Walking Direction Research Articles

Explaining deep learning models for age-related gait classification based on acceleration time series

BackgroundGait analysis holds significant importance in monitoring daily health, particularly among older adults. Advancements in sensor technology enable the capture of movement in real-life environments and generate big data. Machine learning, notably deep learning (DL), shows promise to use these big data in gait analysis. However, the inherent black-box nature of these models poses challenges for their clinical application. This study aims to enhance transparency in DL-based gait classification for aged-related gait patterns using Explainable Artificial Intelligence, such as SHapley Additive exPlanations (SHAP). MethodsIn this cross-sectional study, a total of 244 participants, comprising 129 adults and 115 older adults (age>65), were included. They performed a 3-min walking task while accelerometers were affixed to the lumbar segment L3. DL models, convolutional neural network (CNN) and gated recurrent unit (GRU), were trained using 1-stride and 8-stride accelerations, respectively, to classify adult and older adult groups. SHAP was employed to explain the models' predictions. ResultsCNN achieved a satisfactory performance with an accuracy of 81.4 % and an AUC of 0.89, and GRU demonstrated promising results with an accuracy of 84.5 % and an AUC of 0.94. SHAP analysis revealed that both CNN and GRU assigned higher SHAP values to the data from vertical and walking directions, particularly emphasizing data around heel contact, spanning from the terminal swing to loading response phases. Furthermore, SHAP values indicated that GRU did not treat every stride equally. ConclusionCNN accurately distinguished between adults and older adults based on the characteristics of a single stride's data. GRU achieved accurate classification by considering the relationships and subtle differences between strides. In both models, data around heel contact emerged as most critical, suggesting differences in acceleration and deceleration patterns during walking between different age groups.

Optimization of bus stop layout considering multiple factors including passenger flow direction.

Bus stop layout typically requires consideration of urban population distribution, traffic conditions, and passenger flow demand to establish an efficient foundation for the bus system's operation. Based on the above key factors, this paper introduces a strategic method to optimize the bus stop layout from a macro perspective in order to save passengers' travel time and improve the attractiveness of the bus system. This approach accounts for the matching degree between the Origin-Destination (OD) direction of passengers and their walking direction heading to bus stops. Initially, we take into account factors such as the population and area of traffic districts, and urban road conditions. Utilizing the hypernetwork multidimensional data clustering method along with GIS technology, we construct an alternative set of bus stops based on the hypernetwork framework. This set serves as a reference for the positioning of newly built and moved bus stops. Subsequently, we develop a two-stage model for bus stop layout decision-making. The first stage focuses on determining the bus stop layout at the traffic district level, taking into account multi-factors including the passenger flow matching degree. The second stage is designed to mitigate the negative impact of bus stop optimization on the overall service level of the urban bus system. A case study conducted in XT city demonstrates the effectiveness of our approach. Post-optimization, there is a 15.83% increase in the alignment between passenger flow direction and bus stop layout. Additionally, the average travel time for passengers is reduced by 7.55 minutes.

Natural variability and individuality of walking behavior in Drosophila.

Insects use walking behavior in a large number of contexts, such as exploration, foraging, escape and pursuit, or migration. A lot is known on how nervous systems produce this behavior in general and also how certain parameters vary with regard to walking direction or speed, for instance. An aspect that has not received much attention is if and how walking behavior varies across individuals of a particular species. To address this, we created a large corpus of kinematic walking data of many individuals of the fruit fly Drosophila. We only selected instances of straight walking in a narrow range of walking speeds to minimize the influence of high-level parameters, like turning and walking speed, aiming to uncover more subtle aspects of variability. Using high-speed videography and automated annotation we captured the positions of the six leg tips for thousands of steps and used principal components analysis to characterize the postural space individuals used during walking. Our analysis shows that the largest part of walking kinematics can be described by five principal components (PCs). Separation of these five PCs into a 2-dimensional and a 3-dimensional subspace divided the description of walking behavior into invariant features shared across individuals and features that relate to the specifics of individuals; the latter features can be regarded as idiosyncrasies. We also demonstrate that this approach can detect the effects of experimental interventions in an unbiased manner and that general aspects of individuality, such as the the individual walking posture, can be described.

