Molybdenum disulfide (MoS2) nanosheet as nano reinforcement exhibits great advantages in zinc (Zn) implant due to its coordinated crystal slip and grain boundary strain effect. Nevertheless, the poor ...interface bonding restrains the coordination effect of MoS2. In this work, rare earth yttrium (Y) was used to epitaxial grow on the vacancy nucleation sites of MoS2 plane through a gas phase reduction method, and then introduced into Zn to improve their interface bonding. On one hand, rare earth Y could form a semicoherent interface with Zn due to the similar atomic arrangement and small lattice misfit between (101)Y plane (0.272 nm) and (002)Zn plane (0.248 nm). On the other hand, it could be tightly integrated together with sulfur element of MoS2 via covalent bond. As a result, the plastic strain of composites was improved from 6.1 % to 10.45 %. Simultaneously, the fracture energy was also increased to 201 × 103 J/m2, since rare earth Y considerably promoted load transfer efficiency from Zn matrix to MoS2 and thereby significantly activated slip systems. Encouragingly, the mechanical strength of the Zn-based biocomposite simultaneously reached 273.3 ± 10.9 MPa due to load transfer strengthening and grain refinement.
Corporate financial distress prediction research has been ongoing for more than half a century, during which many models have emerged, among which ensemble learning algorithms are the most accurate. ...Most of the state-of-the-art methods of recent years are based on gradient boosted decision trees. However, most of them do not consider using feature importance for feature selection, and a few of them use the feature importance method with bias, which may not reflect the true importance of features. To solve this problem, a heuristic algorithm based on permutation importance (PIMP) is proposed to modify the biased feature importance measure in this paper. This method ranks and filters the features used by machine learning models, which not only improves accuracy but also makes the results more interpretable. Based on financial data from 4,167 listed companies in China between 2001 and 2019, the experiment shows that compared with using the random forest (RF) wrapper method alone, the bias in feature importance is indeed corrected by combining the PIMP method. After the redundant features are removed, the performance of most machine learning models is improved. The PIMP method is a promising addition to the existing financial distress prediction methods. Moreover, compared with traditional statistical learning models and other machine learning models, the proposed PIMP-XGBoost offers higher prediction accuracy and clearer interpretation, making it suitable for commercial use.
•The model Combines a corrected feature selection measure and XGBoost.•Permutation importance can correct the bias of feature importance.•The model is validated on Chinese listed companies datasets over five metrics.•The model is proved to outperform several benchmark techniques.•The feature importance and partial dependence plot enhance model interpretation.
Credit scoring systems have seen revolutionary development in recent decades, with many classification algorithms being proposed. However, with the increase in the data volume, the performance of ...traditional algorithms tends to encounter bottlenecks. Although deep learning methods have advantages in handling big data, they are not commonly applied in credit scoring. As one of the most frequently used methods in deep learning, convolutional neural network (CNN) use convolutional kernels as feature extraction tools and has been very successful in tasks related to images or text. This is because image and text data naturally have a structural characteristic called spatial local correlation, which means that the pixels or tokens covered by the same convolutional kernel are highly correlated, and they can be jointly processed to extract meaningful feature representations. However, the tabular data used for credit scoring do not naturally have such a characteristic. The main contribution of this paper is to propose a novel end-to-end soft reordering one-dimensional CNN (SR-1D-CNN), which can adaptively reorganize the original tabular data and make them more conducive to CNN learning. Several real-world credit scoring datasets of different sizes are used for a comprehensive comparison with traditional machine learning classifiers and other deep learning methods. The experimental results demonstrate that the soft reordering mechanism can effectively improve the classification effect of the CNN for tabular data. With the increase in the data scale, the proposed approach obtains superior results to those of other benchmark models.
The ionosphere is a vitally dynamic charged particle region in the Earth's upper atmosphere, playing a crucial role in applications such as radio communication and satellite navigation. The slant ...total electron contents (STECs) are an important parameter for characterizing wave propagation, representing the integrated electron density along the ray of radio signals passing through the ionosphere. The accurate prediction of STEC is essential for mitigating the ionospheric impact particularly on Global Navigation Satellite Systems (GNSS). In this work, we propose a high-precision STEC prediction model named deep neural operator network (DeepONet)-STEC, which learns nonlinear operators to predict the 4-D temporal-spatial integrated parameter for the specified satellite-ground station ray path globally. As a demonstration, we validate the performance of the model based on GNSS observation data for global and US Continuously Operating Reference Stations (CORS) regimes under ionospheric quiet and storm conditions. The DeepONet-STEC model results show that the three-day 72 h prediction in quiet periods could achieve high accuracy using observation data by the precise point positioning (PPP) with temporal resolution <inline-formula> <tex-math notation="LaTeX">30~\rm {s} </tex-math></inline-formula>. Under active solar magnetic storm periods, the DeepONet-STEC also demonstrated its robustness and superiority than traditional deep learning methods. This work presents a neural operator regression architecture for predicting the 4-D spatiotemporal ionospheric state for satellite navigation system performance, which may be further extended for various space applications and beyond.
Although barium titanate (BaTiO
) presented tremendous potential in achieving self-powered stimulation to accelerate bone repair, pervasive oxygen vacancies restricted the full play of its ...piezoelectric performance. Herein, BaTiO
-GO nanoparticles were synthesized by the
growth of BaTiO
on graphene oxide (GO), and subsequently introduced into poly-L-lactic acid (PLLA) powders to prepare PLLA/BaTiO
-GO scaffolds by laser additive manufacturing. During the synthesis process, CO and C-OH in GO would respectively undergo cleavage and dehydrogenation at high temperature to form negatively charged oxygen groups, which were expected to occupy positively charged oxygen vacancies in BaTiO
and thereby inhibit the formation of oxygen vacancies. Moreover, GO could be partially reduced to reduced graphene oxide, which could act as a conductive phase to facilitate polarization charge transfer, thus further improving the piezoelectric performance. The results showed that the oxygen peak at the specific electron binding energy in O 1s declined from 54.4% to 14.6% and the Ti
peak that was positively correlated with oxygen vacancies apparently weakened for BaTiO
-GO, illustrating that the introduced GO significantly decreased the oxygen vacancy. As a consequence, the piezoelectric current of PLLA/BaTiO
-GO increased from 80 to 147.3 nA compared with that of PLLA/BaTiO
. The enhanced piezoelectric current effectively accelerated cell differentiation by upregulating alkaline phosphatase expression, calcium salt deposition and calcium influx. This work provides a novel insight for the design of self-powered stimulation scaffolds for bone regeneration.
We consider a q-antenna space diversity system combined with two parallel equalizer branches for the reception of short-burst time-division multiple-access signals. By applying a combination of ...several previously proposed blind equalization algorithms, we make significant improvements over the burst error probability performance reported to date. This is achieved by starting the two blind equalizers from different initial tap settings and applying a specific weighting of the equalizers' outputs in order to derive the symbol decision. A burst error probability of less than 10/sup -3/ is achieved with the new strategy for a root mean square (rms) delay spread of less than 0.4 times the symbol duration.
