Pub Date : 2013-05-06DOI: 10.1109/BSN.2013.6575458
Rolf Adelsberger, G. Tröster
The process of learning a novel body movement exposes a student to multiple difficulties. Understanding the range of motion is fundamental for learning to control the involved body parts. Theory and instructions need to be mapped to body movements: a student not only needs to mimic or copy the range of motion of individual body parts, but he also needs to trigger the motion fragments in the correct order. Not only correct order is important, but also precise timing. If the movements in questions are intensified by additional load, optimality of the motion patterns becomes crucial. Sub-optimal execution of an exercise reduces the performance or can even induce failure of completion. Correct execution is a subtle interplay between the correct forces at the right times. In this paper, we present a sensor system that is able to categorize movements into multiple quality classes and athletes into two experience classes. For this work we conducted a study involving 16 athletes performing squat-presses, a simple yet non-trivial exercise requiring barbells. We calculated various features out of raw accelerometer data acquired by two inertial measurement units attached to the athletes' bodies. We evaluated exercise performances of the participants ranging from beginners to experts. We introduce the biomechanical properties of the movement and show that our system can differentiate between four quality classes (poor, fair, good, perfect) with an accuracy above 93% and discriminate between a beginner athlete and an advanced athlete with an accuracy of more than 94%.
{"title":"Experts lift differently: Classification of weight-lifting athletes","authors":"Rolf Adelsberger, G. Tröster","doi":"10.1109/BSN.2013.6575458","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575458","url":null,"abstract":"The process of learning a novel body movement exposes a student to multiple difficulties. Understanding the range of motion is fundamental for learning to control the involved body parts. Theory and instructions need to be mapped to body movements: a student not only needs to mimic or copy the range of motion of individual body parts, but he also needs to trigger the motion fragments in the correct order. Not only correct order is important, but also precise timing. If the movements in questions are intensified by additional load, optimality of the motion patterns becomes crucial. Sub-optimal execution of an exercise reduces the performance or can even induce failure of completion. Correct execution is a subtle interplay between the correct forces at the right times. In this paper, we present a sensor system that is able to categorize movements into multiple quality classes and athletes into two experience classes. For this work we conducted a study involving 16 athletes performing squat-presses, a simple yet non-trivial exercise requiring barbells. We calculated various features out of raw accelerometer data acquired by two inertial measurement units attached to the athletes' bodies. We evaluated exercise performances of the participants ranging from beginners to experts. We introduce the biomechanical properties of the movement and show that our system can differentiate between four quality classes (poor, fair, good, perfect) with an accuracy above 93% and discriminate between a beginner athlete and an advanced athlete with an accuracy of more than 94%.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125322147","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575508
He Liu, Yadong Wang, Lei Wang
This paper presents first several steps towards an FPGA-based electronic system for remote pulse rate (PR) measurement. The system uses a low-cost digital camera as an image sensor, which operates at up to 30 frames per second (fps) in WXGA (1200×800 pixels) resolution. A novel algorithm for PR measurement was implemented using an FPGA development board. A commercially-available photoplethysmography module (TP-TSD200A from BIOPAC) was used as a golden standard to verify the performance of the suggested system. Ten male subjects were simultaneously examined using both the suggested system and the golden standard, and the results were compared. The proposed system leads to a potential means for providing mobile healthcare using smart phones and other mobile consumer products.
{"title":"FPGA-based remote pulse rate detection using photoplethysmographic imaging","authors":"He Liu, Yadong Wang, Lei Wang","doi":"10.1109/BSN.2013.6575508","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575508","url":null,"abstract":"This paper presents first several steps towards an FPGA-based electronic system for remote pulse rate (PR) measurement. The system uses a low-cost digital camera as an image sensor, which operates at up to 30 frames per second (fps) in WXGA (1200×800 pixels) resolution. A novel algorithm for PR measurement was implemented using an FPGA development board. A commercially-available photoplethysmography module (TP-TSD200A from BIOPAC) was used as a golden standard to verify the performance of the suggested system. Ten male subjects were simultaneously examined using both the suggested system and the golden standard, and the results were compared. The proposed system leads to a potential means for providing mobile healthcare using smart phones and other mobile consumer products.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116616129","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575499
K. Teachasrisaksakul, Zhiqiang Zhang, Guang-Zhong Yang
The aim of this work is to provide a humanoid robot that is able to replicate human's upper body movements by using motion capture data acquired from Biomotion+, developed by the Hamlyn Centre. This work proposes an upper limb motion imitation module for a humanoid robot. The module calculates joint angle trajectories, based on motion capture data, and sends these trajectories to a humanoid robot. The experimental results have demonstrated the effectiveness of the module which can achieve reasonable postural similarity of generated robot motions, compared to the captured human movements.
