RESUMO
Shoulder exosuits are a promising new technology that could enable individuals with neuromuscular impairments to independently perform activities of daily living, however, scarce evidence exists to evaluate their ability to support such activities. Consequently, it is not understood how humans adapt motion in response to assistance from a shoulder exosuit. In this study, we developed a cable-driven shoulder exosuit and evaluated its effect on reaching and drinking tasks within a cohort of 18 healthy subjects to quantify changes to muscle activity and kinematics as well as trial-to-trial learning in duration and actuator switch timing. The exosuit successfully reduced mean muscle activity in the middle (reaching: 23.4±26.3%, drinking: 20.0±25.1%) and posterior (reaching: 12.8±10.3%, drinking: 4.0±7.2%) deltoid across both functional tasks. Likewise, the exosuit reduced integrated muscle activity in the middle deltoid (reaching: 22.2±22.7%, drinking: 14.9±27.0%). Exosuit assistance also altered kinematics such that individuals allowed their arms to follow forces applied by the exosuit. In terms of learning, subjects reduced movement duration by 15.6±11.9% as they practiced using the exosuit. Reducing movement duration allowed subjects to reduce integrated muscle activity in the anterior (15.2±10.3%), middle (14.7±9.7%), and posterior (14.8±9.7%) deltoids. Similarly, subjects activated the actuator switch earlier over the course of many assisted trials. The muscle activity reductions during both reaching and drinking demonstrate the promise of shoulder exosuits to enable independent function among individuals with neuromuscular impairments. The kinematic response to assistance and learning features observed in movement duration provide insight into human-exosuit interaction principles that could inform future exosuit development.
RESUMO
There is evidence that balance performance deteriorates due to exercise-induced muscle fatigue. However, it is unknown if free arm movement during balance testing can compensate for, or restricted arm movement can amplify these performance degradations. Thus, the objective of this study was to compare the effects of free versus restricted arm movement on balance performance under non-fatigued and fatigued conditions. Fifty-two healthy participants (men=31, women=21; age=22.6±1.6 years) were assessed for their dynamic balance (reach distances for the Y Balance Test - Lower Quarter) under non-fatigued and fatigued (repetitive vertical bipedal box jumps until failure) conditions using two different arm positions: free (move the arms freely) and restricted (keep the arms akimbo) arm movement. Restriction of arm movement (all p< 0.001; 0.48≤ η p 2 ≤0.79) and application of fatigue ( p≤ 0.003; 0.16≤ η p 2 ≤0.28) independently, but not the interaction between the two (except for the posteromedial reach direction: p= 0.046; η p 2 =0.08) , resulted in significantly deteriorated lower limb reach distances. These findings suggest that free arm movement and thus the use of an 'upper body strategy' has no compensatory effect on muscle fatigue-induced balance deteriorations.
RESUMO
BACKGROUND: Following a stroke, brain activation reorganisation, movement compensatory strategies, motor performance and their evolution through rehabilitation are matters of importance for clinicians. Two non-invasive neuroimaging methods allow for recording task-related brain activation: functional near-infrared spectroscopy (fNIRS) and electroencephalography (fEEG), respectively based on hemodynamic response and neuronal electrical activity. Their simultaneous measurement during movements could allow a better spatiotemporal mapping of brain activation, and when associated to kinematic parameters could unveil underlying mechanisms of functional upper limb (UL) recovery. This study aims to depict the motor cortical activity patterns using combined fNIRS-fEEG and their relationship to motor performance and strategies during UL functional tasks in chronic post-stroke patients. METHODS: Twenty-one healthy old adults and 21 chronic post-stroke patients were recruited and completed two standardised functional tasks of the UL: a paced-reaching task where they had to reach a target in front of them and a circular steering task where they had to displace a target using a hand-held stylus, as fast as possible inside a circular track projected on a computer screen. The activity of the bilateral motor cortices and motor performance were recorded simultaneously utilizing a fNIRS-fEEG and kinematics platform. RESULTS AND CONCLUSIONS: Kinematic analysis revealed that post-stroke patients performed worse in the circular steering task and used more trunk compensation in both tasks. Brain analysis of bilateral motor cortices revealed that stroke individuals over-activated during the paretic UL reaching task, which was associated with more trunk usage and a higher level of impairment (clinical scores). This work opens up avenues for using such combined methods to better track and understand brain-movement evolution through stroke rehabilitation.