Visual mental imagery of nonpredictive central social cues triggers automatic attentional orienting

Previous research has demonstrated that social cues (e.g., eye gaze, walking direction of biological motion) can automatically guide people's focus of attention, a well-known phenomenon called social attention. The current research shows that voluntarily generated social cues via visual mental imagery, without being physically presented, can produce robust attentional orienting similar to the classic social attentional orienting effect. Combining a visual imagery task with a dot-probe task, we found that imagining a non-predictive gaze cue could orient attention towards the gazed-at hemifield. Such attentional effect persisted even when the imagery gaze cue was counter-predictive of the target hemifield, and could be generalized to biological motion cue. Besides, this effect could not be simply attributed to low-level motion signal embedded in gaze cues. More importantly, an eye-tracking experiment carefully monitoring potential eye movements demonstrated the imagery-induced attentional orienting effect induced by social cues, but not by non-social cues (i.e., arrows), suggesting that such effect is specialized to visual imagery of social cues. These findings accentuate the demarcation between social and non-social attentional orienting, and may take a preliminary step in conceptualizing voluntary visual imagery as a form of internally directed attention.

SWiLoc: Fusing Smartphone Sensors and WiFi CSI for Accurate Indoor Localization.

Dead reckoning is a promising yet often overlooked smartphone-based indoor localization technology that relies on phone-mounted sensors for counting steps and estimating walking directions, without the need for extensive sensor or landmark deployment. However, misalignment between the phone's direction and the user's actual movement direction can lead to unreliable direction estimates and inaccurate location tracking. To address this issue, this paper introduces SWiLoc (Smartphone and WiFi-based Localization), an enhanced direction correction system that integrates passive WiFi sensing with smartphone-based sensing to form Correction Zones. Our two-phase approach accurately measures the user's walking directions when passing through a Correction Zone and further refines successive direction estimates outside the zones, enabling continuous and reliable tracking. In addition to direction correction, SWiLoc extends its capabilities by incorporating a localization technique that leverages corrected directions to achieve precise user localization. This extension significantly enhances the system's applicability for high-accuracy localization tasks. Additionally, our innovative Fresnel zone-based approach, which utilizes unique hardware configurations and a fundamental geometric model, ensures accurate and robust direction estimation, even in scenarios with unreliable walking directions. We evaluate SWiLoc across two real-world environments, assessing its performance under varying conditions such as environmental changes, phone orientations, walking directions, and distances. Our comprehensive experiments demonstrate that SWiLoc achieves an average 75th percentile error of 8.89 degrees in walking direction estimation and an 80th percentile error of 1.12 m in location estimation. These figures represent reductions of 64% and 49%, respectively for direction and location estimation error, over existing state-of-the-art approaches.

Towards human-centric warehousing: the impact of rack configuration and cognitive demands on order picking performance

Within warehouse logistics processes, design concepts and management decisions regarding operations systems determine the demands placed on human operators. While the literature proposes that human-centric work system design positively affects the operator, the impact on operator performance remains under-explored. We analyse the case of a German retail warehouse where the shelf numbering follows the pickers' walking direction from right to left. However, all human order pickers working in this system are familiar with a left-to-right writing system due to their schooling and training. Because cognitive psychology proposes that writing system direction impacts spatial orientation in goal-oriented visual search, we are motivated to explore the interplay of rack configuration and human cognitive demands. We ground our mixed-effects model on archival data, including 470,968 storage location visits. Our results indicate that order pickers work 18.7% faster when picking items starting from the left side of the shelf compared to starting their visual search from the right side. Our findings suggest that human search strategies in warehousing operations are influenced by attention templates like writing direction on a similar level as by system design elements of the warehouse itself. This insight underscores the potential for diversified future human-centric design approaches in warehouse logistics.