{"title":"Demo abstract: Upper limb motion imitation module for humanoid robot using biomotion+ sensors","authors":"K. Teachasrisaksakul, Zhiqiang Zhang, Guang-Zhong Yang","doi":"10.1109/BSN.2013.6575499","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575499","url":null,"abstract":"The aim of this work is to provide a humanoid robot that is able to replicate human's upper body movements by using motion capture data acquired from Biomotion+, developed by the Hamlyn Centre. This work proposes an upper limb motion imitation module for a humanoid robot. The module calculates joint angle trajectories, based on motion capture data, and sends these trajectories to a humanoid robot. The experimental results have demonstrated the effectiveness of the module which can achieve reasonable postural similarity of generated robot motions, compared to the captured human movements.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129229698","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575477
A. Denisov, E. Yeatman
In this paper we discuss a novel approach to delivering wireless power to remote microdevices within Body Sensor/Actuator Networks. With higher energy budgets such devices could extent their functionality from purely diagnostic to therapeutic, and perform such operations as implant mechanical adjustment, drug release, microsurgery, or control of microfluidic valves and pumps. The method is based on ultrasonic power delivery, the novelty being that actuation is powered by ultrasound directly rather than via electrical form. The paper focuses on the main part of the system — a coupled mechanical oscillator driven by acoustic waves — and presents the first experimental results. Several issues related to the biomedical application of the system are also discussed. These include estimating acoustic power levels to avoid adverse bioeffects and tissue damage, as well as studying how the source-receiver misalignment (lateral and angular) affects the system performance.
{"title":"Battery-less microdevices for Body Sensor/Actuator networks","authors":"A. Denisov, E. Yeatman","doi":"10.1109/BSN.2013.6575477","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575477","url":null,"abstract":"In this paper we discuss a novel approach to delivering wireless power to remote microdevices within Body Sensor/Actuator Networks. With higher energy budgets such devices could extent their functionality from purely diagnostic to therapeutic, and perform such operations as implant mechanical adjustment, drug release, microsurgery, or control of microfluidic valves and pumps. The method is based on ultrasonic power delivery, the novelty being that actuation is powered by ultrasound directly rather than via electrical form. The paper focuses on the main part of the system — a coupled mechanical oscillator driven by acoustic waves — and presents the first experimental results. Several issues related to the biomedical application of the system are also discussed. These include estimating acoustic power levels to avoid adverse bioeffects and tissue damage, as well as studying how the source-receiver misalignment (lateral and angular) affects the system performance.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124559161","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575525
Andrea K. Webb, Ashley L. Vincent, Alvin Jin, M. Pollack
Post-traumatic stress disorder (PTSD) currently is diagnosed via subjective reports of experiences related to the traumatic event. More objective measures are needed to assist clinicians in diagnosis. Physiological activity was recorded from 58 participants. Participants in the No Trauma/No PTSD group had no trauma exposure and no PTSD diagnosis. Trauma Exposed/No PTSD participants had experienced a traumatic event but did not have PTSD. PTSD participants had experienced a traumatic event and had PTSD. Baseline and emotionally evocative stimulus-related sensor data were collected. Features were extracted from each sensor stream and submitted to statistical analysis. Significant group differences were present during the viewing of two virtual reality videos. Features were submitted to discriminant function analysis to assess classification accuracy. Classification accuracy was between 89 and 92%. The results from this study suggest the utility of objective physiological measures obtained from wearable sensors in assisting with PTSD diagnosis.
{"title":"Wearable sensors can assist in PTSD diagnosis","authors":"Andrea K. Webb, Ashley L. Vincent, Alvin Jin, M. Pollack","doi":"10.1109/BSN.2013.6575525","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575525","url":null,"abstract":"Post-traumatic stress disorder (PTSD) currently is diagnosed via subjective reports of experiences related to the traumatic event. More objective measures are needed to assist clinicians in diagnosis. Physiological activity was recorded from 58 participants. Participants in the No Trauma/No PTSD group had no trauma exposure and no PTSD diagnosis. Trauma Exposed/No PTSD participants had experienced a traumatic event but did not have PTSD. PTSD participants had experienced a traumatic event and had PTSD. Baseline and emotionally evocative stimulus-related sensor data were collected. Features were extracted from each sensor stream and submitted to statistical analysis. Significant group differences were present during the viewing of two virtual reality videos. Features were submitted to discriminant function analysis to assess classification accuracy. Classification accuracy was between 89 and 92%. The results from this study suggest the utility of objective physiological measures obtained from wearable sensors in assisting with PTSD diagnosis.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"13 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123451886","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575527
J. Williamson, Kate D. Fischl, Andrew Dumas, A. Hess, T. Hughes, M. Buller
The early onset of musculoskeletal injury during ambulation may be detectable due to changes in gait. Body worn accelerometers provide the ability for real-time monitoring and detection of these changes, thereby providing a means for avoiding further injury. We propose algorithms for extracting magnitude and pattern asymmetry features from accelerometers attached to each foot. By registering simultaneous acceleration differences between the two feet, these features provide robustness to a variety of confounding factors, such as changes in walking speed and load carriage. By computing only summary statistics from the acceleration signals, the algorithms can be easily implemented in real-time physiological status monitoring systems. We evaluate the algorithms on a field collection consisting of 32 subjects completing a series of 5 km marches under different loading conditions. We show that changes in the magnitude and pattern asymmetry features are predictive of subject ratings of physical pain and discomfort.
