Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1502025
M. Mirbagheri, C. Tsao, E. Pelosin, W. Rymer
We studied the effects of robotic-assisted locomotor (LOKOMAT) training on the neuromuscular mechanical properties and voluntary movement of the spastic ankle in persons with incomplete spinal cord injury (SCI). System identification techniques were used to characterize the effects of Lokomat training on the mechanical abnormalities of the ankle joint. We also determined the effects of this physical training on repeated voluntary movements of the ankle from full plantarflexion to dorsiflexion at maximum speed, quantified by measuring their kinematics parameters. We found that reflex stiffness, abnormally increased in SCI, was significantly reduced following LOKOMAT training. Active range of motion, peak-velocity and peak-acceleration of voluntary movement increased as a result of LOKOMAT training. These findings demonstrate that LOKOMAT training has a potential to modify abnormal reflex function and improve impaired voluntary movement.
{"title":"Therapeutic effects of robotic-assisted locomotor training on neuromuscular properties","authors":"M. Mirbagheri, C. Tsao, E. Pelosin, W. Rymer","doi":"10.1109/ICORR.2005.1502025","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1502025","url":null,"abstract":"We studied the effects of robotic-assisted locomotor (LOKOMAT) training on the neuromuscular mechanical properties and voluntary movement of the spastic ankle in persons with incomplete spinal cord injury (SCI). System identification techniques were used to characterize the effects of Lokomat training on the mechanical abnormalities of the ankle joint. We also determined the effects of this physical training on repeated voluntary movements of the ankle from full plantarflexion to dorsiflexion at maximum speed, quantified by measuring their kinematics parameters. We found that reflex stiffness, abnormally increased in SCI, was significantly reduced following LOKOMAT training. Active range of motion, peak-velocity and peak-acceleration of voluntary movement increased as a result of LOKOMAT training. These findings demonstrate that LOKOMAT training has a potential to modify abnormal reflex function and improve impaired voluntary movement.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131383874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501126
J. Sensinger, R. Weir
The compliance of series elastic actuators makes them robust to environmental perturbations, and their ability to use impedance control may improve their performance in open-loop environments such as conventional prosthetic control. Series elastic actuators have historically required a backdrivable transmission to ensure adequate bandwidth. The authors have created a non-backdrivable series elastic actuator through the inclusion of a harmonic drive transmission, which contains no backlash; the dominant feature in limiting frequency resolution. The actuator has an acceptable speed and stall torque and an adequate frequency range, and would be used in the future to implement impedance control of prosthetics.
{"title":"Design and analysis of a non-backdrivable series elastic actuator","authors":"J. Sensinger, R. Weir","doi":"10.1109/ICORR.2005.1501126","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501126","url":null,"abstract":"The compliance of series elastic actuators makes them robust to environmental perturbations, and their ability to use impedance control may improve their performance in open-loop environments such as conventional prosthetic control. Series elastic actuators have historically required a backdrivable transmission to ensure adequate bandwidth. The authors have created a non-backdrivable series elastic actuator through the inclusion of a harmonic drive transmission, which contains no backlash; the dominant feature in limiting frequency resolution. The actuator has an acceptable speed and stall torque and an adequate frequency range, and would be used in the future to implement impedance control of prosthetics.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132607197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501105
J. Chu, Inhyuk Moon, M. Mun
This paper proposes a novel real-time EMG pattern recognition for the control of multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. We implement a real-time control system for a multifunction virtual hand. From experimental results, we show that all processes, including virtual hand control, are completed within 125 msec, and the proposed method is applicable to real-time myoelectric hand control without an operation time delay.
{"title":"A real-time EMG pattern recognition based on linear-nonlinear feature projection for multifunction myoelectric hand","authors":"J. Chu, Inhyuk Moon, M. Mun","doi":"10.1109/ICORR.2005.1501105","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501105","url":null,"abstract":"This paper proposes a novel real-time EMG pattern recognition for the control of multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. We implement a real-time control system for a multifunction virtual hand. From experimental results, we show that all processes, including virtual hand control, are completed within 125 msec, and the proposed method is applicable to real-time myoelectric hand control without an operation time delay.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130889145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501085
M. Saleh, A. Caplan, M. Serruya, J. Donoghue
Extracellular recordings of motor cortex (MI) neurons, using a chronically implanted multi-electrode array, promise to yield a high dimensional input signal to external devices such as a computer, exoskeleton or prosthetic arm. For the multi-electrode array to be used as a sensor for a neuromotor prosthesis (NMP), it is important that it continually record movement-related signals over long time periods. Recent studies have demonstrated that it is possible to continually record for up to 1.5 years from a sufficient number of MI neurons in monkeys to enable neural decoding of arm movement. Cyberkinetics Neurotechnology Systems Inc. has initiated an investigational device exemption (TOE) study investigating the safety and efficacy of the BrainGate/spl trade/ Neural Interface System, a medical device that combines this sensor with data acquisition and processing devices to decode movement intent. This device is currently being investigated as a means for a quadriplegic person to operate a range of assistive technologies. Preliminary results from this case study provide evidence that (1) MI neurons remain active more than 3 years after spinal cord injury, (2) units can be recorded 6 months after surgery. This technology may benefit quadriplegic people by providing a new output pathway from the cortex, to control their muscles.
