This article investigates the distributed consensus filtering problem in sensor networks and proposes the optimal distributed sequential consensus fusion filtering (DSCFF) algorithm. Each sensor node in the network sequentially exchanges information with its neighboring nodes over multiple rounds to obtain global information. The filtering results for all sensor nodes tend to agree, but significant information is repeatedly exchanged between individual nodes, consuming the limited energy in the network. A dynamic event-triggering (DET) mechanism based on the minimum covariance per round is proposed to reduce unnecessary energy loss and decrease the communication bandwidth between sensor nodes. In addition, as the optimal DETDSCFF needs to calculate the cross-covariance matrices (CCMs) between sensor nodes, which increases the calculation complexity, this article provides the suboptimal DETDSCFF algorithm that minimizes the upper bound of the error covariance during fusion to solve the consensus gain. The boundedness of this suboptimal filter is proven, and its effectiveness is proven through simulation experiments.

Autonomous underwater vehicles (AUVs) have become an important technology in the field of the Internet of Underwater Things (IoUT). However, the complexity and unknown nature of the underwater environment poses a great challenge to the autonomous operation of AUVs. An efficient and stable path planning algorithm is the key for AUVs to achieve autonomous operation. To address the above problems, this paper proposes an Improved Exponential Distribution Optimizer (IEDO) for three-dimensional path planning. In the proposed algorithm, population initialization, the optimization algorithm itself and the local optimum problem, are all addressed and improved. The algorithm population is first initialized using an oriented initialization method that obeys a Gaussian distribution to improve the efficiency of the algorithm in the early stages. Second, for the exponential distribution optimizer algorithm itself, the convergence rate of the algorithm is further improved by adding the guided solution generated by its iterative process to the iterative selection of the population. Finally, the crossover-mutation idea of the genetic algorithm is integrated to improve the global search ability of the population and avoid falling into the local optimum problem. In terms of algorithm validation, two real seabed terrain datasets are used for a simulation verification of the algorithm, and compared with the existing algorithms. The results prove that the IEDO algorithm proposed in this paper has a strong convergence speed, strong global search capability and good path qualities.

This paper addresses the distributed task allocation problem for maximizing the total number of successfully executed tasks of multirobot systems. Due to the deadline time of tasks and fuel limits of robotic vehicles, not all tasks can be successfully executed sometimes. Based on the performance impact (PI) algorithm, an effective and efficient performance impact (EEPI) algorithm is proposed, its novelty lies in its cost function and task release procedure. The fundamental ideas of the proposed cost function are as follows. First, the traveling time from the initial position of each vehicle to the positions of its tasks is minimized, so that more time can be left for the vehicle to execute more tasks due to the limited fuel. Second, the start time of each task should be close enough to its deadline, so that tasks with earlier deadlines can be assigned earlier than those with later deadlines. To avoid invalid removal performance impacts (RPIs) and inclusion performance impacts (IPIs), the tasks assigned to a vehicle are all released if the number of tasks removed by the vehicle during the task removal phase is the most, which further increases the total number of successfully executed tasks. Both simulations and hardware-in-the-loop experiments suggest that compared with the state-of-the-art distributed task allocation algorithms, the proposed EEPI is not only effective in maximizing the number of successfully executed tasks but efficient in saving the number of iterations and time to converge.Note to Practitioners—This work was motivated by the limitations of the existing distributed task allocation algorithms for maximizing the total number of successfully executed tasks. The consensus-based bundle algorithm (CBBA) has been proven to guarantee convergence and 50% optimality under the diminishing marginal gain (DMG) assumption in previously published works. Based on CBBA, a performance impact (PI) algorithm was proposed, and simulations show that it can assign more tasks than CBBA when applied to time-critical scenarios with low task-to-vehicle ratios. Starting from the results of PI, a rescheduling method named PI for maximizing assignments (PI-maxAss) was proposed, which has been demonstrated to assign more tasks than PI with high task-to-vehicle ratios. However, much more iterations and time are required by PI-maxAss to converge to globally consistent assignments because of the rescheduling. Due to the above considerations, an effective and efficient performance impact (EEPI) algorithm is proposed in this paper to maximize the number of successfully executed tasks without any rescheduling. Both simulations and hardware-in-the-loop experiments suggest that compared with the algorithms mentioned above, the proposed EEPI is effective in maximizing the number of successfully executed tasks and efficient in saving the number of iterations and time to converge. In future work, the distributed task allocation problem in which several vehicles execute a task at the same time cooperatively or a vehicle executes several tasks simultaneously will be further addressed.

