Analysis

Previous research has indicated that individuals with varying levels of reading comprehension (often used as a proxy for general cognitive ability) employ distinct reading eye movement patterns. This exploratory eye-tracking study aimed to investigate the text-reading process in adolescents with differing reading comprehension, specifically examining how these differences manifest at the global eye movement level through scanpath analysis. Our findings revealed two distinct groups of scanpaths characterized by statistically significant differences in eye movement parameters. These groups were identified as “fast readers” and “slow readers”. Both groups exhibited similar oculomotor performance during the initial reading. However, significant differences emerged when they reread and revisited the text. Notably, these findings align with prior research conducted with different samples and languages, although discrepancies emerged in saccade amplitude and first-pass reading behavior. This study contributes to the understanding of how reading comprehension levels are reflected in global eye movement strategies among adolescents. However, limitations inherent in the experimental design, particularly the potential influence of the task on reading patterns, warrant further investigation. Future research should aim to explore these phenomena in more naturalistic reading settings, employing a design specifically tailored to capture the nuances of spontaneous reading behavior.

Fixation patterns in pairs of facial expressions—preferences of self-critical individuals

So far, studies have revealed some differences in how long self-critical individuals fixate on specific facial expressions and difficulties in recognising these expressions. However, the research has also indicated a need to distinguish between the different forms of self-criticism (inadequate or hated self), the key underlying factor in psychopathology. Therefore, the aim of the current research was to explore fixation patterns for all seven primary emotions (happiness, sadness, fear, disgust, contempt, anger, and surprise) and the neutral face expression in relation to level of self-criticism by presenting random facial stimuli in the right or left visual field. Based on the previous studies, two groups were defined, and the pattern of fixations and eye movements were compared (high and low inadequate and hated self). The research sample consisted of 120 adult participants, 60 women and 60 men. We used the Forms of Self-Criticizing and Self-Reassuring Scale to measure self-criticism. As stimuli for the eye-tracking task, we used facial expressions from the Umeå University Database of Facial Expressions database. Eye movements were recorded using the Tobii X2 eye tracker. Results showed that in highly self-critical participants with inadequate self, time to first fixation and duration of first fixation was shorter. Respondents with higher inadequate self also exhibited a sustained pattern in fixations (total fixation duration; total fixation duration ratio and average fixation duration)—fixation time increased as self-criticism increased, indicating heightened attention to facial expressions. On the other hand, individuals with high hated self showed increased total fixation duration and fixation count for emotions presented in the right visual field but did not differ in initial fixation metrics in comparison with high inadequate self group. These results suggest that the two forms of self-criticism - inadequate self and hated self, may function as distinct mechanisms in relation to emotional processing, with implications for their role as potential transdiagnostic markers of psychopathology based on the fixation eye-tracking metrics.

Anticipatory postural adjustment deficits in children with developmental coordination disorder during a self-induced prehension task while standing on one leg

Effective postural control is essential for motor skill development, yet the specific nature of anticipatory control in children with Developmental Coordination Disorder (DCD) remains poorly understood for complex or dynamic stability tasks. This study investigated anticipatory postural adjustments (APA) during a self-initiated dynamic stability task. The Can Placement Task (CPT)—a self-initiated dynamic stability task—was performed by 23 children with DCD and 30 typically developing (TD) children aged 9–12 years. The task involved standing on one leg while also repositioning a can on the floor. Center of pressure (COP) movement was recorded by two force platforms during the five phases of the movement. The ground reaction force measured external support during both descent to pick up the can and ascent after replacing the can. The study used a mixed-design approach with group (DCD, TD) as a between-subject factor and condition (can position close or far) and phase of movement as within-subject. Distinct movement control characteristics were shown for children with DCD including a greater range of COP movement and higher COP velocity in the anterior-posterior direction prior to movement initiation compared with TD. The DCD group also relied more on external support during both the downward and upward phases of the CPT and needed more trials to complete the task. Only two significant interaction effects involving Group and the within-subject factors emerged. Children with DCD swayed significantly more at specific phases of the task, especially when coming up and restoring balance, and did not adapt COP velocity as a function of reaching distance. Dynamic control of posture in children with DCD is impaired as they struggle to generate the effective APAs necessary to maintain dynamic stability which leads to greater reliance on external support and more corrective movements. The CPT provides a valuable assessment of posture and dynamic balance control during a complex prehension movement performed on one leg; the task highlights distinct movement patterns between children with and without DCD.

