Above-ground biomass (AGB) and the leaf area index (LAI) are important indicators for assessment of crop growth, therefore agricultural management. Although improvements have been made in monitoring growth parameters using ground- satellite-based sensors, application these technologies is limited by imaging difficulties, complex data processing, low spatial resolution. Therefore, this study evaluated use hyperspectral indices, red-edge parameters, their combination to estimate map...

In this paper, the multiagent pursuit-evasion (MPE) games are solved in order to obtain optimal strategic policies for all players. these games, multiple pursuers attempt intercept evaders who try avoid capture. A graph-theoretic approach is employed study interactions of agents with limited sensing capabilities, such that distributed control obtained every agent. Furthermore, minimization performance indices associated goals guaranteed. Nash equilibrium among players by means use solutions...

Third-party libraries with rich functionalities facilitate the fast development of JavaScript software, leading to explosive growth NPM ecosystem. However, it also brings new security threats that vulnerabilities could be introduced through dependencies from third-party libraries. In particular, excessively amplified by transitive dependencies. Existing research only considers direct or reasoning based on reachability analysis, which neglects NPM-specific dependency resolution rules as...

The accurate and timely monitoring evaluation of the regional grain crop yield is more significant for formulating import export plans agricultural products, regulating markets adjusting planting structure. In this study, an improved Carnegie–Ames–Stanford approach (CASA) model was coupled with time-series satellite remote sensing images to estimate winter wheat yield. Firstly, in 2009 entire growing season two districts Tongzhou Shunyi Beijing divided into 54 stages at five-day intervals....

With the rapid development of unmanned aerial vehicle (UAV) and sensor technology, UAVs that can simultaneously carry different sensors have been increasingly used to monitor nitrogen status in crops due their flexibility adaptability. This study aimed explore how use image information combined from two mounted on an UAV evaluate leaf content (LNC) corn. Field experiments with corn were conducted using rates cultivars at National Precision Agriculture Research Demonstration Base China 2017....

Low-inertia dc microgrids often rely on storage devices to buffer energy and handle abrupt load changes. An alternative approach involves the concept of power buffers, electronics converters with bulky components that precede final point-of-load converters, decouple grid dynamics. Proper adjustment input impedances buffers helps shape trajectory transient imposed a microgrid. A communication network facilitates information exchange among active loads (loads augmented buffers). Such group...

Urban traffic management is highly complex, and inefficient control strategies often worsen congestion increase energy consumption. This paper introduces a collaborative multi-agent reinforcement learning method tailored for sparse scenarios, IKS-SAC (Improved Knowledge Sharing Soft Actor–Critic), which enhances coordination between signals to optimize flow. incorporates communication protocol knowledge sharing among agents, enabling each agent access utilize environment data collected by...

An algorithm is proposed which combines Zero-pole Model and Hough Transform(HT) to detect singular points. Orientation of points defined on basis can further explain the practicability Model. Contrary orientation field generation, detection simplified determine parameters HT uses rather global information fingerprint images This makes our more robust noise than methods only use local information. As may have a little warp from actual field, Poincare index used make position adjustment in...

This work investigates the model-following control problem associated with a class of non-linear systems in presence modelling uncertainties and actuator failures. The particular interest lies development designer-friendly cost-effective scheme. By combining model-reference mechanism robust adaptive radial basis function (RBF) neural network (NN), several algorithms are derived without need for precise system parameters or analytical-bound estimation on failure variables. It is shown that...

An adaptive iterative learning reliable control (AILRC) strategy is developed in this study for a class of non‐linearly parameterised systems subject to unknown time‐varying state delays and input saturation as well actuator faults. In regard uncertainties, not only the controlled object, but also distribution matrix investigated technical note. Without need precise system parameters or analytically estimating bound on faults variables, novel data‐driven AILRC constructed by non‐linear...

Objective: The aim of this study is to examine the effect traffic density on drivers' lane change and overtaking maneuvers. differences between left right changing/overtaking maneuvers were also investigated.Method: A driving simulator experiment was conducted 24 participants took part in experiment. Based simulation data, frequency, time duration, average speed, acceleration extracted as key variables maneuvers; initial distance headway, instantaneous before analyzed variables. One-way...

Data-driven intelligent transportation systems (D2ITSs) have drawn significant attention lately. This work investigates a novel multi-agent-based data-driven distributed adaptive cooperative control (MA-DD-DACC) method for multi-direction queuing strength balance with changeable cycle in urban traffic signal timing. Compared the conventional strategies, proposed MA-DD-DACC combined an online parameter learning law can be applied manner by merely utilizing collected I/O queueing length data...

This study aims to efficiently estimate the crop water content of winter wheat using high spatial and temporal resolution satellite-based imagery. Synthetic-aperture radar (SAR) data collected by Sentinel-1 satellite optical imagery from Sentinel-2 was used create inversion models for content, respectively. In approach, several enhanced indices were constructed backscatter coefficient imagery, selected one that most sensitive soil as input parameter a cloud model. Finally, model established....

The planting year of apple orchard not only determines the fruit output but also provides information for governmental management industry. However, considering that different orchards use and cultivation methods, this may result in some trees having similar outlines years, it is, therefore, difficult to effectively determine actual based on textural or structural characteristics. Therefore, monitoring method provided paper is monitor growing positively from seedlings time series remote...

This study investigates the speed trajectory tracking problem of high-speed trains with actuator failures and unknown delays as well control input saturations. New adaptive iterative learning fault-tolerant (AILFTC) strategy is derived without need for precise system parameters or analytically estimating bound on variables. It shown that proposed method, both can be accommodated time-varying saturations analysed by means Lyapunov–Krasovskii function. As such, resultant algorithms are able to...

Vulnerabilities from third-party libraries (TPLs) have been unveiled to threaten the Maven ecosystem in long term. Despite patches being released promptly after vulnerabilities are disclosed, and applications community still use vulnerable versions, which makes persistent (e.g., notorious Log4Shell greatly influences nowadays 2021). Both academic industrial researchers proposed user-oriented standards solutions address vulnerabilities, while such fail tackle ecosystem-wide because it...

Dermoscopy is a common method of scalp psoriasis diagnosis, and several artificial intelligence techniques have been used to assist dermoscopy in the diagnosis nail fungus disease, most commonly being convolutional neural network algorithm; however, networks are only basic algorithm, use object detection algorithms has not reported.

Speaker recognition (SR) is widely used in our daily life as a biometric authentication or identification mechanism. The popularity of SR brings serious security concerns, demonstrated by recent adversarial attacks. However, the impacts such threats practical black-box setting are still open, since current attacks consider white-box only. In this paper, we conduct first comprehensive and systematic study on systems (SRSs) to understand their weakness blackbox setting. For purpose, propose an...

In this paper, we focus on parameter optimization for model-free adaptive control, which is currently lacking. Therefore, a novel data-driven control method based Reinforcement Learning (RL-MFAC) proposed class of dis-crete-time single-input and single-output nonlinear systems. RL-MFAC, dynamic linearization adopted, the concept pseudo-partial derivative (PPD) introduced to design controller. Moreover, reward punishment mechanism (RL) was used optimize parameters MFAC in controller design,...