An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area high resolution. So far, the major difficulty in wildfire image classification is lack of unified identification marks, fire features color, shape, texture (smoke, flame, or both) and background vary significantly from one scene to another. Deep learning (e.g., DCNN for Convolutional Neural Network) very effective high-level feature learning, however, a...

Transient stability and short-term voltage have successively attracted the attention of electric power industry. This paper proposes a novel systematic approach for dynamic VAR planning to improve level transient level. The problem is formulated as multi-objective optimization (MOO) model with objectives including investment cost, level, To reduce complexity proposed MOO model, K-means clustering-based severe contingencies selection global sensitivity analysis-based potential buses are...

As the rapid proliferation of Internet Things (IoT) and edge computing, large amounts data are needed to be stored transmitted in online storage system. Data deduplication can adopted improve communication efficiency minimize space. However, brings security functionality requirements that still unsatisfied. Most existing schemes vulnerable brute-force attacks single-point attacks. Moreover, they impose a heavy burden on resource-constrained nodes do not support cross-domain deduplication....

Exploring the influence mechanism of social media users disinformation verification intention is great significance to rumor governance, risk control, improvement health information content ecology and correction disinformation. Due differentiation user behavior among different groups users, it necessary take group characteristics into account. This study takes integrated model planned theory norm activation as theoretical framework model, discusses moderating effect digital generations....

Unmanned aerial vehicles (UAVs) has shown an increasing interests in agricultural applications. However, single UAV is considered impractical for its limited flight endurance. In this paper, A VND (Variable Neighborhood Descend) enhanced Genetic-PSO (Particle Swarm Optimization) algorithm applied to optimize the paths a group of Multiple UAVs. Instead minimizing total distance (approach A), objective our method whole UAVs with minimum make-span B). Both approaches have been verified...

Abstract Antibodies are prominent therapeutic agents but costly to develop. Existing approaches predict developability depend on structure, which requires expensive laboratory or computational work obtain. To address this issue, we present a machine learning pipeline from sequence alone using physicochemical and learned embedding features. Our approach achieves high sensitivity specificity dataset of 2400 antibodies. These results suggest that is predictive developability, enabling more...

Plug-in Hybrid Electric Vehicles (PHEVs), as a new type of environmental-friendly low cost transportation, have attracted growing interests for logistics. The path-planning optimization PHEV has become major challenge. In fact, PHEV-based routing is hybrid vehicle problem (HVRP). Compared with the traditional Traveling Salesman Problem (TSP) and Vehicle Routing (VRP), should consider more constraints, such time limits, capacity constraints (including fuel tank battery capacity), electric...

Electrostatically actuated dual-axis micromirrors suffer from inherently nonlinear electrostatic torques, leading to the problem of 'pull-in' for large tilt angles. Stabilization beyond pull-in angles this device poses a great challenge researchers. This paper presents servo mechanism based on integral sliding mode control (ISMC) purpose. The scheme comprises an integrator controller which is designed achieve zero steady-state error, and overcoming instability. effectiveness closed-loop...

Analysis of spatio-temporal data often involves correlating different events in time and location to uncover relationships between them. It is also desirable identify patterns the data. Visualizing space same chart not trivial. Common methods includes plotting latitude, longitude as three dimensions a 3D chart. Drawbacks these charts include being able scale well due cluttering, occlusion difficulty track case clustered events. In this paper we present novel 2D visualization technique called...

This paper deals with the multi-objective job shop scheduling problem in a robotic cell (MOJRCSP). All jobs are processed according to their operations order on workstations. Different from classical problem, studied considers that jobs' transportation is handled by robot. Also, expected be finished time window, instead of constant due date. A mixed Integer Programming (MIP) model proposed formulate this problem. Due special characteristics and its NP-hard computational complexity,...

This paper focuses on a modified Multi-Depot Unmanned Aerial Vehicle Routing Problem (MMDUAVRP). Comparing to classic multi-depot vehicle routing problem, our studied problem has no constraints restrict the depot where (UAV) departs and returns. work aims minimize number of UAVs total distance traveled by all UAVs. is mathematically formulated in this heuristic-assignment based hybrid large neighborhood search(HLNS) proposed solve it. Extensive computational experiments are conducted verify...

In vehicular networks, the interference is brought about by rapid growth of various services due to scarcity radio resources, which poses great challenges for network connectivity. Unlike connectivity that solely determined signal strength or distance between pairwise vehicles, considered in this paper influenced among multiple links. To improve mitigation, a optimization problem based on resource allocation modeled using graph theory. First, definitions metrics affected networks are given....

The photovoltaic (PV) power generation has randomicity and intermittence due to the influence by meteorological factors it is of significance establish a reasonable prediction model for PV power. Since tough get completely optimal single existence uncertainty, paper considered proposing an ensemble method integrating various individual models achieve better accuracy. In this paper, weight-varying (WVE) forecasting established improve precision short-term First, extraction feature vectors was...

With the increase in global wireless traffic, use of large-scale satellite networking to provide ubiquitous access is one essential trends future 6G network development. Elastic optical networks (EOSNs) are widely considered a flexible solution for communication. However, with continuous proliferation devices and users, growing disparity between user demands limited bandwidth capacity becoming increasingly noticeable. This has led issues such as constrained resource utilization...