| 11. |
- Vanhatalo, Erik, et al.
(författare)
-
On the structure of dynamic principal component analysis used in statistical process monitoring
- 2017
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier. - 0169-7439 .- 1873-3239. ; 167, s. 1-11
-
Tidskriftsartikel (refereegranskat)abstract
- When principal component analysis (PCA) is used for statistical process monitoring it relies on the assumption that data are time independent. However, industrial data will often exhibit serial correlation. Dynamic PCA (DPCA) has been suggested as a remedy for high-dimensional and time-dependent data. In DPCA the input matrix is augmented by adding time-lagged values of the variables. In building a DPCA model the analyst needs to decide on (1) the number of lags to add, and (2) given a specific lag structure, how many principal components to retain. In this article we propose a new analyst driven method to determine the maximum number of lags in DPCA with a foundation in multivariate time series analysis. The method is based on the behavior of the eigenvalues of the lagged autocorrelation and partial autocorrelation matrices. Given a specific lag structure we also propose a method for determining the number of principal components to retain. The number of retained principal components is determined by visual inspection of the serial correlation in the squared prediction error statistic, Q (SPE), together with the cumulative explained variance of the model. The methods are illustrated using simulated vector autoregressive and moving average data, and tested on Tennessee Eastman process data.
|
|
| 12. |
- Brydegaard, Mikkel, et al.
(författare)
-
Complete parameterization of temporally and spectrally resolved laser induced fluorescence data with applications in bio-photonics
- 2015
-
Ingår i: Chemometrics and Intelligent Laboratory Systems. - : Elsevier BV. - 0169-7439. ; 142, s. 95-106
-
Tidskriftsartikel (refereegranskat)abstract
- We present a set of spectrally and temporally resolved clinical fluorescence data-with two separate excitation wavelengths-that was recorded in vivo. We demonstrate that data in the spectral and temporal domains are in certain ways coupled and provide a method for integrated and effective parameterization of spectrally and temporally resolved fluorescence (i.e., time-resolved emission spectra). This parameterization is based on linear algebra, matrix formulation and system identification. We demonstrate how to empirically extract single exponentially decaying components and provide rectified emission spectra without prior knowledge. We investigate the potential for improved cancer diagnostics according to the reduced parameters along the various domains. In this case, in terms of cancer diagnostics, we were unable to identify any benefits of simultaneously measuring both the temporal and spectral properties of the observed fluorescence. However, we note that this may be explained by an important experimental bias present in many studies of optical cancer diagnostics, namely, that, in general, suspected lesions always differ visually from the neighboring healthy tissue. (C) 2015 Elsevier B.V. All rights reserved.
|
|
| 13. |
- Rabetino, Rodrigo, et al.
(författare)
-
Developing the concept of life-cycle service offering
- 2015
-
Ingår i: Industrial Marketing Management. - : Elsevier BV. - 0019-8501 .- 1873-2062. ; 49, s. 53-66
-
Tidskriftsartikel (refereegranskat)abstract
- To extend the previous literature on industrial services, this study develops the concept of the life-cycle service offering by reviewing previous studies and collecting empirical data from seven cases. In particular, the present study develops a framework for life-cycle service offering by synthesizing 11 main categories of services based on an empirical categorization of 1638 services. These categories include administrative services, basic (installed base) services, consulting services, customer services, financial services, maintenance services, operational/outsourcing services, optimization services, research and development services, recycling services, and supply management and warehousing services. The concepts, dimensions and services developed in this study may enable managers of manufacturing firms to better analyze, benchmark, and develop their firms' life-cycle offerings to facilitate value creation and appropriation.
|
|
| 14. |
- Vingeliene, Snieguole, 1985-, et al.
(författare)
-
Longitudinal analysis of loneliness and inflammation at older ages : English longitudinal study of ageing
- 2019
-
Ingår i: Psychoneuroendocrinology. - : Elsevier. - 0306-4530 .- 1873-3360. ; 110
-
Tidskriftsartikel (refereegranskat)abstract
- Loneliness has been associated with adverse health outcomes, including age-related diseases with an inflammatory etiology such as cardiovascular disease. We aimed to identify potential biological pathways linking loneliness with morbidity and mortality by examining associations of loneliness with biomarkers. Participants in the English Longitudinal Study of Ageing (n = 3239) aged 50 years or older with an average age of 64 years, provided data in waves 4 (2008/2009) and 6 (2012/2013). Linear regression conditional change models had three outcomes: C reactive protein (CRP) measured in mg/L (log transformed), fibrinogen in g/L and ferritin in g/dL. In men, the onset of loneliness indicated by answering 'no' at wave 4 and 'yes' at wave 6 to question "Much of the time during the past week, you felt lonely?" was associated with a statistically significant increase in levels of CRP (β = 0.36, 95% confidence interval (0.09 to 0.62)), plasma fibrinogen (0.18 (0.04 to 0.31)) and ferritin (41.04 (6.58 to 75.50)), after full adjustment. A statistically significant increase in CRP in men was also observed for onset of loneliness assessed with the question "How often do you feel lonely?" (0.20 (0.03 to 0.38)). These associations were not mediated by depressive symptoms. Persistent loneliness (loneliness experienced at both baseline and follow-up) assessed using the University of California Los Angeles (UCLA) loneliness scale was associated with an increase in CRP (0.11 (0.004 to 0.22)) among men. Associations of the two latter loneliness measures with fibrinogen and ferritin were mainly null. Among women, the only statistically significant association was for persistent loneliness (loneliness at both waves) identified by question "Much of the time during the past week, you felt lonely?" with a reduction in levels of ferritin (-20.62 (-39.78 to -1.46)). Men may be more susceptible to loneliness-associated disease risks signaled by biological changes, including systemic inflammation. Combined social and targeted medical interventions may help to reduce health risks associated with loneliness.
|
|