{"title":"Individualized detection of ambulatory distress in the field using wearable sensors","authors":"J. Williamson, Kate D. Fischl, Andrew Dumas, A. Hess, T. Hughes, M. Buller","doi":"10.1109/BSN.2013.6575527","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575527","url":null,"abstract":"The early onset of musculoskeletal injury during ambulation may be detectable due to changes in gait. Body worn accelerometers provide the ability for real-time monitoring and detection of these changes, thereby providing a means for avoiding further injury. We propose algorithms for extracting magnitude and pattern asymmetry features from accelerometers attached to each foot. By registering simultaneous acceleration differences between the two feet, these features provide robustness to a variety of confounding factors, such as changes in walking speed and load carriage. By computing only summary statistics from the acceleration signals, the algorithms can be easily implemented in real-time physiological status monitoring systems. We evaluate the algorithms on a field collection consisting of 32 subjects completing a series of 5 km marches under different loading conditions. We show that changes in the magnitude and pattern asymmetry features are predictive of subject ratings of physical pain and discomfort.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129151443","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575480
D. D. Boer, O. S. V. Rheenen, E. V. Zelm, R. Bergmann, J. Bergmann, N. Howard
A remarkably high number of water-skiers suffer from injuries on the lower back and the lower extremity as a result of jumping. A possible explanation for this is the vertical forces that occur on the body during landing, caused by the large amount of deceleration at the moment the skier hits the water surface. The amplitude of the accelerations might be a reason for concern for juveniles participating in this type of sport, due to the vulnerability to high loads during growth. A wearable sensor system could inform both the skier and coach about the impact level encountered by young water-skiers. Pilot testing showed decelerations occurred far above those measured by a 5 g accelerometer system. High-frequency camera data and modeling showed multiples of 10 g can be expected during landing. Therefore, it is suggested that 100 g accelerometers are integrated into the proposed body sensor network design.
{"title":"Design considerations for a wearable sensor network that measures accelerations during Water-Ski jumping","authors":"D. D. Boer, O. S. V. Rheenen, E. V. Zelm, R. Bergmann, J. Bergmann, N. Howard","doi":"10.1109/BSN.2013.6575480","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575480","url":null,"abstract":"A remarkably high number of water-skiers suffer from injuries on the lower back and the lower extremity as a result of jumping. A possible explanation for this is the vertical forces that occur on the body during landing, caused by the large amount of deceleration at the moment the skier hits the water surface. The amplitude of the accelerations might be a reason for concern for juveniles participating in this type of sport, due to the vulnerability to high loads during growth. A wearable sensor system could inform both the skier and coach about the impact level encountered by young water-skiers. Pilot testing showed decelerations occurred far above those measured by a 5 g accelerometer system. High-frequency camera data and modeling showed multiples of 10 g can be expected during landing. Therefore, it is suggested that 100 g accelerometers are integrated into the proposed body sensor network design.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"238 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132091780","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575491
Hesam Sagha, Alberto Calatroni, J. Millán, D. Roggen, G. Tröster, Ricardo Chavarriaga
Activity recognition systems based on body-worn motion sensors suffer from a decrease in performance during the deployment and run-time phases, because of probable changes in the sensors (e.g. displacement or rotatation), which is the case in many real-life scenarios (e.g. mobile phone in a pocket). Existing approaches to achieve robustness tend to sacrifice information (e.g. by rotation-invariant features) or reduce the weight of the anomalous sensors at the classifier fusion stage (adaptive fusion), ignoring data which might still be perfectly meaningful, although different from the training data. We propose to use adaptation to rebuild the classifier models of the sensors which have changed position by a two-step approach: in the first step, we run an anomaly detection algorithm to automatically detect which sensors are delivering unexpected data; subsequently, we trigger a system self-training process, so that the remaining classifiers retrain the “anomalous” sensors. We show the benefit of this approach in a real activity recognition dataset comprising data from 8 sensors to recognize locomotion. The approach achieves similar accuracy compared to the upper baseline, obtained by retraining the anomalous classifiers on the new data.