Assuntos
Eletroencefalografia , Córtex Motor , Movimento , Espectroscopia de Luz Próxima ao Infravermelho , Reabilitação do Acidente Vascular Cerebral , Acidente Vascular Cerebral , Extremidade Superior , Humanos , Masculino , Feminino , Extremidade Superior/fisiopatologia , Acidente Vascular Cerebral/fisiopatologia , Acidente Vascular Cerebral/complicações , Idoso , Pessoa de Meia-Idade , Movimento/fisiologia , Córtex Motor/fisiopatologia , Córtex Motor/diagnóstico por imagem , Fenômenos Biomecânicos , Encéfalo/fisiopatologia , Encéfalo/diagnóstico por imagem , Desempenho Psicomotor/fisiologia , Doença Crônica , AdultoRESUMO
Detecting intentions and estimating movement trajectories in a human-machine interface (HMI) using electromyogram (EMG) signals is particularly challenging, especially for individuals with movement impairments. Therefore, incorporating additional information from other biological sources, potential discrete information in the movement, and the EMG signal can be practical. This study combined EMG and target information to enhance estimation performance during reaching movements. EMG activity of the shoulder and arm muscles, elbow angle, and the electroencephalogram signals of ten healthy subjects were recorded while they reached blinking targets. The reaching target was recognized by steady-state visual evoked potential (SSVEP). The selected target's final angle and EMG were then mapped to the elbow angle trajectory. The proposed bimodal structure, which integrates EMG and final elbow angle information, outperformed the EMG-based decoder. Even under conditions of higher fatigue, the proposed structure provided better performance than the EMG decoder. Including additional information about the recognized reaching target in the trajectory model improved the estimation of the reaching profile. Consequently, this study's findings suggest that bimodal decoders are highly beneficial for enhancing assistive robotic devices and prostheses, especially for real-time upper limb rehabilitation.
RESUMO
Interlimb differences in reach control could impact the learning of a motor sequence that requires whole-arm movements. The purpose of this study was to investigate the learning of an implicit, 3-dimensional whole-arm sequence task with the non-dominant left arm compared to the dominant right arm. Thirty-one right-hand dominant adults completed two consecutive days of practice of a motor sequence task presented in a virtual environment with either their dominant right or non-dominant left arm. Targets were presented one-at-a-time alternating between Random and Repeated sequences. Task performance was indicated by the time to complete the sequence (response time), and kinematic measures (hand path distance, peak velocity) were used to examine how movements changed over time. While the Left Arm group was slower than the Right Arm group at baseline, both groups significantly improved response time with practice with the Left Arm group demonstrating greater gains. The Left Arm group improved performance by decreasing hand path distance (straighter path to targets) while the Right Arm group improved performance through a smaller decrease in hand path distance combined with increasing peak velocity. Gains made during practice on Day 1 were retained on Day 2 for both groups. Overall, individuals reaching with the non-dominant left arm learned the whole-arm motor sequence task but did so through a different strategy than individuals reaching with the dominant right arm. The strategy adopted for the learning of movement sequences that require whole-arm movements may be impacted by differences in reach control between the nondominant and dominant arms.
RESUMO
A vexing characteristic of motor disability after stroke is that many individuals fail to use their affected arm effectively despite having the capacity to do so, a phenomenon termed arm nonuse. Based on the hypothesis that nonuse is influenced by the competing cognitive demands of many daily activities, we examined the effects of cognitive load on arm choice and motor performance in individuals with stroke using a novel virtual reality paradigm that mimics the demands of real-life visual search, object selection, and reaching to targets. Twenty individuals with single left or right hemispheric chronic stroke (11 left cerebrovascular accident; 9 right cerebrovascular accident) and 10 age-matched neurotypical participants completed the Virtual Reality Arm Choice task, in which they reached for target objects in an array under varied cognitive demand. To manipulate cognitive demand, we varied the semantic similarity of objects in the reaching space and the presence or absence of a secondary task. The results showed reduced use of the paretic arm under increased demand. Under cognitive load, participants with stroke also showed slower reach initiation, slower movements, increased reach curvature, and increased performance differences between the paretic and non-paretic arms. The arm choice of neurotypical individuals was also modulated under cognitive load. These data indicate that cognitive factors influence arm choice and motor performance in naturalistic reaching tasks in individuals with chronic stroke. Performance decrements under cognitive load may in turn influence reduced paretic arm use during daily activities.
