Predict Movement Patterns Research Articles

Reliability and usability of a novel inertial sensor-based system to test craniocervical flexion movement control

BackgroundNeck pain has a significant global impact, ranking as the fourth leading cause of disability. Recurrent neck pain often leads to impaired sensorimotor control, particularly in craniocervical flexion (CFF). The Craniocervical Flexion Test (CCFT) has been widely investigated to assess the performance of deep cervical flexor muscles. However, its use requires skilled assessors who need to subjectively detect compensations, progressive increases in range of motion (ROM) or excessive superficial flexor activation during the test. The aim of this study was to design and develop a novel Craniocervical Flexion Movement Control Test (CFMCT) based on inertial sensor technology and real-time computer feedback and to evaluate its safety and usability, as well as inter and intra-rater reliability in both healthy individuals and patients with neck pain.MethodsWe used inertial sensor technology associated with new software that provides real-time computer feedback to assess CCF movement control through two independent test protocols, the progressive consecutive stages protocol (including progressive incremental stages of ROM) and the random stages protocol (providing dynamic and less predictable movement patterns). We determined intra and inter-rater reliability and standard error of the measurement for both protocols. The participants rated their usability was analysed through the System Usability Scale (SUS) and possible secondary effects associated with the tests were registered.ResultsThe progressive consecutive stages protocol and the random stages protocol were safe and easy to use (SUS scores of 82.00 ± 11.55 in the pain group and 79.56 ± 13.36 in the asymptomatic group). The progressive consecutive stages protocol demonstrated good inter-rater reliability (intraclass correlation coefficient [ICC] ≥ 0.75) and moderate to good intra-rater reliability (ICC 0.62–0.80). However, the random stages protocol exhibited lower intra-rater reliability, especially in the neck pain group, where the reliability values were poor in some cases (ICC 0.48–0.72).ConclusionThe CFMCT (progressive consecutive stages protocol) is a promising instrument to evaluate CCF motor control in patients with chronic neck pain. It has potential for telehealth assessment and easy adherence for exercise prescription and seems to be a safe and usable tool for patients with pain and asymptomatic individuals. Its use as a test or for exercise needs to be further investigated to facilitate its transfer to clinical practice.

Tuning in to a hip-hop beat: Pursuit eye movements reveal processing of biological motion

Smooth pursuit eye movements are mainly driven by motion signals to achieve their goal of reducing retinal motion blur. However, they can also show anticipation of predictable movement patterns. Oculomotor predictions may rely on an internal model of the target kinematics. Most investigations on the nature of those predictions have concentrated on simple stimuli, such as a decontextualized dot. However, biological motion is one of the most important visual stimuli in regulating human interaction and its perception involves integration of form and motion across time and space. Therefore, we asked whether there is a specific contribution of an internal model of biological motion in driving pursuit eye movements. Unlike previous contributions, we exploited the cyclical nature of walking to measure eye movement's ability to track the velocity oscillations of the hip of point-light walkers. We quantified the quality of tracking by cross-correlating pursuit and hip velocity oscillations. We found a robust correlation between signals, even along the horizontal dimension, where changes in velocity during the stepping cycle are very subtle. The inversion of the walker and the presentation of the hip-dot without context incurred the same additional phase lag along the horizontal dimension. These findings support the view that information beyond the hip-dot contributes to the prediction of hip kinematics that controls pursuit. We also found a smaller phase lag in inverted walkers for pursuit along the vertical dimension compared to upright walkers, indicating that inversion does not simply reduce prediction. We suggest that pursuit eye movements reflect the visual processing of biological motion and as such could provide an implicit measure of higher-level visual function.

Energy-Efficient Relay Tracking and Predicting Movement Patterns with Multiple Mobile Camera Sensors

Camera sensor networks (CSN) have been widely used in different applications such as large building monitoring, social security, and target tracking. With advances in visual and actuator sensor technology in the last few years, deploying mobile cameras in CSN has become a possible and efficient solution for many CSN applications. However, mobile camera sensor networks still face several issues, such as limited sensing range, the optimal deployment of camera sensors, and the energy consumption of the camera sensors. Therefore, mobile cameras should cooperate in order to improve the overall performance in terms of enhancing the tracking quality, reducing the moving distance, and reducing the energy consumed. In this paper, we propose a movement prediction algorithm to trace the moving object based on a cooperative relay tracking mechanism. In the proposed approach, the future path of the target is predicted using a pattern recognition algorithm by applying data mining to the past movement records of the target. The efficiency of the proposed algorithms is validated and compared with another related algorithm. Simulation results have shown that the proposed algorithm guarantees the continuous tracking of the object, and its performance outperforms the other algorithms in terms of reducing the total moving distance of cameras and reducing energy consumption levels. For example, in terms of the total moving distance of the cameras, the proposed approach reduces the distance by 4.6% to 15.2% compared with the other protocols that do not use prediction.