Evaluating the impact of human movement-induced airflow on particle dispersion: A novel real-time validation using IoT technology

Human movement significantly influences local airflow and particle dispersion in indoor environments. Therefore, this study integrates the dynamics of human walking into the analysis of airborne infection risks in a positive pressure isolation ward designed for the protection of immunocompromised patients. Real-time data collection was performed using an anemometer and IoT-based PM sensors to measure airflow velocities and particulate matter (PM) concentrations within a full-scale experimental chamber. Computational Fluid Dynamics (CFD) was used for the numerical simulations, and a User-Defined Function (UDF) code simulated the translational movement of a manikin. The results demonstrated strong agreement with the experimental data, thereby validating the airflow turbulence and Lagrangian-based Discrete Phase Model (DPM) in predicting the airflow velocities and particle transport. The study revealed that human walking substantially enhanced particle dispersion distance by 10-fold compared to static conditions, primarily attributed to intensified air mixing induced by the body movement. Furthermore, the CFD analysis underscored that the direction of walking plays a crucial role in airborne transmission. Specifically, walking away from a patient did not elevate infection risk, whereas approaching a patient significantly increased particle deposition in the patient-occupied region. This study highlights the critical need to consider both movement patterns and directional flow in managing airborne infection risks, contributing to the development of more effective infection control strategies in healthcare settings.

Sensory feedback and central neuronal interactions in mouse locomotion.

Locomotion is a complex process involving specific interactions between the central neural controller and the mechanical components of the system. The basic rhythmic activity generated by locomotor circuits in the spinal cord defines rhythmic limb movements and their central coordination. The operation of these circuits is modulated by sensory feedback from the limbs providing information about the state of the limbs and the body. However, the specific role and contribution of central interactions and sensory feedback in the control of locomotor gait and posture remain poorly understood. We use biomechanical data on quadrupedal locomotion in mice and recent findings on the organization of neural interactions within the spinal locomotor circuitry to create and analyse a tractable mathematical model of mouse locomotion. The model includes a simplified mechanical model of the mouse body with four limbs and a central controller composed of four rhythm generators, each operating as a state machine controlling the state of one limb. Feedback signals characterize the load and extension of each limb as well as postural stability (balance). We systematically investigate and compare several model versions and compare their behaviour to existing experimental data on mouse locomotion. Our results highlight the specific roles of sensory feedback and some central propriospinal interactions between circuits controlling fore and hind limbs for speed-dependent gait expression. Our models suggest that postural imbalance feedback may be critically involved in the control of swing-to-stance transitions in each limb and the stabilization of walking direction.

Effects of direction cue time and walking speed on spatial-temporal gait adaptations in healthy older and young adults upon approach of turns

Background:Hurrying and turning are each associated with falls in older adults. Losing balance sideways when turning increases the likelihood of hip fracture. Yet 99 % of failures when turning unexpectedly have been traced to an inability to curb forward momentum regardless of age. Research questionDo age-based differences exist in spatial-temporal gait adaptations related to medial-lateral (M-L) balance and posterior-anterior (P-A) propulsion upon approach of turns relative to continuing straight, across walking speeds and whether direction is known in advance? MethodsHealthy young (n=10) and older adults (n = 10) walked at preferred and fast test speeds while randomly cued for direction either early upon initiating gait or late 1–2 steps before entering a spatially defined turning area. An instrumented 4.6 m carpet recorded spatial-temporal changes up to the penultimate footfall prior to turning 900 or continuing straight. ResultsWhen approaching the turning zone across interactions of walking test speed, cue time and direction, other than stride-length being shorter in older adults, both age-groups showed similar adjustments in gait speed and stride-length in managing P-A deceleration perturbations, and similar adaptations in right and left heel-to-heel base of support (BOS) in managing M-L balance destabilizing forces. A three-way interaction (p<.027) suggests a similar foot strategy of BOS narrowing may be used approaching turns relative to straight walks when direction is cued early walking fast (p<.020) and late walking preferred speed (p<.014). SignificanceThe findings were interpreted within the context of regulating center of mass acceleration and processing environmental regulatory conditions to maintain a personal space safety margin. The study supports that in otherwise healthy older adults, gait training for turns include practice to not only manage perturbations which accelerate the body sideways but also those which decelerate forward progression.