RESUMO
During delayed ballistic reaches, motor areas consistently display movement-specific activity patterns prior to movement onset. It is unclear why these patterns arise: while they have been proposed to seed an initial neural state from which the movement unfolds, recent experiments have uncovered the presence and necessity of ongoing inputs during movement, which may lessen the need for careful initialization. Here, we modeled the motor cortex as an input-driven dynamical system, and we asked what the optimal way to control this system to perform fast delayed reaches is. We find that delay-period inputs consistently arise in an optimally controlled model of M1. By studying a variety of network architectures, we could dissect and predict the situations in which it is beneficial for a network to prepare. Finally, we show that optimal input-driven control of neural dynamics gives rise to multiple phases of preparation during reach sequences, providing a novel explanation for experimentally observed features of monkey M1 activity in double reaching.
Assuntos
Modelos Neurológicos , Córtex Motor , Movimento , Córtex Motor/fisiologia , Animais , Movimento/fisiologia , Rede Nervosa/fisiologia , Redes Neurais de Computação , Desempenho Psicomotor/fisiologia , HumanosRESUMO
Identifying the effects of pain catastrophizing on movement patterns in people with chronic low back pain (CLBP) has important clinical implications for treatment approaches. Prior research has shown people with CLBP have decreased lumbar-hip ratios during trunk flexion movements, indicating a decrease in the contribution of lumbar flexion relative to hip flexion during trunk flexion. In this study, we aim to explore the relationship between pain catastrophizing and movement patterns during trunk flexion in a CLBP population. Participants with CLBP (N = 98, male = 59, age = 39.1 ± 13.0) completed a virtual reality standardized reaching task that necessitated a progressively larger amount of trunk flexion. Specifically, participants reached for four virtual targets to elicit 15°, 30°, 45°, and 60° trunk flexion in the mid-sagittal plane. Lumbar flexion was derived from the motion data. Self-report measures of numerical pain ratings, kinesiophobia, and pain catastrophizing were obtained. Pain catastrophizing leads to decreased lumbar flexion angles during forward reaching. This effect is greater in females than males.
RESUMO
Real-world actions often comprise a series of movements that cannot be entirely planned before initiation. When these actions are executed rapidly, the planning of multiple future movements needs to occur simultaneously with the ongoing action. How the brain solves this task remains unknown. Here, we address this question with a new sequential arm reaching paradigm that manipulates how many future reaches are available for planning while controlling execution of the ongoing reach. We show that participants plan at least two future reaches simultaneously with an ongoing reach. Further, the planning processes of the two future reaches are not independent of one another. Evidence that the planning processes interact is twofold. First, correcting for a visual perturbation of the ongoing reach target is slower when more future reaches are planned. Second, the curvature of the current reach is modified based on the next reach only when their planning processes temporally overlap. These interactions between future planning processes may enable smooth production of sequential actions by linking individual segments of a long sequence at the level of motor planning.
Assuntos
Braço , Movimento , Desempenho Psicomotor , Humanos , Braço/fisiologia , Movimento/fisiologia , Desempenho Psicomotor/fisiologia , Masculino , Feminino , Adulto , Adulto JovemRESUMO
BACKGROUND: Planning and executing movements requires the integration of different sensory modalities, such as vision and proprioception. However, neurological diseases like stroke can lead to full or partial loss of proprioception, resulting in impaired movements. Recent advances focused on providing additional sensory feedback to patients to compensate for the sensory loss, proving vibrotactile stimulation to be a viable option as it is inexpensive and easy to implement. Here, we test how such vibrotactile information can be integrated with visual signals to estimate the spatial location of a reach target. METHODS: We used a center-out reach paradigm with 31 healthy human participants to investigate how artificial vibrotactile stimulation can be integrated with visual-spatial cues indicating target location. Specifically, we provided multisite vibrotactile stimulation to the moving dominant arm using eccentric rotating mass (ERM) motors. As the integration of inputs across multiple sensory modalities becomes especially relevant when one of them is uncertain, we additionally modulated the reliability of visual cues. We then compared the weighing of vibrotactile and visual inputs as a function of visual uncertainty to predictions from the maximum likelihood estimation (MLE) framework to decide if participants achieve quasi-optimal integration. RESULTS: Our results show that participants could estimate target locations based on vibrotactile instructions. After short training, combined visual and vibrotactile cues led to higher hit rates and reduced reach errors when visual cues were uncertain. Additionally, we observed lower reaction times in trials with low visual uncertainty when vibrotactile stimulation was present. Using MLE predictions, we found that integration of vibrotactile and visual cues followed optimal integration when vibrotactile cues required the detection of one or two active motors. However, if estimating the location of a target required discriminating the intensities of two cues, integration violated MLE predictions. CONCLUSION: We conclude that participants can quickly learn to integrate visual and artificial vibrotactile information. Therefore, using additional vibrotactile stimulation may serve as a promising way to improve rehabilitation or the control of prosthetic devices by patients suffering loss of proprioception.
