Hierarchical Image Transformation and Multi-Level Features for Anomaly Defect Detection.

Anomalies are a set of samples that do not follow the normal behavior of the majority of data. In an industrial dataset, anomalies appear in a very small number of samples. Currently, deep learning-based models have achieved important advances in image anomaly detection. However, with general models, real-world application data consisting of non-ideal images, also known as poison images, become a challenge. When the work environment is not conducive to consistently acquiring a good or ideal sample, an additional adaptive learning model is needed. In this work, we design a potential methodology to tackle poison or non-ideal images that commonly appear in industrial production lines by enhancing the existing training data. We propose Hierarchical Image Transformation and Multi-level Features (HIT-MiLF) modules for an anomaly detection network to adapt to perturbances from novelties in testing images. This approach provides a hierarchical process for image transformation during pre-processing and explores the most efficient layer of extracted features from a CNN backbone. The model generates new transformations of training samples that simulate the non-ideal condition and learn the normality in high-dimensional features before applying a Gaussian mixture model to detect the anomalies from new data that it has never seen before. Our experimental results show that hierarchical transformation and multi-level feature exploration improve the baseline performance on industrial metal datasets.

Global-and-Local Context Network for Semantic Segmentation of Street View Images.

Semantic segmentation of street view images is an important step in scene understanding for autonomous vehicle systems. Recent works have made significant progress in pixel-level labeling using Fully Convolutional Network (FCN) framework and local multi-scale context information. Rich global context information is also essential in the segmentation process. However, a systematic way to utilize both global and local contextual information in a single network has not been fully investigated. In this paper, we propose a global-and-local network architecture (GLNet) which incorporates global spatial information and dense local multi-scale context information to model the relationship between objects in a scene, thus reducing segmentation errors. A channel attention module is designed to further refine the segmentation results using low-level features from the feature map. Experimental results demonstrate that our proposed GLNet achieves 80.8% test accuracy on the Cityscapes test dataset, comparing favorably with existing state-of-the-art methods.

Influence of job demands and job control on work-life balance among Taiwanese nurses.

AIM: This study investigated the extent to which the job demands and job control of nurses were related to their work-life balance. BACKGROUND: The inability to achieve work-life balance is one of the major reasons for the declining retention rate among nurses. Job demands and job control are two major work domain factors that can have a significant influence on the work-life balance of nurses. METHOD: The study measured the job demands, job control and work-life balance of 2040 nurses in eight private hospitals in Taiwan in 2013. RESULTS: Job demands and job control significantly predicted all the dimensions of work-life balance. Job demands increased the level of work-life imbalance among nurses. While job control showed positive effects on work/personal life enhancement, it was found to increase both work interference with personal life and personal life interference with work. CONCLUSION: Reducing the level of job demands (particularly for psychological demands) between family and career development and maintaining a proper level of job control are essential to the work-life balance of nurses. IMPLICATIONS FOR NURSING MANAGEMENT: Flexible work practices and team-based management could be considered by nursing management to lessen job demand pressure and to facilitate job engagement and participation among nurses, thus promoting a better balance between work and personal life.

QuaBingo: A Prediction System for Protein Quaternary Structure Attributes Using Block Composition.

Background. Quaternary structures of proteins are closely relevant to gene regulation, signal transduction, and many other biological functions of proteins. In the current study, a new method based on protein-conserved motif composition in block format for feature extraction is proposed, which is termed block composition. Results. The protein quaternary assembly states prediction system which combines blocks with functional domain composition, called QuaBingo, is constructed by three layers of classifiers that can categorize quaternary structural attributes of monomer, homooligomer, and heterooligomer. The building of the first layer classifier uses support vector machines (SVM) based on blocks and functional domains of proteins, and the second layer SVM was utilized to process the outputs of the first layer. Finally, the result is determined by the Random Forest of the third layer. We compared the effectiveness of the combination of block composition, functional domain composition, and pseudoamino acid composition of the model. In the 11 kinds of functional protein families, QuaBingo is 23% of Matthews Correlation Coefficient (MCC) higher than the existing prediction system. The results also revealed the biological characterization of the top five block compositions. Conclusions. QuaBingo provides better predictive ability for predicting the quaternary structural attributes of proteins.

A multilevel model of patient safety culture: cross-level relationship between organizational culture and patient safety behavior in Taiwan's hospitals.

BACKGROUND: As health-care organizations endeavor to improve their quality of care, there is a growing recognition of the importance of establishing a culture of patient safety. The main objective of this study was to investigate the cross-level influences of organizational culture on patient safety behavior in Taiwan's hospitals. METHODS: The authors measured organizational culture (bureaucratic, supportive and innovative culture), patient safety culture and behavior from 788 hospital workers among 42 hospitals in Taiwan. Multilevel analysis was applied to explore the relationship between organizational culture (group level) and patient safety behavior (individual level). RESULTS: Patient safety culture had positive impact on patient safety behavior in Taiwan's hospitals. The results also indicated that bureaucratic, innovative and supportive organizational cultures all had direct influence on patient safety behavior. However, only supportive culture demonstrated significant moderation effect on the relationship between patient safety culture and patient safety behavior. Furthermore, organizational culture strength was shown correlated negatively with patient safety culture variability. CONCLUSIONS: Overall, organizational culture plays an important role in patient safety activities. Safety behaviors of hospital staff are partly influenced by the prevailing cultural norms in their organizations and work groups. For management implications, constructed patient priority from management commitment to leadership is necessary. For academic implications, research on patient safety should consider leadership, group dynamics and organizational learning. These factors are important for understanding the barriers and the possibilities embedded in patient safety.