Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning
Not provided.
Science & Technology - Other Topics↗
Engineering topics
Xu, Mengjia
Publications and source records attributed to Xu, Mengjia.
A framework of computer vision-enhanced microfluidic approach for automated assessment of the transient sickling kinetics in sickle red blood cells
The occurrence of vaso-occlusive crisis greatly depends on the competition between the sickling delay time and the transit time of individual sickle cells, i.e., red blood cells from sickle cell disease (SCD) patients, while they are traversing the circulatory system. Many drugs for treating SCD work by inhibiting the polymerization of sickle hemoglobin (HbS), effectively delaying the sickling process in sickle cells (SS RBCs). Most previous studies on screening anti-sickling drugs, such as voxelotor, rely on in vitro testing of sickling characteristics, often conducted under prolonged deoxygenation for up to 1 hour. However, since the microcirculation of RBCs typically takes less than 1 minute, the results of these studies may be less accurate and less relevant for in vitro-in vivo correlation. In our current study, we introduce a computer vision-enhanced microfluidic framework designed to automatically capture the transient sickling kinetics of SS RBCs within a 1-min timeframe. Our study has successfully detected differences in the transient sickling kinetics between vehicle control and voxelotor-treated SS RBCs. This approach has the potential for broader applications in screening anti-sickling therapies.
59 BASIC BIOLOGICAL SCIENCES↗
TransformerG2G: Adaptive time-stepping for learning temporal graph embeddings using transformers
Dynamic graph embedding has emerged as a very effective technique for addressing diverse temporal graph analytic tasks (i.e., link prediction, node classification, recommender systems, anomaly detection, and graph generation) in various applications. Such temporal graphs exhibit heterogeneous transient dynamics, varying time intervals, and highly evolving node features throughout their evolution. Hence, incorporating long-range dependencies from the historical graph context plays a crucial role in accurately learning their temporal dynamics. In this paper, we develop a graph embedding model with uncertainty quantification, TransformerG2G, by exploiting the advanced transformer encoder to first learn intermediate node representations from its current state (t) and previous context (over timestamps [t–1,t–l], l is the length of context). Moreover, we employ two projection layers to generate lower-dimensional multivariate Gaussian distributions as each node's latent embedding at timestamp t. We consider diverse benchmarks with varying levels of "novelty" as measured by the TEA (Temporal Edge Appearance) plots. Here, our experiments demonstrate that the proposed TransformerG2G model outperforms conventional multi-step methods and our prior work (DynG2G) in terms of both link prediction accuracy and computational efficiency, especially for high degree of novelty. Furthermore, the learned time-dependent attention weights across multiple graph snapshots reveal the development of an automatic adaptive time stepping enabled by the transformer. Importantly, by examining the attention weights, we can uncover temporal dependencies, identify influential elements, and gain insights into the complex interactions within the graph structure. For example, we identified a strong correlation between attention weights and node degree at the various stages of the graph topology evolution.
97 MATHEMATICS AND COMPUTING↗
Scalable algorithms for physics-informed neural and graph networks
Physics-informed machine learning (PIML) has emerged as a promising new approach for simulating complex physical and biological systems that are governed by complex multiscale processes for which some data are also available. In some instances, the objective is to discover part of the hidden physics from the available data, and PIML has been shown to be particularly effective for such problems for which conventional methods may fail. Unlike commercial machine learning where training of deep neural networks requires big data, in PIML big data are not available. Instead, we can train such networks from additional information obtained by employing the physical laws and evaluating them at random points in the space–time domain. Such PIML integrates multimodality and multifidelity data with mathematical models, and implements them using neural networks or graph networks. Here, we review some of the prevailing trends in embedding physics into machine learning, using physics-informed neural networks (PINNs) based primarily on feed-forward neural networks and automatic differentiation. For more complex systems or systems of systems and unstructured data, graph neural networks (GNNs) present some distinct advantages, and here we review how physics-informed learning can be accomplished with GNNs based on graph exterior calculus to construct differential operators; we refer to these architectures as physics-informed graph networks (PIGNs). We present representative examples for both forward and inverse problems and discuss what advances are needed to scale up PINNs, PIGNs and more broadly GNNs for large-scale engineering problems.
42 ENGINEERING↗
Fractal analysis of Mo and Nb effects on grain boundary character and hot cracking behavior for Ni-Cr-Fe alloys
Highlights: • Cross section of the weld with lower RHGB fractal dimension exhibited higher DDC susceptibility than the surface section. • Mo and Nb addition induced tortuous GB character to increase fractal dimension and improve cracking resistance. • GROD maps indicated that the local strain increased within the grains close to RGBs till cracking. • At 1050 °C deformation recrystallized grains nucleated adjacent to DDC and blocked the crack propagation. - Abstract: In this paper, two filler metals of alloy 690 were evaluated on their hot cracking resistance based on the fractal analysis of random high-angle grain boundary (RHGB) morphologies. A grain reference orientation deviation (GROD) map based on EBSD technique was conducted to investigate the polycrystalline strain distribution on different RHGB network. It was found that for the 52M weld metal, specimen from the cross section with straight dendritic GBs exhibited lower fractal dimension, showing higher DDC susceptibility than the specimen from the surface section with higher fractal dimension due to equiaxed grains with tortuous GBs. With Mo and more Nb adding to the filler metal 52MSS, smaller grains nucleated and fractal dimension of the RHGB network increased, thus the cracking resistance was greatly improved. The GROD results revealed that local strain commonly concentrated around RHGB at high temperatures, especially near long and straight RHGB. The dense and tortuous RHGB network, resulting in the higher fractal dimension, could bear a more uniform strain distribution and balance the deformation between GB and grains, leading to better performance on cracking resistance. Moreover, dynamic recrystallized grains were observed beside GBs and their amount increases where there was cracking at 1050 °C, especially for the 52MSS. As a result, crack propagation path was blocked and fractal dimension increased as well.
36 MATERIALS SCIENCE↗