A kinematic theory of rapid human movements. Part I. Movement representation and generation

Model-Driven Analysis of ECG Using Reinforcement Learning

Modeling is essential to better understand the generative mechanisms responsible for experimental observations gathered from complex systems. In this work, we are using such an approach to analyze the electrocardiogram (ECG). We present a systematic framework to decompose ECG signals into sums of overlapping lognormal components. We use reinforcement learning to train a deep neural network to estimate the modeling parameters from an ECG recorded in babies from 1 to 24 months of age. We demonstrate this model-driven approach by showing how the extracted parameters vary with age. From the 751,510 PQRST complexes modeled, 82.7% provided a signal-to-noise ratio that was sufficient for further analysis (>5 dB). After correction for multiple tests, 10 of the 24 modeling parameters exhibited statistical significance below the 0.01 threshold, with absolute Kendall rank correlation coefficients in the [0.27, 0.51] range. These results confirm that this model-driven approach can capture sensitive ECG parameters. Due to its physiological interpretability, this approach can provide a window into latent variables which are important for understanding the heart-beating process and its control by the autonomous nervous system.

Observation vs. interaction in the recognition of human-like movements

A crucial aspect in human-robot collaboration is the robot acceptance by human co-workers. Based on previous experiences of interaction with their fellow beings, humans are able to recognize natural movements of their companions and associate them with the concepts of trust and acceptance. Throughout this process, the judgment is influenced by several percepts, first of all the visual similarity to the companion, which triggers a process of self-identification. When the companion is a robot, the lack of these percepts challenges such a self-identification process, unavoidably lowering the level of acceptance. Hence, while, on the one hand, the robotics industry moves towards manufacturing robots that visually resemble humans, on the other hand, a question is still open on whether the acceptance of robots can be increased by virtue of the movements they exhibit, regardless of their exterior aspect. In order to contribute to answering this question, this paper presents two experimental setups for Turing tests, where an artificial agent performs human-recorded and artificial movements, and a human subject is to judge the human likeness of the movement in two different circumstances: by observing the movement replicated on a screen and by physically interacting with a robot executing the movements. The results reveal that humans are more likely to recognize human movements through interaction than observation, and that, under the interaction condition, artificial movements can be designed to resemble human ones for future robots to be more easily accepted by human co-workers.

Standing Balance Control of a Bipedal Robot Based on Behavior Cloning

Bipedal robots have gained increasing attention for their human-like mobility which allows them to work in various human-scale environments. However, their inherent instability makes it difficult to control their balance while they are physically interacting with the environment. This study proposes a novel balance controller for bipedal robots based on a behavior cloning model as one of the machine learning techniques. The behavior cloning model employs two deep neural networks (DNNs) trained on human-operated balancing data, so that the trained model can predict the desired wrench required to maintain the balance of the bipedal robot. Based on the prediction of the desired wrench, the joint torques for both legs are calculated using robot dynamics. The performance of the developed balance controller was validated with a bipedal lower-body robotic system through simulation and experimental tests by providing random perturbations in the frontal plane. The developed balance controller demonstrated superior performance with respect to resistance to balance loss compared to the conventional balance control method, while generating a smoother balancing movement for the robot.

Computerized handwriting evaluation and statistical reports for children in the age of primary school

This study proposed a novel computational method for evaluating logographic handwriting. It can precisely evaluate both the handwriting product and the process. The measures included handwriting performance as well as the temporospatial, kinematics, and kinetics features. For examining the psychometrics of this comprehensive evaluation system, typical development children aged 6 to 9 years old (grade 1 to grade 3) (n = 641) were involved in the study of factor analysis. From twelve measuring variables, the exploratory factor analysis extracted five factors (handwriting performance, motor control, speed and automation, halt and exertion, and “in air” events). The test reliability was confirmed by further recruitment of typically developing children (n = 242). The internal consistency mostly demonstrated good to excellent results for every measure. This study further recruited children with handwriting difficulties (n = 33) for testing the discriminative validity of the evaluation system. A series of two-way ANOVA tests was conducted to test the significance of the main effects of the groups (typical development and handwriting deficit) and grades (1, 2, and 3) and their interaction effects on the handwriting measures. All the measures showed significant differences between the two groups, indicating the discriminative validity for identifying handwriting deficits. Seven of twelve measures showed significant interaction effects, indicating the different trends across the grades between the two groups. Typically-developing children demonstrated ongoing progress from grade 1 to grade 3, suggesting a developmental trend during their early school age. Implications for motor development and clinical evaluation are discussed herein in relation to the five dimensions.

Exploring Orthographic Representation in Chinese Handwriting: A Mega-Study Based on a Pedagogical Corpus of CFL Learners

Writing and reading are closely related and are thus likely to have a common orthographic representation. A fundamental question in the literature on the production of written Chinese characters concerns the structure of orthographic representations. We report on a Chinese character handwriting pedagogical corpus involving a class of 22 persons, 232 composite character types, 1,913 tokens, and 13,057 stroke records, together with the inter-stroke interval (ISI), which reflects the parallel processing of multilevel orthographic representation during the writing execution, and 50 orthographic variables from the whole character, logographeme, and stroke. The results of regression analyses show that orthographic representation has a hierarchy and that different representational levels are active simultaneously. In the multilevel structure of orthographic representation, the representation of the logographeme is absolutely dominant. Writing and reading have both commonalities and individual differences in their orthographic representations. The online processing of the logographeme unit probably occurs at the ISI before the initial stroke of the current logographeme, which may also cascade to the first subsequent logographeme. In addition, we propose a new effective character structure unit for describing orthographic complexity.