CBHQD: A channel state information-based passive line-of-sight human queue detection

As the number of monitored individuals rises and multipath effects disrupt signals, existing queue monitoring solutions fail to meet efficiency needs. This paper proposes a passive line-of-sight (LOS) human queue detection method based on channel state information (CSI), namely CBHQD. We present a novel time series crowd detection network (TSCD-Net), incorporating genetic algorithm, LSTM, and FC layers to automatically extract amplitude and phase features from CSI, enhancing the simulation of indoor conditions. The genetic algorithm effectively addresses the challenge of local optima, while the fully connected layers excel in dimension reduction, facilitating the integration of valuable information obtained from LSTM. Additionally, we design the Fresnel zone detection, merging the Fresnel zone model with WiFi to estimate people's walking direction, thereby maximizing the accuracy performance of crowd detection. Lastly, we validate the feasibility and efficiency of our approach in a realistic testbed, demonstrating its suitability for detecting larger numbers of individuals.

The combination operation of grouping and ensemble coding for structured biological motion crowds in working memory

Massive studies have explored biological motion (BM) crowds processing for their remarkable social significance, primarily focused on uniformly distributed ones. However, real-world BM crowds often exhibit hierarchical structures rather than uniform arrangements. How such structured BM crowds are processed remains a subject of inquiry. This study investigates the representation of structured BM crowds in working memory (WM), recognizing the pivotal role WM plays in our social interactions involving BM. We propose the group-based ensemble hypothesis and test it through a member identification task. Participants were required to discern whether a presented BM belonged to a prior memory display of eight BM, each with distinct walking directions. Drawing on prominent Gestalt principles as organizational cues, we constructed structured groups within BM crowds by applying proximity and similarity cues in Experiments 1 and 2, respectively. In Experiment 3, we deliberately weakened the visibility of stimuli structures by increasing the similarity between subsets, probing the robustness of results. Consistently, our findings indicate that BM aligned with the mean direction of the subsets was more likely to be recognized as part of the memory stimuli. This suggests that WM inherently organizes structured BM crowds into separate ensembles based on organizational cues. In essence, our results illuminate the simultaneous operation of grouping and ensemble encoding mechanisms for BM crowds within WM.

Monitoring the world-oldest zoo-housed male giant panda (Ailuropoda melanoleuca): A case-study on pathway utilization.

Habitat use monitoring is necessary for a comprehensive understanding of the biological and psychological requirements of animals under human care, facilitating improved exhibit designs and promoting animal welfare. Current studies focused on the space use of the exhibit while limited studies examined the pathway use of the zoo-housed animals. This study aimed to investigate the habitat use of An An, the world-oldest male giant panda (Ailuropoda melanoleuca) at Ocean Park Hong Kong using a pathway utilization monitoring method. The result showed uneven utilization of pathways favoring the upper area near his den over the lower area which required longer walking in the hilly exhibit. Moreover, the comparisons of walking directions showed a preference for gentle slopes during uphill movement and a favor for steep slopes during downhill movement. Our study also compared the walking distance between uphill and downhill movements and the results showed that An An walked longer distances heading upward than moving downward due to his choice of pathways. Our results are in line with the findings in the wild population, showing a preference for gentle slopes, especially in uphill movement. Our study demonstrated the value of the pathway monitoring technique. Due to its easy and time-effective use, this technique can be incorporated into the care teams' operation, providing valuable information on daily activity (e.g. accessing the walking ability of the aged animals by investigating the pathway use and walking distance) and habitat use. Consequently, the pathway monitoring technique can help improve exhibit designs promoting welfare.

Real-Time Tracking Data and Machine Learning Approaches for Mapping Pedestrian Walking Behavior: A Case Study at the University of Moratuwa.

The growing urban population and traffic congestion underline the importance of building pedestrian-friendly environments to encourage walking as a preferred mode of transportation. However, a major challenge remains, which is the absence of such pedestrian-friendly walking environments. Identifying locations and routes with high pedestrian concentration is critical for improving pedestrian-friendly walking environments. This paper presents a quantitative method to map pedestrian walking behavior by utilizing real-time data from mobile phone sensors, focusing on the University of Moratuwa, Sri Lanka, as a case study. This holistic method integrates new urban data, such as location-based service (LBS) positioning data, and data clustering with unsupervised machine learning techniques. This study focused on the following three criteria for quantifying walking behavior: walking speed, walking time, and walking direction inside the experimental research context. A novel signal processing method has been used to evaluate speed signals, resulting in the identification of 622 speed clusters using K-means clustering techniques during specific morning and evening hours. This project uses mobile GPS signals and machine learning algorithms to track and classify pedestrian walking activity in crucial sites and routes, potentially improving urban walking through mapping.

