International Journal of Industrial Ergonomics最新文献

Artificial intelligence (AI) agents are integral components of modern intelligent decision support systems (IDSS), providing their capability to assist in decision-making processes. Understanding the influence of AI involvement on human responses within these systems is crucial for fostering appropriate reliance on AI advice and ensuring a comfortable user experience. This study delves into the impact of AI agents on decision change, correct rate change, confidence rate change and pleasure rating among users. It explores the main and interactive effects of user proficiency and AI agent capability on user responses. A block-factorial experiment involving 45 participants was conducted. The results indicated that high-capability AI agents were associated with substantial decision change, correct rate change and confidence rate change. Participants with higher proficiency, both subjectively and objectively, exhibited reduced reliance on AI agents for task execution. Notably, the involvement of AI agents led to a slight decline in correct rates for participants of high competence (i.e., participants' independent correct rate exceeds AI agent capability), while still enhancing their confidence levels. Additionally, agents lacking human-like embodiment tended to enhance participants’ pleasure ratings. Individual differences in gender, collaboration experience with AI agent, and stereotype on AI agent capability also shaped the decision changes and pleasure ratings of participants. These findings underscore the presence of complementary competence interaction between user and AI agent within IDSS, and can be applied in designing capability of advisory AI agents with consideration of user proficiency and individual characteristics.

Relevance to industry

The findings can be used as guidelines for designing AI agents and specifying their application strategies to integrate the assistance of AI agents effectively in intelligent decision support systems.

Background

Adopting patient transfer assistive devices in healthcare is challenging, and poor decision-making can lead to low adoption. This study aims to demonstrate a technique of the decision-making process of selection of patient transfer assistive devices based on work-related musculoskeletal disorders (WMSDs) risk, nurses’ instantaneous emotions, and perceptions.

Methods

A case study based on four different patient transfer assistive devices is used to demonstrate this technique. Seven nurses were recruited. Three confidence ellipse graphs were plotted: the intention of the use scores vs (1) National Aeronautics and Space Administration Task Load Index (NASA-TLX) overall scores, (2) Rapid Entire Body Assessment (REBA) scores, and (3) valence scores of the nurses.

Results

When a large ellipse is represented by an intervention, it suggests poor agreement among users regarding the intervention, whereas a small ellipse indicates a strong consensus. The upper left quadrant, where the intention of use is high and REBA, NASA-TLX, and valence scores are low, is the most optimal location for selecting a device. In the case study, the motorised transfer was identified as the best device as the datasets were located there.

Conclusions

Using this tool allows for the objective selection of patient transfer assistive devices, which can then be communicated to all stakeholders involved. Additionally, the tool helps to identify areas for improvement within each intervention.

The development of novel technologies has resulted in changes in the functions offered by head-up displays (HUDs), which differ considerably from conventional digital dashboard displays. This study aimed to create a scientific framework for automotive services for automobile manufacturers to review their service models and solutions as they transition to developing autonomous vehicles. This study used the two-dimensional Kano quality model to identify and classify quality characteristics of HUDs. A Kano questionnaire survey was conducted to collect data on customer satisfaction with different quality characteristics. These characteristics were then ranked in the order of their importance to consumers, thereby identifying quality characteristics that must be prioritized for providing high-quality services with HUDs. Data were collected on their emphases on and satisfaction with 32 quality characteristics belonging to seven factors across two dimensions, namely tangible specific functions and intangible value-added services. The seven factors were speed and distance support, driver alerts, information and communication, display settings, active matching, automatic systems, and software–hardware integration. A statistical analysis was performed to determine the presence of significant differences in the customers’ perception of the quality characteristics. On the basis of the analysis results, 11 quality characteristics were classified as attractive quality, four as one-dimensional quality, six as must-be quality, seven as indifferent quality, and four as reverse quality. By referencing the classification of quality characteristics in their products, automotive companies can adopt the product improvement priority scheme proposed in this study to effectively enhance customer satisfaction with their services.

