Worldwide, skin cancer prevalence necessitates accurate diagnosis to alleviate public health burdens. Although the application of artificial intelligence in image analysis and pattern recognition has improved the accuracy and efficiency of early skin cancer diagnosis, existing supervised learning methods are limited due to their reliance on a large amount of labeled data. To overcome the limitations of data labeling and enhance the performance of diagnostic models, this study proposes a semi-supervised skin cancer diagnostic model based on Self-feedback Threshold Focal Learning (STFL), capable of utilizing partial labeled and a large scale of unlabeled medical images for training models in unseen scenarios. The proposed model dynamically adjusts the selection threshold of unlabeled samples during training, effectively filtering reliable unlabeled samples and using focal learning to mitigate the impact of class imbalance in further training. The study is experimentally validated on the HAM10000 dataset, which includes images of various types of skin lesions, with experiments conducted across different scales of labeled samples. With just 500 annotated samples, the model demonstrates robust performance (0.77 accuracy, 0.6408 Kappa, 0.77 recall, 0.7426 precision, and 0.7462 F1-score), showcasing its efficiency with limited labeled data. Further, comprehensive testing validates the semi-supervised model’s significant advancements in diagnostic accuracy and efficiency, underscoring the value of integrating unlabeled data. This model offers a new perspective on medical image processing and contributes robust scientific support for the early diagnosis and treatment of skin cancer.
The monopile-friction wheel composite foundation is an innovative offshore wind turbines (OWTs) foundation type for its good bearing properties and anti-erosion advantages. The local scouring is a non-negligible challenge by moving surrounding soils away till even some engineering disasters. To explore this kind of unfavorable effects, we model the response of scouring to the bearing capacity of the composite foundation by means of laboratory flume tests. Furthermore, the influence of different loading sequences (i.e., T→H or H→T) is considered, and the failure envelopes are also obtained. On this basis, a 3D finite element model is established to investigate the impact of key scouring parameters and different loading point heights on the bearing capacity. The conclusions are as follows: local scouring can significantly reduce the bearing capacity; the scouring depth has the most significant effect, followed successively by the scouring angle and extent; compared with pure horizontal foundations, the ultimate torsional bearing capacity of the foundations under the combined T→H loading sequence decreases by about 1.95%–11.1%, while the horizontal bearing capacity under the combined H→T loading sequence decreases by about 0.82%–1% compared with pure torsional foundations; the loading point height has noticeable effects on the lateral resistance for the composite foundation.
This paper deals with the parameter identification and nonlinear analysis of the nonlinear dynamical system in glycerol metabolism. Firstly, the nonlinear dynamical system for the continuous bio-dissimilation process of glycerol is established. A parameter identification problem is given, which takes the nonlinear ordinary differential equations of the continuous fermentation process as steady-state constrains. By using the sequential quadratic programming algorithm, the optimal parameters are obtained. The results show that the parameter identification optimization model of the nonlinear dynamical system can obtain more accurate parameters. Secondly, the calculation of the equilibrium points and stability analysis of the nonlinear dynamical system are carried out. The equilibrium points are calculated by the symbolized real root isolation method, and the stability of equilibrium points is estimated according to the stability theory of almost linear system.
为鉴定控制谷子抽穗的关键基因,通过甲基磺酸乙酯(ethyl methyl sulfonate,EMS)诱变谷子参考基因组测序品种豫谷1号,获得遗传稳定的谷子超早抽穗突变体jt1242-14b.与豫谷1号相比,jt1242-14b抽穗期明显提前,茎秆变细,叶片变窄、变短.遗传分析表明,突变性状受隐性单基因控制.以SSR41(父本)、jt1242-14b(母本)和F2群体进行突变基因定位,结果表明,该基因位于第9号染色体,在分子标记In4746和In9-11之间的4 447 kb之内.进一步测序比对分析发现突变位点位于PHYB基因内部,因此,PHYB很可能是该早熟突变体的目标基因.本研究为谷子早抽穗基因克隆及PHYB基因功能研究提供材料基础.
