Accurate landslide displacement prediction is a key component of IoT-enabled landslide monitoring and warning support frameworks, supporting risk-informed warning analysis and risk-informed decision-making. However, precise forecasting remains challenging due to the non-stationary characteristics of displacement data and the complex spatiotemporal correlations among monitoring points. To this end, this article proposes a novel attention-guided spatiotemporal fusion framework, named VMAG (Variational Mode Decomposition and Multi-head Attention-based GRU), for accurate multi-step landslide displacement prediction. Specifically, a differential fluctuation sequence is first constructed using Ground-Based Synthetic Aperture Radar (GB-SAR) displacement observations to enhance the perceptibility of displacement mutations. Then, based on the inherent characteristics of the time series, the Variational Mode Decomposition (VMD) algorithm is applied to decompose the sequence into multi-scale components to mitigate non-stationarity. Subsequently, a multi-head attention mechanism is employed to dynamically extract spatial dependencies between the target node and reference monitoring nodes, which are then fed into a Gated Recurrent Unit (GRU) network to capture temporal evolutions. Experimental results on datasets from the Moshi Gully (MSG) landslide demonstrate that the proposed VMAG significantly outperforms mainstream benchmarks. For instance, the Root Mean Square Error (RMSE) is reduced to 1.6960 mm, and the Mean Absolute Percentage Error (MAPE) achieves 0.63%, showing superior accuracy compared to ANN, LSTM, and standard GRU models.

2D-3D cross modal retrieval (CMR) aims to retrieve query image matching points from a 3D reference map. Existing classical CMR datasets and methods commonly support database-based retrieval only, i.e., the point cloud retrieval results are fixed-scale geometric surfaces. The failure to consider geometric regions and information scales fundamentally limits the practical deployment of CMR in engineering systems that require dynamic spatial reasoning, such as autonomous navigation or three-dimensional industrial measurement. In this article, we introduce a new benchmark called cross modal regional retrieval, which extends the classic CMR to allow the free retrieval of associated regions within the point cloud from images. Toward this, a multiview training paradigm is proposed in the training phase, which enables the model to identify occluded points in the region based on a single view. Autoencoders are utilized to learn the mapping of fusion features from a single view to multiple views. We also convert the image retrieval task within the scene cloud into a point classification task in the image to implement global free retrieval. The information fusion and guidance provided by the global point cloud enhances the capability of image cross-modal retrieval. To match the input patterns of the model, we propose a method for constructing datasets from three benchmark sources. Extensive experiments demonstrate that our method achieves state-of-the-art performance compared to existing methods for 2D-3D cross modal regional retrieval.

Detecting insulators and their defects is a key task in real-time power grid surveillance with the rapid development of national smart grid. Traditional surveillance usually relies on maintenance personnel, leading to the issues of inefficiency and unsafety. Thus, with the prosperity of deep learning, we proposed a detection algorithm, named E-VarifocalNet, which is an enhanced version of the basic VarifocalNet method. The proposed E-VarifocalNet is specifically designed for detecting insulators and their defects. We developed a classification loss based on varifocal loss and the number of samples to solve the imbalance problem in object detection. Furthermore, a regression loss based on GIoU loss and Wasserstein distance is designed to gain higher flexibility in the representation of bounding boxes. Additionally, we applied a feature pyramid network based on dilated convolution and heatmap to build global and local semantic relations among pixels so as to enhance the detection accuracy on salient areas. Our dataset containing 2,100 images and 5,217 object instances was collected through real-time drones and an open data platform. Our E-VarifocalNet gets the highest mAP and a low model complexity on our dataset among state-of the-art object detectors, indicating the potential of our algorithm in real-time power grid surveillance applications.

Building energy prediction plays critical roles in the study of green building and smart city. The most challenging issue is to predict energy demand profiles over multiple time steps, which may have inconsistent timescales. Due to complex temporal dependence, existing prediction approaches cannot satisfy certain requirements in multistep (MS) or multitimescale (MTS) applications. In this article, a deep-chain echo state network (DCESN) is proposed to enhance the mapping capability for the MS demand prediction. The DCESN composed of many submodules of echo state network (ESN) belongs to the single-input multi-output (SIMO) model, and neuron states generated by sequential steps are utilized to prevent accumulative error in the recursive chain. Due to the novel learning mechanism of DCESN, numerical coefficients of temporal dependence are presented to explain the short-term and long-term impacts on future energy consumption. Experimental results in four cases indicate that the proposed DCESN has promising performance on MS and MTS prediction, and temporal dependence can be explained in a visible way. Comparative results of DCESN, sliding-window ESN, and long-short term memory (LSTM) demonstrate that the proposed learning mechanism could prevent error accumulation effectively.