{"title":"Case study: reliability of multi-electrode array in the knob area of human motor cortex intended for a neuromotor prosthesis application","authors":"M. Saleh, A. Caplan, M. Serruya, J. Donoghue","doi":"10.1109/ICORR.2005.1501085","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501085","url":null,"abstract":"Extracellular recordings of motor cortex (MI) neurons, using a chronically implanted multi-electrode array, promise to yield a high dimensional input signal to external devices such as a computer, exoskeleton or prosthetic arm. For the multi-electrode array to be used as a sensor for a neuromotor prosthesis (NMP), it is important that it continually record movement-related signals over long time periods. Recent studies have demonstrated that it is possible to continually record for up to 1.5 years from a sufficient number of MI neurons in monkeys to enable neural decoding of arm movement. Cyberkinetics Neurotechnology Systems Inc. has initiated an investigational device exemption (TOE) study investigating the safety and efficacy of the BrainGate/spl trade/ Neural Interface System, a medical device that combines this sensor with data acquisition and processing devices to decode movement intent. This device is currently being investigated as a means for a quadriplegic person to operate a range of assistive technologies. Preliminary results from this case study provide evidence that (1) MI neurons remain active more than 3 years after spinal cord injury, (2) units can be recorded 6 months after surgery. This technology may benefit quadriplegic people by providing a new output pathway from the cortex, to control their muscles.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127899280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501119
Xin Feng, J. Winters
This paper addresses how UniTherapy, a telerehabilitation platform developed primarily for computer-assisted motivating rehabilitation applications, is being turned into an accessible service. This process has involved transformation to a service-oriented universal access infrastructure that also supports intelligent context-aware user interface generation that is dependent on current and emerging standards such as the V2 standard for universal remote consoles. It also has involved support for a steadily increasing, diverse menu of approaches for performance assessment, and of interfaces for promoting universal access. Progress and key issues are discussed.
{"title":"Progress towards a service-oriented universal access telerehabilitation platform","authors":"Xin Feng, J. Winters","doi":"10.1109/ICORR.2005.1501119","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501119","url":null,"abstract":"This paper addresses how UniTherapy, a telerehabilitation platform developed primarily for computer-assisted motivating rehabilitation applications, is being turned into an accessible service. This process has involved transformation to a service-oriented universal access infrastructure that also supports intelligent context-aware user interface generation that is dependent on current and emerging standards such as the V2 standard for universal remote consoles. It also has involved support for a steadily increasing, diverse menu of approaches for performance assessment, and of interfaces for promoting universal access. Progress and key issues are discussed.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"45 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125677512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501043
N. Pernalete, S. Edwards, Ramakrishna Gottipati, J. Tipple, V. Kolipakam, R. Dubey
In this paper we discuss the possibility of improving eye-hand coordination in children diagnosed with this problem, using a robotic mapping from a haptic user interface to a virtual environment. Our goal is to develop an assessment and training procedure that will result in improving handwriting taking advantage of the force feedback provided by the haptic device. We also incorporate inertia and viscosity effects to decrease the tremor in the hand as well as to stimulate the muscles involved in the task of holding a pencil (known as facilitation technique in the occupational therapy field). A set of assessment tests, commonly used by occupational therapists, were chosen to implement various functions using force, inertia and viscosity effects. The test bed used for these tasks consisted of a six-degree-of-freedom force-reflecting haptic interface device, PHANToM with the GHOST SDK Software.
