Design and application of coal gangue sorting system based on deep learning.

With the advancement of science and technology, coal-washing plants are transitioning to intelligent, information-based, and professional sorting systems. This shift accelerates the construction a modern economic system characterized by green and low-carbon development, thereby promoting the high-quality advancement of the coal industry. Traditional manual gangue picking and multi-axis robotic arm gangue selection currently suffer from low recognition accuracy, slow sorting efficiency, and high worker labor intensity. This paper proposes a deep learning-based, non-contact gangue recognition and pneumatic intelligent sorting system. The system constructs a dynamic database containing key feature information such as the target gangue's contour, quality, and center of mass. The system elucidates the relationships between ejection speed, mass, volume, angle of incidence, and the impact energy matching mechanism. Demonstration experiments using the system prototype for coal gangue sorting reveal that, compared to existing robotic arm sorting methods in coal washing plants, this system achieves a gangue identification accuracy exceeding 97%, a sorting rate above 91%, and a separation time of less than 3 s from identification to separation, thereby effectively enhancing raw coal purity.

Cuproptosis scoring model predicts overall survival and assists in immunotherapeutic decision making in pancreatic carcinoma.

Background: Cuproptosis is a newly identified form of non-apoptotic cell death that is associated with the progression and treatment responses in pancreatic adenocarcinoma (PAAD). However, its impact on oncology and tumor microenvironment (TME) remains unclear. Methods: Hub genes were identified using least absolute shrinkage and selection operator (LASSO) Cox regression for 25 newly reported cuproptosis-related regulators and subjected to stepwise regression to obtain cuproptosis-related score (CuRS). Additionally, the clinical significance, functional status, role on TME, and genomic variation of CuRS were further examined systematically. Results: A CuRS model incorporating TRAF2, TRADD, USP21, FAS, MLKL, TNFRSF10B, MAPK8, TRAF5, and RIPK3 was developed. The stability and accuracy of this risk model as an independent prognostic factor for PAAD were confirmed in the training and external validation cohorts. Patients in the high-CuRS group had "cold" tumors with active tumor proliferation and immunosuppression, whereas those in the low-CuRS group comprised "hot" tumors with active immune function and cell killing capacity. Additionally, patients in the high-CuRS group carried fewer genomic copy number variations (CNVs) and greater somatic mutations. Furthermore, patients in the low- and high-CuRS groups exhibited increased sensitivity to immunotherapy and chemotherapy, respectively. Conclusion: We developed and validated a robust CuRS model based on cuproptosis to assess patients' prognoses and guide clinical decision-making. Overall, the findings of this study are expected to contribute to the comprehensive understanding of cuproptosis and facilitate precise treatment of PAAD.