Search

As a typical big data representative, the information of global Cellular Signal Strength (CSS), defined as the signal power received by mobile phones, plays an important role in geographic flow analysis, because the density of such information can reflect the urbanization variables such as population, gross domestic product, built-up area, electric power consumption, and etc. Despite the importance, the real-time analysis of global CSS distribution remains a challenging problem due to the large data scale. In this paper, a Display-driven Computing (DisDC) technique is designed and applied to provide efficient large scale interactive CSS visualization, generating results by calculating the value of each pixel that directly for display that can dramatically improve system capacity in big data handling. Specifically, we present an efficient CSS measurement algorithm, which introduces spatial indexes and a corresponding query strategy; besides, an optimized parallel computing architecture is proposed to ensure the ability of real-time visualization. Experiments show that our approach obviously outperforms traditional methods and is capable of handling more than 40 million base stations in real-time. Moreover, an online demonstration is provided at https://github.com/MemoryMmy/CSSMap.

Knowledge graph is becoming an indispensable resource for numerous AI applications. However, the knowledge graph often suffers from its incompleteness. Building a complete, high-quality knowledge graph is time-consuming and requires significant human annotation efforts. In this paper, we study the Knowledge Graph Population task, which aims at extending the scale of structured knowledge, with a special focus on reducing data preparation and annotation efforts. Previous works mainly based on discriminative methods build classifiers and verify candidate triplets that are extracted from texts, which heavily rely on the quality of data collection and co-occurrance of entities in the text. We introduce a generative perspective to approach this task. A generative model KGGEN is proposed, which samples from the learned data distribution for each relation and can generate triplets regardless of entity pair co-occurrence in the corpus. To further improve the generation quality while alleviate human annotation efforts, adversarial learning is adopted to not only encourage generating high quality triplets, but also give model the ability to automatically assess the generation quality. Quantitative and qualitative experimental results conducted on two real-world generic knowledge graphs show that KGGEN generates novel and meaningful triplets and less human annotation comparing with the state-of-the-art approaches.

Query feeds recommendation is a new recommended paradigm in mobile search applications, where a stream of queries need to be recommended to improve user engagement. It requires a great quantity of attractive queries for recommendation. A conventional solution is to retrieve queries from a collection of past queries recorded in user search logs. However, these queries usually have poor readability and limited coverage of article content, and are thus not suitable for the query feeds recommendation scenario. Furthermore, to deploy the generated queries for recommendation, human validation, which is costly in practice, is required to filter unsuitable queries. In this paper, we propose TitIE, a query mining system to generate valuable queries using the titles of documents. We employ both an extractive text generator and an abstractive text generator to generate queries from titles. To improve the acceptance rate during human validation, we further propose a model-based scoring strategy to pre-select the queries that are more likely to be accepted during human validation. Finally, we propose a novel dual learning approach to jointly learn the generation model and the selection model by making full use of the unlabeled corpora under a semi-supervised scheme, thereby simultaneously improving the performance of both models. Results from both offline and online evaluations demonstrate the superiority of our approach.

Semantic segmentation of remote sensing images is always a critical and challenging task. Graph neural networks, which can capture global contextual representations, can exploit long-range pixel dependency, thereby improving semantic segmentation performance. In this paper, a novel self-constructing graph attention neural network is proposed for such a purpose. Firstly, ResNet50 was employed as backbone of a feature extraction network to acquire feature maps of remote sensing images. Secondly, pixel-wise dependency graphs were constructed from the feature maps of images, and a graph attention network is designed to extract the correlations of pixels of the remote sensing images. Thirdly, the channel linear attention mechanism obtained the channel dependency of images, further improving the prediction of semantic segmentation. Lastly, we conducted comprehensive experiments and found that the proposed model consistently outperformed state-of-the-art methods on two widely used remote sensing image datasets.

Robust zero-watermarking is an effective and distortion-free technique for copyright protection and has become a research hotspot in the field of digital watermarking. In the face of weak robustness and security of existing schemes, this paper presents a novel robust and secure color image zero-watermarking algorithm based on majority voting pattern and hyper-chaotic encryption. In the proposed algorithm, firstly an original color image is decomposed by one-level discrete wavelet transform (DWT) and the corresponding low-frequency components of three channels are partitioned into blocks. Then, to resist strong attacks, we construct a distinguishable robust binary feature matrix extracted from all blocks and color components by using a combination of Frobenius norm in the singular value decomposition (SVD) domain and majority voting pattern. To promote security, a binary copyright logo is confused and diffused by hyper-chaotic Lorenz system. Finally, it performs a bitwise exclusive-or operation on the binary feature matrix and the encrypted copyrighted logo to obtain a zero-watermark signal. Experimental results indicate that in addition to the high-level security, the proposed zero-watermarking algorithm also has a stronger robustness against common geometric and non-geometric attacks, including rotation, scaling, filtering, JPEG compression and noise addition, compared with some existing typical zero-watermarking and traditional watermarking methods.

