The Experts below are selected from a list of 312 Experts worldwide ranked by ideXlab platform
Philip Ogunbona - One of the best experts on this subject based on the ideXlab platform.
-
Weakly structured information aggregation for upper-body Posture Assessment using ConvNets
2017 IEEE International Conference on Multimedia and Expo (ICME), 2017Co-Authors: Zewei Ding, Wanqing Li, Pichao Wang, Philip OgunbonaAbstract:Posture Assessment aims to determine the risk associated with poor Posture and thus avoid injury in subjects. Upper-body Posture Assessment from images offers an attractive alternative to manual methods by directly extracting relevant features for classification. A deep convolutional neural network is proposed to extract structured features from different body parts and learn shared features that are used to determine the appropriate Assessment. The structured features are learned with triplet-based rank constraints based on head and torso separately. The shared feature and Assessment function are learned with soft-max constraints based on Posture risk measurements. Experimental evaluation on a self-collected upper-body Posture dataset has verified the efficacy of the proposed method and network architecture.
-
ICME - Weakly structured information aggregation for upper-body Posture Assessment using ConvNets
2017 IEEE International Conference on Multimedia and Expo (ICME), 2017Co-Authors: Zewei Ding, Wanqing Li, Pichao Wang, Philip OgunbonaAbstract:Posture Assessment aims to determine the risk associated with poor Posture and thus avoid injury in subjects. Upper-body Posture Assessment from images offers an attractive alternative to manual methods by directly extracting relevant features for classification. A deep convolutional neural network is proposed to extract structured features from different body parts and learn shared features that are used to determine the appropriate Assessment. The structured features are learned with triplet-based rank constraints based on head and torso separately. The shared feature and Assessment function are learned with soft-max constraints based on Posture risk measurements. Experimental evaluation on a self-collected upper-body Posture dataset has verified the efficacy of the proposed method and network architecture.
Catherine Trask - One of the best experts on this subject based on the ideXlab platform.
-
trunk Posture Assessment during work tasks at a canadian recycling center
International Journal of Industrial Ergonomics, 2018Co-Authors: Benedicta O Asante, Brenna Bath, Catherine TraskAbstract:Abstract Musculoskeletal disorders are common among waste workers but preventative effort is lagging behind. This exploratory study assessed trunk Posture during waste sorting tasks via statistical and experimental means. Posture exposure exceeded levels previously shown and related to elevated risk of Low Back Disorders (LBD). Results show predisposition of waste workers to LBDs.
-
observer variability in Posture Assessment from video recordings the effect of partly visible periods
Applied Ergonomics, 2017Co-Authors: Catherine Trask, Svend Erik Mathiassen, Mehdi Rostami, Marina HeidenAbstract:Abstract Observers rank partly visible Postures on video frames differently than fully visible Postures, but it's not clear if this is due to differences in observer perception. This study investigated the effect of Posture visibility on between-observer variability in Assessments of trunk and arm Posture. Trained observers assessed trunk and arm Postures from video recordings of 84 pulp mill shifts using a work sampling approach; Postures were also categorized as ‘fully’ or ‘partly’ visible. Between-worker, between-day, and between-observer variance components and corresponding confidence intervals were calculated. Although no consistent gradient was seen for the trunk, right upper arm Posture showed smaller between-observer variance when all observers rated a Posture as fully visible. This suggests that, partly-visible data, especially when observers disagree as to the level of visibility, introduces more between-observer variability when compared to fully visible data. Some previously-identified differences in daily Posture summaries may be related to this phenomenon.
-
Cost-efficient Assessment of variation in arm Posture during paper mill work
2016Co-Authors: Marina Heiden, Catherine Trask, Jennifer L. Bruno Garza, Svend Erik MathiassenAbstract:Background. Arm Posture is a recognized risk factor for occupational upper extremity musculoskeletal disorders and thus often assessed in research and practice. Posture Assessment methods differ in ...