Sharing transportation systems can significantly promote travelers convenience and efficiency. As a vital part, bike-sharing system (BSS) has effectively solved “the-last-mile” problem during transportation interchange, but bike imbalance between docks severely deteriorates operational efficiency of BSS. In this paper, we present multi-objective optimization and predictive control approaches to tackle the bike rebalancing problem, where optimal redistributing strategies can maximize the operational efficiency of BSS with respects to equilibrium state and redistribution cost. A dock-based BSS dynamic network is modeled based on a proximity graph, in which connection relation, bike usage, and redistribution flow are formulated. To measure the operational efficiency, a performance metric is presented to consider both benefits of user and operator. To satisfy bike renting, returning, and redistributing requirements, model predictive control (MPC) is then employed to compute feasible and optimal redistribution strategies based on the network model. The effectiveness of multi-objective optimization and MPC is verified on different topologies of BSS. Experimental results show that when the BSS reaches the equilibrium state, the operational efficiency will be maximized in the proposed approaches.

In this article, a chain-structure echo state network (CESN) with stacked subnetwork modules is newly proposed as a new kind of deep recurrent neural network for multivariate time series prediction. Motivated by the philosophy of "divide and conquer," the related input vectors are first divided into clusters, and the final output results of CESN are then integrated by successively learning the predicted values of each clustered variable. Network structure, mathematical model, training mechanism, and stability analysis are, respectively, studied for the proposed CESN. In the training stage, least-squares regression is first used to pretrain the output weights in a module-by-module way, and stochastic local search (SLS) is developed to fine-tune network weights toward global optima. The loss function of CESN can be effectively reduced by SLS. To avoid overfitting, the optimization process is stopped when the validation error starts to increase. Finally, SLS-CESN is evaluated in chaos prediction benchmarks and real applications. Four different examples are given to verify the effectiveness and robustness of CESN and SLS-CESN.

Solar irradiance forecast is closely related with efficiency and reliability of renewable energy systems. Multi-timescale irradiance forecast is a new and efficient way to simultaneously predict solar energy generation on different timescales for hierarchical decision making. This article newly adopts the multi-task learning mechanism to study the multi-timescale forecast for improving accuracy and computational efficiency. A novel multi-timescale (MTS) prediction framework is presented to fulfill the multi-task application, and echo state network (ESN) is studied in the proposed MTS framework. The multi-timescale ESN (MTS-ESN) is proposed to enhance the information sharing among correlated tasks. Simulation results of hourly solar data demonstrate that the proposed MTS-ESN could achieve promising performance at both hourly and daily level in parallel. The MTS-ESN outperforms the single-timescale ESN (STS-ESN), which indicates the information sharing in the multi-task learning is effective in this application.

Ahstract— With the rapid development of vehicular applications and mobile devices, demands for resources to process time-critical and computation-intensive tasks are increasingly prominent. In this paper, we propose a two-layer Vehicular Fog Computing (VFC) architecture, including the client layer and the fog layer. Vehicles may generate tasks as clients, which are further assigned to the nodes in the fog layer for processing. The fog layer aggregates available resources of vehicles and infrastructures by exploiting their communication, computation and storage capabilities. Each task requires certain amount of resources for processing at the fog nodes. We formulate a distributed task allocation (DTA) problem, which takes deadline, vehicle mobility and fog capacity into consideration, and aims at maximizing the overall resource utilization of system, via the cooperation of vehicles and fog nodes. We linearize DTA into a 0–1 integer linear programming (ILP) problem to obtain the optimal solution. Further, we design a heuristic algorithm to obtain near-optimal performance with low computational overhead, which decomposes DTA into two subprocess and schedules tasks in each fog node independently. Finally, we build the simulation model and conduct a series of experiments based on real-world vehicle trajectories, which demonstrate the effectiveness and scalability of the proposed algorithm.