Wearability of clothing is important for enhancing work efficiency and resistance among industrial workers. In this study, we developed wearable suit designs for shoulder and upper limb support when lifting objects considering the wearability of the user in the development stage. We provide basic data on the wearability of functional clothing and wearable suits, with emphasis on improving safety and work efficiency. Two distinct wearable suit designs, namely long- and short-sleeved, were developed and evaluated with a primary focus on wearer comfort. Employing a comprehensive approach encompassing textile analysis, performance assessment, brainwave investigation, and satisfaction surveys, this study provides objective insights for refining the wearability in wearable suit development. A short-sleeved design is recommended for the development of wearable suits tailored to assist industrial workers in tasks requiring muscle strength for heavy loads and repetitive motions. Our results provide foundational data on the wearability of robotic suits in a bid to enhance the safety and efficiency of industrial workers.

When using electronic devices, older adults usually face challenges associated with difficulties in understanding icons. This study investigated age-related differences in icon identification using various design principles (Experiment 1), as well as the impacts of adding text labels (Experiment 2) and learning strategies (Experiment 3) on improving the performance of older adults. Participants, including older adults (aged 60 or older) and younger individuals, were asked to identify icons matching previous descriptions. The results revealed that the identification performance between older and younger adults varied across icon categories. The addition of text labels resolved differences in icon comprehension related to age of participant and design principles. Learning strategies had diverse effects on the identification performance of older and younger participants, depending on the icon category. These findings provide guidance for designers to apply effective principles and identify optimal strategies to support older adults in the identification and understanding of icons.

The Black Hole Illusion (BHI) is a nighttime aviation landing illusion where pilots overestimate their descent angle. This dangerous illusion can cause pilots to compensate by flying lower than intended, which can result in them crashing into the ground or obstacles in front of the runway. A common interpretation of the BHI is that it is a perceptual illusion, and two quantitative perception based theories have been proposed. The first theory was developed by Perrone (1983), and it assumes that pilots misestimate their descent angle due to the loss of contextual information surrounding the runway, such as ground texture, during nighttime landing conditions. Adapted from work by Galanis et al. (1998) and Robinson et al. (2020), the second (eye-level) theory assumes that pilots misestimate their descent angle due to loss of the horizon during nighttime landing conditions. Quantitative analyses of Perrone's theory suggest that the magnitude of the illusion should vary with runway width and length in nighttime conditions, but in daylight conditions there should be no illusion and no effect of runway width or length. Analyses of the eye-level theory predict no impact of runway width or length for any condition. Across two empirical laboratory studies, we do demonstrate a BHI for nighttime evaluations of descent angle, but the data do not support either theory. Thus, the two algorithms analyzed here are not sufficient to explain the BHI; and the BHI may reflect general disorientation due to limited information.

Significant difference exists in spatial fitness and perception between elderly and non-elderly drivers. However, due to dynamic and real-time changes in human subjective feelings and joint movements, two-dimensional human body templates and human-machine simulation software are not enough to obtain necessary space parameters. In this study, seven key dimensions of the legroom were measured thrice and averaged, in the situation that the seat and posture are comfortable. Such anthropometric data can reflect dynamic perception that may change due to personal emotions and environmental influences. Extreme learning machine (ELM) was adopted to build a prediction model of leg space discomfort degree, and the influence of the activation function and the number of hidden layer neurons on the prediction accuracy of the model were analyzed. In addition, a multiple linear regression (MLR) model was established with the discomfort score as the dependent variable and the seven key dimensions as the independent variables. The results indicated that the ELM model could effectively predict elderly drivers’ discomfort degree (MSE = 0.182, MRE = 9.364, R² = 0.869) by learning the dimensions of the seven key positions. The MLR model (R² = 0.861) did not perform as well as ELM. However, the regression coefficients could reflect the degree to which each dimension affects the discomfort degree of leg space for elderly drivers. The conclusions could function in elderly-oriented in-vehicle space arrangement and driving risk assessment of elderly people.

