Residential Electricity Consumption Behavior Mining Based on System Cluster and Grey Relational Degree

In order to improve the utilization of the residential electricity consumption data which contains the information on the user’s electricity consumption habits, a residential electricity consumption behaviors mining algorithm model is constructed. Firstly, according to the attribute, the collected data can be divided into the global data and the phase data, then the appropriate global variables are selected to mine the user’s electricity consumption patterns in the near future on the system clustering algorithm. Based on the theory of grey relational analysis, combing phase data with the power modes to analyze the potential characteristics of residential electricity consumption behaviors deeply that verify the ability of latest power mode to predict household electricity consumption situation in the coming few days and the effect of dominant phase variables on the peak load shifting. Finally, from the actual data of a certain family, the proposed data mining algorithm is testified that it can effectively explore the electricity consumption behavior habits and characteristics of the family.

Reshaping the imprinting strategy through the thermo-responsive moiety-derived“deep eutectic solvents”effect

As a new concept having emerged in last few years,the“deep eutectic solvents”(DESs)effect integrated into the imprinting technology inevitably exposes design limitations of stimuli-responsive molecularly imprinted polymers(MIPs),as well as inadequate analysis of the adsorption performance of MIPs.Herein,a simple yet defined N-isopropylacrylamide/(3-acrylamidopropyl)trimethylammonium chloride(NIPAM/APTMAC)binary DESs system was proposed to prepare intelligent MIPs with thermo-sensitivity.Accordingly,magnetic and thermo-responsive MIPs based on functional monomers-derived DESs(TMDESs-MIPs1)were synthesized,revealing DESs effect-regulated affinity/kinetics for the enhanced adsorption capability,eco-friendly thermo-regulated elution for high release efficiency,and simple magnetic separation,along with superior selectivity to rhein(RH)and good regeneration ability.TM-DESs-MIPs1 were utilized to extract RH from Cassiae semen samples coupled with high performance liquid chromatography(HPLC),yielding satisfactory recoveries(79.47%−110.82%)and low limits of detection(LOD)(16.67μg/L).Another two kinds of MIPs adopting the thermo-responsive moiety-derived DESs effect strategy further demonstrated great applicability of such intelligent MIPs for analyses of complicated samples.

Rock Climbing‑Inspired Electrohydrodynamic Cryoprinting of Micropatterned Porous Fiber Scaffolds with Improved MSC Therapy for Wound Healing

Impaired wound healing imposes great health risks to patients.Recently,mesenchymal stem cell(MSC)therapy has shown potential to improve the healing process,but approaches to employ MSCs in the treatment of wounds remain elusive.In this study,we reported a novel electrohydrodynamic(EHD)cyroprinting method to fabricate micropatterned fiber scaffolds with polycaprolactone(PCL)dissolved in glacial acetic acid(GAC).Cyroprinting ensured the formation of a porous struc-ture of PCL fibers by preventing the evaporation of GAC,thus increasing the surface roughness parameter Ra from 11 to 130 nm.Similar to how rough rocks facilitate easy climbing,the rough surface of fibers was able to increase the adhesion of adipose-derived MSCs(AMSCs)by providing more binding sites;therefore,the cell paracrine action of secreting growth factors and chemokines was enhanced,promoting fibroblast migration and vascular endothelial cell tube formation.In rat models with one-centimeter wound defects,enhanced MSC therapy based on porous PCL fiber scaffolds improved wound healing by augmenting scarless collagen deposition and angiogenesis and reducing proinflammatory reactions.Altogether,this study offers a new and feasible strategy to modulate the surface topography of polymeric scaffolds to strengthen MSC therapy for wound healing.

Dynamics in Deep Classifiers Trained with the Square Loss:Normalization,Low Rank,Neural Collapse,and Generalization Bounds

We overview several properties—old and new—of training overparameterized deep networks under the square loss.We first consider a model of the dynamics of gradient flow under the square loss in deep homogeneous rectified linear unit networks.We study the convergence to a solution with the absolute minimumρ,which is the product of the Frobenius norms of each layer weight matrix,when normalization by Lagrange multipliers is used together with weight decay under different forms of gradient descent.A main property of the minimizers that bound their expected error for a specific network architecture isρ.In particular,we derive novel norm-based bounds for convolutional layers that are orders of magnitude better than classical bounds for dense networks.Next,we prove that quasi-interpolating solutions obtained by stochastic gradient descent in the presence of weight decay have a bias toward low-rank weight matrices,which should improve generalization.The same analysis predicts the existence of an inherent stochastic gradient descent noise for deep networks.In both cases,we verify our predictions experimentally.We then predict neural collapse and its properties without any specific assumption—unlike other published proofs.Our analysis supports the idea that the advantage of deep networks relative to other classifiers is greater for problems that are appropriate for sparse deep architectures such as convolutional neural networks.The reason is that compositionally sparse target functions can be approximated well by“sparse”deep networks without incurring in the curse of dimensionality.