Solving dynamic multi-objective optimization problem (DMOP) requires optimizing multiple conflicting objectives simultaneously. When a dynamic is detected in the changing environment, most of existing prediction-based strategies predict the trajectory of changing Pareto-optimal solutions (POS), based on the historical solutions obtained in the solution space. In this paper, we present a new prediction method to track the moving optima for solving DMOP. In contrast to existing approaches, we propose to build the prediction model in the objective space. As the evaluation for solving a DMOP is based on the Pareto-optimal front (POF), to predict directly in the objective space could provide more useful information than the prediction in the solution space. In particular, to efficiently capture the complex relationships among POFs found along the evolutionary search, here we build a prediction model in Reproducing Kernel Hilbert Space, which holds a closed-form solution. To evaluate the performance of the proposed method, empirical studies have been conducted by comparing against three state-of-the-art prediction-based strategies on fourteen commonly used DMOP benchmarks. The results obtained by using different optimization solvers confirmed the superiority of the proposed method for solving DMOP in terms of both solution quality and time efficiency.

The popularity of the Internet has brought profound influence to electronic commerce. A kind of review-oriented consumption mode is gradually expanding in the market and consumers will refer to the reviews provided by consumers who bought the product in the past. How to accurately analyze users' sentiments from massive data of e-commerce reviews has become one of the key issues for e-commerce platforms. Current standard sentiment analysis classifies overall sentiment of e-commerce reviews without an extended description of the entity. We set up an optimized Aspect-based sentiment analysis (ABSA) that includes four elements: aspect, category, polarity, and opinion. Aiming at the above problems, this paper proposes a Chinese e-commerce reviews sentiment analysis algorithm based on BERT. By using pre-training model, we use the BIO(B-begin,I-inside,O-outside) data labeling pattern to label entities and study sentiment analysis by the annotation data. Experimental results on the Taobao cosmetics review datasets show that compared with the ordinary deep learning methods, our approach in the accuracy rate and the F1 score has significant improvement.

Recent studies on three-dimensional(3D) point cloud data (PCD) simplification have played significant roles in computer-aided models for alleviating computational and storage burden. However, existing simplification methods are not suitable for the large-scale PCD with even billions of points. In this paper, a decomposed simplification method based on graph filter is developed to extract Haar-like feature of PCD. The new method is based on divide-and-conquer philosophy and thus effectively reduce the memory usage. In the proposed approach, point cloud is divided into several subsets according to the relationship of natural neighbor, and decomposed graph filtering with adaptive resampling rate is designed. Validation experiment is conducted on large scale PCD, which could indicate the effectiveness and feasibility of the proposed approach.

Most existing models of energy efficiency retrofit are able to evaluate energy saving and retrofit cost for a certain stakeholder, but unable to guide how to allocate retrofit task and incentive among multiple stakeholders. The multistakeholder situation is firstly modeled in the proposed crowdsourcing model (CM), which contributes to quantify the utility of each competitive stakeholder with respect to participation decision. To solve the CM, a Stackelberg game approach is newly developed in this article to find rational and efficient strategies of task/incentive allocation. For the building energy efficiency retrofit, the challenge of CM is to handle mixed-integer decisions of energy service companies. We prove the existence of Stackelberg equilibrium (SE), which introduces the optimal budget, and the Nash equilibrium of task allocation. To compute the SE of CM, effective search algorithms are designed based on best response and optimization techniques. Simulation results have verified the CM and game theoretical approach. The resulted SE has provided stable and efficient strategies of incentive/task allocation.

The Fusion Architecture for Learning, COgnition, and Navigation (FALCON) is an extension of the self-organizing neural network i.e., Adaptive Resonance Theory (ART), which has been successfully applied in many reinforcement learning tasks, and demonstrated fast and stable real-time learning capabilities. However, the learning of reinforcement FALCON relies on the positive feedbacks obtained from the environment, which may not be always available in many real-world applications. Although TD-FALCON has been proposed in the literature, to integrate the temporal difference method to estimate the payoff value when immediate reward is not available, the accuracy of the estimation also relies on the received feedback from environment. In complex environments with much delayed evaluation, the reinforcement FALCON may be hard to learn the proper knowledge to adapt in the given task quickly. To the best of our knowledge, there is no existing work has been conducted to improve the reinforcement FALCON learning in such environment. Taking this cue, inspired from the science of memetics, in this paper, we propose to improve the reinforcement FALCON learning in complex environment where positive reward is hard to achieve, via memetic automaton. In particular, by defining the particular representation of memes in the context of FALCON, the corresponding designs of meme selection and meme transmission for meme evolution are presented, to transfer the knowledge meme from well-learned agents in simple environment to improve the learning performance of FALCON agents in complex environment. Lastly, simulations of FALCON based multi-agent system using the mine navigation task platform, confirmed the efficacy of the proposed memetic model.