{"title":"Robust activity recognition combining anomaly detection and classifier retraining","authors":"Hesam Sagha, Alberto Calatroni, J. Millán, D. Roggen, G. Tröster, Ricardo Chavarriaga","doi":"10.1109/BSN.2013.6575491","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575491","url":null,"abstract":"Activity recognition systems based on body-worn motion sensors suffer from a decrease in performance during the deployment and run-time phases, because of probable changes in the sensors (e.g. displacement or rotatation), which is the case in many real-life scenarios (e.g. mobile phone in a pocket). Existing approaches to achieve robustness tend to sacrifice information (e.g. by rotation-invariant features) or reduce the weight of the anomalous sensors at the classifier fusion stage (adaptive fusion), ignoring data which might still be perfectly meaningful, although different from the training data. We propose to use adaptation to rebuild the classifier models of the sensors which have changed position by a two-step approach: in the first step, we run an anomaly detection algorithm to automatically detect which sensors are delivering unexpected data; subsequently, we trigger a system self-training process, so that the remaining classifiers retrain the “anomalous” sensors. We show the benefit of this approach in a real activity recognition dataset comprising data from 8 sensors to recognize locomotion. The approach achieves similar accuracy compared to the upper baseline, obtained by retraining the anomalous classifiers on the new data.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130851402","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575516
M. Giuberti, G. Ferrari, L. Contin, V. Cimolin, N. Cau, M. Galli, C. Azzaro, G. Albani, A. Mauro
In this paper, we focus on the characterization of the Leg Agility (LA) task, which contributes to the evaluation of the degree of severity of the Parkinson's Disease (PD) through semiquantitative evaluation scales, such as the Unified Parkinson's Disease Rating Scale (UPDRS). By extracting relevant kinematic variables, such as the angular amplitude and speed of thighs' motion, we analyze, in a comparative way, the results obtained when a healthy subject and a PD patient perform the LA task. Our investigation relies on the use of wireless inertial systems, whose accuracy is confirmed by direct comparison with optoelectronic systems. Although preliminary, the proposed analysis allows to derive significant insights in possible approaches to accurately evaluate the degree of severity of PD.
{"title":"On the characterization of Leg Agility in patients with Parkinson's Disease","authors":"M. Giuberti, G. Ferrari, L. Contin, V. Cimolin, N. Cau, M. Galli, C. Azzaro, G. Albani, A. Mauro","doi":"10.1109/BSN.2013.6575516","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575516","url":null,"abstract":"In this paper, we focus on the characterization of the Leg Agility (LA) task, which contributes to the evaluation of the degree of severity of the Parkinson's Disease (PD) through semiquantitative evaluation scales, such as the Unified Parkinson's Disease Rating Scale (UPDRS). By extracting relevant kinematic variables, such as the angular amplitude and speed of thighs' motion, we analyze, in a comparative way, the results obtained when a healthy subject and a PD patient perform the LA task. Our investigation relies on the use of wireless inertial systems, whose accuracy is confirmed by direct comparison with optoelectronic systems. Although preliminary, the proposed analysis allows to derive significant insights in possible approaches to accurately evaluate the degree of severity of PD.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125860744","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 : 2013-05-06DOI: 10.1109/BSN.2013.6575492
D. Jarchi, Guang-Zhong Yang
This paper proposes a new approach to gait pattern analysis based on acceleration signals during different walking conditions. Instead of applying traditional classification techniques, the proposed method looks into the characteristics of acceleration signals. Filtering and template matching methods based on singular spectrum analysis (SSA) and longest common subsequence algorithm (LCSS) have been used. The method has been used to discriminate walking downstairs, level walking and walking upstairs using 10 healthy subjects. The results suggest that the proposed method gives new insight into quantitative aspects of gait patterns.
{"title":"Singular spectrum analysis for gait patterns","authors":"D. Jarchi, Guang-Zhong Yang","doi":"10.1109/BSN.2013.6575492","DOIUrl":"https://doi.org/10.1109/BSN.2013.6575492","url":null,"abstract":"This paper proposes a new approach to gait pattern analysis based on acceleration signals during different walking conditions. Instead of applying traditional classification techniques, the proposed method looks into the characteristics of acceleration signals. Filtering and template matching methods based on singular spectrum analysis (SSA) and longest common subsequence algorithm (LCSS) have been used. The method has been used to discriminate walking downstairs, level walking and walking upstairs using 10 healthy subjects. The results suggest that the proposed method gives new insight into quantitative aspects of gait patterns.","PeriodicalId":138242,"journal":{"name":"2013 IEEE International Conference on Body Sensor Networks","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131128909","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：