Browsing by Author "Mgbemena, Chika Edith"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Gesture detection towards real-time ergonomic analysis for intelligent automation assistance
    (Springer, 2016-07-10) Mgbemena, Chika Edith; Oyekan, John; Tiwari, Ashutosh; Xu, Yuchun; Fletcher, Sarah R.; Hutabarat, Windo; Prabhu, Vinayak Ashok
    Manual handling involves transporting of load by hand through lifting or lowering and operators on the manufacturing shop floor are daily faced with constant lifting and lowering operations which leads to Work-Related Musculoskeletal Disorders. The trend in data collection on the Shop floor for ergonomic evaluation during manual handling activities has revealed a gap in gesture detection as gesture triggered data collection could facilitate more accurate ergonomic data capture and analysis. This paper presents an application developed to detect gestures towards triggering real-time human motion data capture on the shop floor for ergonomic evaluations and risk assessment using the Microsoft Kinect. The machine learning technology known as the discrete indicator—precisely the AdaBoost Trigger indicator was employed to train the gestures. Our results show that the Kinect can be trained to detect gestures towards real-time ergonomic analysis and possibly offering intelligent automation assistance during human posture detrimental tasks.
  • Thumbnail Image
    ItemOpen Access
    Real-time evaluation and feedback system for ergonomics on the shop floor.
    (2017-09) Mgbemena, Chika Edith; Tiwari, Ashutosh; Xu, Yuchun
    Despite the greatly increased automation in manufacturing industries, manual operations still exist, and ergonomic risk factors that arise because of manual operations can lead to Work-Related Musculoskeletal Disorders (WMSDs). To mitigate the risk, manual operations should be assessed to identify if any risk, such as awkward posture, exist. Most assessments are carried out offline but this cannot alert and prevent operators from adopting awkward postures in time. Hence, due to the popularity of flexible manufacturing systems that require immediate response to changes, there is need for a real-time assessment. Therefore, the aim of this research is to develop a real-time knowledge-based ergonomic assessment system for use in the real-time evaluation of work postures on the shop floor and provision of feedback to workers, using 3D motion sensors. The developed intelligent system utilizes the knowledge from health and safety (H&S) guidelines, set of rules and an inference engine, to automatically capture and assess worker’s postures and provide real-time feedback to the worker through an easy-to-understand user interface. The system has been validated using many case studies which include the posture assessment of: 6 operators assembling engine valve, 4 seated researchers conducting desk-based reading and 15 operators during lifting, assembly and hammering of IKEA table. The system when tested proved to achieve: real-time assessment, easy-to-understand feedback, reliable measurements with Cronbach’s alpha of 0.978, p=0.045 and Kendall’s coefficient of concordance of 0.634, p = 0.000. The main contribution of this work lies in providing real-time feedback to workers. This contribution is in three sub-areas namely: i) Development of a real-time Kinect-based tool for H&S-compliant ergonomic assessment. ii) Development of a knowledge-based real-time feedback system for improved posture assessment. iii) Provision of real-time feedback to alert workers in time. The novelty of this research is in the development of a knowledge-based system for real-time ergonomic assessment and feedback to workers using 3D motion sensors.