To solve economic load dispatch problems, this paper designs a combination of artificial bee colony (ABC) and covariance matrix adaptation evolution strategy (CMA-ES). In this method, multiple variables are updated at the employed bee stage. The onlooker bee stage of the ABC method is replaced by the CMA-ES method. To begin with a good position, the CMA-ES method is initialized based on the state of employed bees of the ABC method. The proposed method is used to solve economic load dispatch problem with different sizes, and compared with three other methods. Simulation results show that the method attains better performance by combining ABC and CMA-ES. Moreover, the sensitivity of parameter settings is also discussed, and a default setting is obtained for such problems.

With the ever-increasing demand of location-based services (LBS), Wi-Fi based indoor localization has attracted increasing attentions. This paper is dedicated to addressing two critical problems: a) signal fluctuation due to unforeseeable interferences during the offline training phase; b) insufficient real-time signal measurements at certain point due to the target movement during the online localization phase. Specifically, we first give an intensive analysis on the characteristics of received signal strength indicator (RSSI) in indoor environments with respect to both time-domain and frequency-domain. Then, inspired from the advantages of Stacked Denosing Autoencoder (SDA) in terms of recognizing and stabilizing the original features, we propose a dual-band SDA (DBSDA) based model to create more distinguishable fingerprints by extracting the RSSI features at each reference point (RP). In this model, both 2.4GHz and 5GHz RSSIs are exploited to train the SDA neural network and construct the offline fingerprint database. On this basis, we propose a data generation scheme, which is designed based on the observation that environmental interferences are similar in proximate spots. So, the designed scheme can generate signal values at certain point based on its nearby RSSI measurements when there are not enough inputs for the SDA neural network. Finally, we propose a locally weighted liner regression (LWLR) based method to predict the coordinate of the target. For performance evaluation, we implement the system prototype and give comprehensive experiments in real-world environments, which demonstrate the effectiveness and robustness of the proposed solutions.

Design and construction of reinforced concrete (RC) structures are two important phases in a building construction project. Structural engineers are difficult to reject all rebar clashes in RC beam-column joints at the design phase. Construction engineers and steel fixers have to identify rebar spatial clashes and avoid rebar clashes in a manual way, which is tedious and time consuming. In this paper, an intelligent design method is urgent with the ability to avoid rebar clashes automatically. A novel artificial potential field (APF) approach is presented for the clash free layout of rebar in RC beam-column joints. Using the APF method, the layout of rebar can be regarded as the path planning of multi-agents. APF is used to generate the coordinate of the centerline of clash free rebars in a RC beam-column joint. Repulsive and attractive force can ensure a reachable and optimal solution. The simulation results showed that the proposed method is efficiency and accurate.

Memetic algorithms (MAs) refer to hybrid methods of global search and local search, which aims to systematically balance exploitation and exploration for solving an optimization problem. This paper attempts to create a sawtooth growing exploitation framework for MAs. Under the framework, a sawtooth-wave function is used to control ratios of global search and local search, and thus the exploitation is restricted to sawtooth growing patterns. An MA instance is implemented by combining modified differential evolution and neighborhood field algorithms, named as MDE-NF. Compared with several state-of-the-art algorithms, the MDE-NF algorithm shows promising performance on several benchmark functions.

A novel multi-context cooperatively coevolving particle swarm optimization (MCC-PSO) algorithm is proposed for the large-scale global optimization (LSGO) problems. As most optimization algorithms lose to find the global optimum on LSGO due to the curse of dimensionality, the famous cooperative co-evolution (CC) framework is proposed to overcome such weakness. In the basic CC framework, a single context vector is utilized for cooperatively but greedily coevolving different subcomponents, which sometimes loses its effectiveness. In this study, a novel multi-context cooperative coevolution framework and its application in PSO is proposed, in which more than one context vectors are employed to provide robust and effective co-evolution, as well as a new PSO updating rule based on the subpopulation in subcomponent (SPSC) structure and Gaussian distribution. On a comprehensive set of benchmarks (up to 1000 dimensionalities), the performance of MCC-PSO can rival several state-of-the-art evolutionary algorithms. Experimental results indicate that the novel multi-context CC framework is effective to improve the performance of PSO on LSGO and can be generally extended in other evolutionary algorithms.