Temporally resolved neural dynamics underlying handwriting

How do the temporal dynamics of neural activity encode highly coordinated visual-motor behaviour? To capture the millisecond-resolved neural activations associated with fine visual-motor skills, we devised a co-registration system to simultaneously record electroencephalogram and handwriting kinematics while participants were performing four handwriting tasks (writing in Chinese/English scripts with their dominant/non-dominant hand). The neural activation associated with each stroke was clearly identified with a well-structured and reliable pattern. The functional significance of this pattern was validated by its significant associations with language, hand and the cognitive stages and kinematics of handwriting. Furthermore, the handwriting rhythmicity was found to be synchronised to the brain's ongoing theta oscillation, and the synchronisation was associated with the factor of language and hand. These major findings imply an implication between motor skill formation and the interplay between the rhythms in the brain and the peripheral systems.

Sit-to-Stand Test for Neurodegenerative Diseases Video Classification

In this extended version of this paper, an automatic video diagnosis system for dementia classification is presented. Starting from video recordings of patients and control subjects, performing sit-to-stand test, the designed system is capable of extracting relevant patterns for binary discern patients with dementia from healthy subjects. The original system achieved an accuracy 0.808 by using the rigorous inter-patient separation scheme especially suited for medical purposes. This separation scheme provides the use of some people for training and others, different, people for testing. The implementation of features from the kinematic theory of rapid human movement and its sigma-lognormal model together with classic features increased the overall accuracy of the system to 0.947 F1 score. In addition, multi-class classification was performed with the aim of classifying neurodegenerative disease severities. This work is an original and pioneering work on sit-to-stand video classification for neurodegenerative diseases, its novelties are on phases segmentation, experimental setup and the application of kinematic theory of rapid human movements to sit-to-stand videos for neurodegenerative disease assessment.

A dot that went for a walk: People prefer lines drawn with human-like kinematics

A dominant theory of embodied aesthetic experience (Freedberg & Gallese, 2007, Trends in Cognitive Sciences, 11, 197) posits that the appreciation of visual art is linked to the artist's movements when creating the artwork, yet a direct link between the kinematics of drawing actions and the aesthetics of drawing outcomes has not been experimentally demonstrated. Across four experiments, we measured aesthetic responses of students from arts and non-arts backgrounds to drawing movements generated from computational models of human writing. Experiment 1 demonstrated that human-like drawing movements with bell-shaped velocity profiles (Sigma Lognormal [SL] and Minimum Jerk [MJ]) are perceived as more natural and pleasant than movements with a uniform profile, and in both Experiments 1 and 2 movements that were perceived as more natural were also preferred. Experiment 3 showed that this effect persists if lower-level dynamic stimulus features are fully matched across experimental and control conditions. Furthermore, aesthetic preference for human-like movements were associated with greater perceptual fluency in Experiment 3, evidenced by unbiased estimations of the duration of natural movements. In Experiment 4, line drawings with visual features consistent with the dynamics of natural, human-like movements were preferred, but only by art students. Our findings directly link the aesthetics of human action to the visual aesthetics of drawings, but highlight the importance of incorporating artistic expertise into embodied accounts of aesthetic experience.

Restoration of bilateral motor coordination from preserved agonist-antagonist coupling in amputation musculature

Background

Neuroprosthetic devices controlled by persons with standard limb amputation often lack the dexterity of the physiological limb due to limitations of both the user’s ability to output accurate control signals and the control system’s ability to formulate dynamic trajectories from those signals. To restore full limb functionality to persons with amputation, it is necessary to first deduce and quantify the motor performance of the missing limbs, then meet these performance requirements through direct, volitional control of neuroprosthetic devices.

Methods

We develop a neuromuscular modeling and optimization paradigm for the agonist-antagonist myoneural interface, a novel tissue architecture and neural interface for the control of myoelectric prostheses, that enables it to generate virtual joint trajectories coordinated with an intact biological joint at full physiologically-relevant movement bandwidth. In this investigation, a baseline of performance is first established in a population of non-amputee control subjects (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n = 8$$\end{document}n=8). Then, a neuromuscular modeling and optimization technique is advanced that allows unilateral AMI amputation subjects (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n = 5$$\end{document}n=5) and standard amputation subjects (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n = 4$$\end{document}n=4) to generate virtual subtalar prosthetic joint kinematics using measured surface electromyography (sEMG) signals generated by musculature within the affected leg residuum.

Results

Using their optimized neuromuscular subtalar models under blindfolded conditions with only proprioceptive feedback, AMI amputation subjects demonstrate bilateral subtalar coordination accuracy not significantly different from that of the non-amputee control group (Kolmogorov-Smirnov test, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P \ge 0.052$$\end{document}P≥0.052) while standard amputation subjects demonstrate significantly poorer performance (Kolmogorov-Smirnov test, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$P < 0.001$$\end{document}P<0.001).

