Radio frequency identification (RFID) networks planning (RNP) is a challenging task on how to deploy RFID readers under certain constraints. Existing RNP models are usually derived from the flat and centralized-processing framework identified by vertical integration within set of objectives which couple different types control variables. This paper proposes two-level model based hierarchical decoupling principle reduce computational complexity, in costefficient at top levels modeled with...

With the advancement of autonomous driving technology, vehicle lane-change decision (LCD) has become a critical issue for improving safety and efficiency. Traditional deep reinforcement learning (DRL) methods face challenges such as slow convergence, unstable decisions, low accuracy when dealing with complex traffic environments. To address these issues, this paper proposes novel integrated model called “SGD-TripleQNet” decision-making. This method integrates three types Q-learning networks...

The degradation of the ecosystem and loss natural capital have seriously threatened sustainable development human society economy. Currently, most research on Gross Ecosystem Product (GEP) is based statistical modeling methods, which face challenges such as high difficulty, costs, inaccurate quantitative methods. However, machine learning models are characterized by efficiency, fewer parameters, higher accuracy. Despite these advantages, their application in GEP not widespread, particularly...

This paper revisits the thorny issue of energy consumption and carbon emissions associated with Ethereum blockchain, introducing network's strategic resolution for improving footprint - Merge. The main focus is transitioning from a Proof Work (PoW) to Stake (PoS) consensus algorithm. Theoretically, we dissect feasibility PoW PoS algorithms in ameliorating efficiency emissions. Additionally, have amassed curated data relevant research bodies about this issue. Both theoretical analyses...

Fast and accurate prediction of pedestrian trajectory around vehicles can reduce or even prevent most traffic accidents improve the safety participants. This involves real-time interaction fusion various information, such as vehicle’s motion characteristics, pedestrian’s historical trajectory, relationship between people cars. However, existing algorithms use RNN skeleton to process information which is weak in extracting internal different running time algorithm long. To solve these...

In this work, a new plant-inspired optimization algorithm namely the hybrid artificial root foraging optimizion (HARFO) is proposed, which mimics iterative behaviors for complex optimization. HARFO model, two innovative strategies were developed: one root-to-root communication strategy, enables individual exchange information with each other in different efficient topologies that can essentially improve exploration ability; co-evolution structure hierarchical spatial population driven by...

A new multi-objective optimized bacterial foraging algorithm - Hybrid Multi-Objective Optimized Bacterial Foraging Algorithm (HMOBFA) is presented in this article. The proposed combines the crossover-archives strategy and life-cycle optimization strategy, look for best method through research area. crossover-archive with an external archive internal assigned to different selection principles focus on diversity convergence separately. Additionally, according local landscape satisfy population...

We develop an optimization model for risk management in a virtual enterprise environment based on novel multiswarm particle swarm optimizer called PS 2 O. The main idea of O is to extend the single population PSO interacting multiswarms by constructing hierarchical interaction topology and enhanced dynamical update equations. With topology, suitable diversity whole can be maintained. At same time, rule significantly speeds up converge global optimum. five mathematical benchmark functions,...

Drivers' visual distraction serves as the main cause of traffic accidents, different ambient illuminance can also exert a considerable impact on drivers' cognition efficiency. It is therefore very important to study color visibility AR-HUD interface under illuminance. In this st

This paper proposes a new plant-inspired optimization algorithm for multilevel threshold image segmentation, namely, hybrid artificial root foraging optimizer (HARFO), which essentially mimics the iterative behaviors. In this growth operators of branching, regrowing, and shrinkage are initially designed to optimize continuous space search by combining root-to-root communication coevolution mechanism. With auxin-regulated scheme, various guided systematically. communication, individuals...

Abstract A novel multi‐input multi‐output adaptive control strategy applied to the combined active front steering (AFS) and direct yaw moment (DYC) system is proposed in this paper. Studies have been conducted show potential for electric vehicles be affected by time delay, which may appear states. Aiming address state radial basis function neural network (RBFNN) Lyapunov‐Krakovskii functional‐based AFS DYC controllers are constructed, also can process parameter uncertainties due powerful...

Background: With the trend of intelligent display, interface design in-vehicle HUD is an expanding research field; Methods: To solve subjectivity and uncertainty in optimization schemes, this paper proposed a hybrid scheme evaluation method based on entropy weight VIKOR. The was used to reduce decision-maker's weighting obtain objective each indicator; VIKOR best ranking alternative then optimal selected; Results: schemes were taken as example for verification calculation. results showed...

Aiming at the problem that frame difference method will deal with moving target incorrectly when moves slowly or stops for some times, a novel based on object detection is proposed. Firstly, algorithm confirms number of frames used to generate background by comparing binary current initial and establishes model using determined frame; Then subtraction utilized detect through established background. Relevant experiments show can better slow-moving targets.

With the help of powerful function mapping capability Multi-swarm Coevolution work, this paper presents a real-time data forecasting model which is suitable for atmospheric environmental monitoring by using correlation between temperature, humidity and humidity. The based on size coefficient to identify weights relative factors. functional relationship can be mapped more accurately. Then trends could predicted By comparing unimproved work algorithm, it proved that has high prediction...

This paper considers a case that Chinese healthcare organizations in China leverage mobile smart cloud platform (MSCP) to build self-sustaining ecosystem, which presents an evolutionary process of three phases. Multiple elements have been involved the system, has reinforced one another. Finally, ecosystem is formed, economically sustainable and scalable nationwide. The study adds understanding ecosystem-based approach address complex problems. It offers important implications for designing...

In recent years, the continuous development of in-vehicle information systems (IVIS) has greatly enriched driving experience, while also occupying driver's cognitive resources to varying degrees, causing distraction. Therefore, studying influence AR-HUD system on behaviour is great significance for manage complexity and enhance safety. This experiment applied five typical risky scenarios under two weather conditions (daytime night), as stimulus materials. The effects eye movement risk...

Micro projection systems not only can be applied in portable display technology, but also to adaptive automobile headlamps.Present DLP technology cannot collect and utilize the light which is reflected by micromirrors of DMD "OFF" state.Aiming at this defect, a design scheme micro system based on LEDs an innovative pipe presented.First, related parameters each part are calculated according nonimaging optics theory.Second, lens optimized using ZEMAX software.Finally, we build model simulate...

K-medoids clustering algorithm is used to classify data, but the approach sensitive initial selection of centers and divided cluster quality not high. Basic Artificial Fish Swarm Algorithm a new type heuristic swarm intelligence algorithm, optimization difficult get very high precision due randomness artificial fish behavior. A novel method based on improved global proposed in this paper by analyzing advantages disadvantages two algorithms, which has ability optimize effect. The result...

According to the deficiency of Chord algorithm supporting single keyword query only, a P2P framework-Z_mirror by combining Z_mirror and is proposed for managing service resources, which supports DHT-based multi-keyword approximate means index improve resources searching ability. Experiments show that Z_mirrorChord has better efficiency scalability under large scale environment with higher density services.