Assuntos
Sinais (Psicologia) , Desempenho Psicomotor , Vibração , Percepção Visual , Humanos , Masculino , Feminino , Adulto , Percepção Visual/fisiologia , Desempenho Psicomotor/fisiologia , Adulto Jovem , Retroalimentação Sensorial/fisiologia , Propriocepção/fisiologia , Percepção do Tato/fisiologia , Incerteza , Estimulação Física/métodos , Percepção Espacial/fisiologia , Movimento/fisiologiaRESUMO
BACKGROUND: Reaching and grasping (R&G) in rats is commonly used as an outcome measure to investigate the effectiveness of rehabilitation or treatment strategies to recover forelimb function post spinal cord injury. Kinematic analysis has been limited to the wrist and digit movements. Kinematic profiles of the more proximal body segments that play an equally crucial role in successfully executing the task remain unexplored. Additionally, understanding of different forelimb muscle activity, their interactions, and their correlation with the kinematics of R&G movement is scarce. NEW METHOD: In this work, novel methodologies to comprehensively assess and quantify the 3D kinematics of the proximal and distal forelimb joints along with associated muscle activity during R&G movements in adult rats are developed and discussed. RESULTS: Our data show that different phases of R&G identified using the novel kinematic and EMG-based approach correlate with the well-established descriptors of R&G stages derived from the Whishaw scoring system. Additionally, the developed methodology allows describing the temporal activity of individual muscles and associated mechanical and physiological properties during different phases of the motor task. COMPARISON WITH EXISTING METHOD(S): R&G phases and their sub-components are identified and quantified using the developed kinematic and EMG-based approach. Importantly, the identified R&G phases closely match the well-established qualitative descriptors of the R&G task proposed by Whishaw and colleagues. CONCLUSIONS: The present work provides an in-depth objective analysis of kinematics and EMG activity of R&G behavior, paving the way to a standardized approach to assessing this critical rodent motor function in future studies.
Assuntos
Eletromiografia , Membro Anterior , Força da Mão , Músculo Esquelético , Animais , Fenômenos Biomecânicos/fisiologia , Membro Anterior/fisiologia , Eletromiografia/métodos , Músculo Esquelético/fisiologia , Força da Mão/fisiologia , Ratos , Traumatismos da Medula Espinal/fisiopatologia , Feminino , Destreza Motora/fisiologia , Masculino , Ratos Sprague-Dawley , Comportamento Animal/fisiologia , Movimento/fisiologiaRESUMO
Incentives tend to drive improvements in performance. But when incentives get too high, we can "choke under pressure" and underperform right when it matters most. What neural processes might lead to choking under pressure? We studied rhesus monkeys performing a challenging reaching task in which they underperformed when an unusually large "jackpot" reward was at stake, and we sought a neural mechanism that might result in that underperformance. We found that increases in reward drive neural activity during movement preparation into, and then past, a zone of optimal performance. We conclude that neural signals of reward and motor preparation interact in the motor cortex (MC) in a manner that can explain why we choke under pressure.
Assuntos
Macaca mulatta , Córtex Motor , Desempenho Psicomotor , Recompensa , Animais , Córtex Motor/fisiologia , Desempenho Psicomotor/fisiologia , Masculino , Motivação/fisiologia , Neurônios/fisiologia , Movimento/fisiologiaRESUMO
Computational principles shed light on why movement is preceded by preparatory activity within the neural networks that control muscles.