Unmanned aerial vehicles (UAVs) have become an indispensable part of our intelligent society. Accurate UAV image geo-localization is fundamental in many applications such as search and rescue, precision agriculture, change detection. Previously, the UAV image geo-localization was usually calculated by photogrammetry method or by matching with the well-located reference images. The photogrammetry method relies heavily on the accuracy of the UAV positioning parameters, however, the construction and use of high-precision positioning equipment are expensive and difficult to be widely used. The method based on image matching requires good similarity between matching images, which is hard to be satisfied as the reference image and UAV image are heterologous. The existing methods are difficult to achieve accurate image geo-location on UAVs equipped with economical positioning devices. To address this issue, we propose a coarse-to-fine UAV image geo-localization pipeline. Firstly, we implement the coarse UAV image geo-localization by utilizing the UAV’s position parameters. Then, a deep learning algorithm multi-stage Lucas-Kanade (MS-LK) is proposed to refine the UAV image geo-localization results iteratively. MS-LK can make full use of the UAV images’ global texture. We validate the effectiveness of the proposed method on two real UAV data sets. The results show that the proposed UAV image geo-localization method can promote the results of the traditional photogrammetry-based approaches.

The current Digital Rights Management (DRM) is a centralized management system, that the private and sensitive information may be leaked, and data barriers exist between various platforms. The decentralization and traceability of blockchain provide new ideas and solutions for the standardization of digital rights protection. The consensus algorithm is the core of blockchain technology, but it cannot be directly applied to digital rights protection because of their drawbacks. Researchers have optimized and improved the consensus algorithm to meet the needs of digital rights protection. This paper reviews the application of blockchain in digital rights protection, and analyses their improvements of the consensus algorithm.

Real-time waveform recognition and parameter evaluation for linear frequency modulated (LFM) pulse waveform is crucially important while challenging in microwave detection systems. To address this issue, in this work, we proposed a new artificial intelligence enabled classification method based on reservoir computing (RC). A sampled sequence, generated by random concatenation of LFM signals with different chirp rates and initial frequencies, is used to training the designed reservoir with 200 nodes. The testing result shows that the RC can recognize individual LFM signals in the sequence, and estimate the instantaneous frequency of an LFM signal within the sequence. Compared to conventional computing methods for instantaneous frequency identification such as Hilbert transform or short-time Fourier transform, RC-based approach features faster speed and great potential for hardware implementation using photonic devices.

We present DiSA, a Display-driven Spatial Analysis framework for interactive analysis of large-scale geographical vector data. DiSA calculates visualization of analysis results directly using a parallel per-pixel approach with efficient fine-grained spatial indexes. Compared with conventional object-based methods, DiSA can greatly reduce the computational complexity (from O(n) to O(log(n)) in some cases), making it less sensitive to data volumes. Experimental results verify that DiSA can provide analysis of billion-scale spatial objects in milliseconds. We demonstrate DiSA with various application scenarios including raw data exploration, spatial buffer and overlay analysis, and global cellular signal strength analysis. Users can explore 10 millions of spatial objects, adjust algorithm parameters, and always see the results in real-time on a personal computer.

With the increasing amount of data in the marine environment and the user's affluent requirements for visualization, traditional CPU-based visualization is becoming more and more difficult to complete specific tasks. To visualize the large-scale marine vector data, the particle system method is one of the most popular methods, but the data scale and complex calculations heavily restrict the efficiency of these CPU-based algorithms. This paper proposes a frame buffer visualization method with two strategies based on WebGL (FBO-W). To reduce the dense particle resulted by the increased visualization resolution, we dynamically set the number of particles based on different resolutions (PN-R); then, to alleviate the problem of unbalanced particle distribution during visualization, the strategy of dynamically adjusting particle drop rate based on particle velocity (DR-V) is incorporated. Experimental results show that the efficiency of data loading and rendering is greatly improved with higher visualization quality.

A new low-cost and data-efficient method for high-throughput microfluidic single-cell screening is proposed and demonstrated. Only one low-speed single-pixel photodetector is needed. Morphology-based object classification is achieved using reservoir computing. Our experiment shows that the frames involving the target cell can be recognized distinctly.

In order to realize the autonomous greeting and greeting of the field guests, the autonomous greeting robot needs to collect and analyze the environmental data. Through the optimization algorithm, an optimal autonomous moving path from the starting point of greeting to a certain guest is found. In this paper, aiming at the autonomous greeting robot, the path planning problem of the autonomous greeting robot based on ant colony algorithm is proposed, and the related design scheme is given. The simulation example shows that the greeting robot can visit specific guests in the shortest path and time. It can effectively ensure that the robot avoids obstacles and other guests in the process of moving. It verifies the feasibility and validity of the path planning proposed in this paper, and lays a theoretical foundation for the further application of the autonomous greeting robot in non-specific environment.

