Language models have contributed to breakthroughs in interdisciplinary research, such as protein design and molecular dynamics understanding. In this study, we reveal that beyond language, ...representations of other entities, such as human behaviors, that are mappable to learnable sequences can be learned by language models. One compelling example is the real-world delivery route optimization problem. We here propose a novel approach based on the language model to optimize delivery routes on the basis of drivers’ historical experiences. Although a broad range of optimization-based approaches have been designed to optimize delivery routes, they do not capture the implicit knowledge of complex delivery operating environments. The model we propose integrates this knowledge in the route optimization process by learning from driving behaviors in experienced drivers. A real-world delivery route that preserves drivers’ implicit behavioral patterns is first analogized to a sentence in natural language. Through unsupervised learning, we then learn the vector representations of words and infer the drivers’ delivery chains on the basis of the tailored chain-reaction-based algorithm. We also provide insights into the fusion of language models and operations research methods. In our approach, language models are applied to learn drivers’ delivery behaviors and infer new deliveries at the delivery zone level, while the classic traveling salesman problem (TSP) model is embedded into the hybrid framework for intra-zone optimization. Numerical experiments performed on real-world data from Amazon’s delivery service demonstrate that the proposed approach outperforms pure optimization, supporting the effectiveness, efficiency, and extensibility of our model. As a versatile approach, the proposed framework can easily be extended to various disciplines in which the data follow certain grammar rules. We anticipate that our work will serve as a stepping stone toward the understanding and application of language models in tackling interdisciplinary research problems.
▪
•Revealing that language models can learn human behavioral sequences.•Integrating the implicit knowledge of drivers in the route optimization process.•A novel algorithm to optimize delivery routes emulating real-world driving behaviors.•Broadening the scope of language models to diverse domains with certain grammar rules.
Bi/Bi2O3 nanoparticles were deposited on the surface of TiO2 nanotube arrays (TiO2 NTs) by a simple solvothermal method by changing the C6H12O6 concentration. The intimate interface contact of Bi2O3 ...and TiO2 NTs formed Z-scheme heterojunction with high visible-light response. The concomitant Bi0 not only accelerated charge carrier transfer, but also improved the visible light absorption by the local surface plasmon resonance (LSPR). The Z-scheme heterojunction Bi/Bi2O3/TiO2 NTs photocatalysts significantly improved the visible light absorption, photocurrent and photocatalytic activity. The visible light photocurrent density and photovoltage achieved 6.42 mA/cm2 and -0.35 V, and the photoelectrocatalytic removal efficiencies of MO and RhB dyes achieved 75% and 80%, respectively. The photocatalytic degradation mechanism was tentatively proposed based on the electron transfer path and photocatalytic data. The enhanced photoelectrochemical performance of Bi/Bi2O3/TiO2 NTs was ascribed to synergistic effect of Z-scheme heterojunction interface and LSPR effect of Bi0.
Display omitted
•Different morphology of Bi3O3 were loaded to TiO2 NTs surface by simple solvothermal method.•The morphology of Bi2O3 was controlled through changing content of C6H12O6.•The heterojunction photocatalysts showed the excellent photoelectric converting and PEC properties.•The PEC mechanism of Z-scheme heterojunction Bi/Bi2O3/TiO2 NTs photocatalysts was proposed.
In the present study, we fabricated a biocomposite scaffold composed of carboxymethyl chitosan (CMC), gelatin and LAPONITE® (Lap) nanoparticles
via
freeze-drying and investigated its potential use in ...bone tissue engineering. The prepared gelatin/carboxymethyl chitosan (GC) scaffolds and laponite-incorporated scaffolds were characterized by scanning electron microscopy (SEM), and Fourier transform infrared spectroscopy (FTIR) analyses. The swelling and biodegradation were also investigated.
In vitro
assays such as cell attachment and proliferation, osteogenic differentiation of rat bone marrow-derived mesenchymal stem cells (rBMCSs) grown on those scaffolds and
in vivo
cranial bone defect assays were further carried out. We found that our prepared scaffolds had a porous architecture, and the increased Lap content resulted in improved mechanical strength, whereas the swelling ratio and degradation rate decreased.