{"title":"Eye-hand coordination assessment/therapy using a robotic haptic device","authors":"N. Pernalete, S. Edwards, Ramakrishna Gottipati, J. Tipple, V. Kolipakam, R. Dubey","doi":"10.1109/ICORR.2005.1501043","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501043","url":null,"abstract":"In this paper we discuss the possibility of improving eye-hand coordination in children diagnosed with this problem, using a robotic mapping from a haptic user interface to a virtual environment. Our goal is to develop an assessment and training procedure that will result in improving handwriting taking advantage of the force feedback provided by the haptic device. We also incorporate inertia and viscosity effects to decrease the tremor in the hand as well as to stimulate the muscles involved in the task of holding a pencil (known as facilitation technique in the occupational therapy field). A set of assessment tests, commonly used by occupational therapists, were chosen to implement various functions using force, inertia and viscosity effects. The test bed used for these tasks consisted of a six-degree-of-freedom force-reflecting haptic interface device, PHANToM with the GHOST SDK Software.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130571569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501116
L. Lünenburger, G. Colombo, R. Riener, V. Dietz
Neurological disorders, such as spinal cord injury, stroke, and traumatic brain injury, affect the motor performance of affected individuals. The most important result is the loss of function, e.g. gait function. A reduction of normal features and an increase in pathological features lead to this loss. Muscle weakness and increased involuntary muscle tone (spasticity) are most commonly affected. Robotic rehabilitation devices are available for re-training impaired functions. For example, the Lokomat supports patients during body-weight supported treadmill training. The robotic devices are equipped with sensors (e.g. position and force) and actuators needed for their control. Beyond pure training, advanced tools can use these sensors and actuators to measure physiological and other properties of the patient using the device. We report here the design, implementation, and first tests of tools that allow (i) measurement of spasticity and (ii) measurement of voluntary muscle force with the Lokomat. The spasticity tool measures mechanical stiffness during controlled passive movements of the legs. The voluntary force tool measures maximum isometric torque in the hip and knee joint. Mechanical stiffness is higher in patients with higher spasticity. The voluntary force tool can be used in patients with incomplete spinal cord injury. We conclude that the use of robotic devices for assessment of patients during their training would be an efficient and important addition to robotic-supported therapy in the future.
{"title":"Clinical assessments performed during robotic rehabilitation by the gait training robot Lokomat","authors":"L. Lünenburger, G. Colombo, R. Riener, V. Dietz","doi":"10.1109/ICORR.2005.1501116","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501116","url":null,"abstract":"Neurological disorders, such as spinal cord injury, stroke, and traumatic brain injury, affect the motor performance of affected individuals. The most important result is the loss of function, e.g. gait function. A reduction of normal features and an increase in pathological features lead to this loss. Muscle weakness and increased involuntary muscle tone (spasticity) are most commonly affected. Robotic rehabilitation devices are available for re-training impaired functions. For example, the Lokomat supports patients during body-weight supported treadmill training. The robotic devices are equipped with sensors (e.g. position and force) and actuators needed for their control. Beyond pure training, advanced tools can use these sensors and actuators to measure physiological and other properties of the patient using the device. We report here the design, implementation, and first tests of tools that allow (i) measurement of spasticity and (ii) measurement of voluntary muscle force with the Lokomat. The spasticity tool measures mechanical stiffness during controlled passive movements of the legs. The voluntary force tool measures maximum isometric torque in the hip and knee joint. Mechanical stiffness is higher in patients with higher spasticity. The voluntary force tool can be used in patients with incomplete spinal cord injury. We conclude that the use of robotic devices for assessment of patients during their training would be an efficient and important addition to robotic-supported therapy in the future.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127982155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1502028
L. Cai, A. Fong, C. Otoshi, Y. Liang, J. Cham, H. Zhong, R. Roy, V. Edgerton, J. Burdick
This paper studies the possible benefit that can be obtained by introducing variability into the robotic control of trajectories used to train hindlimb locomotion in adult spinal mice. The spinal cords of adult female Swiss-Webster mice were completely transected at a mid-thoracic level. Fourteen days post-transection, the spinal mice were robotically trained to step in the presence of a 5-HT agonist, quipazine, for a period of six weeks. In this pilot study nine animals were divided into three groups, each receiving a different control strategy: a fixed training trajectory (Group A), a variable training trajectory without interlimb coordination imposed (Group B) and a variable training trajectory with hindlimb bilateral coordination imposed (Group C). Preliminary results indicate that Group A recovers more slowly than the two groups receiving variable modes of robotic training. Groups B and C show higher levels of recovery than Group A in terms of the number of steps performed during testing sessions, as well as in their step periodicity and shape consistency. Group C displays a higher incidence of alternating stepping than Group B. These results indicate that variable trajectory robotic training paradigms may be more effective than fixed trajectory paradigms in promoting robust post-injury stepping behavior. Furthermore, it appears that the inclusion of interlimb coordination is an important contribution to successful training.
