Browsing by Autor "Xiaoyan Li"

Now showing 1 - 2 of 2

Phylogenetic analysis and taxonomy of the subgenus Gnathopaederus Chapin and related groups of Paederus s.l. (Coleoptera : Staphylinidae : Paederinae)
(CSIRO Publishing, 2009) Xiaoyan Li; Hong‐Zhang Zhou
The paederine genus Paederus s.l. (Coleoptera : Staphylinidae) is a hyperdiverse group of some 500 species worldwide. Although the subtribe Paederina, in which the genus resides, is monophyletic the status of numerous genera and subgenera is questionable and the current classification is likely to be flawed. As part of detailed studies on the paederine fauna of China, we undertook a preliminary morphologically-based phylogenetic analysis to determine the relationships of Paederus (Gnathopaederus) and related subgenera, as a basis for a revision of the subgenus, and as an attempt to provide a better framework for future taxonomic studies on the group as a whole. The analysis was based on 66 adult morphological characters for 30 ingroup taxa, including all six species of P. (Gnathopaederus). The results show that P. (Gnathopaederus) and P. (Paederus), and the genera Megalopaederus, Pachypaederus and Paederidus are monophyletic, and that P. (Eopaederus) and P. (Harpopaederus) are paraphylyetic. However, our analysis did not offer a robust solution to relationships among other clades within Paederus s.l. although it seems clear that Paederus s.l. is not monophyletic with respect to the above genera. The monophyly of P. (Gnathopaederus) is supported by the mandibular basal medial tooth having two cuspids separated dorsoventrally. Based largely on this character state, the definition of the subgenus is refined; six species are recognized, including two new species described from China as follows: P. (G.) daozhenensis, sp. nov. from Guizhou, and P. (G.) jilongensis, sp. nov. from Xizang; three species, P. bursavacua Willers, P. yunnanensis Willers and P. solodovnikovi Willers, are newly assigned to the subgenus according to a revised subgeneric definition. New morphological characters including important secondary sexual characters and sexual dimorphism are described and male genitalia are illustrated for the first time for the type species of the subgenus, P. (G.) szechuanus (Chapin). A key to the six species is presented and the distribution of each species is documented and discussed.
Using Advanced Convolutional Neural Network Approaches to Reveal Patient Age, Gender, and Weight Based on Tongue Images
(Hindawi Publishing Corporation, 2024) Xiaoyan Li; Li Li; Wei Jing; Pengwei Zhang; Volodymyr Turchenko; Naresh Vempala; Evgueni Kabakov; Faisal Habib; Arvind Gupta; Huaxiong Huang
The human tongue has been long believed to be a window to provide important insights into a patient's health in medicine. The present study introduced a novel approach to predict patient age, gender, and weight inferences based on tongue images using pretrained deep convolutional neural networks (CNNs). Our results demonstrated that the deep CNN models (e.g., ResNeXt) trained on dorsal tongue images produced excellent results for age prediction with a Pearson correlation coefficient of 0.71 and a mean absolute error (MAE) of 8.5 years. We also obtained an excellent classification of gender, with a mean accuracy of 80% and an AUC (area under the receiver operating characteristic curve) of 88%. ResNeXt model also obtained a moderate level of accuracy for weight prediction, with a Pearson correlation coefficient of 0.39 and a MAE of 9.06 kg. These findings support our hypothesis that the human tongue contains crucial information about a patient. This study demonstrated the feasibility of using the pretrained deep CNNs along with a large tongue image dataset to develop computational models to predict patient medical conditions for noninvasive, convenient, and inexpensive patient health monitoring and diagnosis.