A deep learning-based worker assistance system for error prevention: Case study in a real-world manual assembly

Modern assembly systems adapt to the requirements of customised and short-lived products. As assembly tasks become increasingly complex and change rapidly, the cognitive load on employees increases. This leads to the use of assistance systems for manual assembly to detect and avoid human errors and thus ensure consistent product quality. Most of these systems promise to improve the production environment but have hardly been studied quantitatively so far. Recent advances in deep learning-based computer vision have also not yet been fully exploited. This study aims to provide architectural, and implementational details of a state-of-the-art assembly assistance system based on an object detection model. The proposed architecture is intended to be representative of modern assistance systems. The error prevention potential is determined in a case study in which test subjects manually assemble a complex explosion-proof tubular lamp. The results show 51 % fewer assembly errors compared to a control group without assistance. Three of the four considered types of error classes have been reduced by at least 42 %. In particular, errors by omission are most likely to be prevented by the system. The reduction in the error rate is observed over the entire period of 30 consecutive product assemblies, comparing assisted and unassisted assembly. Furthermore, the recorded assembly data are found to be valuable regarding traceability and production improvement processes.

Best Practices for Reducing Interface Errors in Electronic Medical Records

As Electronic Medical Records (EMR) become increasingly prevalent, the application of human factors principles is essential to facilitate efficiency and usability of these systems and, in turn, to reduce adverse patient outcomes due to user errors relating to the EMR. This paper describes five “best practices” found in the literature which aim to prevent error in the use of Electronic Medical Records. These practices are: Watermarking, Information Control and Management, Hybrid Systems, Cross-Checking Methodology, and Interface Modification. The paper describes each practice and examines the research underlying each approach. Although some practices may be easier to apply than others, they all merit further research and have potential for error prevention on a large scale.

Improving Quality of Care in Virtual Visits: Heuristic Evaluations of the User Interface in Telehealth

The COVID-19 pandemic has expedited the growing rate of reliance on telehealth. Beyond the benefits of telehealth for patients and healthcare providers during atypical circumstances, the changes prompted by the pandemic have possibly altered the position of telehealth to the point that virtual communication will become the new normal. Therefore, the importance of designing an interface to facilitate user interaction with the system and consequently with one another is of utmost importance. Building on Nielsen’s usability heuristics and mapping them to the six aspects of quality of care introduced by the Institute of Medicine, we identify the design features that have the highest impact on the quality of care. Our analysis shows that error prevention and recovery is the most influential design feature, followed by help and documentation, visibility of the system, match between the system and the real world, flexibility and efficiency of use, and user control and freedom.