Conclusions

These results suggest that the absence of an intact biological joint does not necessarily remove the ability to produce neurophysical signals with sufficient information to reconstruct physiological movements. Further, the seamless manner in which virtual and intact biological joints are shown to coordinate reinforces the theory that desired movement trajectories are mentally formulated in an abstract task space which does not depend on physical limb configurations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12984-021-00829-z.

Trunk control during repetitive sagittal movements following a real-time tracking task in people with chronic low back pain

Precision of trunk movement has commonly been examined by testing relocation accuracy rather than evaluating accuracy of tracking dynamic movement. In this study we used a 3-D motion capture system to provide a novel real-time tracking task to assess trunk motor control at varying movement speeds between people with and without chronic non-specific low back pain (LBP). Eleven asymptomatic volunteers and 15 participants with chronic non-specific LBP performed 12 continuous cycles of trunk flexion-extension following real time visual feedback, during which, trunk motion was measured using eight optoelectronic infrared cameras. Significant time differences between the feedback and actual trunk motion were found between groups (P = 0.001). Both groups had similar variability of tracking accuracy when following the feedback (P > 0.05). However, tracking variability at a slow speed correlated (P = 0.03; r = 0.55) with the Fear-Avoidance Beliefs Questionnaire (FABQ) scores in those with LBP. This study shows that both asymptomatic people and individuals with LBP displayed anticipatory behaviour, however, the response of those with LBP was consistently delayed in tracking the visual feedback compared to the asymptomatic group. Additionally, the extent of variability of tracking accuracy over repeated tracking cycles was associated with the degree of fear of movement in people with LBP.

Sigma-Lognormal Modeling of Speech

Human movement studies and analyses have been fundamental in many scientific domains, ranging from neuroscience to education, pattern recognition to robotics, health care to sports, and beyond. Previous speech motor models were proposed to understand how speech movement is produced and how the resulting speech varies when some parameters are changed. However, the inverse approach, in which the muscular response parameters and the subject’s age are derived from real continuous speech, is not possible with such models. Instead, in the handwriting field, the kinematic theory of rapid human movements and its associated Sigma-lognormal model have been applied successfully to obtain the muscular response parameters. This work presents a speech kinematics-based model that can be used to study, analyze, and reconstruct complex speech kinematics in a simplified manner. A method based on the kinematic theory of rapid human movements and its associated Sigma-lognormal model are applied to describe and to parameterize the asymptotic impulse response of the neuromuscular networks involved in speech as a response to a neuromotor command. The method used to carry out transformations from formants to a movement observation is also presented. Experiments carried out with the (English) VTR-TIMIT database and the (German) Saarbrucken Voice Database, including people of different ages, with and without laryngeal pathologies, corroborate the link between the extracted parameters and aging, on the one hand, and the proportion between the first and second formants required in applying the kinematic theory of rapid human movements, on the other. The results should drive innovative developments in the modeling and understanding of speech kinematics.

Central and Peripheral Shoulder Fatigue Pre-screening Using the Sigma-Lognormal Model: A Proof of Concept

Background

Clinical tests for detecting central and peripheral shoulder fatigue are limited. The discrimination of these two types of fatigue is necessary to better adapt recovery intervention. The Kinematic Theory of Rapid Human Movements describes the neuromotor impulse response using lognormal functions and has many applications in pathology detection. The ideal motor control is modeled and a change in the neuromuscular system is reflected in parameters extracted according to this theory.

Objective

The objective of this study was to assess whether a shoulder neuromuscular fatigue could be detected through parameters describing the theory, if there is the possibility to discriminate central from peripheral fatigue, and which handwriting test gives the most relevant information on fatigue.

Methods

Twenty healthy participants performed two sessions of fast stroke handwriting on a tablet, before and after a shoulder fatigue. The fatigue was in internal rotation for one session and in external rotation during the other session. The drawings consisted of simple strokes, triangles, horizontal, and vertical oscillations. Parameters of these strokes were extracted according to the Sigma–Lognormal model of the Kinematic Theory. The evolution of each participant was analyzed through a U-Mann–Whitney test for individual comparisons. A Hotelling’s T²-test and a U-Mann–Whitney test were also performed on all participants to assess the group evolution after fatigue. Moreover, a correlation among parameters was calculated through Spearman coefficients to assess intrinsic parameters properties of each handwriting test.

Results

Central and peripheral parameters were statistically different before and after fatigue with a possibility to discriminate them. Participants had various responses to fatigue. However, when considering the group, parameters related to the motor program execution showed significant increase in the handwriting tests after shoulder fatigue. The test of simple strokes permits to know more specifically where the fatigue comes from, whereas the oscillations tests were the most sensitive to fatigue.

Conclusion

The results of this study suggest that the Sigma–Lognormal model of the Kinematic Theory is an innovative approach for fatigue detection with discrimination between the central and peripheral systems. Overall, there is a possibility to implement the setting for clinics and sports personalized follow-up.