A multi-context mechanism is newly reported to solve large-scale optimization problems (separable and nonseparable) within a general cooperative co-evolution (CC) framework. The basic CC is widely used to decompose a large-scale problem into several less difficult subproblems. When any two subproblems have no interaction, for example, when the problem is separable, the basic CC is effective. However, in practical cases there exist intensive interactions between subproblems, then the basic CC fails to find the global optimum. In this paper, the main reason of such failures has been studied and summarized. A general CC is proposed to use multiple context variables to avoid trapping caused by interactions. For the 500-dimension Rosenbrock's function with the optimum 0, the best result reported in existing CC methods is at the 102level, but the global optimum can be found in the proposed CC. On a comprehensive set of benchmark, the proposed CC performs significantly better than existing CC in terms of accuracy.

The aim of multimodal optimization is to locate multiple peaks/optima in a single run and to maintain these found optima until the end of a run. The results of seven variants of particle swarm optimization (PSO) algorithms on IEEE Congress on Evolutionary Computation (CEC) 2015 single objective multi-niche optimization problems are reported in this paper. The PSO algorithms include PSO with star structure, PSO with ring structure, PSO with four clusters structure, PSO with Von Neumann structure, social-only PSO with star structure, social-only PSO with ring structure, and cognition-only PSO. The experimental tests are conducted on fifteen benchmark functions. Based on the experimental results, the conclusions could be made that the PSO with ring structure performs better than the other PSO variants on multimodal optimization. To obtain good performance on the multimodal optimization problems, an algorithm needs to converge the candidate solutions to the global optima while keep the population diversity during whole search process.

The insufficiency of labeled samples is a major problem in automatic image annotation. However, unlabeled samples are readily available and abundant. Hence, semi-supervised learning methods, which utilize partly labeled samples and a large amount of unlabeled samples, have attracted increased attention in the field of image classification. During the past decade, graph-based semi-supervised learning became one of the most important research areas in semi-supervised learning. In this letter, we propose a novel and effective graph based semi-supervised learning method for image classification. The new method is based on local and global regression regularization. The local regression regularization adopts a set of local classification functions to preserve both local discriminative and geometrical information; while the global regression regularization preserves the global discriminative information and calculates the projection matrix for out-of-sample extrapolation. Extensive simulations based on synthetic and real-world datasets verify the effectiveness of the proposed method.

Renewable hybrid systems, which can generate power from solar or wind with low cost, is commonly installed in remote areas. When some areas get grid connection, customers installed the hybrid system can earn cost savings if taking part in demand response programs. In this paper an optimal energy management for a grid connected photovoltaic-battery hybrid system is proposed to sufficiently utilize the solar energy and to optimally dispatch the power flow under into the time-of-use program. The management of power flow aims to minimize electricity bills subject to a number of constraints, such as demand balance, solar energy, and battery capacity. An optimal control method (open-loop) is developed to schedule the power flows of the hybrid system over 24 hours. As shown in results, optimal solution of scheduling the hybrid system can be obtained with great bill savings.

The cooperation behaviors existing in the animal and human being societies, have been modeled for the numerical optimization, but the local cooperation has not been modeled separately in optimization problems. In this paper the local cooperation is newly modeled as Neighborhood Field Model (NFM). Based on NFM, a new optimization technique called Neighborhood Field Optimization algorithm (NFO) is firstly proposed to deliver global optimization. In NFO, each individual is attracted by its superior neighbor and repulsed by its inferior neighbor to search a better solution. In this paper, NFO is compared with certain algorithms under twelve different benchmark functions. The results show that NFO can outperform them on multimodal functions in the respect of accuracy, effectiveness and robustness. It also can be noted that the cooperation behavior can play a dominant role in the optimization algorithm separately.

Linear Discriminant Analysis (LDA) is a well-known dimensionality reduction algorithm for pattern recognition and machine learning. And Trace Ratio LDA (TR-LDA) and Null-space LDA (NLDA) are two popular variants of LDA. Both NLDA and TR-LDA can result in orthogonal transformations. However, they applied different schemes in deriving the optimal transformation. NLDA computes an orthogonal transformation in the null space of the within-class scatter matrix, while TRLDA computes an orthogonal transformation by an iterative procedure. In this paper, by using the trace difference problem as a bridge, we show that the above two algorithms can be equivalent when confronts with singularity problem. In addition, extensive simulations were conducted based on several datasets. Both theoretical analysis and simulation results confirm the equivalent relationship.