The 3D printer is a machine for cumulative manufacturing, which is a digital model file, and three-dimensional objects are made of printing layer adhesive material. At present, the items printed out by a 3D printer will have a higher amount of heat, and taking out the printed items directly will cause burns to their hands. In addition, in the moment of picking up the print, the sudden release of the heat will also cause damage to the print. In the process of printing, the main control board will increase the environment of the printing area because of the working heat and the temperature of the print head, which will seriously affect the printing quality and the service life of the printer. Therefore, the open 3D printer is designed in the paper. The heat dissipation and cooling device of the machine is optimized to reduce the temperature of the main control board, and the extrusion head temperature of the printer reaches the printing working temperature without affecting the surrounding structure. Through the experimental verification and analysis, the effectiveness of the heat dissipation and cooling device of 3D printer designed in this paper is proved, which provides an effective solution for the heat dissipation research of 3D printer.

Rapid visualization of large-scale spatial vector data is a long-standing challenge in Geographic Information Science. In existing methods, the computation overheads grow rapidly with data volumes, leading to the incapability of providing real-time visualization for large-scale spatial vector data, even with parallel acceleration technologies. To fill the gap, we present HiVision, a display-driven visualization model for large-scale spatial vector data. Different from traditional data-driven methods, the computing units in HiVision are pixels rather than spatial objects to achieve real-time performance, and efficient spatial-index-based strategies are introduced to estimate the topological relationships between pixels and spatial objects. HiVision can maintain exceedingly good performance regardless of the data volume due to the stable pixel number for display. In addition, an optimized parallel computing architecture is proposed in HiVision to ensure the ability of real-time visualization. Experiments show that our approach outperforms traditional methods in rendering speed and visual effects while dealing with large-scale spatial vector data, and can provide interactive visualization of datasets with billion-scale points/segments/edges in real-time with flexible rendering styles. The HiVision code is open-sourced at https://github.com/MemoryMmy/HiVision with an online demonstration., 19 pages 16 figures

Online visualization and query of massive geo-spatial data are facing increasing challenges with the explosive growth of location-based spatial datasets. In the practical scenario, online visualization is carried out in a progressive way, namely, a sketchy view map is first presented, and more detailed view maps are produced gradually as the viewport scale goes deeper. One approach is to use the multi-scale spatial index technique. However, it loses the original data attribute and cannot provide spatial statistics information. The paper is to provide an improved index structure, the Geo-Gap tree, which aims to enhance online interactive access to large spatial datasets, as well as enable one to compute statistical attributes like aggregation at the coarse level. Therefore, the first focus of Geo-Gap tree is improving the efficiency of tree building. For this purpose, an adaptive geohash coding is introduced to reduce the computing of neighboring objects. And, this phase can be improved in parallel once objects are partitioned. Compare to Gap tree, the cost of building the Geo-Gap tree can be greatly reduced. The second contribution is to choose data at different level based on sampling so that a sample for each level can be served as a progressive query result. The third contribution is an estimation of progressive query results, which ensure that progressive query accuracy can be controlled within the range of theoretical analysis. With the query continuing to execute, the query results become more and more accurate. The method is now integrated successfully into a high-performance geographic information system called HiGIS.

Geographic meshing system is an essential technology in the digital earth framework and has essential applications in the integration and organization of heterogeneous spatial data, along with corresponding coding method. But current meshing and coding methods show unsatisfying locality and performance. To make an improvement, an adaptive Hilbert-Geohash meshing and coding method called AHG is proposed, which could represent both the location and the approximate size of the coded object directly by the meshing hierarchy and the corresponding coding length. This unique feature helps to accelerate the spatial range query and neighbor query. By simple string operations, many candidate objects that do not meet the query criteria can be quickly filtered out without precise spatial calculation. In addition, AHG code can also support spatial size query by finding objects whose size is within a certain interval quickly, without calculating the precise size of each object, which brings great convenience to spatial size statistics of a massive spatial dataset. Demonstrated by experiments over different types of the spatial dataset in a common PC environment, AHG shows favorable stability and scalability besides its capability in accelerating spatial query. The method is now applied successfully in several spatial query tools in a high-performance geographic information system called HiGIS.