Empowering the Blind: Contactless Activity Recognition with Commodity Software-Defined Radio and Ultra-High-Frequency Radio Frequency Identification.

This study presents a novel computational radio frequency identification (RFID) system designed specifically for assisting blind individuals, utilising software-defined radio (SDR) with coherent detection. The system employs battery-less ultra-high-frequency (UHF) tag arrays in Gen2 RFID systems, enhancing the transmission of sensed information beyond standard identification bits. Our method uses an SDR reader to efficiently manage multiple tags with Gen2 preambles implemented on a single transceiver card. The results highlight the system's real-time capability to detect movements and direction of walking within a four-meter range, indicating significant advances in contactless activity monitoring. This system not only handles the complexities of multiple tag scenarios but also delineates the influence of system parameters on RFID operational efficiency. This study contributes to assistive technology, provides a platform for future advancements aimed at addressing contemporary limitations in pseudo-localisation, and offers a practical, affordable assistance system for blind individuals.

Effect of spatial context on perceived walking direction.

Contextual modulation occurs for many aspects of high-level vision but is relatively unexplored for the perception of walking direction. In a recent study, we observed an effect of the temporal context on perceived walking direction. Here, we examined the spatial contextual modulation by measuring the perceived direction of a target point-light walker in the presence of two flanker walkers, one on each side. Experiment 1 followed a within-subjects design. Participants (n = 30) completed a spatial context task by judging the walking direction of the target in 13 different conditions: a walker alone in the center or with two flanking walkers either intact or scrambled at a flanker deviation of ±15°, ±30°, or ±45°. For comparison, participants completed an adaptation task where they reported the walking direction of a target after adaptation to ±30° walking direction. We found the expected repulsive effects in the adaptation task but attractive effects in the spatial context task. In Experiment 2 (n = 40), we measured the tuning of spatial contextual modulation across a wide range of flanker deviation magnitudes ranging from 15° to 165° in 15° intervals. Our results showed significant attractive effects across a wide range of flanker walking directions with the peak effect at around 30°. The assimilative versus repulsive effects of spatial contextual modulation and temporal adaptation suggest dissociable neural mechanisms, but they may operate on the same population of sensory channels coding for walking direction, as evidenced by similarity in the peak tuning across the walking direction of the inducers.

Geometrical multiscale tortuosity of desert ant walking trajectories.

Desert ants stand out as some of the most intriguing insect navigators, having captured the attention of scientists for decades. This includes the structure of walking trajectories during goal approach and search behaviour for the nest and familiar feeding sites. In the present study, we analysed such trajectories with regard to changes in walking direction. The directional change of the ants was quantified, i.e. an angle θ between trajectory increments of a given arclength λ was computed. This was done for different length scales λ, according to our goal of analysing desert ant path characteristics with respect to length scale. First, varying λ through more than two orders of magnitude demonstrated Brownian motion characteristics typical of the random walk component of search behaviour. Unexpectedly, this random walk component was also present in - supposedly rather linear - approach trajectories. Second, there were small but notable deviations from a uniform angle distribution that is characteristic of random walks. This was true for specific search situations, mostly close to the (virtual) goal position. And third, experience with a feeder position resulted in straighter approaches and more focused searches, which was also true for nest searches, albeit to a lesser extent. Taken together, these results both verify and extend previous studies on desert ant path characteristics. Of particular interest are the ubiquitous Brownian motion signatures and specific deviations thereof close to the goal position, indicative of unexpectedly structured search behaviour.

A Step Forward Understanding Directional Limitations in Markerless Smartphone-Based Gait Analysis: A Pilot Study.

The progress in markerless technologies is providing clinicians with tools to shorten the time of assessment rapidly, but raises questions about the potential trade-off in accuracy compared to traditional marker-based systems. This study evaluated the OpenCap system against a traditional marker-based system-Vicon. Our focus was on its performance in capturing walking both toward and away from two iPhone cameras in the same setting, which allowed capturing the Timed Up and Go (TUG) test. The performance of the OpenCap system was compared to that of a standard marker-based system by comparing spatial-temporal and kinematic parameters in 10 participants. The study focused on identifying potential discrepancies in accuracy and comparing results using correlation analysis. Case examples further explored our results. The OpenCap system demonstrated good accuracy in spatial-temporal parameters but faced challenges in accurately capturing kinematic parameters, especially in the walking direction facing away from the cameras. Notably, the two walking directions observed significant differences in pelvic obliquity, hip abduction, and ankle flexion. Our findings suggest areas for improvement in markerless technologies, highlighting their potential in clinical settings.