Dynamic Handwriting Analysis for Neurodegenerative Disease Assessment: A Literary Review

Studying the effects of neurodegeneration on handwriting has emerged as an interdisciplinary research topic and has attracted considerable interest from psychologists to neuroscientists and from physicians to computer scientists. The complexity of handwriting, in fact, appears to be sensitive to age-related impairments in cognitive functioning; thus, analyzing handwriting in elderly people may facilitate the diagnosis and monitoring of these impairments. A large body of knowledge has been collected in the last thirty years thanks to the advent of new technologies which allow researchers to investigate not only the static characteristics of handwriting but also especially the dynamic aspects of the handwriting process. The present paper aims at providing an overview of the most relevant literature investigating the application of dynamic handwriting analysis in neurodegenerative disease assessment. The focus, in particular, is on Parkinon’s disease (PD) and Alzheimer’s disease (AD), as the two most widespread neurodegenerative disorders. More specifically, the studies taken into account are grouped in accordance with three main research questions: disease insight, disease monitoring, and disease diagnosis. The net result is that dynamic handwriting analysis is a powerful, noninvasive, and low-cost tool for real-time diagnosis and follow-up of PD and AD. In conclusion of the paper, open issues still demanding further research are highlighted.

Kinematic analysis of fast pen strokes in children with ADHD

In this study, we aimed to determine whether a new measure of fine motor skills, the Pen Stroke Test (PST), can discriminate between children with and without attention-deficit/hyperactivity disorder (ADHD). Twelve children with ADHD and 12 controls age 8-11 were asked to produce handwriting strokes on a digitizer. The sigma-lognormal model derived from the Kinematic Theory of rapid human movements was used to analyze the strokes. Standard measurements of fine motor skills and handwriting were also obtained. Children with ADHD demonstrated poorer motor planning (t₀, D) and execution (nbLog) and greater variability in motor control (SNR/nbLog) than did controls. Parameters extracted from the PST were significantly correlated with performance on other motor and handwriting measures. This study provides preliminary evidence that the PST may be useful as a tool for rapidly detecting motor skill problems in the context of ADHD.

Static and Dynamic Synthesis of Bengali and Devanagari Signatures

Developing an automatic signature verification system is challenging and demands a large number of training samples. This is why synthetic handwriting generation is an emerging topic in document image analysis. Some handwriting synthesizers use the motor equivalence model, the well-established hypothesis from neuroscience, which analyses how a human being accomplishes movement. Specifically, a motor equivalence model divides human actions into two steps: 1) the effector independent step at cognitive level and 2) the effector dependent step at motor level. In fact, recent work reports the successful application to Western scripts of a handwriting synthesizer, based on this theory. This paper aims to adapt this scheme for the generation of synthetic signatures in two Indic scripts, Bengali (Bangla), and Devanagari (Hindi). For this purpose, we use two different online and offline databases for both Bengali and Devanagari signatures. This paper reports an effective synthesizer for static and dynamic signatures written in Devanagari or Bengali scripts. We obtain promising results with artificially generated signatures in terms of appearance and performance when we compare the results with those for real signatures.

A 12-Week Cycling Training Regimen Improves Upper Limb Functions in People With Parkinson's Disease

Background: It has been proposed that physical exercise can help improve upper limb functions in Parkinson’s disease (PD) patients; yet evidence for this hypothesis is limited.

Objective: To assess the effects of aerobic exercise training (AET) on general upper limb functions in sedentary people with PD and healthy adults (HA).

Methods: Two groups, 19 PD patients (Hoehn & Yahr ≤ 2) and 20 HA, matched on age and sedentary level, followed a 3-month stationary bicycle AET regimen. We used the kinematic theory framework to characterize and quantify the different motor control commands involved in performing simple upper-limb movements as drawing lines. Repeated measures ANCOVA models were used to assess the effect of AET in each group, as well as the difference between groups following the training regimen.

Results: At baseline, PD individuals had a larger antagonist response, a longer elapsed time between the visual stimulus and the end of the movement, and a longer time of displacement of the stylus than the HA. Following the 12-week AET, PD participants showed significant decreases of the agonist and antagonist commands, as well as the antagonist response spread. A significant group ^∗ session interaction effect was observed for the agonist command and the response spread of the antagonist command, suggesting a significant change for these two parameters only in PD patients following the AET. Among the differences observed at baseline, only the difference for the time of movement remained after AET.

Conclusion: A 3-month AET has a significant positive impact on the capacity to draw lines in a more efficiency way, in PD patients, indicating an improvement in the upper limb motor function.

Sustained sensorimotor control as intermittent decisions about prediction errors: computational framework and application to ground vehicle steering

A conceptual and computational framework is proposed for modelling of human sensorimotor control and is exemplified for the sensorimotor task of steering a car. The framework emphasises control intermittency and extends on existing models by suggesting that the nervous system implements intermittent control using a combination of (1) motor primitives, (2) prediction of sensory outcomes of motor actions, and (3) evidence accumulation of prediction errors. It is shown that approximate but useful sensory predictions in the intermittent control context can be constructed without detailed forward models, as a superposition of simple prediction primitives, resembling neurobiologically observed corollary discharges. The proposed mathematical framework allows straightforward extension to intermittent behaviour from existing one-dimensional continuous models in the linear control and ecological psychology traditions. Empirical data from a driving simulator are used in model-fitting analyses to test some of the framework's main theoretical predictions: it is shown that human steering control, in routine lane-keeping and in a demanding near-limit task, is better described as a sequence of discrete stepwise control adjustments, than as continuous control. Results on the possible roles of sensory prediction in control adjustment amplitudes, and of evidence accumulation mechanisms in control onset timing, show trends that match the theoretical predictions; these warrant further investigation. The results for the accumulation-based model align with other recent literature, in a possibly converging case against the type of threshold mechanisms that are often assumed in existing models of intermittent control.

