Congestion in wireless sensor networks not only causes packet loss, but also leads to excessive energy consumption. Therefore congestion WSNs needs be controlled order prolong system lifetime. In addition, this is necessary improve fairness and provide better quality of service (QoS), which required by multimedia applications networks. paper, we propose a novel upstream control protocol for WSNs, called priority-based (PCCP). Unlike existing work, PCCP innovatively measures degree as the...

Unplanned urban settlements exist worldwide. The geospatial information of these areas is critical for management and reconstruction planning but usually unavailable. Automatically characterizing individual buildings in the unplanned village using remote sensing imagery very challenging due to complex landscapes high-density settlements. newly emerging deep learning method provides potential characterize a village. This study proposed an mapping paradigm based on U-net architecture. area...

Mercury is one of the five most toxic heavy metals to human body. In order select a high-precision method for predicting mercury content in soil using hyperspectral techniques, 75 samples were collected Guangdong Province obtain by chemical analysis and data based on an indoor experiment. A multiple linear regression (MLR), back-propagation neural network (BPNN), genetic algorithm optimization BPNN (GA-BPNN) used establish relationship between predict content. addition, feasibility modeling...

This article aims to solve the Moore-Penrose inverse of time-varying full-rank matrices in presence various noises real time. For this purpose, two varying-parameter zeroing neural networks (VPZNNs) are proposed. Specifically, VPZNN-R and VPZNN-L models, which based on a new design formula, designed right left inversion problems matrices, respectively. The VPZNN models activated by novel nonlinear activation functions. Detailed theoretical derivations presented show desired finite-time...

Missing values are common in cyber-physical systems (CPS) for a variety of reasons, such as sensor faults, communication malfunctions, environmental interferences, and human errors. An accurate missing value imputation is crucial to promote the data quality mining statistical analysis tasks. Unfortunately, most existing methods take use whole set impute value, which could have unfavorable influences impacts (low accuracy or high complexity) on imputed results caused by irrelevant records....

Soil heavy metals affect human life and the environment, thus, it is very necessary to monitor their contents. Substantial research has been conducted estimate map soil in large areas using hyperspectral data machine learning methods (such as neural network), however, lower estimation accuracy often obtained. In order improve accuracy, this study, a back propagation network (BPNN) was combined with particle swarm optimization (PSO), which led an integrated PSO-BPNN method used contents of...

Rapid and accurate agricultural land evaluation provides essential guidance for the supervision allocation of resources; it also helps to ensure food security. Previous work has mainly evaluated quality at county level by using field sampling data based on a factor approach. However, is difficult achieve uniform, large-scale via conventional approaches because its spatial heterogeneity, as well large temporal economic costs associated with acquisition. In this study, we integrated publicly...

In wireless sensor networks (WSNs), congestion occurs, for example, when nodes are densely distributed, and/or the application produces high flow rate near sink due to convergent nature of upstream traffic. Congestion may cause packet loss, which in turn lowers throughput and wastes energy. Therefore WSNs needs be controlled energy-efficiency, prolong system lifetime, improve fairness, quality service (QoS) terms (or link utilization) loss ratio along with delay. This paper proposes a node...

Developing countries have been undergoing dramatic urban growth over the past three decades. It is essential to understand and simulate process for smart planning sustainable development purposes. Cellular automata (CA) modeling an efficient approach simulating land use/cover change; however, traditional CA method has limitations in various patterns processes. This study aims analyze influences of different characteristics on effectiveness by conducting a case area Pearl River Delta Southern...

As a typical representative of the recurrent neural network (RNN), Zhang (ZNN) has been proved as powerful parallel-processing solver for time-varying matrix problems. Recent studies have shown that, in absence noise, ZNN model activated by combined activation function (CAF), which is linear combination sign-bi-power (SBP) and functions (termed CAF-ZNN), can achieve much better finite-time convergence compared with other models pseudoinversion. This paper investigates first time influence...

This study addresses the problem of inverse hysteretic compensation for a class uncertain dynamic non-linear systems preceded by unknown non-linearities, where hysteresis is described Prandtl–Ishlinskii (P–I) model. First, continuous P–I model decomposed into discrete operator and small-bounded error. Then, constructed to eliminate effects, bounded error estimated controller. To avoid possible chattering caused sign function, smooth robust adaptive controller with hyperbolic tangent function...

Research in time-series remote sensing data is receiving increasing attention. With the availability of relatively short repeat cycle and high spatial resolution satellite data, construction application spatiotemporal promising. In this paper, we proposed a method to construct complete time series with Savitzky-Golay filter for smoothing locally-adaptive linear interpolation generating daily NDVI imagery. An IDL-based program was developed achieve goal. The China's HJ-1 A/B were employed...

For a class of linear discrete-time uncertain systems, feedback feed-forward iterative learning control (ILC) scheme is proposed, which comprised an controller and two current iteration controllers. The used to improve the performance along direction controllers are time direction. First all, ILC system presented by two-dimensional Roesser model system. Then, robust schemes proposed. One can ensure that bounded-input bounded-output stable direction, other asymptotically Both guarantee...

This paper focuses on an operation optimisation problem for a class of multi-head surface mounting machines in printed circuit board assembly lines. The involves five interrelated sub-problems: assigning nozzle types as well components to heads, feeders slots and determining component pickup placement sequences. According the depth making decisions, sub-problems are first classified into two layers. Based classification, two-stage mixed-integer linear programming (MILP) is developed describe...

Containers underwent a whirlwind adoption across cloud providers recently, as the Open Container Initiative works toward standardizing container format and configuration. The could become infrastructure's "narrow waist," bridging proliferation of existing emerging services.

Clustering is a fundamental and important technique under many circumstances including data mining, pattern recognition, image processing other industrial applications. During the past decades, clustering algorithms have been developed, such as DBSCAN, AP CFS. As latest algorithm proposed in Science magazine 2014, by fast search find of density peaks, named CFS, simple outstanding for its promising performance on sets arbitrary shape. However, CFS's usually affected cutoff distance dc,...

Industrial process monitoring is a significant task and has started to get better solved by deep learning. However, ensuring that the learned features from data are effective interpretable for remains challenge. In this article, slow feature analysis-aided autoencoder (SFA-AE) proposed monitoring. The SFA-AE, which combines advantages of SFA an (AE), enables learning variation patterns high-level extracted AE. Particularly, AE additionally incorporates in convolutional long short-term...