Search for: All records

Accurate road networks play a crucial role in modern mobile applications such as navigation and last-mile delivery. Most existing studies primarily focus on generating road networks in open areas like main roads and avenues, but little attention has been given to the generation of community road networks in closed areas such as residential areas, which becomes more and more significant due to the growing demand for door-to-door services such as food delivery. This lack of research is primarily attributed to challenges related to sensing data availability and quality. In this paper, we design a novel framework called SmallMap that leverages ubiquitous multi-modal sensing data from last-mile delivery to automatically generate community road networks with low costs. Our SmallMap consists of two key modules: (1) a Trajectory of Interest Detection module enhanced by exploiting multi-modal sensing data collected from the delivery process; and (2) a Dual Spatio-temporal Generative Adversarial Network module that incorporates Trajectory of Interest by unsupervised road network adaptation to generate road networks automatically. To evaluate the effectiveness of SmallMap, we utilize a two-month dataset from one of the largest logistics companies in China. The extensive evaluation results demonstrate that our framework significantly outperforms state-of-the-art baselines, achieving a precision of 90.5%, a recall of 87.5%, and an F1-score of 88.9%, respectively. Moreover, we conduct three case studies in Beijing City for courier workload estimation, Estimated Time of Arrival (ETA) in last-mile delivery, and fine-grained order assignment. 

Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domain setting, where all data come from the same domain (e.g., the same dataset). However, many real-world tasks often involve multiple domains. For example, in visual recognition, it is often desirable to train an image classifier that works across different environments (e.g., different backgrounds), where images from each environment constitute one domain. Such a multi-domain AL setting is challenging for prior methods because they (1) ignore the similarity among different domains when assigning labeling budget and (2) fail to handle distribution shift of data across different domains. In this paper, we propose the first general method, dubbed composite active learning (CAL), for multi-domain AL. Our approach explicitly considers the domain-level and instance-level information in the problem; CAL first assigns domain-level budgets according to domain-level importance, which is estimated by optimizing an upper error bound that we develop; with the domain-level budgets, CAL then leverages a certain instance-level query strategy to select samples to label from each domain. Our theoretical analysis shows that our method achieves a better error bound compared to current AL methods. Our empirical results demonstrate that our approach significantly outperforms the state-of-the-art AL methods on both synthetic and real-world multi-domain datasets. Code is available at https://github.com/Wang-ML-Lab/multi-domain-active-learning. 

Abstract Electrochemical oxygen reduction to hydrogen peroxide (H 2 O 2 ) in acidic media, especially in proton exchange membrane (PEM) electrode assembly reactors, suffers from low selectivity and the lack of low-cost catalysts. Here we present a cation-regulated interfacial engineering approach to promote the H 2 O 2 selectivity (over 80%) under industrial-relevant generation rates (over 400 mA cm −2 ) in strong acidic media using just carbon black catalyst and a small number of alkali metal cations, representing a 25-fold improvement compared to that without cation additives. Our density functional theory simulation suggests a “shielding effect” of alkali metal cations which squeeze away the catalyst/electrolyte interfacial protons and thus prevent further reduction of generated H 2 O 2 to water. A double-PEM solid electrolyte reactor was further developed to realize a continuous, selective (∼90%) and stable (over 500 hours) generation of H 2 O 2 via implementing this cation effect for practical applications. 

Abstract Electrochemical water oxidation reaction (WOR) to hydrogen peroxide (H 2 O 2 ) via a 2e − pathway provides a sustainable H 2 O 2 synthetic route, but is challenged by the traditional 4e − counterpart of oxygen evolution. Here we report a CO 2 /carbonate mediation approach to steering the WOR pathway from 4e − to 2e − . Using fluorine-doped tin oxide electrode in carbonate solutions, we achieved high H 2 O 2 selectivity of up to 87%, and delivered unprecedented H 2 O 2 partial currents of up to 1.3 A cm −2 , which represents orders of magnitude improvement compared to literature. Molecular dynamics simulations, coupled with electron paramagnetic resonance and isotope labeling experiments, suggested that carbonate mediates the WOR pathway to H 2 O 2 through the formation of carbonate radical and percarbonate intermediates. The high selectivity, industrial-relevant activity, and good durability open up practical opportunities for delocalized H 2 O 2 production.