Lack of the biodynamic data of lightweight and heavyweight human bodies in seating posture becomes an impediment to developing dynamic dummies and relevant standards for improving vehicle ride comfort and reducing health risks caused by vibration. To acquire missing data and gain an understanding of relevant biodynamic responses, the vertical apparent masses of seated subjects in lightweight and heavyweight groups as well as the mediumweight group (targeted mass 55 kg, 98–115 kg, and 75 kg) were experimentally measured and studied under 9 vibration magnitudes (0.25, 0.315, 0.4, 0.5, 0.63, 0.8, 1.0, 1.25 and 1.6 ms⁻² r.m.s. with a common ratio of ca. 1.25) without and with the support of an upright backrest. Each group had twelve subjects. With an increase in the vibration magnitude from 0.25 to 1.6 ms⁻² r.m.s., the resonance frequency of the vertical apparent mass showed a decreasing trend. This was observed with all three bodyweight groups and two backrest conditions. Results of pairwise Wilcoxon signed-rank tests showed that, when the vibration magnitude increased by a factor of ca. 1.25, its effect on the resonance frequency was statistically insignificant in most cases. The results provided data on the vertical apparent mass for the heavyweight subjects that have not been reported and augmented the database of those for the lightweight subjects.

Multiple incidents in the offshore oil and gas industry have been associated with poor safety culture. Regular assessments of safety culture among operators and contractors is recommended as part of a safety management system. Poor safety culture has also shown to impact how operators manage offshore hazards, such as worker fatigue. Assessing workers' fatigue states is also critical to ensure safety in the offshore oil industry. This paper describes findings from an interview study that aimed to identify current safety culture assessment and worker fatigue management practices in the offshore oil and gas industry. One-hour virtual semi-structured interviews were conducted with eighteen offshore oil rig supervisors. Various state-of-the-art methods for assessing safety culture (e.g., experience sampling method) and worker fatigue (e.g., physiological sensors and psychomotor vigilance test) were introduced to the participants. Participants commented on the feasibility and potential barriers to implementation/administration of the various methods, as well as how the information might be useful in their supervisory decisions. User expectations for a safety dashboard displaying data from such tools and user requirements for such a dashboard were elicited. In addition, participants completed a modified technology readiness and acceptance model questionnaire to assess participants' readiness levels and perceived usefulness of a safety dashboard. The interview results revealed a mixed understanding of what safety culture is and opinions about safety culture measurements. Participants indicated that efforts to manage fatigue currently relied solely on supervisors' observation and workers' self-reports. Participants’ opinions about the new assessment methods varied. Some were supportive and commented that the new methods will be helpful to improve supervisory-level decisions, whereas others pointed out potential compliance issues.

With the continuous development of human-computer interaction technologies and the widespread use of graphical interfaces, icons that represent various objects and functions have a particularly important role. This study investigates the effect of semantic distance of icons on cognitive performance through an eye-movement-based experiment which involves a visual search for icons. The findings show that the semantic distance of icons has a significant effect on cognitive performance. A higher cognitive performance is found with semantically close icons which can better capture user attention. In addition, we use eye-movement indicators that are highly correlated with semantic distance, including mean pupil diameter, mean gaze duration and initial gaze time of an AOI, and analyze the objective relationship between these three eye-movement indicators and the semantic distance of icons to establish a dataset. The dataset is used as input for a Gradient Boosting Decision Tree (GBDT), which is a machine learning-based method for classifying the semantic distance of the icons in this study. The output of the GBDT model is classifying the semantic distance as far and close, and the experimental results show that the accuracy of the model reaches 84.28% after a comparison with other types of classifiers, which is in good agreement with the experimental results. Therefore, the model can address the relevant application requirements and simplify the evaluation process of icons to a certain extent, which has great significance in the field of icon design.