Design and Performance Analysis of Soft Crawling Robot Based on Photoelectric Sensor/STM32

In this study, a control system based on STM32/photoelectric sensor is designed for soft crawling robot. The system consists of a front-end camera installed on soft robot, wireless routing, STM32 single-chip microcomputer and several photoelectric sensors. In this design, STM32 single-chip microcomputer is used as the main controller to send instructions to the four-limb drive steering gear through RS-485 module, and the feedback incentive mechanism is adopted to improve the accuracy and stability of the digital steering gear system. In order to better perceive the working environment, this design is also equipped with a variety of photoelectric level sensors, and photoelectric pressure sensors are installed to monitor the perceived pressure of the robot to make it move better on the ground. The photoelectric sensor is used to realize the soft crawling robot walking according to the planned route. The photoelectric tilt robot is used to change the walking direction during the moving process. Through the overall cooperation of the above components, the movement angle of limbs can be changed to make them crawl under narrow conditions. In the experiment, soft robot’s posture information is collected by various photoelectric sensors and displayed on the corresponding control interface, so that it can walk at the specified gait and leg swinging frequency. On the flat road, the swinging frequency of the robot first increases and then gradually stabilizes, and the movement efficiency is maintained at about 75% at the maximum movement speed.

An Adaptive Heading Estimation Method based on Holding Styles Recognition Using Smartphone Sensors

Pedestrian Dead Reckoning (PDR), which comes with many sensors integrated into widely available smartphones, is known as one of the most popular indoor positioning techniques. Sensors such as accelerometers, gyroscopes, and magnetometers are used to determine three important components in PDR: step detection, step length estimation, and heading estimation. Among them, the last component is the most challenging since a small heading error accumulates to produce a very large positioning error, especially when the pedestrian holds the smartphone in unconstrained styles such as swinging the phone freely along the pedestrian’s walking direction or putting the phone into the pants’ front pockets. The research proposes an adaptive heading estimation method to deal with heading errors caused by smartphone holding styles. The novelties are described as follows. Firstly, the proposed method attempts to classify the four basic smartphone holding styles using a machine learning algorithm based on simple features of acceleration values to give pedestrians more freedom during the walking period. Secondly, the proposed method adaptively combines the two heading estimation methods, which are calculated from the integrated sensors, to determine the walking direction for different smartphone holding styles. The experimental results show that the proposed heading estimation method achieves average heading errors of less than 30 degrees when testing in two different walking paths with the smartphone held in dynamic styles. It helps to reduce the heading errors by more than 15% compared to previous heading estimation methods.

Analysis of Gait Pattern Affected by Various Disease : A Review

Gait is pattern of walking of individual, is unique pattern of a person. The gait pattern is affected by various disease, ill condition of a person. In this review article we discuss about various diseases by which gait of an individual gets affected. Some disease are ; Parkinson's disease (PD) is a degenerative brain disorder causing shuffled gait, impaired balance, and freezing of gait. Morquio A syndrome, a group of disorders called mucopolysaccharidosis, can lead to vision, hearing, bone, brain, and heart problems. The anterior cruciate ligament (ACL) is a key stabilizer in the knee, and a torn ACL can cause instability when walking or changing directions. Examination of the gait pattern of a those person who having a disease such as ; Parkinson’s disease, Morquio A syndrome, Anterior Crucial Ligament, etc. In normal human the Gait Cycle has two phases ; Stance and swing phase. The stance phase covers approx 60% gait cycle and swing phase covers remaining 40% of gait cycle. In further studies we can analysis on how this cycle varies in abnormal walking.These review article summarises about gait pattern affected by various diseases. Study of gait pattern used for solving criminal cases as we can recognize various abnormalities a person may have by the analysis of his or her gait pattern. It is used as secondary evidence. By using gait pattern we can find out individuals age, sex, and height.