Analysis of pedestrian crossing violations at an overpass location by using a logit model

Jaywalking significantly increases accident risks compared to marked crosswalks. Overpasses are often installed to address this, but violations continue. This study examines pedestrian behavior at overpass locations, focusing on 438 individuals recorded on video. Factors like parked vehicles, gender, age, group size, mobile phone distraction, carrying items, the number of waiting pedestrians upon arrival, waiting times, and traffic volume were analyzed. Since jaywalking is more frequent during off-peak hours when traffic is not congested, observations were made at random intervals during these times. A binary logit model was used to identify the factors influencing jaywalking. The study found that points of interest near overpasses significantly affect pedestrian behavior. Additionally, parked vehicles near the overpass reduce crossing distance, encouraging jaywalking. Policy recommendations include implementing parking restrictions and strategically locating overpasses to align with pedestrian movement patterns and nearby points of interest.

Relationships Between Functional Movement Quality and Sports Performance in Elite Figure Skating Athletes of China.

Zhitao, L, Junlong, D, Rui, Y, Leijiao, Y, Cheng, G, and Jun, Y. Relationships between functional movement quality and sports performance in elite figure skating athletes of China. J Strength Cond Res 38(11): e678-e685, 2024-This study aimed to determine the optimal functional movement screen (FMS) cut score for assessing the risk of sports injuries and to explore the correlations between functional movement quality and sports performance among elite figure skaters. A total of 22 elite figure pairs skaters in China underwent FMS, sports performance, and clinical examinations for sports injuries. The FMS cut score was determined using the receiver operating characteristic curve. Pearson's rank correlation analysis was used to quantify associations between the variables. (a) The optimal FMS cut score for assessing the risk of sports injuries was 13 (p = 0.008), with an area under curve of 0.838. The sensitivity and specificity were 0.889 and 0.692, respectively. (b) The trunk stability push-up (TSPU), an individual FMS test, predicted injuries in figure skaters (p = 0.015). (c) Moderate correlations were found between shoulder mobility and bench strength (r = -0.453, p = 0.034), counter movement jump (r = -0.582, p = 0.007), and 30-m sprint (r = 0.567, p = 0.009). A strong correlation was observed with squat jump (r = -0.774, p = 0.001). In addition, TSPU scores moderately correlated with 30-m sprint times (r = -0.511, p = 0.021) and 30-s average anaerobic power (r = 0.503, p = 0.024). These findings indicate that both the FMS total score ≤13 and the FMS individual score serve as indicators of injury risk in figure skaters. However, only the FMS individual score reflected the sports performance. This likely results from the similarity in kinetic chain systems and movement patterns involved in both the FMS individual test and sports performance, suggesting a promising assessment strategy for sports performance.

THE ESSENTIAL ROLE OF PHYSIOTHERAPY IN PROFESSIONAL FOOTBALL

The role of physiotherapists in professional football is critical for both the physical recovery of athletes and the implementation of strategies that promote injury prevention and enhance performance. With a comprehensive understanding of biomechanics and movement principles, physiotherapists can assess players’ performance and work closely with coaching staff to devise effective game tactics. Their expertise enables them to identify movement patterns and areas of stress that can lead to injuries, ultimately helping to minimize these risks. Education plays a vital part in the physiotherapist's responsibilities, as they teach athletes about health maintenance and the significance of injury prevention. This educational component is essential for ensuring that players can sustain a long and successful sports career. Despite progress in prevention and rehabilitation practices, studies reveal persistent gaps between clinical practice and scientific evidence. Increased regulation of the profession, coupled with a multidisciplinary approach that incorporates psychological support, emphasizes the growing importance of physiotherapy within football. Moreover, recognizing the psychological factors that influence recovery and utilizing evidence-based protocols are vital for optimizing rehabilitation outcomes. The physiotherapist’s influence extends beyond physical recovery; they are integral in fostering the overall health and well-being of athletes, which significantly impacts team performance. Moving forward, the field of physiotherapy in football must prioritize continuous professional development, the adoption of innovative practices, and the establishment of an environment that values both the physical and mental health of players.

