Purpose: In large-scale monitoring systems, sensors in different locations are deployed to collect massive useful time-series data, which can help in real-time data analytics and its related applications. However, affected by hardware device itself, sensor nodes often fail to work, resulting in a common phenomenon that the collected data are incomplete. The purpose of this study is to predict and recover the missing data in sensor networks.Design/methodology/approach: Considering the spatio-temporal correlation of large-scale sensor data, this paper proposes a data recover model in sensor networks based on a deep learning method, i.e. deep belief network (DBN). Specifically, when one sensor fails, the historical time-series data of its own and the real-time data from surrounding sensor nodes, which have high similarity with a failure observed using the proposed similarity filter, are collected first. Then, the high-level feature representation of these spatio-temporal correlation data is extracted by DBN. Moreover, to determine the structure of a DBN model, a reconstruction error-based algorithm is proposed. Finally, the missing data are predicted based on these features by a single-layer neural network.Findings: This paper collects a noise data set from an airport monitoring system for experiments. Various comparative experiments show that the proposed algorithms are effective. The proposed data recovery model is compared with several other classical models, and the experimental results prove that the deep learning-based model can not only get a better prediction accuracy but also get a better performance in training time and model robustness.Originality/value: A deep learning method is investigated in data recovery task, and it proved to be effective compared with other previous methods. This might provide a practical experience in the application of a deep learning method.

Airspace sectorization is a powerful means to balance the increasing air traffic flow and limited airspace resources, which is related to the efficiency and safety of operations. In order to divide sectors reasonably, a multi-objective optimization framework for 3D airspace sectorization is proposed in this paper, including four core modules: Flight clustering, sector generation, workload evaluation, and sector optimization. Specifically, it clusters flights and generates initial sectors using a Voronoi diagram. To further optimize sector shape, the concept of dynamic density is introduced to evaluate the controller workload, based on which a sector optimization model is constructed. The model not only considers intra-sector and inter-sector workloads as objective functions but also sets hard constraints to meet operation and safety requirements. To solve it, a Non-dominated Sorting Genetic Algorithm II (NSGA-II) with prior knowledge and an external archive is designed. By analyzing the optimization results of actual operational data in the Singapore regional airspace, our approach obtains diverse optimal sectorization schemes for decision makers to choose from. Qualitative and quantitative experimental results confirm that the initial population strategy with prior knowledge significantly accelerates the convergence process. At the same time, the mechanism of the external archive effectively enriches the diversity of solutions.

Gate allocation has always been a fundamental but critical issue in the daily operation of airports, which is related to service quality and schedule efficiency. In order to obtain reasonable and efficient gate allocation results, in this paper, a multi-commodity network flow model is proposed to describe the gate allocation process in flight flow, based on which a multi-objective optimization model is constructed. It not only comprehensively considers the flight information of aircraft arrivals and departures, but also integrates the broader interests of passengers, airlines, and airports. To solve it, a linear weighting technique is applied. In addition, K-means cluster analysis is used to explore different weight combinations, and on this basis, the idle time of the gate is introduced as a performance evaluation index to guide the selection of the final weight. By analyzing the optimization results of actual operation data, the proposed model significantly balances the interests of multiple parties and the number of flights at each gate and has a relatively high gate-utilization rate. It can provide rich decision support and a reasonable allocation scheme for airport management to a certain extent.