Search results

This purpose of this paper is to develop a change detection technique for activity recognition model. The approach aims to detect changes in the initial accuracy of the model after training and when the model is deployed for recognizing new unseen activities without access to the ground truth. The changes between the two sessions may occur because of differences in sensor placement, orientation and user characteristics such as age and gender. However, many of the existing approaches for model adaptation in activity recognition are blind methods because they continuously adapt the recognition model without explicit detection of changes in the model performance.

The approach determines the variation between reference activity data belonging to different classes and newly classified unseen data. If there is coherency between the data, it means the model is correctly classifying the instances; otherwise, a significant variation indicates wrong instances are being classified to different classes. Thus, the approach is formulated as a two-level architectural framework comprising of the off-line phase and the online phase. The off-line phase extracts of Shewart Chart change parameters from the training data set. The online phase performs classification of new samples and the detection of the changes in each class of activity present in the data set by using the change parameters computed earlier.

The approach is evaluated using a real activity-recognition data set. The results show that there are consistent detections that correlate with the error rate of the model.

The developed approach does not use ground truth to detect classifier performance degradation. Rather, it uses a data discrimination method and a base classifier to detect the changes by using the parameters computed from the reference data of each class to discriminate outliers in the new data being classified to the same class. The approach is the first, to the best of the authors’ knowledge, that addresses the problem of detecting within-user and cross-user variations that lead to concept drift in activity recognition. The approach is also the first to use statistical process control method for change detection in activity recognition, with a robust integrated framework that seamlessly detects variations in the underlying model performance.

Based on the job demand and resource (JD–R) model, this study identifies the factors influencing fatigue among seafarers in Malaysia.

A total of 250 responses were gathered via an online survey applying a purposive sampling method. The derived data were analysed using partial least squares-structural equation modelling (PLS-SEM) via SmartPLS 4.

Job demand positively influences sleep problems and occupational stress, while job resources positively impact job autonomy. The research analysis also confirms the positive effect of sleep problems and occupational stress on fatigue. Furthermore, the study reveals the negative effect of job autonomy on fatigue. In-depth analysis confirms the mediation and sequential mediation effects as the determinants of fatigue among seafarers in Malaysia.

Besides enriching the literature on fatigue, the findings provide practical insights to maritime agencies to develop an effective policy to reduce fatigue among seafarers.

The study develops a new model for seafarers’ fatigue via the JD–R model by introducing work pressure, sleep problems, occupational stress and autonomy as sequential mediators.

Work-from-home (WFH) arrangement is implemented to enable employees to achieve work–life balance. However, WFH arrangement can be less than ideal. This study developed a WFH framework using qualitative data.

An open-ended survey was conducted and participated by 621 employees. The data were examined using the qualitative content analysis method.

Work performance and personal well-being have been identified as WFH outcomes, and 12 relevant research propositions have been developed. Constraints to WFH effectiveness include household and organisational factors whilst instrumental and emotional support were identified as the facilitating conditions. Two moderators were also identified: temporal flexibility and commitment orientation.

This study provides a framework that support effective implementation of WFH and similar flexible work arrangements. Managing time, situation, emotions and attitudes are coping strategies used by WFH employees, and the efficacy of these strategies needs further empirical investigation.

Three main factors have been identified as significant in determining WFH effectiveness. Understanding these elements can help managers design solutions to help employees manage work-home boundaries, improving their work performance and well-being.

The Constraints–Coping–Effectiveness WFH framework and research propositions help organisations build WFH guidelines and policies. This study also recognises commitment orientation, which links resources, strategies and outcomes. The inclusion of this variable in future empirical studies could explain the gaps in the current literature.