Air quality information such as the concentration of PM2.5 is great significance for human health and city management. It affects way traveling, urban planning, government policies so on. However, in major cities there typically only a limited number air monitoring stations. In meantime, varies areas can be large differences, even between closely neighboring regions. this paper, random forest approach predicting (RAQ) proposed sensing systems. The data generated by includes meteorology data,...

Face alignment, especially on real-time or large-scale sequential images, is a challenging task with broad applications. Both generic and joint alignment approaches have been proposed varying degrees of success. However, many methods are heavily sensitive to initializations usually rely offline-trained static models, which limit their performance images extensive variations. On the other hand, restricted offline applications, since they require all frames conduct batch alignment. To address...

In citrus cultivation, it is a difficult task for farmers to classify different pests correctly and make proper decisions prevent damage. This work proposes an efficient modified lightweight transfer learning model which combines the effectiveness accuracy of pest characterization with mobile terminal counting. Firstly, we utilized typical feature extraction networks such as ResNet50, InceptionV3, VGG16, MobileNetV3, pre-trained single-shot multibox detector (SSD) network compare analyze...

Instant delivery is an important urban service in recent years because of the increasing demand. An issue for platforms to keep updating status couriers especially real-time locations, which challenging when they are indoor environment. We argue previous localization techniques cannot be applied instant scenario require extra deployed infrastructures and extensive labor work. In this work, we perform couriers' transparently a predictive manner without actions by existing data from platform...

The emergence of Online-to-Offline (O2O) stores based on delivery platforms (e.g., Uber Eats, DoorDash, and Eleme) provides great convenience to people's lives. In the O2O model, one essential problems for merchants is select a suitable store site, i.e., site recommendation problem. We argue that existing works traditional brick-and-mortar cannot address this problem due two unique factors in model including (i) dynamic supply caused by courier capacity dispatching strategies (ii) various...

Urban anomalies have a large impact on passengers' travel behavior and city infrastructures, which can cause uncertainty time estimation. Understanding the of urban is great value for various applications such as planning, human mobility studies navigation systems. Most existing been focused total riding between two locations an individual transportation modality. However, passengers often take different modes transportation, e.g., taxis, subways, buses or private vehicles, significant...

We report a 3-year city-wide study of an operational indoor sensing system based on Bluetooth Low Energy (BLE) called <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">aBeacon</monospace> (short for <underline xmlns:xlink="http://www.w3.org/1999/xlink">a</u> libaba xmlns:xlink="http://www.w3.org/1999/xlink">Beacon</u> ). is pilot-studied, A/B tested, deployed, and operated in Shanghai, China to infer the status Alibaba couriers, e.g.,...

Picking fruits from tall fruit trees manually is laborious and inefficient. Rotary-wing drones, a low-altitude carrier platform, can enhance the picking efficiency for when combined with robotic arms. However, during operation of rotary-wing wind field changes dramatically, center gravity drone shifts at moment picking, leading to poor aerodynamic stability making it difficult achieve optimized attitude control. To address aforementioned issues, this paper constructs testing platform employs...

Estimating service capabilities for logistics terminal stations is essential guiding operations adjustments to enhance customer experience. However, existing studies often focus on isolated metrics like on-time delivery or complaint rates, each reflecting a specific aspect of capabilities. To provide more comprehensive evaluation, we design AdaService, an Adaptive multi-faceted Service co-estimation framework. We begin by constructing Multi-faceted Hypergraph encode using multiple...

Microperforated panels (MPP) are widely used in noise control applications due to their excellent sound absorption performance. However, traditional single-layer MPPs suffer from a narrow bandwidth, making it difficult meet the demands for broadband absorption. To address this limitation, study proposes design approach double-layer optimized using genetic algorithm (GA). By optimizing structural parameters such as perforation diameter, panel thickness, ratio, and cavity depth, performance of...

To investigate the seismic performance of steel tube-reinforced concrete (ST-RC) columns after fire on one side, this study employs numerical simulation and theoretical analysis methods. A model ST-RC post-fire is established using ABAQUS to simulate analyze their under cyclic loading. The characteristics hysteresis curves side loading are described in detail. Comparisons made between skeleton curves, ductility, stiffness degradation, energy dissipation capacity three conditions: unexposed...

In the process of drama development, audience is always passively accepting. recent years, public has been pursuing ‘immersion’.In a sense, immersive theatre broken previous 's inherent concepts such as type performance venue, form performance, and relationship between actors audiences. On this basis, paper also explores path development evolution Chinese drama, on integrates new ideas concepts.

Estimating travel time on the highway in real is of great importance for transportation services. Previous work has been mainly focusing city scale a particular system, e.g., taxi, bus, and metro. Little research conducted to estimate fine-grained real-time state-level systems. This because traditional solutions based probe vehicles or loop sensors cannot systems due their large spatial coverage. Recently, adoption Electric Toll Collection (ETC) (e.g. EZ-pass) brings new opportunity with...

The real-time vehicle sensing at urban scale is essential to various services. To date, most existing approaches rely on static infrastructures (e.g., traffic cameras) or mobile services smartphone apps). However, these are often inadequate for the individual level because of their natures low penetration rates. In this paper, we design a system called coSense utilize commercial vehicular fleets taxis, buses, and trucks) scale, given (i) availability well-equipped other vehicles by onboard...

Understanding and predicting real-time vehicle mobility patterns on highways are essential to address traffic congestion respond the emergency. However, almost all existing works (e.g., based cellphones, onboard devices, or cameras) suffer from high costs, low penetration rates, only aggregate results. To these drawbacks, we utilize Electric Toll Collection systems (ETC) as a large-scale sensor network design system called VeMo transparently model predict at individual level with full rate....

Shared electric micromobility (e.g., shared bikes and scooters), as an emerging way of urban transportation, has been increasingly popular in recent years. However, managing thousands vehicles a city, such rebalancing charging to meet spatial-temporally varied demand, is challenging. Existing management frameworks generally consider demand the number requests without energy consumption these requests, which can lead less effective management. To address this limitation, we design RECOMMEND,...

Traffic accident prediction is a crucial problem for public safety, emergency treatment, and urban management. Existing works leverage extensive data collected from city infrastructures to achieve encouraging performance based on various machine learning techniques but cannot good in situations with limited (i.e., scarcity). Recent developments transfer bring new opportunity solve the scarcity problem. In this paper, we design novel cross-city framework named CARPG predicting traffic...

( 5 at. % ) cobalt-doped LiNbO3 (Co:LN) films were prepared by combinatorial laser molecular-beam epitaxy on Si (100). The Co:LN with Co2+ replacing Nb exhibit room temperature ferromagnetism of 1.2μB∕Co and Curie ∼540K. Through a Ag∕Co:LN∕Si metal-ferroelectric-semiconductor field effect transistor configuration, ferroelectric measurements show that the display hysteresis loops at 300K transition ∼610K. asymmetry in capacitance-voltage leakage-voltage curves are ascribed to...

The popularity of e-commerce has promoted the rapid development logistics industry in recent years. As an important step logistics, last-mile delivery from stations to customers' addresses is now mainly finished by couriers, which requires accurate workload assessment based on actual efforts. However, state-of-the-practice methods neglect a vital factor that orders with same customer's address (i.e., Homogeneous orders) can be delivered group single trip) or separately multiple trips). It...