A Dynamically Weighted Directed Network (DWDN) fundamentally illustrates the complex interactions among massive nodes from a big-data-oriented application, like the dynamic interactions among numerous terminals in a metropolitan network management system (MNMS). A High-Dimensional and Incomplete (HDI) tensor is able to flexibly quantize it, where lots of entries are missing primarily due to the impossibility in discovering the full interactions among numerous nodes. Such an HDI tensor can be effectively represented by a Latent Factorization of Tensors (LFT) model for extracting useful knowledge like potential links from it, while existing LFT models commonly adopt general regularization schemes without considering an HDI tensor's imbalanced known data, which impairs their generality. To address this issue, this paper develops an Fine-grained Regularized Nonnegative Latent factorization of tensors (FRNL) model based on two-fold ideas: a) innovatively proposing an Swish-p-based and fine-grained regularization scheme where the regularization effects acting on individual latent feature is proportional to its related instance count for precisely representing the imbalanced distribution of an HDI tensor's known data; b) implementing the self-adaptation of the model hyper-parameters via a fuzzy controller to achieve high practicability. The convergence ability of FRNL is justified theoretically. Experimental studies on eight DWDNs emerging from a real MNMS illustrate that compared with state-of-the-art LFT models, the proposed FRNL model obtains significantly higher learning accuracy and computational efficiency in representing a DWDN.

Last-mile logistics is a crucial phase of online commodity trades. In last-mile logistics, one of the critical problems is to reasonably assign couriers to distribute the products in time in order to ensure the quality of service, especially for fresh produce. The last-mile assignment problem (LMAP) for fresh produce poses a challenge on traditional logistics since fresh produce is difficult to preserve. This article formalizes the LMAP for fresh produce via the group role assignment framework and proposes a role awareness method by using adaptive clustering in spatiotemporal crowdsourcing based on task granularity. The formalization of LMAP makes it easy to find a solution using the IBM ILOG CPLEX optimization package (CPLEX). The proposed method allows one to take the time and space factor into consideration, helps spatiotemporal crowdsourcing assign couriers for efficient delivering daily orders, and improves the quality of service in last-mile logistics. It is verified by simulation experiments. The experimental results demonstrate the practicability of the proposed solutions in this article.

Transportation services play an increasingly significant role for people's daily lives and bring a lot of benefits to individuals and economic development. The randomness and volatility of traffic flows, however, constrains the effective provision of transportation services to a certain extent. Precise traffic flow forecasting becomes the key and primary task to realize the stability of intelligent transport systems and ensure efficient scheduling of traffic. This paper investigates the application of an ensemble approach based on deep belief networks for short-term traffic flow forecasting. Traffic flow data, collected from the real world, is decomposed into several Intrinsic Mode Functions (IMFs) and a residue with EEMD (Ensemble Empirical Mode Decomposition). Then, for each component, the essential feature subset is extracted by the mRMR (minimum Redundancy Maximum Relevance Feature Selection) method considering weather conditions and day properties. Furthermore, each component is trained by DBN (Deep belief networks) and their forecasting results are summed up as the output of the ensemble model at last. Results indicate that the proposed approach achieves significant performance improvement over the single DBN and other selected methods.

Industrial robots are regarded as the essential instruments for advanced industry upgrading. The kinematic parameters of an industrial robot should be calibrated precisely to guarantee its absolute positioning accuracy, which can be implemented via an evolutionary computing (EC) algorithm. However, existing calibrators are mostly based on an EC algorithm with a homogeneous learning scheme, which may lead to performance loss due to limited searching ability. On the other hand, the existing hybrid algorithm schemes based on multiple EC algorithms mostly work by training different base-models with different EC algorithms and then building the ensemble for performance gain, which leads to high computational and storage costs. Motivated by these discoveries, this paper proposes a novel Hybrid-of-Evolutionary-Schemes (HOEs) model with three-fold ideas: a) aggregating the principle of six different EC algorithms’ learning schemes to build a hybrid evolution scheme, where the learning scheme of each EC algorithm is adopted to make the swarm evolve in sequence, thereby building an expert ensemble where each expert’s learning is taken based on previous results for establishing high calibration accuracy; b) establishing a memory system that consists of diversified and highly efficient individuals in a specific population during the update process of each expert for obtaining the solution diversity; c) designing a punishment system to dismiss the experts with poor calibration performance to achieve high computational efficiency. The convergence of the HOEs model is rigorously proved in theory. To validate its performance, a large dataset HSR-C has been established and published for industrial robot calibration. Empirical studies on HSR-C demonstrate that the proposed HOEs model outperforms several state-of-the-art algorithms (including both sole algorithms and HOEs model’s variants) in terms of calibration accuracy, which strongly supports its potential in addressing calibration issues for industrial robots.

When earthquakes occur, solar-powered unmanned aerial vehicles (SUAVs), deployed as communication relay points, can construct a signal relay network to assist the ground mobile communication vehicles in resuming communication. Considering the urgency of disaster relief, a practical, accurate, and robust modeling method for multiple SUAVs deployments is vital. For this concern, this article first formalizes the deployment problem of multiple solar-powered UAVs in communication recovery by extending Group MultiRole Assignment (GMRA) (UGRA). In the second step, the success in this assignment process depends on the choice of the agent evaluation method. The evaluation benchmark in UGRA is SUAV path planning in a complex environment with uncertain subpaths and accumulative attitude errors. In response to this issue, we propose two innovative algorithms: 1) dynamic curve path-planning algorithm (DCPPA) and 2) greedy curved straight path-planning algorithm (GCSPPA). Moreover, with the time requirement in mind, one sufficient condition and one necessary condition are established to help the DCPPA achieve fast convergence. With these two novel agent evaluation algorithms, UGRA can rapidly deploy multiple SUAVs to establish a collaborative relay network within an acceptable time. Finally, simulation experiments at different scales are carried out to demonstrate the accuracy and effectiveness of the proposed solution.

Dynamic Quality-of-Service (QoS) data can be efficiently represented by a Non-negative Latent-factorization-of-tensors model, which relies on a Non-negative and Multiplicative Update on Incomplete Tensors (NMU-IT) algorithm. Nevertheless, NMU-IT frequently encounters slow convergence and inefficient hyper-parameters selection. Targeting at overcome these critical defects, this paper proposed to improve the NMU-IT algorithm from two perspectives: a) integrating a generalized Nesterov's accelerated gradient method to accelerate the resultant model's convergence rate, and b) establishing the hyper-parameter adaptation mechanism through the particle swarm optimization strategy. On the basis of these conceptions, this study successfully builds a G eneralized Nesterov's Accelerated Gradient-incorporated N on-negative L atent-factorization-of-tensors (GNL) model for precisely and high-efficiently representing the dynamic QoS data. The proposed GNL model has shown its superiority over several advanced models concerning both the precision of estimating missing QoS data and training efficiency, as demonstrated by the experiments conducted on two dynamic QoS datasets.