Cranio-Caudal Kinematic Turn Signature Assessed with Inertial Systems As a Marker of Mobility Deficits in Parkinson's Disease

Background

Turning is a challenging mobility task requiring proper planning, coordination, and postural stability to be executed efficiently. Turn deficits can impair mobility and lead to falls in patients with neurodegenerative disease, such as Parkinson's disease (PD). It was previously shown that the cranio-caudal sequence involved during a turn (i.e., motion is initiated by the head, followed by the trunk) exhibits a signature that can be captured using an inertial system and analyzed through the Kinematics Theory. The so-called cranio-caudal kinematic turn signature (CCKS) metrics derived from this approach could, therefore, be a promising avenue to develop and track markers to measure early mobility deficits.

Objective

The current study aims at exploring the discriminative validity and sensitivity of CCKS metrics extracted during turning tasks performed by patients with PD.

Methods

Thirty-one participants (16 asymptomatic older adults (OA): mean age = 69.1 ± 7.5 years old; 15 OA diagnosed with early PD ON and OFF medication, mean age = 65.8 ± 8.4 years old) performed repeated timed up-and-go (TUG) tasks while wearing a portable inertial system. CCKS metrics (maximum head to trunk angle reached and commanded amplitudes of the head to trunk neuromuscular system, estimated from a sigma-lognormal model) were extracted from kinematic data recorded during the turn phase of the TUG tasks. For comparison purposes, common metrics used to analyze the quality of a turn using inertial systems were also calculated over the same trials (i.e., the number of steps required to complete the turn and the turn mean and maximum velocities).

Results

All CCKS metrics discriminated between OA and patients (p ≤ 0.041) and were sensitive to change in PD medication state (p ≤ 0.033). Common metrics were also able to discriminate between OA and patients (p < 0.014), but they were unable to capture the change in medication state this early in the disease (p ≥ 0.173).

Conclusion

The enhanced sensitivity to change of the proposed CCKS metrics suggests a potential use of these metrics for mobility impairments identification and fluctuation assessment, even in the early stages of the disease.

Combined Vision and Wearable Sensors-based System for Movement Analysis in Rehabilitation

Background: Traditional rehabilitation sessions are often a slow, tedious, disempowering and non-motivational process, supported by clinical assessment tools, i.e. evaluation scales that are prone to subjective rating and imprecise interpretation of patient’s performance. Poor patient motivation and insufficient accuracy are thus critical factors that can be improved by new sensing/processing technologies.

Objectives: We aim to develop a portable and affordable system, suitable for home rehabilitation, which combines vision-based and wearable sensors. We introduce a novel approach for examining and characterizing the rehabilitation movements, using quantitative descriptors. We propose new Movement Performance Indicators (MPIs) that are extracted directly from sensor data and quantify the symmetry, velocity, and acceleration of the movement of different body/hand parts, and that can potentially be used by therapists for diagnosis and progress assessment.

Methods: First, a set of rehabilitation exercises is defined, with the supervision of neurologists and therapists for the specific case of Parkinson’s disease. It comprises full-body movements measured with a Kinect device and fine hand movements, acquired with a data glove. Then, the sensor data is used to compute 25 Movement Performance Indicators, to assist the diagnosis and progress monitoring (assessing the disease stage) in Parkinson’s disease. A kinematic hand model is developed for data verification and as an additional resource for extracting supplementary movement information.

Results: Our results show that the proposed Movement Performance Indicators are relevant for the Parkinson’s disease assessment. This is further confirmed by correlation of the proposed indicators with clinical tapping test and UPDRS clinical scale. Classification results showed the potential of these indicators to discriminate between the patients and controls, as well as between the stages that characterize the evolution of the disease.

Conclusions: The proposed sensor system, along with the developed approach for rehabilitation movement analysis have a significant potential to support and advance traditional rehabilitation therapy. The main impact of our work is two-fold: (i) the proposition of an approach for supporting the therapists during the diagnosis and monitoring evaluations by reducing subjectivity and imprecision, and (ii) offering the possibility of the system to be used at home for rehabilitation exercises in between sessions with doctors and therapists.

Dynamic Signature Verification System Based on One Real Signature

The dynamic signature is a biometric trait widely used and accepted for verifying a person's identity. Current automatic signature-based biometric systems typically require five, ten, or even more specimens of a person's signature to learn intrapersonal variability sufficient to provide an accurate verification of the individual's identity. To mitigate this drawback, this paper proposes a procedure for training with only a single reference signature. Our strategy consists of duplicating the given signature a number of times and training an automatic signature verifier with each of the resulting signatures. The duplication scheme is based on a sigma lognormal decomposition of the reference signature. Two methods are presented to create human-like duplicated signatures: the first varies the strokes' lognormal parameters (stroke-wise) whereas the second modifies their virtual target points (target-wise). A challenging benchmark, assessed with multiple state-of-the-art automatic signature verifiers and multiple databases, proves the robustness of the system. Experimental results suggest that our system, with a single reference signature, is capable of achieving a similar performance to standard verifiers trained with up to five signature specimens.