The structural information of offshore oil production equipment is the basis for the functional modification and upgrading of offshore oil drilling platforms. In order to solve the problems of low efficiency in the process of acquiring offshore oil production equipment structure information by traditional measurement methods, we propose a deep learning-based point cloud data processing scheme for offshore oil production equipment. First, a point cloud dataset of offshore oil production equipment for deep learning is constructed, and a deep learning network based on the two-step downsampling method and the local feature aggregation of each point after downsampling is implemented for the semantic segmentation of the dataset. Second, the combined point cloud filtering process based on radius filtering and statistical filtering is implemented on the segmented point cloud data. Third, an implicit surface reconstruction based on contextual prior information is implemented for offshore oil production equipment components. The dataset contains six types of point clouds, including pipelines, flanges, shelves, bends, valves, and oil recovery trees. Based on this dataset for semantic segmentation, the overall segmentation accuracy reaches 98.87% and the mIoU reaches 92.79%. Combined filtering is performed on the segmented offshore oil production equipment data, and the denoising rate can reach 94%. Finally, the denoised point cloud data is utilized for 3-D reconstruction, and the overall consistency accuracy can reach 1.85 mm, which can provide fast, efficient, and reliable data support for the upgrading of offshore oil rigs.

Recently, interferometric altimeters (IA), such as the Surface Water and Ocean Topography (SWOT) satellite, have been launched, and will improve the observation of ocean dynamics. The validation of altimeters is a complex and important process that can effectively improve their observation accuracy. For the IA validation of sea surface height in two-dimensional, it is normal to use the steric height to validate the sea surface height. However, the validation method is affected by many factors. In order to improve the validation accuracy, the South China Sea, which is a suitable area for validation of China’s offshore, was selected in this study to analyze the impact of wind on the validation procedures. Through the analysis of the spatial-temporal relationships between wind speed, steric height and sea surface height (SH-SSH), we found correlations between wind speed and validation results. The high wind speeds can lead to a certain deviation in the relationship between SH and SSH, and the special weather conditions make it unsuitable for validation. Meanwhile, in terms of time, May is the time when the wind speed is relatively low, making it more suitable for validation. These analyses are useful for the validation procedures in sea surface height.

GNSS signals are easily affected by the complex urban environment, resulting in reduced navigation and positioning accuracy and poor usability. In this paper, low-cost survey GNSS receivers are used in complex urban areas to receive primitive observations such as pseudorange, carrier, Doppler, and signal-to-noise ratio. Single-point positioning, pseudorange differential, and carrier double-difference positioning modes are used for solution analysis. On this basis, the impact of the environment on the accuracy of observations is evaluated, and the impact of GNSS interference on the high-precision application of satellite navigation systems is analyzed.

Multi-hop machine reading comprehension (MRC) task aims to enable models to answer the compound question according to the bridging information. Existing methods that use graph neural networks to represent multiple granularities such as entities and sentences in documents update all nodes synchronously, ignoring the fact that multi-hop reasoning has a certain logical order across granular levels. In this paper, we introduce an Asynchronous Multi-grained Graph Network (AMGN) for multi-hop MRC. First, we construct a multigrained graph containing entity and sentence nodes. Particularly, we use independent parameters to represent relationship groups defined according to the level of granularity. Second, an asynchronous update mechanism based on multi-grained relationships is proposed to mimic human multi-hop reading logic. Besides, we present a question reformulation mechanism to update the latent representation of the compound question with updated graph nodes. We evaluate the proposed model on the HotpotQA dataset and achieve top competitive performance in distractor setting compared with other published models. Further analysis shows that the asynchronous update mechanism can effectively form interpretable reasoning chains at different granularity levels.

Evapotranspiration (ET), including soil evaporation and vegetation transpiration, is a vital component of the water cycle and energy exchange. The end-member-based soil and vegetation energy partitioning approach (ESVEP model) for estimating ET is the first model considering the differing responses of soil water content at the upper surface layer and at the deeper root zone layer. In this paper, we have improved the ESVEP model by 1) improving estimates of canopy resistance from three parts: stomatal conductance, cuticular conductance and leaf boundary-layer conductance; 2) adding the influence of atmosphere pressure and atmosphere temperature on resistance; 3) dividing aerodynamic resistance into convective resistance and radiative heat transfer resistance. Compared to the original ESVEP model, the improved algorithm is more applicable for different biome types and has a great potential in operational estimation of regional and global evapotranspiration. Due to the underestimation of soil temperature, the estimated ET is biased, which means that the biome properties and resistance are required to be further reparameterized in future study.

In recent years, the big data industry chain has become more mature. Analyzing and managing cities by utilizing various big data in cities has become a hot research topic. Urban functional regions discovering is one of the important applications. The mainstream in urban functional regions discovering are probabilistic topic models, such as latent Dirichlet allocation (LDA) based topic model, which seeing the regions as documents and their functions are their topics. These methods require feature engineering by hand, which will construct features of limited expressiveness. To overcome these methods' shortcomings, we introduced a deep learning topic model called document neural autoregressive distribution estimation (DocNADE) into urban functional regions mining. And we did an experiment to test its effect. The experimental result shows that this DocNADE framework has achieved a considerable result in urban function inference compared with Dirichlet Multinomial Regression (DMR) based topic model which is a state of the art of urban functional regions discovering.

