Self-expansion full information optimization strategy: Convenient and efficient method for near infrared spectrum auto-analysis.

An essential step in the application of near infrared spectroscopy technology is the spectrum preprocessing. A reasonable implementation of it ensures that the effective spectral information is correctly extracted and, also that the model's accuracy is increased. However, some analysts' research still uses the manual approach of trial and error, particularly those less skilled ones. Previous papers have provided preprocessing optimization algorithms for NIR, but there are still some problems that need to be resolved, such as the unwieldy sequence determination of preprocessing method or, the fluctuated optimization outcomes or, lack of sufficient statistical information. This research suggests a spectrum auto-analysis methodology named self-expansion full information optimization strategy, a new powerful open-source technique for concurrently addressing all of these above issues simultaneously. For the first time in the field of chemometrics, this algorithm offers a reliable and effective automatic near infrared auto-modelling method based on the statistical informatics. With the aid of its built-in modules, such as information generators, spectrum processors, etc., it is able to fully search the common preprocessing techniques, which is determined by Monte Carlo cross validation. Then the final ensemble calibration model is built by employing the optimized preprocessing schemes, along with the wavelength variables screening algorithm. The optimization strategy can offer the user objective useful statistics information created throughout the modeling process to further examine the model's effectiveness. The results demonstrate that the suggested method can easily and successfully extract spectrum information and develop calibration models by putting it to the test on two groups of actual near-infrared spectral data. Additionally, this optimization strategy can also be applied to other spectrum analysis areas, such Raman spectroscopy or infrared spectroscopy, by changing a few of its parameters, and has extraordinary application value.

An Inquiry-Based Teaching Model for Nursing Professional Courses Based on Data Mining and Few-Shot Learning Technology.

Teaching is defined as a relatively stable structural framework and activity process of teaching activities established under the guidance of specific teaching concepts and theories. It serves as a link between teaching theory and practice, as well as between the teaching system's static and dynamic conditions. The ITM (Inquiry-Based Teaching Model) has received a lot of attention and has been used in a lot of classrooms. Data mining (DM) is a method for discovering knowledge in databases and a technology for mining information in large data sets. It is primarily used to discover unknown relationships and patterns in related data. This paper applies DM's core technology, particularly the decision tree algorithm, to give hospital managers more comprehensive and in-depth data analysis capabilities, as well as strong technical support for hospitals in developing management plans. Furthermore, due to the scarcity of research data in the nursing profession, this paper introduces the few-shot learning technology to improve the model's analysis ability.