Search

Combining the travel modes of human activities, fully mining multi-source data, and analyzing the relationship between the urban ecological environment and human activities are important topics in urban ecological environment planning. Human activity indicators were constructed based on the data of POI points, OSM road network, and residential areas. Machine learning models such as support vector regression machine, extreme gradient boosting regression, polynomial regression, and random forest regression were combined with remote sensing images to construct an urban ecological environment indicator system. These models were used to conduct regression analysis of urban ecological environment indicators and human activity indicators in Chengdu, China. The research shows that the three indicators of human activities all show a trend of increasing in the center and gradually decreasing in the surrounding areas, while the sustainable urban ecological environment indicators show the opposite trend. On the relationship between urban ecological environment and human activities, XGB has the best effect; the correlation between the street vitality index and the urban function mixing index and the sustainable urban ecological environment is stronger, and the correlation between the walkability measure index of the residential area and the sustainable urban ecological environment is even worse.

The goal of this work is to improve the generalization of remaining useful life (RUL) prognostics for wheel hub bearings. The traditional life prognostics methods assume that the data used in RUL prognostics is composed of one specific fatigue damage type, the data used in RUL prognostics is accurate, and the RUL prognostics are conducted in the short term. Due to which, a generalizing RUL prognostics method is designed based on fault signal data. Firstly, the fault signal model is designed with the signal in a complex and mutative environment. Then, the generalizing RUL prognostics method is designed based on the fault signal model. Lastly, the simplified solution of the generalizing RUL prognostics method is deduced. The experimental results show that the proposed method gained good accuracies for RUL prognostics for all the amplitude, energy, and kurtosis features with fatigue damage types. The proposed method can process inaccurate fault signals with different kinds of noise in the actual working environment, and it can be conducted in the long term. Therefore, the RUL prognostics method has a good generalization.

The robot dynamic model is often rarely known due to various uncertainties such as parametric uncertainties or modeling errors existing in complex environments. It is a key problem to find the relationship between the changes of neural network structure and the changes of input and output environments and their mutual influences. Firstly, this paper defined the conceptions of neural network solution, neural network eigen solution, neural network complete solution, and neural network partial solution and the conceptions of input environments, output environments, and macrostructure of neural networks. Secondly, an eigen solution theory of general neural networks was proposed and proven including consistent approximation theorem, eigen solution existence theorem, consistency theorem of complete solution, the partial solution, and none solution theorem of neural networks. Lastly, to verify the eigen solution theory of neural networks, the proposed theory was applied to a novel prediction and analysis model of controller parameters of grinding robot in complex environments with deep neural networks and then build prediction model with deep learning neural networks for controller parameters of grinding robot. The morphological subfeature graph with multimoment was constructed to describe the block surface morphology using rugosity, standard deviation, skewness, and kurtosis. The results of theoretical analysis and experimental test show that the output traits have an optional effect with joint action. When the input features functioning in prediction increase, higher predicted accuracy can be obtained. And when the output traits involving in prediction increase, more output traits can be predicted. The proposed prediction and analysis model with deep neural networks can be used to find and predict the inherent laws of the data. Compared with the traditional prediction model, the proposed model can predict output features simultaneously and is more stable.

An M-estimator-based online sequential extreme learning machine (M-OSELM) is proposed to predict chaotic time series with outliers. The M-OSELM develops from the online sequential extreme learning machine (OSELM) algorithm and retains the same excellent sequential learning ability as OSELM, but replaces the conventional least-squares cost function with a robust M-estimator-based cost function to enhance the robustness of the model to outliers. By minimizing the M-estimator-based cost function, the possible outliers are prevented from entering the model’s output weights updating scheme. Meanwhile, in the sequential learning process of M-OSELM, a sequential parameter estimation approach based on error sliding window is introduced to estimate the threshold value of the M-estimator function for online outlier detection. Thanks to the built-in median operation and sliding window strategy, this approach is efficient to provide a stable estimator continuously without high computational costs, and then the potential outliers can be effectively detected. Simulation results show that the proposed M-OSELM has an excellent immunity to outliers and can always achieve better performance than its counterparts for prediction of chaotic time series when the training dataset contains outliers, ensuring at the same time all benefits of an online sequential approach.