Oral Cavity Movements of the Tongue During Large Interval Slurs in High-Level Horn Players: A Descriptive Study.

Recent publications describing lingual movement strategies within the oral cavity of brass players have established the existence of efficient and predictable movement patterns in healthy performers for a variety of performance tasks. In this study we extend the research to include the playing of large interval slurs in horn players. Real-time MRI films at 40-msec resolution were simultaneously obtained in the sagittal and coronal planes in 9 professional horn players as they performed 2 repetitions each of 3 slur sequences spanning 1 octave, 1 octave + 3rd, and 1 octave + 5th at a mezzo forte dynamic level. Nine profile lines were overlaid on the images allowing the measurement of dorsal tongue edge movement using a customized MATLAB toolkit. Movement along lines representing the anterior, middle, and posterior oral cavity in the sagittal plane, as well as the vertical height of an air channel observed in the coronal plane, are reported. Both sagittal and coronal views demonstrate patterned tongue movements that narrow and widen the air channel during ascending and descending slurs, respectively. The magnitude of these movements is greater during larger intervals, though not perfectly consistent within each slur sequence. Additionally, the tongue position during notes tends to drift in the direction of the subsequent note in each sequence. We suggest that the observed movements may help to modulate air speed through the lips, possible attenuating embouchure muscle tension changes by assisting changes in lip vibration frequency.

Human Prediction of Robot’s Intention in Object Handling Tasks

Trained human workers can predict the intentions of other workers from observed movement patterns when working collaboratively. The intentions prediction is crucial to identify their future actions. In human-machine teams, predictable movement patterns can enhance the interaction and improve team performance. In this article, we investigated the effects of different robot trajectory characteristics on the early prediction performance in human-machine teaming and on perceived robot’s human-likeness. The results showed that humans can predict the robot’s intention quicker and more accurately when the observed robot’s trajectory was generated with relatively lower energy expenditure. We found that the amount of jerk and acceleration in the robot’s joint-space affected perceived robot’s human-likeness.

A unified energy-optimality criterion predicts human navigation paths and speeds

Navigating our physical environment requires changing directions and turning. Despite its ecological importance, we do not have a unified theoretical account of non-straight-line human movement. Here, we present a unified optimality criterion that predicts disparate non-straight-line walking phenomena, with straight-line walking as a special case. We first characterized the metabolic cost of turning, deriving the cost landscape as a function of turning radius and rate. We then generalized this cost landscape to arbitrarily complex trajectories, allowing the velocity direction to deviate from body orientation (holonomic walking). We used this generalized optimality criterion to mathematically predict movement patterns in multiple contexts of varying complexity: walking on prescribed paths, turning in place, navigating an angled corridor, navigating freely with end-point constraints, walking through doors, and navigating around obstacles. In these tasks, humans moved at speeds and paths predicted by our optimality criterion, slowing down to turn and never using sharp turns. We show that the shortest path between two points is, counterintuitively, often not energy-optimal, and, indeed, humans do not use the shortest path in such cases. Thus, we have obtained a unified theoretical account that predicts human walking paths and speeds in diverse contexts. Our model focuses on walking in healthy adults; future work could generalize this model to other human populations, other animals, and other locomotor tasks.

Highway Speed Prediction Using Gated Recurrent Unit Neural Networks

Movement analytics and mobility insights play a crucial role in urban planning and transportation management. The plethora of mobility data sources, such as GPS trajectories, poses new challenges and opportunities for understanding and predicting movement patterns. In this study, we predict highway speed using a gated recurrent unit (GRU) neural network. Based on statistical models, previous approaches suffer from the inherited features of traffic data, such as nonlinear problems. The proposed method predicts highway speed based on the GRU method after training on digital tachograph data (DTG). The DTG data were recorded in one month, giving approximately 300 million records. These data included the velocity and locations of vehicles on the highway. Experimental results demonstrate that the GRU-based deep learning approach outperformed the state-of-the-art alternatives, the autoregressive integrated moving average model, and the long short-term neural network (LSTM) model, in terms of prediction accuracy. Further, the computational cost of the GRU model was lower than that of the LSTM. The proposed method can be applied to traffic prediction and intelligent transportation systems.