-
data processing costs for three Posture Assessment methods
BMC Medical Research Methodology, 2013Co-Authors: Catherine Trask, Svend Erik Mathiassen, Jennie A Jackson, Jens WahlstromAbstract:Background: Data processing contributes a non-trivial proportion to total research costs, but documentation of these costs is rare. This paper employed a priori cost tracking for three Posture Assessment methods (self-report, observation of video, and inclinometry), developed a model describing the fixed and variable cost components, and simulated additional study scenarios to demonstrate the utility of the model. Methods: Trunk and shoulder Postures of aircraft baggage handlers were assessed for 80 working days using all three methods. A model was developed to estimate data processing phase costs, including fixed and variable components related to study planning and administration, custom software development, training of analysts, and processing time. Results: Observation of video was the most costly data processing method with total cost of € 30,630, and was 1.2-fold more costly than inclinometry (€ 26,255), and 2.5-fold more costly than self-reported data (€ 12,491). Simulated scenarios showed altering design strategy could substantially impact processing costs. This was shown for both fixed parameters, such as software development and training costs, and variable parameters, such as the number of work-shift files processed, as well as the sampling frequency for video observation. When data collection and data processing costs were combined, the cost difference between video and inclinometer methods was reduced to 7%; simulated data showed this difference could be diminished and, even, reversed at larger study sample sizes. Self-report remained substantially less costly under all design strategies, but produced alternate exposure metrics. Conclusions: These findings build on the previously published data collection phase cost model by reporting costs for post-collection data processing of the same data set. Together, these models permit empirically based study planning and identification of cost-efficient study designs.
-
anthropometry corrected exposure modeling as a method to improve trunk Posture Assessment with a single inclinometer
Journal of Occupational and Environmental Hygiene, 2013Co-Authors: Robin Van Driel, Jack P Callaghan, Catherine Trask, Peter Johnson, Mieke Koehoorn, Kay TeschkeAbstract:Measuring trunk Posture in the workplace commonly involves subjective observation or self-report methods or the use of costly and time-consuming motion analysis systems (current gold standard). This work compared trunk inclination measurements using a simple data-logging inclinometer with trunk flexion measurements using a motion analysis system, and evaluated adding measures of subject anthropometry to exposure prediction models to improve the agreement between the two methods. Simulated lifting tasks (n = 36) were performed by eight participants, and trunk Postures were simultaneously measured with each method. There were significant differences between the two methods, with the inclinometer initially explaining 47% of the variance in the motion analysis measurements. However, adding one key anthropometric parameter (lower arm length) to the inclinometer-based trunk flexion prediction model reduced the differences between the two systems and accounted for 79% of the motion analysis method's variance. Al...
Zewei Ding - One of the best experts on this subject based on the ideXlab platform.
-
Weakly structured information aggregation for upper-body Posture Assessment using ConvNets
2017 IEEE International Conference on Multimedia and Expo (ICME), 2017Co-Authors: Zewei Ding, Wanqing Li, Pichao Wang, Philip OgunbonaAbstract:Posture Assessment aims to determine the risk associated with poor Posture and thus avoid injury in subjects. Upper-body Posture Assessment from images offers an attractive alternative to manual methods by directly extracting relevant features for classification. A deep convolutional neural network is proposed to extract structured features from different body parts and learn shared features that are used to determine the appropriate Assessment. The structured features are learned with triplet-based rank constraints based on head and torso separately. The shared feature and Assessment function are learned with soft-max constraints based on Posture risk measurements. Experimental evaluation on a self-collected upper-body Posture dataset has verified the efficacy of the proposed method and network architecture.
-
ICME - Weakly structured information aggregation for upper-body Posture Assessment using ConvNets
2017 IEEE International Conference on Multimedia and Expo (ICME), 2017Co-Authors: Zewei Ding, Wanqing Li, Pichao Wang, Philip OgunbonaAbstract:Posture Assessment aims to determine the risk associated with poor Posture and thus avoid injury in subjects. Upper-body Posture Assessment from images offers an attractive alternative to manual methods by directly extracting relevant features for classification. A deep convolutional neural network is proposed to extract structured features from different body parts and learn shared features that are used to determine the appropriate Assessment. The structured features are learned with triplet-based rank constraints based on head and torso separately. The shared feature and Assessment function are learned with soft-max constraints based on Posture risk measurements. Experimental evaluation on a self-collected upper-body Posture dataset has verified the efficacy of the proposed method and network architecture.
Marko Munih - One of the best experts on this subject based on the ideXlab platform.
