Unveiling the Stability Mechanism of Oriented Ni-Rich Layered Oxides.

Single-crystal and polycrystalline structures are the two main structural forms of the Ni-rich layered cathode for lithium-ion batteries. The structural difference is closely related to the electrochemical performance and thermal stability, but its internal mechanism is unclear and is worthy of further exploration. In this study, both polycrystalline and single-crystal LiNi0.83Co0.12Mn0.05O2 cathodes were prepared by adjusting the calcination temperature and mechanical post-treatment, respectively. Systematic comparisons were made to assess the effects of different grain structures on the electrochemical performance and thermal stability. The study revealed the superior thermal stability of monocrystalline cathodes, attributing it to oxygen vacancies and phase transitions. From the perspective of grain boundaries, it was demonstrated that the diffusion of oxygen vacancies and the reduction of Ni in polycrystalline cathodes exhibit anisotropy. This research elucidates the origins of the superior thermal stability of monocrystalline cathodes in lithium-ion batteries, providing valuable insights into battery material design.

A Data-Efficient Framework for the Identification of Vaginitis Based on Deep Learning.

Vaginitis is a gynecological disease affecting the health of millions of women all over the world. The traditional diagnosis of vaginitis is based on manual microscopy, which is time-consuming and tedious. The deep learning method offers a fast and reliable solution for an automatic early diagnosis of vaginitis. However, deep neural networks require massive well-annotated data. Manual annotation of microscopic images is highly cost extensive because it not only is a time-consuming process but also needs highly trained people (doctors, pathologists, or technicians). Most existing active learning approaches are not applicable in microscopic images due to the nature of complex backgrounds and numerous formed elements. To address the problem of high cost of labeling microscopic images, we present a data-efficient framework for the identification of vaginitis based on transfer learning and active learning strategies. The proposed informative sample selection strategy selected the minimal training subset, and then the pretrained convolutional neural network (CNN) was fine-tuned on the selected subset. The experiment results show that the proposed pipeline can save 37.5% annotation cost while maintaining competitive performance. The proposed promising novel framework can significantly save the annotation cost and has the potential of extending widely to other microscopic imaging applications, such as blood microscopic image analysis.