An activity‐based framework for detecting human movement patterns in an urban environment

AbstractThe continuous development of positioning technologies and computing solutions for the integration of large trajectory data sets offers many novel research opportunities. Among various research domains, the extraction of users' movement patterns is an important issue that is yet to be addressed. While many previous studies have analyzed human and animal movements from a predominantly geometrical point of view, additional semantics are still required to provide a better understanding of the patterns that emerge. User activity data provide important information resources to analyze and predict movement patterns in urban environments. This study introduces a computational framework that combines the geometric and activity‐based dimensions of human trajectories. First, the geometrical dimension considers a series of parameters (i.e., turning points, curvature, and self‐intersection) that are extracted by a convex‐hull algorithm and characterizes a given trajectory. Second, user activity transitions are modeled and then denote some recurrent patterns. Finally, geometric and activity patterns are integrated into a unified trajectory modeling framework. This favors the analysis of human movement patterns by taking into account the geometric and activity dimensions. The entire approach and framework have experimented with the LifeMap Korean trajectory data set commonly considered as a reference benchmark. The experiments showed how the integration of geometrical and activity‐based dimensions could provide a better understanding of the patterns and trends that emerge from a large trajectory data set.

Perspective on musculoskeletal modelling and predictive simulations of human movement to assess the neuromechanics of gait.

Locomotion results from complex interactions between the central nervous system and the musculoskeletal system with its many degrees of freedom and muscles. Gaining insight into how the properties of each subsystem shape human gait is challenging as experimental methods to manipulate and assess isolated subsystems are limited. Simulations that predict movement patterns based on a mathematical model of the neuro-musculoskeletal system without relying on experimental data can reveal principles of locomotion by elucidating cause-effect relationships. New computational approaches have enabled the use of such predictive simulations with complex neuro-musculoskeletal models. Here, we review recent advances in predictive simulations of human movement and how those simulations have been used to deepen our knowledge about the neuromechanics of gait. In addition, we give a perspective on challenges towards using predictive simulations to gain new fundamental insight into motor control of gait, and to help design personalized treatments in patients with neurological disorders and assistive devices that improve gait performance. Such applications will require more detailed neuro-musculoskeletal models and simulation approaches that take uncertainty into account, tools to efficiently personalize those models, and validation studies to demonstrate the ability of simulations to predict gait in novel circumstances.

Ensemble model for estimating continental-scale patterns of human movement: a case study of Australia

Understanding human movement patterns at local, national and international scales is critical in a range of fields, including transportation, logistics and epidemiology. Data on human movement is increasingly available, and when combined with statistical models, enables predictions of movement patterns across broad regions. Movement characteristics, however, strongly depend on the scale and type of movement captured for a given study. The models that have so far been proposed for human movement are best suited to specific spatial scales and types of movement. Selecting both the scale of data collection, and the appropriate model for the data remains a key challenge in predicting human movements. We used two different data sources on human movement in Australia, at different spatial scales, to train a range of statistical movement models and evaluate their ability to predict movement patterns for each data type and scale. Whilst the five commonly-used movement models we evaluated varied markedly between datasets in their predictive ability, we show that an ensemble modelling approach that combines the predictions of these models consistently outperformed all individual models against hold-out data.

Associations between isometric quadriceps strength characteristics, knee flexion angles, and knee extension moments during single leg step down and landing tasks after anterior cruciate ligament reconstruction