Many real world applications are of time-varying nature and an online learning algorithm is preferred in tracking the real-time changes of the time-varying system. Online sequential extreme learning machine (OSELM) is an excellent online learning algorithm, and some improved OSELM algorithms incorporating forgetting mechanism have been developed to model and predict the time-varying system. But the existing algorithms suffer from a potential risk of instability due to the intrinsic ill-posed problem; besides, the adaptive tracking ability of these algorithms for complex time-varying system is still very weak. In order to overcome the above two problems, this paper proposes a novel OSELM algorithm with generalized regularization and adaptive forgetting factor (AFGR-OSELM). In the AFGR-OSELM, a new generalized regularization approach is employed to replace the traditional exponential forgetting regularization to make the algorithm have a constant regularization effect; consequently the potential ill-posed problem of the algorithm can be completely avoided and a persistent stability can be guaranteed. Moreover, the AFGR-OSELM adopts an adaptive scheme to adjust the forgetting factor dynamically and automatically in the online learning process so as to better track the dynamic changes of the time-varying system and reduce the adverse effects of the outdated data in time; thus it tends to provide desirable prediction results in time-varying environment. Detailed performance comparisons of AFGR-OSELM with other representative algorithms are carried out using artificial and real world data sets. The experimental results show that the proposed AFGR-OSELM has higher prediction accuracy with better stability than its counterparts for predicting time-varying system.

Valid wake sensors.Balance parameters.Distributed algorithm.Actual experiment. In order to improve energy-effectiveness in wireless sensor network, in practice some sensors in observation points are selected not to gather data. In this case, the insufficient data gathered by the rest of sensors have to cover the total network so that the complete information of the whole environment could be estimated rationally, which is similar to compressive sensing. However, the process of estimation has to cost a lot of energy, which is a crucial problem. This paper proposes a practical and effective information coverage approach in which an actual constrained condition is considered for consensus estimation to reduce unnecessary energy cost reasonably. In our experiments, the method has been proved valuable and feasible.

Uninorms are important generalizations of triangular norms and conorms, with the neutral elements lying anywhere in the unit interval, left (right) semi-uninorms are non-commutative and non-associative extensions of uninorms, and coimplications are extensions of the Boolean coimplication. In this paper, we study the relationships between left (right) semi-uninorms and coimplications on a complete lattice. We first discuss the residual coimplicators of left and right semi-uninorms and show that the right (left) residual coimplicator of a disjunctive right (left) infinitely ∧-distributive left (right) semi-uninorm is a right infinitely ∨-distributive coimplication which satisfies the neutrality principle. Then, we investigate the left and right semi-uninorms induced by a coimplication and demonstrate that the operations induced by right infinitely ∨-distributive coimplications, which satisfy the order property or neutrality principle, are left (right) infinitely ∧-distributive left (right) semi-uninorms or ...

In this article, a partial synchronization scheme is proposed based on Lyapunov stability theory to track the signal of the delay hyperchaotic Lu system using the Coullet system based on only one single controller. The proposed tracking control design has two advantages: only one controller is adopted in our approach and it can allow us to drive the hyperchaotic system to a simple chaotic system even with uncertain parameters. Numerical simulation results are given to demonstrate the effectiveness and robustness of the proposed partial synchronization scheme. © 2014 Wiley Periodicals, Inc. Complexity, 2014

Human motion detection based on CSI (Channel State Information) is a hot research topic. Many researchers started to focus on it. In this paper, we employ the CSI to detect fall behavior. Firstly, a data weighting operation to smooth the noise will be implemented. Secondly, we extract behaviors data by effect size. Thirdly, several features will be extracted to represent the original data. Finally, we use neural network to distinguish fall behaviors between several behaviors. Experimental results show a better accuracy of our algorithm.

Human motion detection based on CSI (Channel State Information) is a hot research topic. Many researchers started to focus on it. By extracting amplitude and phase of CSI, it can be applied to detect human motions. In this paper, we employ the phase to detect intrusion. Firstly, we use a liner transformation to eliminate the shift of phases of different subcarriers. Subsequently, we defined two reference points for the short-term case(SES) and the long-term case(LES). The former is used to detect if someone is walking in indoor room and the latter is to detect whether the person is walking continuously. We implemented our approaches with the normal WiFi equipment and evaluated the performances of our algorithm in real environment. Experimental results show a high accuracy of our algorithm.