Assuntos
Movimento , Humanos , Animais , Rede Nervosa/fisiologia , Músculo Esquelético/fisiologiaRESUMO
Background: A rodent autism spectrum disorder (ASD) model based on prenatal exposure to valproic acid (VPA) is widely recognized as a prominent model. Social behavior in rodent ASD models has primarily been evaluated through a three-chamber approach test. However, in this study, we focused on social attention in the VPA model of ASD. Methods: In male C57BL/6 J mice, attentional behaviors toward conspecifics were examined through reaching tasks around 9-11 weeks of age. On embryonic day 12.5, pregnant mice underwent a subcutaneous injection of 600 mg/kg VPA sodium salt dissolved in 0.9% saline solution (VPA group) or saline solution alone (Sal group) into their neck fat. Thirty-six mice-nine each in the VPA and saline groups, and 18 partners-underwent training in reaching behavior. Subsequently, we examined whether the VPA or Sal group demonstrated focused attention toward their partners during reaching tasks. A two-way analysis of variance (ANOVA) (condition [VPA/Sal] × situation [face-to-face (attention)/not paying attention (not attention)]) was conducted on the average success rate of the situation. Additionally, we measured the duration of sniffing behavior between pairs of mice in an open field twice in total at 4 and 8 weeks of age before reaching task. The pairs were constructed by pairing a VPA or Sal group mouse with its partner, with the objective of facilitating initial encounters between the mice. A one-way ANOVA was conducted on the average duration of sniffing behavior data from 4 weeks and a second one-way ANOVA on data from 8 weeks. Results: The analysis revealed a significant interaction between condition and situation in the reaching task [F (1, 28) = 6.75, p = 0.015, ηp 2 = 0.19]. The simple main effect test exhibited that the "not paying attention" rate was significantly higher than that of the "face-to-face" in the VPA group (p < 0.01). The results revealed a not significant difference in the average duration of sniffing behavior at 4 weeks [F (3, 32) = 2.71, p = 0.06, n.s., ηp 2 = 0.20], but significant difference at 8 weeks [F (3, 32) = 4.12, p < 0.05, ηp 2 = 0.28]. Multiple comparisons using the Bonferroni method revealed significant differences in the sniffing duration at 8 weeks between from the partner toward the VPA mouse and from the partner toward the Sal mouse (p < 0.05). Conclusion: The VPA rodent model of ASD exhibited differences in social attention compared to the saline group. By focusing on social attention and exploring various ASD models, insights can be gained from the neural mechanisms underlying gaze abnormalities during social interaction in individuals with ASD.
RESUMO
Decision making is often necessary before performing an action. Traditionally, it has been assumed that decision making and motor control are independent, sequential processes. Ogasa et al. challenge this view, and demonstrate that the decision-making process significantly impacts on the formation and retrieval of motor memory by tagging it with the level of confidence.
Assuntos
Tomada de Decisões , Memória , Humanos , Tomada de Decisões/fisiologia , Memória/fisiologia , Desempenho Psicomotor/fisiologia , Atividade Motora/fisiologiaRESUMO
BACKGROUND: A valid and reliable assessment tool to describe the quality of the movement pattern of reaching can provide valuable insights into motor performance deficits in persons with MS (pwMS). The Reaching Performance Scale, developed for stroke, is a promising scale to assess movement patterns in pwMS. However, psychometric properties of the scale are lacking in pwMS. OBJECTIVES: Firstly, to investigate the content validity of the modified Reaching Performance Scale for application in patients with MS (mRPS). Secondly, to investigate the psychometric properties (within- and between-session reliability and concurrent validity) of the mRPS for pwMS. METHODS: Forty-five pwMS (mean EDSS 6.6 pt, IQR 6-7.5) executed the mRPS that rates the quality of movement patterns and compensations during reach to grasp tasks. The content validity was determined by an expert panel based on observations of subjects performing the RPS. The reliability was based on five repetitions within one day, and between two days. For the concurrent validity, outcome measures at two levels of the International Classification of Functioning were correlated with the mRPS: Body Structure and Function level: Fugl-Meyer Assessment of the Upper Limb (FMA-UL), maximal isometric hand grip strength (HGS; Activity level: Action Research Arm Test (ARAT), Box and Blocks Test (BBT), Nine Hole Peg Test (NHPT) and Trunk Impairment Scale 2.0 (TIS 2.0) as well as perceived performance by the Manual Ability Measure-36 (MAM-36). RESULTS: Scale modifications were made only on the ratings of the trunk displacement subscale. The mRPS had excellent agreement scores for within-session reliability (range of Kappa between 0.85 and 0.98) and moderate-to-excellent agreement scores for between-session reliability (K: 0.66-1.00). Regarding validity, the mRPS was highly correlated with the ARAT (rho=0.74, p < 0.001), followed by moderate correlations with trunk performance (TIS 2.0, rho= 0.61, p < 0.001), hand function (BBT: rho=0.64, p < 0.001; NHPT: rho=-0.61, p < 0.001) and perceived performance (MAM36 rho= 0.53, p < 0.001). CONCLUSION: The mRPS is a reliable measurement tool to describe the movement pattern quality and motor compensations used during reaching in pwMS. Concerning concurrent validity, the mRPS is partially related to other measures of upper limb and trunk performance.