Motor control of handwriting in the developing brain: A review

This review focuses on the acquisition of writing motor aspects in adults, and in 5-to 12-year-old children without learning disabilities. We first describe the behavioural aspects of adult writing and dominant models based on the notion of motor programs. We show that handwriting acquisition is characterized by the transition from reactive movements programmed stroke-by-stroke in younger children, to an automatic control of the whole trajectory when the motor programs are memorized at about 10 years old. Then, we describe the neural correlates of adult writing, and the changes that could occur with learning during childhood. The acquisition of a new skill is characterized by the involvement of a network more restricted in space and where neural specificity is increased in key regions. The cerebellum and the left dorsal premotor cortex are of fundamental importance in motor learning, and could be at the core of the acquisition of handwriting.

Capturing the Cranio-Caudal Signature of a Turn with Inertial Measurement Systems: Methods, Parameters Robustness and Reliability

Background

Turning is a challenging mobility task requiring coordination and postural stability. Optimal turning involves a cranio-caudal sequence (i.e., the head initiates the motion, followed by the trunk and the pelvis), which has been shown to be altered in patients with neurodegenerative diseases, such as Parkinson’s disease as well as in fallers and frails. Previous studies have suggested that the cranio-caudal sequence exhibits a specific signature corresponding to the adopted turn strategy. Currently, the assessment of cranio-caudal sequence is limited to biomechanical labs which use camera-based systems; however, there is a growing trend to assess human kinematics with wearable sensors, such as attitude and heading reference systems (AHRS), which enable recording of raw inertial signals (acceleration and angular velocity) from which the orientation of the platform is estimated. In order to enhance the comprehension of complex processes, such as turning, signal modeling can be performed.

Aim

The current study investigates the use of a kinematic-based model, the sigma-lognormal model, to characterize the turn cranio-caudal signature as assessed with AHRS.

Methods

Sixteen asymptomatic adults (mean age = 69.1 ± 7.5 years old) performed repeated 10-m Timed-Up-and-Go (TUG) with 180° turns, at varying speed. Head and trunk kinematics were assessed with AHRS positioned on each segments. Relative orientation of the head to the trunk was then computed for each trial and relative angular velocity profile was derived for the turn phase. Peak relative angle (variable) and relative velocity profiles modeled using a sigma-lognormal approach (variables: Neuromuscular command amplitudes and timing parameters) were used to extract and characterize the cranio-caudal signature of each individual during the turn phase.

Results

The methodology has shown good ability to reconstruct the cranio-caudal signature (signal-to-noise median of 17.7). All variables were robust to speed variations (p > 0.124). Peak relative angle and commanded amplitudes demonstrated moderate to strong reliability (ICC between 0.640 and 0.808).

Conclusion

The cranio-caudal signature assessed with the sigma-lognormal model appears to be a promising avenue to assess the efficiency of turns.

A Behavioral Handwriting Model for Static and Dynamic Signature Synthesis

The synthetic generation of static handwritten signatures based on motor equivalence theory has been recently proposed for biometric applications. Motor equivalence divides the human handwriting action into an effector dependent cognitive level and an effector independent motor level. The first level has been suggested by others as an engram, generated through a spatial grid, and the second has been emulated with kinematic filters. Our paper proposes a development of this methodology in which we generate dynamic information and provide a unified comprehensive synthesizer for both static and dynamic signature synthesis. The dynamics are calculated by lognormal sampling of the 8-connected continuous signature trajectory, which includes, as a novelty, the pen-ups. The forgery generation imitates a signature by extracting the most perceptually relevant points of the given genuine signature and interpolating them. The capacity to synthesize both static and dynamic signatures using a unique model is evaluated according to its ability to adapt to the static and dynamic signature inter- and intra-personal variability. Our highly promising results suggest the possibility of using the synthesizer in different areas beyond the generation of unlimited databases for biometric training.

Gestures à Go Go

Training a high-quality gesture recognizer requires providing a large number of examples to enable good performance on unseen, future data. However, recruiting participants, data collection, and labeling, etc., necessary for achieving this goal are usually time consuming and expensive. Thus, it is important to investigate how to empower developers to quickly collect gesture samples for improving UI usage and user experience. In response to this need, we introduce Gestures à Go Go (g3), a web service plus an accompanying web application for bootstrapping stroke gesture samples based on the kinematic theory of rapid human movements. The user only has to provide a gesture example once, andg3 will create a model of that gesture. Then, by introducing local and global perturbations to the model parameters,g3 generates from tens to thousands of synthetic human-like samples. Through a comprehensive evaluation, we show that synthesized gestures perform equally similar to gestures generated by human users. Ultimately, this work informs our understanding of designing better user interfaces that are driven by gestures.

