To develop models using different machine learning algorithms to predict high-risk symptom burden clusters in breast cancer patients undergoing chemotherapy, and to determine an optimal model. Data from 647 breast cancer patients were analyzed to develop a model predicting high-risk symptom burden clusters. Five machine learning algorithms, including an artificial neural network (ANN), a decision tree (DT), a support vector machine (SVM), a random forest (RF), and extreme gradient boosting (XGBoost), were tested, as was traditional logistic regression. Performance was evaluated by deriving the predictive accuracy, precision, discriminatory capacity, calibration, and clinical utility, and an optimal model was identified. A model based on the RF algorithm exhibited better accuracy, precision, and discriminatory capacity than the other models. The area under the receiver operator curve was 0.91, the sensitivity was 65.8%, the specificity was 93.5%, the positive predictive value was 98.02%, and the false positive rate was only 0.91%. The model created using the RF algorithm was excellent in terms of predictive accuracy and precision, and can be used for early identification of the risk of self-reported symptom burden clusters in breast cancer patients undergoing chemotherapy.
Microalloying and heat treatment have been regarded as an efficient way to get higher wear resistance in high manganese steel, and multiscale precipitates can be obtained randomly by the aging process; however, most of the previous work on heat treatment was more concerned with peak aging time and not the synergistic mechanism of different sized precipitates. Here, we propose a novel wear-resistant mechanism by multiscale precipitates regulated via a retrogression and re-aging (RRA) process. Micron, submicron, and nano precipitates are obtained by the RRA process and jointly form micro-scale ultrafine precipitation zones (MUPZs), which can protect the matrix surface and reduce the abrasive embedded probability, thus ameliorating the micro-cutting and micro-plowing mechanisms. This novel wear-resistant mechanism induced by MUPZs shows better effect under high impact energy due to sufficient work hardening caused by the interaction between dislocations and multi-scale precipitates in MUPZs. This work was investigated using SEM, EDS, and TEM, combined with mechanical properties and impact abrasive wear tests.
Direct discharge of wastewater from flotation processes can pose a significant threat to environmental protection due to the presence of residual organic surfactants.These surfactants can decrease the surface tension of aqueous solutions and generate stable foam, which can interfere with further purification treatments.To address this issue, sodium oleate (NaOL), one of the most commonly used surfactants, was studied, and the Fenton oxidation process was utilized to degrade NaOL and mitigate foam generation.In this work, the foamability of NaOL before and after Fenton oxidation pretreatment, the optimal conditions for NaOL degradation, and the effect of temperature on the oxidative process were examined.The findings demonstrate that the foamability of NaOL solution is directly proportional to its concentration, and the Fenton oxidation process can significantly reduce the maximum foam volume and half-life period of the foam.Moreover, the activation energy was determined to be 37.60 kJ/mol, indicating that the oxidative reaction proceeds with a low energy barrier.
Conventional flighted rotary drums usually have flights parallel to the rotating axis, which cannot facilitate the axial motion of the materials in the drum. Here, a new type of horizontal rotary drum with inclined flights and beads was designed. Inclined flights are used to facilitate the axial movement of beads and material, while beads are used as fillers to increase the gas-liquid contact area and to crush the solid materials. We simulated the drum and studied the axial motion of fillers using the discrete element method (DEM). To improve the mass and heat transfer performance, we optimized the distribution of beads in the active phase. The effects of the rotational speed, joint angle, and inlet flow rate in the drum were investigated systematically. The individual effects were evaluated in terms of the mass of particles in the active phase (MAP) and passive phase (MPP), the percentage of the active phase occupied by the particles (OAR), and the axial speed (AS). The response surface methodology (RSM) was used to investigate the significant effects of the interaction between the parameters. The maximum MAP value can be obtained by the following parameters: a rotational speed of 37 rpm, joint angle of 139°, and inlet flow rate of 7.83 kg/s. The interaction between rotational speed and inlet flow rate is the most significant for MAP. The joint angle and inlet flow rate have a significant interactive effect on AS. Besides, the rotational speed, joint angle and inlet flow rate show an interactive effect on OAR and AS. Based on the optimization results, the effect of the inclined angle on the axial motion of beads was also evaluated. The axial motion of the beads occurs mainly in the active phase. Compared to the drum without inclined flights, the drum with inclined flights has an enhanced axial speed increased by 26%. This study will be helpful for the design and optimization of drums with inclined flights.
Lithium-ion batteries are critical components of various advanced devices, including electric vehicles, drones, and medical equipment. However, their performance degrades over time, and unexpected failures or discharges can lead to abrupt operational interruptions. Therefore, accurate prediction of the remaining useful life is essential to ensure device safety and reliability. Conventional RUL prediction methods typically rely on regression analysis, signal processing, and machine learning techniques to assess battery conditions such as charge/discharge cycles, voltage, temperature, and durability. Although effective, these approaches are constrained by their dependence on large amounts of labeled data and the necessity for complex feature engineering to capture battery physical characteristics. In this study, we propose an approach that employs deep transfer learning to address these limitations. By leveraging pretrained model weights, the proposed method significantly improves the efficiency and accuracy of RUL prediction even under limited training data conditions. Furthermore, we investigate the impact of external environmental factors and physical battery characteristics on RUL prediction precision, thereby contributing to a more robust and reliable prediction framework.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