Research on Motion Patterns of Soft Robots Based on Bionic Structure

Bionic soft robot is a new type of robot whose main body is composed of flexible material, with the advantages of adjustable size and strong environmental adaptability, which has a broad application prospect in logistics, medical care, resource exploration and other fields. Novel smart materials also shine in the design of soft robots. This paper highlights the research advancements in the locomotion patterns of bionic soft robots. The mechanism of movement of animals such as inchworms, starfish, earthworms, etc. and the soft robots designed to imitate them are introduced. Novel smart materials required to realise these designs, such as Shape Memory Alloy (SMA), dielectric elastomer (DE), a collapsible actuator (PFA), pNIPAM/CNTs hydrogel composite, are also presented. Methods to drive and control the motion of these soft robots are presented, including thermally driven shape memory alloys, pneumatic airbags, and laser-driven, magnetic field-driven, and electrically driven dielectric materials, among other types. After discussing the materials and methods, the current challenges to the innovation of motion patterns for bionic soft robots are analyzed.

Predict the musculoskeletal injuries in young skaters using Functional Movement Screen (FMSTM)

Background. Skating is a great way to improve heart rate, coordination, and strengthen the muscles, and burn calories. It works on the muscles of the legs, gluteus, and core and causes 50% less stress to the joints than running, along with improving flexibility and endurance. The FMS™ is a clinical screening tool used to assess seven fundamental movement patterns. It consists of overhead deep squats, hurdle steps, inline lunges, straight leg raises, trunk stability pushups, shoulder mobility, and rotary stability. Injuries are more common in sports, especially skating, where balance and coordination are required. A study like this is necessary to screen skaters, help predict injuries, and train them accordingly to prevent injuries. Objective. The objective is to predict musculoskeletal injuries in young skaters using the Functional Movement Screen (FMS™). Methodology. This is an observational cross-sectional study. Sixty-four skaters of both genders, aged between 6 and 18 years, were conveniently selected based on the inclusion and exclusion criteria and were assessed using FMS™. Outcome measures. Functional Movement Screening scores. Results. 31.3% of young skaters scored between 0 and 13 and are at high risk for musculoskeletal injuries, while 68.8% are at a low risk of injury with FMS™ scores ranging from 14 to 21. Conclusion. This study concluded that 31.3% of young skaters have a high risk for musculoskeletal injuries according to the Functional Movement Screen.

Chronic Pain Influences Lower Extremity Energetics During Landing Cutting in Patients with Chronic Ankle Instability.

Chronic ankle instability (CAI) patients exhibit altered movement patterns during jump landing/cutting movements. Persistent pain is one of the residual symptoms that may affect movements. Calculating joint energetics affected by chronic pain offers a novel method to understand how chronic pain influences energetics of lower extremity joints in CAI patients. To identify the effects of chronic pain on lower extremity energy dissipation and generation during jump landing and cutting in CAI patients. Cross-sectional Study. Laboratory. Fifteen CAI patients with higher pain (6 males, 9 females; age=22.1±2.1year; height=1.74±0.09m; mass=71.3±10.6kg, pain=66.9±9.4), 15 CAI patients with lower pain (6 males, 9 females; age=22.3±2.1year; height=1.74±0.08m; mass=70.1±10.7kg, pain=89.3±2.6), and 15 healthy controls (6 males, 9 females; age=21.3±1.7year; height=1.73±0.08m; mass=70±10.3kg, pain=100±0). Ground reaction force data were collected during 5 trials of maximal jump landing/cutting tasks. Joint power was defined as the product of angular velocity and joint moment. Energy dissipation and generation by the ankle, knee, and hip joints were calculated by integrating regions of the joint power curve. CAI patients with higher pain displayed less ankle energy dissipation (p=.013 and p=.018) and generation in the ankle (p=.002 and p=.028) than CAI patients with lower pain and healthy controls during the jump landing/cutting phase. CAI patients with higher pain showed more hip energy generation than CAI patients with lower pain (P=.038) and healthy controls (P=.013) during the cutting phase. CAI patients with higher pain changed both energy dissipation and generation in the lower extremities, reducing the burden of the ankle joint during jump landing/cutting and having a hip dominant compensatory strategy during the cutting phase. Our results suggest that chronic pain could be one of the factors that affect motor strategies in the CAI population.

Terra incognita of the uncontrolled manifold (UCM).

