Browsing by Author "Zhao K"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Dynamics of Porcine Circovirus Type 3 Detection in Pre-Weaning Piglets: Insight From Multiple Sampling Methods
    (John Wiley and Sons Ltd, 2025-01-24) Yang DA; Li M; Wang Y; Zhao K; Zhang Q; Laven RA; Yang Z; Chen N-H
    Porcine circovirus type 3 (PCV3) has been identified worldwide and is associated with reproductive and systemic diseases, yet the dynamics of PCV3 within pig farms remain unclear. Building upon our previous study, which initialised comparisons of different sample types for the detection of PCV3 in a sow farm, this study expanded both the range of sample types and the timeline of sampling in piglets and sows to better understand the PCV3 dynamics. This study collected two additional sample types—oropharyngeal swab (OS) and oral fluid (OF) along with placental umbilical cord (PUC) blood and processing fluid (PF) that were used in the previous study. Data were collected from July to August and October 2022; the aforementioned four sample types from 51 litters were collected, and additional OS samples were collected from two to three identified piglets per litter on days 1, 7, 14, and 21 post-farrowing. Besides, blood swabs were taken from 135 sows subject to both PCR test and oestrogen measurement. PF showed the highest detection rates (50/51), while OS and OF revealed 33/51 (95% confidence interval [CI]: 51.2%–76.8%) and 37/51 (95% CI: 59.5%–83.5%) detection rates; both were higher than that of PUC blood (22/51, 95% CI: 30.2%–56.8%). Despite the similarity between OS and OF samples, they did not identify the same population as infected, as the agreement between the samples was only fair at 90% level. The Bayesian generalised linear mixed model suggested PCV3 was more likely to be detected in both OS and OF compared to PUC blood, and PCV3 was present in the farrowing room throughout the pre-weaning period using an OS. Finally, we observed higher PCV3 detection rates in sows after farrowing; however, no evidence was found that such a pattern was associated with the decreased concentration of oestrogen.
  • Thumbnail Image
    Item
    Parameter-Free Extreme Learning Machine for Imbalanced Classification Authors Li, L - China Agric
    (Springer Science+Business Media, LLC, 2020-12) Li L; Zhao K; Sun R; Gan J; Yuan G; Liu T
    Imbalanced data distribution is a common problem in classification situations, that is the number of samples in different categories varies greatly, thus increasing the classification difficulty. Although many methods have been used for the imbalanced data classification, there are still problems with low classification accuracy in minority class and adding additional parameter settings. In order to increase minority classification accuracy in imbalanced problem, this paper proposes a parameter-free weighting learning mechanism based on extreme learning machine and sample loss values to balance the number of samples in each training step. The proposed method mainly includes two aspects: the sample weight learning process based on the sample losses; the sample selection process and weight update process according to the constraint function and iterations. Experimental results on twelve datasets from the KEEL repository show that the proposed method could achieve more balanced and accurate results than other compared methods in this work.