Refine
Document Type
- Article (2)
- Conference Proceeding (1)
Language
- English (3)
Has Fulltext
- no (3)
Keywords
- Uncertainty (3) (remove)
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the individual image-level predictions. Those methods take advantage of the uncertainty in the image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.
Guiding through the Fog
(2021)
Corporate Entrepreneurship (CE) programs are formalized efforts to realize entrepreneurial activities in established companies. Despite the growing and evolving landscape of CE programs, effectively managing them remains a challenging endeavor which results in disappointing outcomes and oftentimes leads to the early termination of such programs. We unmask the differences in goal setting of CE programs and highlight that setting appropriate goals is imperative for their desired outcomes. In practice, companies seem to struggle with the goal setting, and scholars have not yet fully solved the puzzle of goals setting in the context of CE programs either. Therefore, we set out to explore the current state of goal setting in the context of CE programs building upon 61 semi-structured interviews with CE program executives from cross-industry companies with different sizes. Our study contributes to a better understanding of goal setting in the context of CE programs by (1) characterizing the goal setting of CE programs based on goal attributes and goal types and (2) identifying differences among the goal setting of CE programs. We provide implications to practice for a more effective management of CE programs and conclude with a discussion for future research on the impact of the different goal settings.
This study aims to investigate the utilization of Bayesian techniques for the calibration of micro-electro-mechanical system (MEMS) accelerometers. These devices have garnered substantial interest in various practical applications and typically require calibration through error-correcting functions. The parameters of these error-correcting functions are determined during a calibration process. However, due to various sources of noise, these parameters cannot be determined with precision, making it desirable to incorporate uncertainty in the calibration models. Bayesian modeling offers a natural and complete way of reflecting uncertainty by treating the model parameters as variables rather than fixed values. In addition, Bayesian modeling enables the incorporation of prior knowledge, making it an ideal choice for calibration. Nevertheless, it is infrequently used in sensor calibration. This study introduces Bayesian methods for the calibration of MEMS accelerometer data in a straightforward manner using recent advances in probabilistic programming.