Refine
Year of publication
- 2023 (2)
Document Type
- Journal article (2)
Language
- English (2) (remove)
Has full text
- yes (2)
Is part of the Bibliography
- yes (2)
Institute
- ESB Business School (1)
- Informatik (1)
Publisher
- Frontiers Research Foundation (2) (remove)
The fierce market competition environment makes employees feel insecure at work. While it is difficult for enterprises to provide employees with a sense of security, they have to rely on employees’ innovative behavior to seek competitive advantage. Therefore, this study focuses on how employees engage in innovative behavior when they face job insecurity.MethodsUsing a variable-centered approach, this study aims to examine the mediating effects of intrinsic and impression management motivation in the relationship between quantitative and qualitative job insecurity and innovative behavior, including proactive and reactive innovative behavior. In addition, a person-centered approach is used to investigate whether it is possible to distinguish different combinations of quantitative and qualitative job insecurity, and examine the effect of these job insecurity profiles on motivation and innovative behavior. We used 503 data sets collected via the Credamo platform in China into the data analysis.ResultsThe study found that quantitative job insecurity affects proactive and reactive innovative behavior through impression management motivation and that qualitative job insecurity affects proactive and reactive innovative behavior through intrinsic and impression management motivation. In addition, three job insecurity profiles were identified: balanced high job insecurity, balanced low job insecurity, and a profile dominated by high quantitative job insecurity, all of which have significantly different effects on motivation and innovative behavior.DiscussionThis study contributes to provide new insights into the relationship between job insecurity and innovative behavior and compensate for the limitation of the traditional variable-centered approach that cannot capture heterogeneity within the workforce.
Background: Polysomnography (PSG) is the gold standard for detecting obstructive sleep apnea (OSA). However, this technique has many disadvantages when using it outside the hospital or for daily use. Portable monitors (PMs) aim to streamline the OSA detection process through deep learning (DL).
Materials and methods: We studied how to detect OSA events and calculate the apnea-hypopnea index (AHI) by using deep learning models that aim to be implemented on PMs. Several deep learning models are presented after being trained on polysomnography data from the National Sleep Research Resource (NSRR) repository. The best hyperparameters for the DL architecture are presented. In addition, emphasis is focused on model explainability techniques, concretely on Gradient-weighted Class Activation Mapping (Grad-CAM).
Results: The results for the best DL model are presented and analyzed. The interpretability of the DL model is also analyzed by studying the regions of the signals that are most relevant for the model to make the decision. The model that yields the best result is a one-dimensional convolutional neural network (1D-CNN) with 84.3% accuracy.
Conclusion: The use of PMs using machine learning techniques for detecting OSA events still has a long way to go. However, our method for developing explainable DL models demonstrates that PMs appear to be a promising alternative to PSG in the future for the detection of obstructive apnea events and the automatic calculation of AHI.