-
IROS - Using sensory data fusion methods for infant body Posture Assessment
2015 IEEE RSJ International Conference on Intelligent Robots and Systems (IROS), 2015Co-Authors: Andraž Rihar, Janko Kolar, Jure Pašič, Matjaz Mihelj, Marko MunihAbstract:Infant body Posture Assessment is very important for monitoring the development of motor skills. The currently utilized sensory-supported measurement systems are often subject to shortcomings, such as system complexity or inaccuracy. This paper presents a novel approach integrating a combination of a pressure mattress along with inertial and magnetic measurement units on infant trunk and arms to diminish the effects of such drawbacks. The proposed multi-sensor system is validated by comparison of kinematic parameters, such as head movement, arm workspace area, and spectral arc length of hand velocity data to results of a referential optoelectronic measurement system. Integration of sensory data fusion methods provides high system accuracy and reliability. Acquired results confirm that the proposed system can be used as an adequate substitution to expensive optoelectronic measurement systems, as the arm kinematic estimation errors are in the range of 2 cm. Also presented are the results of simplified system versions with only 1 IMU per arm. Such approaches however result in lower system complexity, but also lower accuracy. Nevertheless results imply that the arm Posture and workspace Assessment is still reliable enough for frequent practical use. By taking into account all the evaluation results, the proposed measurement system could importantly contribute to the field of sensory-supported infant body Posture Assessment.
-
Using sensory data fusion methods for infant body Posture Assessment
IEEE International Conference on Intelligent Robots and Systems, 2015Co-Authors: Andraž Rihar, Janko Kolar, Jure Pašič, Matjaz Mihelj, Marko MunihAbstract:Infant body Posture Assessment is very important for monitoring the development of motor skills. The currently utilized sensory-supported measurement systems are often subject to shortcomings, such as system complexity or inaccuracy. This paper presents a novel approach integrating a combination of a pressure mattress along with inertial and magnetic measurement units on infant trunk and arms to diminish the effects of such drawbacks. The proposed multi-sensor system is validated by comparison of kinematic parameters, such as head movement, arm workspace area, and spectral arc length of hand velocity data to results of a referential optoelectronic measurement system. Integration of sensory data fusion methods provides high system accuracy and reliability. Acquired results confirm that the proposed system can be used as an adequate substitution to expensive optoelectronic measurement systems, as the arm kinematic estimation errors are in the range of 2 cm. Also presented are the results of simplified system versions with only 1 IMU per arm. Such approaches however result in lower system complexity, but also lower accuracy. Nevertheless results imply that the arm Posture and workspace Assessment is still reliable enough for frequent practical use. By taking into account all the evaluation results, the proposed measurement system could importantly contribute to the field of sensory-supported infant body Posture Assessment.
-
infant trunk Posture and arm movement Assessment using pressure mattress inertial and magnetic measurement units imus
Journal of Neuroengineering and Rehabilitation, 2014Co-Authors: Andraž Rihar, Janko Kolar, Jure Pašič, Matjaz Mihelj, Marko MunihAbstract:Background Existing motor pattern Assessment methods, such as digital cameras and optoelectronic systems, suffer from object obstruction and require complex setups. To overcome these drawbacks, this paper presents a novel approach for biomechanical evaluation of newborn motor skills development. Multi-sensor measurement system comprising pressure mattress and IMUs fixed on trunk and arms is proposed and used as alternative to existing methods. Observed advantages seem appealing for the focused field and in general. Combined use of pressure distribution data and kinematic information is important also for Posture Assessment, ulcer prevention, and non-invasive sleep pattern analysis of adults.
Jack P Callaghan - One of the best experts on this subject based on the ideXlab platform.
-
anthropometry corrected exposure modeling as a method to improve trunk Posture Assessment with a single inclinometer
Journal of Occupational and Environmental Hygiene, 2013Co-Authors: Robin Van Driel, Jack P Callaghan, Catherine Trask, Peter Johnson, Mieke Koehoorn, Kay TeschkeAbstract:Measuring trunk Posture in the workplace commonly involves subjective observation or self-report methods or the use of costly and time-consuming motion analysis systems (current gold standard). This work compared trunk inclination measurements using a simple data-logging inclinometer with trunk flexion measurements using a motion analysis system, and evaluated adding measures of subject anthropometry to exposure prediction models to improve the agreement between the two methods. Simulated lifting tasks (n = 36) were performed by eight participants, and trunk Postures were simultaneously measured with each method. There were significant differences between the two methods, with the inclinometer initially explaining 47% of the variance in the motion analysis measurements. However, adding one key anthropometric parameter (lower arm length) to the inclinometer-based trunk flexion prediction model reduced the differences between the two systems and accounted for 79% of the motion analysis method's variance. Al...