BackgroundIt is unclear of how peak knee extension torque and early rate of torque development outcomes are related to lower extremity loading and sagittal plane movement in activities of daily living and landing tasks despite consistent deficits after anterior cruciate ligament reconstruction. The purpose of this cross-section study is to assess the ability of quadriceps strength characteristics to predict movement patterns during a step down and single leg drop crossover hopping tasks. MethodsFifty-two individuals with a unilateral history of anterior cruciate ligament reconstruction completed three trials of the step down and crossover hopping tasks on their involved limb. Participants completed three isometric knee extension contractions at 90° knee flexion with visual feedback to assess peak knee extension torque and rate of torque development during the first 0–100 ms and 100–200 ms of the contraction. FindingsPeak knee extension torque explained the greatest variance in peak knee extension moment (R2 = 40.4%, p < 0.001) and knee flexion angle (R2 = 46.7%, p < 0.001) during the crossover hop landing. Rate of torque development (0–100 ms) was the only predictor of knee flexion angle (R2 = 19.8%, p = 0.01) at initial contact during the crossover hopping landing. Rate of torque development (100–200 ms) explained 17.6% of the variance in peak knee extension moment during the step down (p = .03). InterpretationPeak knee extension torque and early rate of torque development outcomes demonstrate limited relationships between movement of activities of daily living and sport-specific tasks. These limitations should be considered when interpreting the results of isometric strength testing in a clinical setting.

Method of predicting human mobility patterns using deep learning

Abstract As human location and movement data are becoming easily accessible, owing to the prevalence of mobile devices, the use of such mobility data is gaining an increasing amount of interest. In our work, we establish a relationship between human mobility and personality, and attempt to model and predict movement patterns. Deep-neural-network and deep-belief-network models of deep learning are used in conjunction, for training the neural network. Both passive positioning information and active location information are used for the mobility information dataset, and the big five factors are used for the personality data. Both mobility information and personality information are split into training and verification groups, and are subsequently used to train and verify the neural network. The results are expressed in terms of hit ratios according to model factors comparing the predicted and observed values, and the parameters for the neural networks for the highest accuracy are identified. We use this optimal neural network to show the correlation between human personality and mobility patterns. Actual prediction is attempted, and is found meaningful in some conditions.

Supervised learning techniques and their ability to classify a change of direction task strategy using kinematic and kinetic features

This study examines the ability of commonly used supervised learning techniques to classify the execution of a maximum effort change of direction task into predefined movement pattern as well as the influence of fuzzy executions and the impact of selected features (e.g. peak knee flexion) towards classification accuracy. The experiment utilized kinematic and kinetic data from 323 male subjects with chronic athletic groin pain. All subjects undertook a biomechanical assessment and had been divided previously into 3 different movement strategies in an earlier paper. Examined supervised learning techniques were: a decision tree, an ensemble of decision trees, a discriminant analysis model, a naive Bayes classifier, a k-nearest-neighbour model, a multi-class model for support vector machines, a stepwise forward regression model, a neural network and a correlation approach. Performance (measured by comparing the predefined and classified movement pattern) was highest for the correlation approach (82% - CI 81–83%) and support vector machine (80% - CI 79–80%). The percentage of fuzzy observations within the data was between 16 and 25%. The most informative features for classification were: hip flexion and ankle rotation as well as ankle flexion moment, thorax [flexion and frontal sway], abduction angle in [hip and pelvis] and hip rotation. Findings of this study support the assumption that multiple patterns are used to execute a movement task and demonstrate that classification models can predict movement patterns with a high accuracy (~84%).

Decentralized content sharing among tourists in visiting hotspots

Content sharing with smart mobile devices using decentralized approach enables users to share contents without the use of any fixed infrastructure, and thereby offers a free-of-cost platform that does not add to Internet traffic which, in its current state, is approaching bottleneck in its capacity. Most of the existing decentralized approaches in the literature consider spatio-temporal regularity in human movement patterns and pre-existing social relationship for the sharing scheme to work. However, such predictable movement patterns and social relationship information are not available in places like tourist spots where people visit only for a short period of time and usually meet strangers. No works exist in literature that deals with content sharing in such environment. In this work, we propose a content sharing approach for such environments. The group formation mechanism is based on users' interest score and stay probability in the individual region of interest (ROI) as well as on the availability and delivery probabilities of contents in the group. The administrator of each group is selected by taking into account its probability of stay in the ROI, connectivity with other nodes, its trustworthiness and computing and energy resources to serve the group. We have also adopted an incentive mechanism as encouragement that awards nodes for sharing and forwarding contents. We have used network simulator NS3 to perform extensive simulation on a popular tourist spot in Australia which facilitates a number of activities. The proposed approach shows promising results in sharing contents among tourists, measured in terms of content hit, delivery success rate and latency.