Development of a city cultivates regions with different functions such as working areas and entertainment venues. People in a city usually travel among these regions in certain movement patterns. Identifying those regions will facilitate government management and promote further development of the city. In this paper, we proposed a framework to identify urban functional regions in Chengdu city based upon mobility pattern and point of interest (POIs) information extracted from mobile check-ins data. Firstly, unlike GPS trajectories, location check-ins were discontinuous. Thus, the typical mobility patterns of location check-ins was mined. Secondly, an arrival/departure matrix based on the typical mobility patterns was constructed to obtain the topics of regions by clustering POIs. Because we considered a region's function as our topics, we transferred the problem into a topic modeling problem, and applied an improved probabilistic topic model to infer functions of the regions. We evaluated our approach with 227,428 check-ins in Chengdu collected from Sina Weibo from April 12 2012 to February 16 2013. The results showed that our method outperformed baseline methods solely clustering POIs.

Land use and land cover change (LUCC) is necessary to explore the factors leading to heavy drought and rainy-flood disaster in some districts of Sichuan province. A method based RS, GIS, GPS and Google earth (GE) is presented to establish LUCC database in Sichuan province and Chengdu district. At first, LUCC is interpreted based on the new temporal images and the land use and land cover database from TM in 2000.Secondly, some ground objects, which could not be identified in the new temporal images, were interpreted utilizing GE with some higher spatial resolution images. Thirdly, the new interpreted LUCC was validated in the field with GPS handheld receiver. Then, LUCC of Sichuan province was updated. A comparative analysis of LUCC between in Sichuan province and in Chengdu district was conducted and the result showed: (1) a large amount of farmland in Sichuan Province was occupied from 2000 to 2005 and the area is 84 573 ha. While construction land gained obviously and the area was 35 828 ha. The dynamic degree of construction land was 111.100/00from 2000 to 2005. The LUCC demonstrated that the economy of Sichuan province continued to develop, the cities were overspreading and the urban heat island effect was deteriorated from 2000 to 2005. (2) A large amount of farmland was also occupied in Chengdu district from 2000 to 2005, the area amounted to 12 989 ha. The farmland lost was mainly changed to construction land, amounting to 93%. And the dynamic degree was 117.410/00from 2000 to 2005, which was bigger than that in Sichuan province.

Hyperspectral remote sensing image (HSI) consists of hundreds of bands that contain rich space, radiation and spectral information. The high-dimensional data can also lead to the curse of dimensionality problem making it difficult to be used effectively. In this paper, we proposed a manifold learning algorithm to reduce the dimensionality for HSI data. For high dimensional datasets with continuous variables, it is often the case that the data points are arranged along with low dimensional structures, named manifolds, in the high dimensional space. Manifold learning aims to identifying those special low dimensional structures for subsequent usage such as classification or regression. However, many manifold learning algorithms perform an eigenvector analysis on a data similarity matrix whose size is N×N, where N is the number of data points. The memory complexity of the analysis is at least O(N2) that is not feasible for a regular computer to compute or storage for very large datasets. To solve this problem, we used statistical sampling methods to sample a subset of data points as landmarks. A skeleton of the manifold was then identified based on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding (LLE). We tested our algorithm on AVIRIS Salinas-A data set. The experimental results showed that the HSI dataset could be reduced to a lower-dimensional space for land use classification with good performance, and the main structure was preserved well.

High-dimensional data such as hyperspectral images contain abundant information of surface radiation. But the massive redundant information makes it complex to be utilized conveniently. To solve this problem, a manifold learning dimensionality reduction framework for hyperspectral image is proposed. Firstly, statistical sampling methods were used to sample a subset of data points as landmarks. A skeleton of the manifold was then identified basing on the landmarks. The remaining data points were then inserted into the skeleton by Locally Linear Embedding algorithm. At last, original data sets and data sets reduced with different manifold learning approaches were classified by KNN classifier to evaluate the performance of the proposed framework. The framework was tested on AVIRIS Salinas-A dataset. The experimental results showed that the tradeoff of accuracy with different landmarks is of great significant. Insufficient landmarks lead to low accuracy and excess landmarks may spend a considerable amount of time.

Double-row layout problem (DRLP) is a new problem proposed in 2010. Different from single or multi-row layout problems, DRLP needs to determine not only the sequence of machines on both rows but also the exact location of each machine. Aiming at the dynamic environment of product processing in practice, in this paper we study DRLP under dynamic environment and propose a dynamic double-row layout problem (DDRLP) where the material flows may change over time. A mixed-integer programming model is established for the DDRLP. An improved simulated annealing (ISA) algorithm is proposed to for this problem. To represent a feasible solution, a mixed coding scheme is suggested to express the sequence of facilities and the exact location of each facility. Five operators are devised to make the ISA able to effectively solve this problem. Experiment results show that the proposed algorithm is able to find the optimal solutions for small size problem instances and outperform an exact approach (CPLEX) under limited run time for large size instances.

Based on the theory and technology of artificial intelligence, internet, and cognitive psychology, word problem auto-solving and intelligent tutoring technologies have become hot issues of research in recent years. However, since word problem is described by natural language, the number of resolved problems is limited. The paper researches the algorithm of processing You-sentence and develops an auto-solving system based on it to prove the validity of the algorithm.