-
the effect of Posture category salience on decision times and errors when using observation based Posture Assessment methods
Ergonomics, 2012Co-Authors: David M Andrews, Patricia L Weir, Krysia M Fiedler, Jack P CallaghanAbstract:Observation-based Posture Assessment methods (e.g. RULA, 3DMatch) require classification of body Postures into categories. This study investigated the effect of improving Posture category salience (adding borders, shading and colour to the Posture categories) on Posture selection error rates and decision times of novice analysts. Ninety university students with normal or corrected normal visual acuity and who were not colourblind, were instructed to select Posture categories as quickly and accurately as possible, in five salience conditions (Plain (no border, no shading, no colour); Grey Border; Red Border; Grey Shading (GS) and Red Shading (RS)) for images presented in randomised blocks (240 classifications made by each participant) on a computer interface. Participants responded quickest in the Border conditions, classifying Postures about 5% faster than in the Plain condition. Coloured diagrams significantly reduced Posture classification errors by approximately 1.5%. Overall, the best performance, bas...
-
the influence of training on decision times and errors associated with classifying trunk Postures using video based Posture Assessment methods
Ergonomics, 2011Co-Authors: Patricia L Weir, David M Andrews, Jack P CallaghanAbstract:The purpose of this study was to examine the influence of training on the decision times and errors associated with video-based trunk Posture classifications. Altogether, 30 amateur and 30 knowledge-based participants completed a three-phase study (pre-training, training, post-training) that required them to classify static trunk Postures in images on a computer screen into a Posture category that represented the angle of the trunk depicted. Trunk Postures were presented in both flexion/extension and lateral bend views and at several distances from the boundaries of the Posture categories. Both decision time and errors decreased as distance from the boundaries increased. On average, amateur analysts experienced a larger decrease in decision time per Posture classification than knowledge-based analysts (amateur: 0.79 s, knowledge-based: 0.60 s; p <0.05) suggesting that training can have beneficial effects on classification performance. The implications are that the analysis time associated with video-based...
-
determining the optimal size for Posture categories used in video based Posture Assessment methods
Ergonomics, 2009Co-Authors: Patricia L Weir, David M Andrews, Krysia M Fiedler, Jack P CallaghanAbstract:Currently, there are no standards for the development of Posture classification systems used in observation-based ergonomic Posture Assessment methods. This study was conducted to determine if an optimal Posture category size for different body segments and Posture views could be established by examining the trade-off between magnitude of error and the number of Posture category misclassification errors made. Three groups (trunk flexion/extension and lateral bend; shoulder flexion/extension and adduction/abduction; elbow flexion/extension) of 30 participants each selected Postures they perceived to correctly represent the video image shown on a computer screen. For each view, 10 images were presented for five different Posture category sizes, three times each. The optimal Posture category sizes established were 30° for trunk, shoulder and elbow flexion/extension, 30° for shoulder adduction/abduction and 15° for trunk lateral bend, suggesting that Posture category size should be based on the body segment a...
-
the effect of camera viewing angle on Posture Assessment repeatability and cumulative spinal loading
Ergonomics, 2007Co-Authors: C A Sutherland, Wayne J Albert, Allan T Wrigley, Jack P CallaghanAbstract:Video-based task analysis in the workplace is often limited by equipment location and production line arrangement, therefore making it difficult to capture the motion in a single plane. The purpose of this study was to investigate the effects of camera placement on an observer's ability to accurately assess working Postures in three dimensions and the resultant influence on the reliability and repeatability of calculated cumulative loading variables. Four video cameras were placed at viewing angles of 0°, 45°, 60° and 90° to the frontal plane, enabling the simultaneous collection of views of four lifting tasks (two symmetric and two asymmetric). A total of 11 participants were trained in the use of the 3DMatch 3-D Posture matching software package (developed at the University of Waterloo) and were required to analyse 16 lifting trials. Four of the participants were randomly selected to return within 72 h and repeat the analysis protocol to test intra-observer repeatability. Posture matching agreement betw...