Search

Background: Breast cancer poses a significant health risk to women worldwide, with approximately 30% being diagnosed annually in the United States. The identification of cancerous mammary tissues from non-cancerous ones during surgery is crucial for the complete removal of tumors. Results: Our study innovatively utilized machine learning techniques (Random Forest (RF), Support Vector Machine (SVM), and Convolutional Neural Network (CNN)) alongside Raman spectroscopy to streamline and hasten the differentiation of normal and late-stage cancerous mammary tissues in mice. The classification accuracy rates achieved by these models were 94.47% for RF, 96.76% for SVM, and 97.58% for CNN, respectively. To our best knowledge, this study was the first effort in comparing the effectiveness of these three machine-learning techniques in classifying breast cancer tissues based on their Raman spectra. Moreover, we innovatively identified specific spectral peaks that contribute to the molecular characteristics of the murine cancerous and non-cancerous tissues. Conclusions: Consequently, our integrated approach of machine learning and Raman spectroscopy presents a non-invasive, swift diagnostic tool for breast cancer, offering promising applications in intraoperative settings. [ABSTRACT FROM AUTHOR]

In view of problem of low precision of parameter identification based on least square method, a parameter identification method of mine-used robot driving system based on whale optimization algorithm was proposed. Driving system model of mine-used robot is established to determine parameters to be identified which are considered as individual position of whale colony. Fitness function is used to measure the individual position of whale colony. The optimal identification parameters can be obtained by continuously updating the individual position of whale colony with whale foraging strategy until the optimal individual position of whale colony is obtained. The simulation and experimental results show that the method has higher identification accuracy than the parameter identification method based on least square method.

The randomness and time variability of power load are the main problems in the load modeling, in which the model error and measurement noise greatly affect the modeling accuracy. In this paper, an adaptive fuzzy logic strong tracking based load modeling method is proposed. The problems of load characteristics and parameter identification of load model are transformed into a real-time tracking of load. The optimal model set is first selected from the initial load model set, and according to the mixing probability, the state estimation and error covariance are mixed as the input of the filter. In order to reduce the model error in the parallel filtering, the strong tracking filter (STF) is constructed based on the orthogonality principle and the filter gain is adjusted by introducing a time-varying fading factor. The adaptive fuzzy logic strong tracking filter is constructed by combining the fuzzy logic with the STF to adjust the covariance matrix of the STF according to the change of measurement noise. Moreover, the weights of each sub model are updated in real time by the parallel filtering, and the sub models are fused to get a comprehensive load model which can reflect the actual load characteristics. The effectiveness of the method is verified by the simulation of IEEE 39-bus system. This method can establish an accurate load model and has good robustness. [ABSTRACT FROM AUTHOR]