Hip and ankle responses for reactive balance emerge from varying priorities to reduce effort and kinematic excursion: A simulation study

Although standing balance is important in many daily activities, there has been little effort in developing detailed musculoskeletal models and simulations of balance control compared to other whole-body motor activities. Our objective was to develop a musculoskeletal model of human balance that can be used to predict movement patterns in reactive balance control. Similar to prior studies using torque-driven models, we investigated how movement patterns during a reactive balance response are affected by high-level task goals (e.g., reducing center-of-mass movement, maintaining vertical trunk orientation, and minimizing effort). We generated 23 forward dynamics simulations where optimal muscle excitations were found using cost functions with different weights on minimizing these high-level goals. Variations in hip and ankle angles observed experimentally (peak hip flexion=7.9−53.1°, peak dorsiflexion=0.5−4.7°) could be predicted by varying the priority of these high-level goals. More specifically, minimizing center-of-mass motion produced a hip strategy (peak hip flexion and ankle dorsiflexion angles of 45.5° and 2.3°, respectively) and the response shifted towards an ankle strategy as the priority to keep the trunk vertical was increased (peak hip and ankle angles of 13.7° and 8.5°, respectively). We also found that increasing the priority to minimize muscle stress always favors a hip strategy. These results are similar to those from sagittal-plane torque-driven models. Our muscle-actuated model facilitates the investigation of neuromechanical interactions governing reactive balance control to predict muscle activity and movement patterns based on interactions between neuromechanical elements such as spinal reflexes, muscle short-range stiffness, and task-level sensorimotor feedback.

Predicting Missing Marker Trajectories in Human Motion Data Using Marker Intercorrelations.

Missing information in motion capture data caused by occlusion or detachment of markers is a common problem that is difficult to avoid entirely. The aim of this study was to develop and test an algorithm for reconstruction of corrupted marker trajectories in datasets representing human gait. The reconstruction was facilitated using information of marker inter-correlations obtained from a principal component analysis, combined with a novel weighting procedure. The method was completely data-driven, and did not require any training data. We tested the algorithm on datasets with movement patterns that can be considered both well suited (healthy subject walking on a treadmill) and less suited (transitioning from walking to running and the gait of a subject with cerebral palsy) to reconstruct. Specifically, we created 50 copies of each dataset, and corrupted them with gaps in multiple markers at random temporal and spatial positions. Reconstruction errors, quantified by the average Euclidian distance between predicted and measured marker positions, was ≤ 3 mm for the well suited dataset, even when there were gaps in up to 70% of all time frames. For the less suited datasets, median reconstruction errors were in the range 5–6 mm. However, a few reconstructions had substantially larger errors (up to 29 mm). Our results suggest that the proposed algorithm is a viable alternative both to conventional gap-filling algorithms and state-of-the-art reconstruction algorithms developed for motion capture systems. The strengths of the proposed algorithm are that it can fill gaps anywhere in the dataset, and that the gaps can be considerably longer than when using conventional interpolation techniques. Limitations are that it does not enforce musculoskeletal constraints, and that the reconstruction accuracy declines if applied to datasets with less predictable movement patterns.

Movements and space use of giant trevally in coral reef habitats and the importance of environmental drivers

Effective conservation of large predators requires a broad understanding of their ecology. Caranx ignobilis is a large marine predator well represented in coral reef environments, yet they are poorly studied. Passive acoustic monitoring was used to track the movements of 20 C. ignobilis at offshore reefs in the central Great Barrier Reef from 2012 to 2014. Using a modelling approach, temporal changes in movement patterns of C. ignobilis were explored to determine if individuals exhibited predictable movement patterns. The effects of biological and environmental variables on monthly space use, daily presence and hourly depth use were investigated to define any response to environmental changes. Caranx ignobilis typically remained at their capture reef with 98.8% of detections recorded at these locations. Individuals were recorded in the study site for periods from 9 to 335 days (mean = 125.9) with a mean residency index of 0.53, indicating movements away from the reef or out of detection range occurred on the scale of days. Inter-reef movements from only three individuals were recorded which coincided with the summer full moon so may have been related to spawning behaviour. Environmental drivers were correlated with daily presence and hourly depth use of C. ignobilis but had little influence on monthly space use. There was little or no effect of fish size on space use, presence and depth use. By improving the current understanding of movement patterns of this large teleost among individual coral reefs, the results of this study reveal that site attachment may be present and that environmental parameters play a role in observed movement patterns related to depth and presence. These data provide useful information for the development of management plans, particularly in relation to space-based protection.