In vitro
cell proliferation and live cell staining experiments demonstrated that the addition of Lap (5 and 10 wt% relative to gelatin, GC-Lap5% and GC-Lap10% respectively) would facilitate cell proliferation, but caused an inhibition effect at 15% of Lap content (GC-Lap15%). Furthermore, GC-Lap10% induced a higher degree of osteogenic differentiation of rBMSCs compared with the GC scaffold and GC-Lap5% scaffold. More importantly,
in vivo
cranial defect experiments revealed that the addition of Lap into the GC scaffold promoted bone regeneration. These findings indicate that a composite scaffold with Lap incorporation is a promising material for bone tissue engineering.
In the present study, we fabricated a biocomposite scaffold composed of carboxymethyl chitosan (CMC), gelatin and LAPONITE® (Lap) nanoparticles
via
freeze-drying and investigated its potential use in bone tissue engineering.
Memristive synapses based on resistive switching are promising electronic devices that emulate the synaptic plasticity in neural systems. Short‐term plasticity (STP), reflecting a temporal ...strengthening of the synaptic connection, allows artificial synapses to perform critical computational functions, such as fast response and information filtering. To mediate this fundamental property in memristive electronic devices, the regulation of the dynamic resistive change is necessary for an artificial synapse. Here, it is demonstrated that the orientation of mesopores in the dielectric silica layer can be used to modulate the STP of an artificial memristive synapse. The dielectric silica layer with vertical mesopores can facilitate the formation of a conductive pathway, which underlies a lower set voltage (≈1.0 V) compared to these with parallel mesopores (≈1.2 V) and dense amorphous silica (≈2.0 V). Also, the artificial memristive synapses with vertical mesopores exhibit the fastest current increase by successive voltage pulses. Finally, oriented silica mesopores are designed for varying the relaxation time of memory, and thus the successful mediation of STP is achieved. The implementation of mesoporous orientation provides a new perspective for engineering artificial synapses with multilevel learning and forgetting capability, which is essential for neuromorphic computing.
Orientation of mesopores mediates the short‐term plasticity in an artificial memristive synapse. The vertical mesopores provide directional channels for resistance switching at a lower energy consumption but faster response and shorter relaxation time upon identical simulating voltage pulses, compared to those with parallel mesopores and dense amorphous silica.
We report a general activated amide to ester transformation catalyzed by Cs2CO3. Using this approach, esterification proceeds under relatively mild conditions and without the need for a transition ...metal catalyst. This method exhibits broad substrate scope and represents a practical alternative to existing esterification strategies. The synthetic utility of this protocol is demonstrated via the facile synthesis of crown ether derivatives and the late-stage modification of a representative natural product and several sugars in reasonable yields.
Abstract Locally resonant metamaterials usually have narrow bandgaps, which significantly limits their applications in realistic engineering environments. In this paper, an optimization method based ...on the genetic algorithm is proposed to broaden bandgaps in multi-resonant piezoelectric metamaterial through the merging of multiple separated bandgaps. Using the effective medium theory, the equivalent bending stiffness and dispersion relationship of a metamaterial plate are first obtained. Then, the criteria for determining the bandgap ranges for the two cases with and without damping are provided and analyzed. Furthermore, based on the bandgap merging phenomena, an optimization method for widening the bandgap is proposed based on the genetic algorithm. By investigating the bandgap widening effects in cases without and with damping, it is found that, when there is no damping, the bandgap can only be slightly widened; while after introducing damping into the transfer functions, the bandgap can be significantly widened by more than 200%. The bandgap widening effects are verified by comparing with finite element simulation results.