Combining sigma-lognormal modeling and classical features for analyzing graphomotor performances in kindergarten children

This paper investigates the advantage of using the kinematic theory of rapid human movements as a complementary approach to those based on classical dynamical features to characterize and analyze kindergarten children's ability to engage in graphomotor activities as a preparation for handwriting learning. This study analyzes nine different movements taken from 48 children evenly distributed among three different school grades corresponding to pupils aged 3, 4, and 5 years. On the one hand, our results show that the ability to perform graphomotor activities depends on kindergarten grades. More importantly, this study shows which performance criteria, from sophisticated neuromotor modeling as well as more classical kinematic parameters, can differentiate children of different school grades. These criteria provide a valuable tool for studying children's graphomotor control learning strategies. On the other hand, from a practical point of view, it is observed that school grades do not clearly reflect pupils' graphomotor performances. This calls for a large-scale investigation, using a more efficient experimental design based on the various observations made throughout this study regarding the choice of the graphic shapes, the number of repetitions and the features to analyze.

Modeling the lexical morphology of Western handwritten signatures

A handwritten signature is the final response to a complex cognitive and neuromuscular process which is the result of the learning process. Because of the many factors involved in signing, it is possible to study the signature from many points of view: graphologists, forensic experts, neurologists and computer vision experts have all examined them. Researchers study written signatures for psychiatric, penal, health and automatic verification purposes. As a potentially useful, multi-purpose study, this paper is focused on the lexical morphology of handwritten signatures. This we understand to mean the identification, analysis, and description of the signature structures of a given signer. In this work we analyze different public datasets involving 1533 signers from different Western geographical areas. Some relevant characteristics of signature lexical morphology have been selected, examined in terms of their probability distribution functions and modeled through a General Extreme Value distribution. This study suggests some useful models for multi-disciplinary sciences which depend on handwriting signatures.

Static Signature Synthesis: A Neuromotor Inspired Approach for Biometrics

In this paper we propose a new method for generating synthetic handwritten signature images for biometric applications. The procedures we introduce imitate the mechanism of motor equivalence which divides human handwriting into two steps: the working out of an effector independent action plan and its execution via the corresponding neuromuscular path. The action plan is represented as a trajectory on a spatial grid. This contains both the signature text and its flourish, if there is one. The neuromuscular path is simulated by applying a kinematic Kaiser filter to the trajectory plan. The length of the filter depends on the pen speed which is generated using a scalar version of the sigma lognormal model. An ink deposition model, applied pixel by pixel to the pen trajectory, provides realistic static signature images. The lexical and morphological properties of the synthesized signatures as well as the range of the synthesis parameters have been estimated from real databases of real signatures such as the MCYT Off-line and the GPDS960GraySignature corpuses. The performance experiments show that by tuning only four parameters it is possible to generate synthetic identities with different stability and forgers with different skills. Therefore it is possible to create datasets of synthetic signatures with a performance similar to databases of real signatures. Moreover, we can customize the created dataset to produce skilled forgeries or simple forgeries which are easier to detect, depending on what the researcher needs. Perceptual evaluation gives an average confusion of 44.06 percent between real and synthetic signatures which shows the realism of the synthetic ones. The utility of the synthesized signatures is demonstrated by studying the influence of the pen type and number of users on an automatic signature verifier.

The effect of computer-assisted therapeutic practice for children with handwriting deficit: a comparison with the effect of the traditional sensorimotor approach

The objective of this study was to compare the effect of computer-assisted practice with the sensorimotor approach on the remediation of handwriting problems in children with dysgraphia. In a randomized controlled trial, experiments were conducted to verify the intervention effect. Forty two children with handwriting deficit were assigned to computer-assisted instruction, sensorimotor training, or a control group. Handwriting performance was measured using the elementary reading/writing test and computerized handwriting evaluation before and after 6 weeks of intervention. Repeated-measures ANOVA of changed scores were conducted to show whether statistically significant differences across the three groups were present. Significant differences in the elementary reading/writing test were found among the three groups. The computer group showed more significant improvements than the other two groups did. In the kinematic and kinetic analyses, the computer group showed promising results in the remediation of handwriting speed and fluency. This study provided clinical evidence for applying a computer-assisted handwriting program for children with dysgraphia. Clinicians and school teachers are provided with a systematic intervention for the improvement of handwriting difficulties.

The lognormal handwriter: learning, performing, and declining

The generation of handwriting is a complex neuromotor skill requiring the interaction of many cognitive processes. It aims at producing a message to be imprinted as an ink trace left on a writing medium. The generated trajectory of the pen tip is made up of strokes superimposed over time. The Kinematic Theory of rapid human movements and its family of lognormal models provide analytical representations of these strokes, often considered as the basic unit of handwriting. This paradigm has not only been experimentally confirmed in numerous predictive and physiologically significant tests but it has also been shown to be the ideal mathematical description for the impulse response of a neuromuscular system. This latter demonstration suggests that the lognormality of the velocity patterns can be interpreted as reflecting the behavior of subjects who are in perfect control of their movements. To illustrate this interpretation, we present a short overview of the main concepts behind the Kinematic Theory and briefly describe how its models can be exploited, using various software tools, to investigate these ideal lognormal behaviors. We emphasize that the parameters extracted during various tasks can be used to analyze some underlying processes associated with their realization. To investigate the operational convergence hypothesis, we report on two original studies. First, we focus on the early steps of the motor learning process as seen as a converging behavior toward the production of more precise lognormal patterns as young children practicing handwriting start to become more fluent writers. Second, we illustrate how aging affects handwriting by pointing out the increasing departure from the ideal lognormal behavior as the control of the fine motricity begins to decline. Overall, the paper highlights this developmental process of merging toward a lognormal behavior with learning, mastering this behavior to succeed in performing a given task, and then gradually deviating from it with aging.