Compressive Sampling(CS) has been currently utilized to save transmission consumption of sensors. In spite of the remarkable efforts the community put to a variety of designs, a vital question still remains unclear that whether the execution costs of sensors employing CS is not worth being considered, motivating us to explore the answer from a point of real deployment platform view. Presenting observations from our operating sensor network with 124 nodes deployed in the forest, we verify two important facts for energy consumption: 1) Different from previous literature, the cost of measure processing is not trivial. As the number of measurements increasing, it is a considerable percentage contrasted to transmission cost. 2) The value of measurement constantly changes along the routing, which may cause a cost jump in a specific location. Based on our findings from the system measurements, we propose an energy-efficient transmission approach based on CS. With our experiments, energy will be economized at least 15%. Our work gives a potential guideline for future designs in the field of the prolongation of lifetime of WSN.

Geographic routing is appropriate for sensor networks because of their special characteristics, such as Wireless Local Area Networks. However, the existing holes in the practical networks may probably impact the performance of geographic routing. In this paper, we employ hyperbolic Ricci flow to compute a new embedding of sensor nodes, which could achieve the conformal map of the topology of the network to virtual coordinates in hyperbolic space even if its topology contains multiple holes, and is easy to establish the corresponding routing. In actual experiments and simulations, our method has been proved valuable and feasible.

Synchronization of bursting neuron system with stochastic noise is investigated. When parameters are known, based on Lyapunov stability theory, via appropriate controllers, synchronization of delay Hindmarsh–Rose system with stochastic noise is obtained. When parameters are unknown, by adaptive control technique, corresponding parameter update laws are proposed to achieve synchronization of Hindmarsh–Rose system with stochastic noise. Finally, numerical simulations are given to demonstrate the effectiveness of the proposed schemes.

In this paper, pinning synchronization of unilateral coupling time delay neuron network with stochastic noise is investigated. Based on Lyapunov stability theory, by designing appropriate controller and particular Lyapunov function, pinning synchronization of unilateral coupling Hindmarsh–Rose network with stochastic noise is obtained. This method needs only one single controller. Simulation results are given to verify the effectiveness of the proposed scheme. From the simulations, the relation between the time needed to achieve pinning synchronization of unilateral coupling neuron network with stochastic noise and the number of nodes, the noise intensity, the coupling intensity is illustrated.

Geographic Routing is suitable for the limited resource in wireless sensor networks and Ricci flow-based methods have been employed. Unfortunately, iterative process through previous methods may spend abundant energy in order to discovery route, which obviously effect their advantageous of this sort of schemes. In this paper, we focus on avoiding unnecessary iterations and propose an algorithm through optimizing in hyperbolic domain. We choose a set of suitable candidate nodes to decrease superfluous costs and testify in our network system. Experiments demonstrate that our schemes are superior to the existing approaches.

In this paper, we lay bare some new formulas for calculating the upper and lower approximation left (right) semi-uninorms of a binary operation and further discuss the relations between the upper and lower approximation left (right) semi-uninorms of a given binary operation and the lower and upper approximation left (right) semi-uninorms of its dual operation, respectively.

Compressive Sampling(CS) has been utilized to save transmission consumption of sensors. In spite of the remarkable efforts the community put to a variety of designs, a everlasting issue still remains that how sensors further economize energy through referring to their CS-based execution operations, motivating us to explore the answer from a point of real deployment platform view. In our work, we propose an adaptable CS-based transmission scheme, ACS, which is not mutually exclusive but forms a complementary unity with the traditional scheme. According to experimental validations on our real-world operating sensor network, energy of sensors will be economized at least 15% compared to the existing methods.

Geographic routing can provide efficient routing at a fixed overhead. However, the performance of geographic routing is impacted by physical voids, and localization errors. Accordingly, virtual coordinate systems (VCS) were proposed as an alternative approach that is resilient to localization errors and that naturally routes around physical voids. However, since VCS faces virtual anomalies,existing geographic routing can’t work to banlance energy efficiently. Moreover, there are no effective complementary routing algorithm that can be used to address energy balance.In this paper we present An Energy Balanced virtual coordinate Routing in Wireless Sensor Networks(EBVCR),which combines both distance- and direction-based strategies in a flexible manner, is Proposed to resolve energy balance of Geographic routing in VCS .Our simulation results show that the proposed algorithm outperforms the best existing solution, over a variety of network densities and scenarios.

In this paper, we further investigate the constructions of fuzzy connectives on a complete lattice. We firstly illustrate the concepts of strict left (right)-conjunctive left (right) semi-uninorms by means of some examples. Then we give out the formulas for calculating the upper and lower approximation strict left (right)-conjunctive left (right) semi-uninorms of a binary operation.