The review addresses the central concept of the uncontrolled manifold (UCM) hypothesis, which has become a major framework for analysis of performance-stabilizing motor synergies. The major goals are to summarize the status quo in the field and to ask new questions stimulating new studies. We focus on a few main questions: What is the UCM? What are the likely neural origins of the UCM? How is the UCM reflected in movement patterns? Are properties of the UCM similar in all directions? We contrast experience-based features of movements seen very soon after the movement initiation vs. those based on on-line sensory feedback signals. Further, we address a number of poorly explored issues such as the differences in characteristic times of processes within the UCM and orthogonal to the UCM space, the interplay between movement stability and optimality, the origin of preferred sharing patterns of performance variables across abundant sets of elements and of their inter-trial variability, problems with the UCM-based analysis in different spaces, and likely neurophysiological mechanisms contributing to the UCM formation. In particular, we focus on the UCM in spaces of hypothetical neural control variables, which we associate with the reciprocal and coactivation commands to the effectors. Analysis of performance-stabilizing synergies within the UCM framework in abundant spaces of kinetic, kinematic and electromyographic variables at the selected level of analysis may be practically useful. However, mapping findings in such studies onto neural control mechanisms has been challenging.

Few-shot Learning for Sign Language Recognition with Embedding Propagation

Sign language is a primary channel for the deaf and hard-hearing to communicate. Sign language consists of many signs with different variations in hand shapes, motion patterns, and positioning of hands, faces, and body parts. This makes sign language recognition (SLR) a challenging field in computer vision research. This paper tackles the problem of few-shot SLR, where models trained on known sign classes are utilized to recognize instances of unseen signs with only a few examples. In this approach, a transformer encoder is employed to learn the spatial and temporal features of sign gestures, and an embedding propagation technique is used to project these features into the embedding space. Subsequently, a label propagation method is applied to smooth the resulting embeddings. The obtained results demonstrate that combining embedding propagation with label propagation enhances the performance of the SLR system and achieved an accuracy of 76.6%, which surpasses the traditional few-shot prototypical network's accuracy of 72.4%.

Victim, perpetrator, or witness of peer sexual harassment? Middle-school students’ movements between roles across time

ABSTRACT Previous research on peer sexual harassment at school has mostly considered students’ involvement in the victim role while overlooking the roles of witnessing and perpetration, and students’ movements between different roles over time. In this two-wave longitudinal study (N = 783) conducted in Sweden, we examined students’ involvement in peer sexual harassment from ages 10 to 11 years to identify patterns of movements within and between roles. Through illustrations and Configural Frequency Analysis, we identified three central patterns. First, many students remained in the same roles across time, especially those who were involved in a combination of roles. Secondly, students often first encountered peer sexual harassment by witnessing it and then became targets themselves. Finally, students who perpetrated peer sexual harassment often had previous experience with other roles in peer sexual harassment. The findings suggest that social learning processes may influence how students move between different roles over time.

Social interactions and movement patterns of rangeland-raised beef cows and their calves

Understanding the spatial and temporal relationships between beef calves and their dams is crucial for effective rangeland management. This study investigated these dynamics on semiarid rangeland using GPS collars fitted on cow-calf pairs. Data were collected on 46 crossbred cows and 34 calves grazing two adjacent 219 and 146 ha pastures. The primary objective was to determine the proximity of calves to their dams and other adult cows at different calf ages (1, 2 and 4 mos.). Over a 24 h period, calves spent on average 10.5 and 17.5 h within 5 or 10 m of an adult cow, respectively, and spent 2.6, 5.6 and 2.3 h within 5 m of their dams, other adult cows and a guard cow (cow other than the dam that spent the most time in the proximity of a calf), respectively. Calves spent more time within 5 or 10 m of an adult cow during night vs. daytime hours and spent detectably (P < 0.05) more time within 5 or 10 m of other adult cows vs. their dam (5.6 vs. 2.6 or 10.3 vs. 3.5 h). Calves spent a similar (P > 0.05) amount of time within 5 or 10 m of their dam vs. the guard cow (2.6 vs. 2.3 or 3.5 vs. 3.7 h) regardless of age during both day and nighttime hours. In general, calves spent more time within 5 and 10 m of an adult cow at 2 vs. 1 or 4 mos. of age. Greater mother-offspring clustering occurred at 2 vs. 1 or 4 mos. of age regardless of the spatial threshold considered. Regardless of calf age, calves and nursing cows traveled on average 4.5 and 6.7 km/day, respectively. Calves at 4 mo of age traveled farther than younger calves. Nursing cows traveled farther when calves were 4 mo. vs. 1 or 2 mos. of age and tended to travel farther when calves were 1 vs. 2 mos. old. Calves spent more time close to other nursing cows vs. their dam. These findings suggest that while dams play a crucial role in calf development, other nursing cows may also influence their foraging behaviors. Further research is needed to fully understand the dynamics of these relationships and their implications for rangeland management, such as optimizing grazing strategies and improving calf health and productivity.