Quantifying long-term scientific impact

The lack of predictability of citation-based measures frequently used to gauge impact, from impact factors to short-term citations, raises a fundamental question: Is there long-term predictability in citation patterns? Here, we derive a mechanistic model for the citation dynamics of individual papers, allowing us to collapse the citation histories of papers from different journals and disciplines into a single curve, indicating that all papers tend to follow the same universal temporal pattern. The observed patterns not only help us uncover basic mechanisms that govern scientific impact but also offer reliable measures of influence that may have potential policy implications.

Handwriting movement analyses comparing first and second graders with normal or dysgraphic characteristics

Dysgraphia of sufficient severity to interfere with the school work has been recognized as representing a distinct deficit; characterization of its movement problem is a necessary step toward offering improved intervention. From among children aged 6-8, 69 children with dysgraphic characteristics (study group) and 69 matched proficient hand-writers (control group) were recruited into this study. Four copying tests of differing complexity levels were administered using a digital tablet. The acquired data included direct measure (axial pen tip force) and derived parameters (stroke velocity, pause time, number of velocity peaks and ratio of In Air to On Paper measures). The major finding is that children with dysgraphic characteristics had increased pause time per stroke and an increased number of directional changes in velocity. Significant differences were also found between students in two different grades, especially in the control group. The parameters extracted and observed in this study can further differentiate and characterize the handwriting problems originating from fine motor deficits.

Using kinematic analysis of movement to predict the time occurrence of an evoked potential associated with a motor command

This article presents an exploratory study investigating the possibility of predicting the time occurrence of a motor event related potential (ERP) from a kinematic analysis of human movements. Although the response-locked motor potential may link the ERP components to the recorded response, to our knowledge no previous attempt has been made to predict a priori (i.e. before any contact with the electroencephalographic data) the time occurrence of an ERP component based only on the modeling of an overt response. The proposed analysis relies on the delta-lognormal modeling of velocity, as proposed by the kinematic theory of rapid human movement used in several studies of motor control. Although some methodological aspects of this technique still need to be fine-tuned, the initial results showed that the model-based kinematic analysis allowed the prediction of the time occurrence of a motor command ERP in most participants in the experiment. The average map of the motor command ERPs showed that this signal was stronger in electrodes close to the contra-lateral motor area (Fz, FCz, FC1, and FC3). These results seem to support the claims made by the kinematic theory that a motor command is emitted at time t(0), the time reference parameter of the model. This article proposes a new time marker directly associated with a cerebral event (i.e. the emission of a motor command) that can be used for the development of new data analysis methodologies and for the elaboration of new experimental protocols based on ERP.

Cluster-based exposure variation analysis

Background

Static posture, repetitive movements and lack of physical variation are known risk factors for work-related musculoskeletal disorders, and thus needs to be properly assessed in occupational studies. The aims of this study were (i) to investigate the effectiveness of a conventional exposure variation analysis (EVA) in discriminating exposure time lines and (ii) to compare it with a new cluster-based method for analysis of exposure variation.

Methods

For this purpose, we simulated a repeated cyclic exposure varying within each cycle between “low” and “high” exposure levels in a “near” or “far” range, and with “low” or “high” velocities (exposure change rates). The duration of each cycle was also manipulated by selecting a “small” or “large” standard deviation of the cycle time. Theses parameters reflected three dimensions of exposure variation, i.e. range, frequency and temporal similarity.

Each simulation trace included two realizations of 100 concatenated cycles with either low (ρ = 0.1), medium (ρ = 0.5) or high (ρ = 0.9) correlation between the realizations. These traces were analyzed by conventional EVA, and a novel cluster-based EVA (C-EVA). Principal component analysis (PCA) was applied on the marginal distributions of 1) the EVA of each of the realizations (univariate approach), 2) a combination of the EVA of both realizations (multivariate approach) and 3) C-EVA. The least number of principal components describing more than 90% of variability in each case was selected and the projection of marginal distributions along the selected principal component was calculated. A linear classifier was then applied to these projections to discriminate between the simulated exposure patterns, and the accuracy of classified realizations was determined.

Results

C-EVA classified exposures more correctly than univariate and multivariate EVA approaches; classification accuracy was 49%, 47% and 52% for EVA (univariate and multivariate), and C-EVA, respectively (p < 0.001). All three methods performed poorly in discriminating exposure patterns differing with respect to the variability in cycle time duration.

Conclusion

While C-EVA had a higher accuracy than conventional EVA, both failed to detect differences in temporal similarity. The data-driven optimality of data reduction and the capability of handling multiple exposure time lines in a single analysis are the advantages of the C-EVA.