The dual role of rivers in facilitating or hindering movements of the false heath fritillary butterfly.

BackgroundSpecies movement responses to landscape structures have been studied using a variety of methods, but movement research is still in need of simple methods that help predicting and comparing movements across structurally different landscapes. We demonstrate how habitat-specific movement models can be used to disentangle causes of differentiated movement patterns in structurally different landscapes and to predict movement patterns in altered and artificial landscapes. In our case study, we studied the role of riparian landscapes to the persistence of the endangered false heath fritillary butterfly (Melitaea diamina) in its newly discovered coastal distribution region in Finland. We compared the movement parameters of the riparian population to two reference populations by using capture-recapture data and habitat-specific diffusion modelling, and analysed the role of the river and riverbank buffer zones in facilitating or hindering false heath fritillary movement with movement simulations.ResultsThe riparian population of the false heath fritillary did not show major differences to reference populations in terms of movement parameters within breeding habitat, high-quality matrix and low-quality matrix. However, movement simulations showed that the habitat-specific movement parameters estimated for the false heath fritillary can lead into markedly different movement patterns in structurally different landscapes. An artificial riparian landscape mimicking those of the coastal distribution resulted into more directional, longitudinal movements both parallel and perpendicular to the river than a more mosaic-like landscape, but the existence of the river in the landscape reduced movements across the river.ConclusionsOur study demonstrates how habitat-specific movement models enable comparisons of movement patterns across structurally different real, altered and artificial landscapes. As such, they can be used to compare movement parameters across populations, to study the effects of management interventions to endangered species and to identify areas that have high sensitivity to individual movement. In our case study, the river is shown to perform a dual role for the movements of the riparian false heath fritillary population. Whereas the river acts as a moderate movement barrier for the false heath fritillary, the longitudinal configuration of riverbank habitats provides a means especially for the male false heath fritillaries to move across the landscape.Electronic supplementary materialThe online version of this article (doi:10.1186/s40462-015-0031-z) contains supplementary material, which is available to authorized users.

Geomagnetic imprinting predicts spatio-temporal variation in homing migration of pink and sockeye salmon.

Animals navigate using a variety of sensory cues, but how each is weighted during different phases of movement (e.g. dispersal, foraging, homing) is controversial. Here, we examine the geomagnetic and olfactory imprinting hypotheses of natal homing with datasets that recorded variation in the migratory routes of sockeye (Oncorhynchus nerka) and pink (Oncorhynchus gorbuscha) salmon returning from the Pacific Ocean to the Fraser River, British Columbia. Drift of the magnetic field (i.e. geomagnetic imprinting) uniquely accounted for 23.2% and 44.0% of the variation in migration routes for sockeye and pink salmon, respectively. Ocean circulation (i.e. olfactory imprinting) predicted 6.1% and 0.1% of the variation in sockeye and pink migration routes, respectively. Sea surface temperature (a variable influencing salmon distribution but not navigation, directly) accounted for 13.0% of the variation in sockeye migration but was unrelated to pink migration. These findings suggest that geomagnetic navigation plays an important role in long-distance homing in salmon and that consideration of navigation mechanisms can aid in the management of migratory fishes by better predicting movement patterns. Finally, given the diversity of animals that use the Earth's magnetic field for navigation, geomagnetic drift may provide a unifying explanation for spatio-temporal variation in the movement patterns of many species.

Simulation and Validation of Human Movement in Building Spaces

Data on human movement are valuable input data for building-simulation tools such as indoor-climate simulation and working-condition assessment. However, reliable data on human movement in buildings are scarcely available. Existing human-movement models are, typically, developed for (semi)public spaces and lack applicability to indoor spaces. The research presented here focuses on indoor office-building spaces and normal working conditions. The simulation model was developed in conjunction with a validation method. Web-based diaries and radio frequency identification technology were used to collect data on human behaviour in a real-life situation. The performance of the model was tested against a set of newly developed criterion variables (for example, the usage of facilities or the movement behaviour of employees) related to human movement in building spaces. Observed and predicted movement patterns were compared for these criteria. Results indicate close correspondence between simulated and observed behaviour, providing evidence of the validity of the model. The model can be used to accurately predict the space utilisation of an organisation.