{"title":"Effects of consistency vs. variability in robotically controlled training of stepping in adult spinal mice","authors":"L. Cai, A. Fong, C. Otoshi, Y. Liang, J. Cham, H. Zhong, R. Roy, V. Edgerton, J. Burdick","doi":"10.1109/ICORR.2005.1502028","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1502028","url":null,"abstract":"This paper studies the possible benefit that can be obtained by introducing variability into the robotic control of trajectories used to train hindlimb locomotion in adult spinal mice. The spinal cords of adult female Swiss-Webster mice were completely transected at a mid-thoracic level. Fourteen days post-transection, the spinal mice were robotically trained to step in the presence of a 5-HT agonist, quipazine, for a period of six weeks. In this pilot study nine animals were divided into three groups, each receiving a different control strategy: a fixed training trajectory (Group A), a variable training trajectory without interlimb coordination imposed (Group B) and a variable training trajectory with hindlimb bilateral coordination imposed (Group C). Preliminary results indicate that Group A recovers more slowly than the two groups receiving variable modes of robotic training. Groups B and C show higher levels of recovery than Group A in terms of the number of steps performed during testing sessions, as well as in their step periodicity and shape consistency. Group C displays a higher incidence of alternating stepping than Group B. These results indicate that variable trajectory robotic training paradigms may be more effective than fixed trajectory paradigms in promoting robust post-injury stepping behavior. Furthermore, it appears that the inclusion of interlimb coordination is an important contribution to successful training.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131318821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501052
P. Culmer, A. Jackson, R. Richardson, B. Bhakta, M. Levesley, A. Cozens
Stroke is a common condition resulting in 30,000 people per annum left with significant disability. In patients with severe arm paresis after stroke, functional recovery in the affected arm is poor. Inadequate intensity of treatment is cited as one factor accounting for the lack arm recovery found in some studies. Given that physical therapy resource is limited, strategies to enhance the physiotherapists' efforts are needed. One approach is to use robotic techniques to augment movement therapy. Kinematic analysis of upper limb movement during a patient's physiotherapy session was used to determine the appropriate therapeutic workspace. An existing single robot arm is adapted to optimize its operating area to allow full movement in this desired workspace. The kinematic data is also used to look at the constraints involved in attaching two robot arms to the user's forearm and upper arm. An optimized design and configuration of the dual robot arms is proposed that allows appropriate control of the patient's arm throughout the desired workspace.
{"title":"Development of a dual robotic system for upper-limb stroke rehabilitation","authors":"P. Culmer, A. Jackson, R. Richardson, B. Bhakta, M. Levesley, A. Cozens","doi":"10.1109/ICORR.2005.1501052","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501052","url":null,"abstract":"Stroke is a common condition resulting in 30,000 people per annum left with significant disability. In patients with severe arm paresis after stroke, functional recovery in the affected arm is poor. Inadequate intensity of treatment is cited as one factor accounting for the lack arm recovery found in some studies. Given that physical therapy resource is limited, strategies to enhance the physiotherapists' efforts are needed. One approach is to use robotic techniques to augment movement therapy. Kinematic analysis of upper limb movement during a patient's physiotherapy session was used to determine the appropriate therapeutic workspace. An existing single robot arm is adapted to optimize its operating area to allow full movement in this desired workspace. The kinematic data is also used to look at the constraints involved in attaching two robot arms to the user's forearm and upper arm. An optimized design and configuration of the dual robot arms is proposed that allows appropriate control of the patient's arm throughout the desired workspace.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123360276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2005-08-29DOI: 10.1109/ICORR.2005.1501049
A. Ajiboye, R. Weir
We seek to quantify the electromyographic similarities and differences between six major grasping patterns of the human hand: cylindrical, hook, palmar, lateral, spherical, and tip. Fuzzy c-means clustering (FCM) is a data reduction technique that allows continuous membership, on a [0,1] interval, of data points in the representative clusters. We found no grasp to be completely distinct from any other grasp, and found significant overlap of characteristics between several grasps. This overlap is quantified and discussed.
{"title":"Fuzzy c-means clustering analysis of the EMG patterns of six major hand grasps","authors":"A. Ajiboye, R. Weir","doi":"10.1109/ICORR.2005.1501049","DOIUrl":"https://doi.org/10.1109/ICORR.2005.1501049","url":null,"abstract":"We seek to quantify the electromyographic similarities and differences between six major grasping patterns of the human hand: cylindrical, hook, palmar, lateral, spherical, and tip. Fuzzy c-means clustering (FCM) is a data reduction technique that allows continuous membership, on a [0,1] interval, of data points in the representative clusters. We found no grasp to be completely distinct from any other grasp, and found significant overlap of characteristics between several grasps. This overlap is quantified and discussed.","PeriodicalId":131431,"journal":{"name":"9th International Conference on Rehabilitation Robotics, 2005. ICORR 2005.","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125165400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：