Assuntos
Esclerose Múltipla , Psicometria , Humanos , Psicometria/normas , Masculino , Feminino , Pessoa de Meia-Idade , Reprodutibilidade dos Testes , Adulto , Esclerose Múltipla/fisiopatologia , Esclerose Múltipla/complicações , Extremidade Superior/fisiopatologia , Desempenho Psicomotor/fisiologia , Força da Mão/fisiologia , Avaliação da DeficiênciaRESUMO
Reaching movements can be redirected during their progress to handle unexpected visual changes, such as a change in target location. It is important to know when these redirections start, i.e., the online reaction time (oRT), but this information is not readily evident since redirections are embedded within a time-varying baseline movement that differs from trial to trial. The one previous study that evaluated the performance of different oRT identification methods utilized simulated redirections with the exact same onset, rather than a range of onsets as would be typically encountered. We addressed this gap by utilizing batches of "hybrid" trials with temporal spread in their oRTs. Each hybrid trial combined a sampled baseline movement with an idealized corrective response. Two new methods had the most accurate identification of online reaction times: 1) a threshold-aligned grand mean regression, and 2) a template-based approach we term the canonical correction search. The threshold-aligned grand mean regression is simple to implement and effective. The canonical correction search is a more complex procedure but arguably better linked to the underlying response. Applying the two methods to a published dataset revealed more delayed oRTs than was previously reported along with new information such as the width of oRT distributions. Taken together, our results demonstrate the utility of two new methods for dissecting corrective action from ongoing movement.NEW & NOTEWORTHY Advancing our understanding of visual feedback control requires methods that accurately identify the onset of corrective action. We developed a modified regression approach and a template-based approach to identify the online reaction time of single-reaching movements. Both outperform previous methods when challenged by temporal jitter in the response onset and increased background noise.
Assuntos
Desempenho Psicomotor , Tempo de Reação , Humanos , Tempo de Reação/fisiologia , Desempenho Psicomotor/fisiologia , Masculino , Adulto , Feminino , Movimento/fisiologia , Adulto JovemRESUMO
Striatum and its predominant input, motor cortex, are responsible for the selection and performance of purposive movement, but how their interaction guides these processes is not understood. To establish its neural and behavioral contributions, we bilaterally lesioned motor cortex and recorded striatal activity and reaching performance daily, capturing the lesion's direct ramifications within hours of the intervention. We observed reaching impairment and an absence of striatal motoric activity following lesion of motor cortex, but not parietal cortex control lesions. Although some aspects of performance began to recover after 8-10 days, striatal projection and interneuronal dynamics did not-eventually entering a non-motor encoding state that aligned with persisting kinematic control deficits. Lesioned mice also exhibited a profound inability to switch motor plans while locomoting, reminiscent of clinical freezing of gait (FOG). Our results demonstrate the necessity of motor cortex in generating trained and untrained actions as well as striatal motoric dynamics.
Assuntos
Corpo Estriado , Córtex Motor , Córtex Motor/fisiologia , Animais , Camundongos , Corpo Estriado/fisiologia , Masculino , Destreza Motora/fisiologia , Camundongos Endogâmicos C57BL , Desempenho Psicomotor/fisiologia , Movimento/fisiologia , Fenômenos Biomecânicos/fisiologia , Lobo Parietal/fisiologiaRESUMO
Intention detection of the reaching movement is considerable for myoelectric human and machine collaboration applications. A comprehensive set of handcrafted features was mined from windows of electromyogram (EMG) of the upper-limb muscles while reaching nine nearby targets like activities of daily living. The feature selection-based scoring method, neighborhood component analysis (NCA), selected the relevant feature subset. Finally, the target was recognized by the support vector machine (SVM) model. The classification performance was generalized by a nested cross-validation structure that selected the optimal feature subset in the inner loop. According to the low spatial resolution of the target location on display and following the slight discrimination of signals between targets, the best classification accuracy of 77.11 % was achieved for concatenating the features of two segments with a length of 2 and 0.25 s. Due to the lack of subtle variation in EMG, while reaching different targets, a wide range of features was applied to consider additional aspects of the knowledge contained in EMG signals. Furthermore, since NCA selected features that provided more discriminant power, it became achievable to employ various combinations of features and even concatenated features extracted from different movement parts to improve classification performance.