Real-time traffic state (e.g., speed) prediction is an essential component for traffic control and management in an urban road network. How to build an effective large-scale traffic state prediction ...system is a challenging but highly valuable problem. This study focuses on the construction of an effective solution designed for spatio-temporal data to predict the traffic state of large-scale traffic systems. In this study, we first summarize the three challenges faced by large-scale traffic state prediction, i.e., scale, granularity, and sparsity. Based on the domain knowledge of traffic engineering, the propagation of traffic states along the road network is theoretically analyzed, which are elaborated in aspects of the temporal and spatial propagation of traffic state, traffic state experience replay, and multi-source data fusion. A deep learning architecture, termed as Deep Traffic State Prediction (DeepTSP), is therefore proposed to address the current challenges in traffic state prediction. Experiments demonstrate that the proposed DeepTSP model can effectively predict large-scale traffic states.
Bacteria play an important role in water purification in drinking water treatment systems. On one hand, bacteria present in the untreated water may help in its purification through biodegradation of ...the contaminants. On the other hand, some bacteria may be human pathogens and pose a threat to consumers. The present study investigated bacterial communities using Illumina MiSeq sequencing of 16S rRNA genes and their functions were predicted using PICRUSt in a treatment system, including the biofilms on sand filters and biological activated carbon (BAC) filters, in 4 months. In addition, quantitative analyses of specific bacterial populations were performed by real-time quantitative polymerase chain reaction (qPCR). The bacterial community composition of post-ozonation effluent, BAC effluent and disinfected water varied with sampling time. However, the bacterial community structures at other treatment steps were relatively stable, despite great variations of source water quality, resulting in stable treatment performance. Illumina MiSeq sequencing illustrated that
was dominant bacterial phylum. Chlorine disinfection significantly influenced the microbial community structure, while other treatment processes were synergetic. Bacterial communities in water and biofilms were distinct, and distinctions of bacterial communities also existed between different biofilms. By contrast, the functional composition of biofilms on different filters were similar. Some functional genes related to pollutant degradation were found widely distributed throughout the treatment processes. The distributions of
spp. and
spp. in water and biofilms were revealed by real-time quantitative polymerase chain reaction (qPCR). Most bacteria, including potential pathogens, could be effectively removed by chlorine disinfection. However, some bacteria presented great resistance to chlorine. qPCRs showed that
spp. could not be effectively removed by chlorine. These resistant bacteria and, especially potential pathogens should receive more attention. Redundancy analysis (RDA) showed that turbidity, ammonia nitrogen and total organic carbon (TOC) exerted significant effects on community profiles. Overall, this study provides insight into variations of microbial communities in the treatment processes and aids the optimization of drinking water treatment plant design and operation for public health.
•A 10 wt% SiC-reinforced AlSi10Mg-based composites with higher density is prepared by selective laser melting.•Al4SiC4 phase forms because the in situ reaction between SiC and Al melt occurs.•The ...SLM-fabricated AlSi10Mg-10SiC composite (90.64 J/mm3) displays the high yield strength (408 Mpa) and modulus (90 Gpa).
In this study, a 10 wt% SiC-reinforced AlSi10Mg-based composites is prepared by selective laser melting (SLM) process. The effect of laser linear energy density on phase morphology, microstructure, and mechanical properties of AlSi10Mg-10SiC composite is investigated. There is relatively higher density, no obvious pores and cracks in the SLM-fabricated AlSi10Mg-10SiC composites with laser linear energy densities ranging from 90.64 J/mm3 to 104.16 J/mm3. The high laser linear energy density promotes the in-situ reaction between SiC particle and Al melt in the melt pool, the Al4SiC4 phase forms during SLM fabrication process. Driven by Marangoni convection, the fine SiC particles and Al4SiC4 phase distributes uniformly. When the laser linear energy density is 104.16 J/mm3, the composite exhibits the highest average microhardness of 208.5 HV0.1. When the laser linear energy density is 90.64 J/mm3, the composite displays the highest yield strength and modulus with values of 408 MPa and 90 Gpa, respectively. During the deformation process of tensile test, the higher modulus SiC particles could withstand greater load transfer, which improves the modulus and yield strength of the composites.