Onboard observation task planning plays an essential role in satellite autonomy, which has attracted considerable attention from researchers in recent years. Most of the existing studies solve the satellite onboard observation task planning problem (SOOTP) by searching algorithms. However, the limited computing resources and the changes of onboard condition present a new challenge for these methods. In this paper, we develop a sequential decision-making model and propose a deep learning-based planning method to solve the SOOTP. Instead of generating a short-term or long-term plan in advance, the sequential decision-making model enables the satellite to decide the observation task to execute in real-time. In the deep learning-based planning method, a long short-term memory-based encoding network is designed to extract the features and a classification network is used to make such a decision. In the experiment, we compared our method with the gated recurrent unit network and other three searching algorithms based on five scenarios. The experimental results show that our method can solve problems with 90.3%–93.7% accuracy, 2.19%–3.95% profit gap, and 0.004–0.006 s response time per task, which confirms its feasibility.

In the big data era, real-time analysis of large-scale spatial data remains a challenging problem since the computational scales of conventional data-driven methods expand rapidly with data volumes. This paper presents display-driven computing (DisDC), a new computing model for interactive analysis of large-scale spatial vector data. The computing units in DisDC are screen pixels for display rather than spatial objects in traditional data-driven methods, and the core task of DisDC is to judge the spatial relationships between pixels and spatial objects. As the number of pixels for display is stable, DisDC is less sensitive to data volumes and can be used to provide real-time data analysis of large-scale spatial vector data. Experiments show that DisDC is capable of handling billion-scale spatial vector data, and an online demonstration is provided (https://github.com/MemoryMmy/DisDC).

Measuring the similarity between a pair of trajectories is the basis of many spatiotemporal clustering methods and has wide applications in trajectory pattern mining. However, most measures of trajectory similarity in the literature are based on precise models that ignore the inherent uncertainty in trajectory data recorded by sensors. Traditional computing or mining approaches that assume the preciseness and exactness of trajectories therefore risk underperforming or returning incorrect results. To address the problem, we propose an amended ellipse model which takes both interpolation error and positioning error into account by making use of motion features of trajectory to compute the ellipse&rsquo, s shape parameters. A specialized similarity measure method considering uncertainty called UTSM based on the model is also proposed. We validate the approach experimentally on both synthetic and real-world data and show that UTSM is not only more robust to noise and outliers but also more tolerant of different sample frequencies and asynchronous sampling of trajectories.

The relevance of geographic entities has long been the focus of research on geographic information retrieval, geographic knowledge graph, and recommendation systems. Traditional research methods use spatial similarity or semantic similarity to calculate the correlation strength between regions. The calculation process is complex and has certain one-sidedness and limitations, and it is difficult to reveal the essential characteristics of geographic entities. The rapid development of graph models and related algorithms provides researchers with new ideas. By constructing network topology, it focuses on the relationship between entities and is more suitable for mining potential correlations between entities. This study attempts to explore the geographic entity association of integrated semantics and spatial factors by using network mining algorithms. At the same time, unlike traditional semantic information, this paper uses text data as a source of semantically related information. Experiments show that this method can effectively represent geographical entity associations and reflect regional characteristics.

Road networks play a significant role in modern city management. It is necessary to continually extract current road structure, as it changes rapidly with the development of the city. Due to the success of semantic segmentation based on deep learning in the application of computer vision, extracting road networks from VHR (Very High Resolution) imagery becomes a method of updating geographic databases. The major shortcoming of deep learning methods for road networks extraction is that they need a massive amount of high quality pixel-wise training datasets, which is hard to obtain. Meanwhile, a large amount of different types of VGI (volunteer geographic information) data including road centerline has been accumulated in the past few decades. However, most road centerlines in VGI data lack precise width information and, therefore, cannot be directly applied to conventional supervised deep learning models. In this paper, we propose a novel weakly supervised method to extract road networks from VHR images using only the OSM (OpenStreetMap) road centerline as training data instead of high quality pixel-wise road width label. Large amounts of paired Google Earth images and OSM data are used to validate the approach. The results show that the proposed method can extract road networks from the VHR images both accurately and effectively without using pixel-wise road training data.

The traditional flood inundation algorithms generally adopt seed filling algorithm along with several improved serial methods to evaluate flooding region. When dealing with huge amount of data, some of these algorithms fail due to large recursive depth, others end up spending overmuch time in obtaining large flooding zone. Due to the dependency of digital terrain data in flooding analysis, few parallel flooding algorithms has been developed to improve the computational efficiency, which fails to make full use of the performance advantages of computer clusters. To solve above problems, this paper proposes a parallel flood inundation algorithm for massive DEM data. The algorithm presents a boundary component method using strip data partition and run length code to generate potential flooding area in parallel, after which it traverses all strips in sequence to gain whole flooding region. The computational efficiency of the proposed algorithm is verified by comparing it with the strip seed filling algorithm over practical DEM data. Meanwhile, the capability to process massive data of the proposed algorithm is proved by experimental results.

As an essential part of geographic information retrieval, gazetteer services are closely related to people's life quality. It is important to construct intelligent gazetteer service and improve its retrieval quality. Considering that the accuracy of document matching in large-scale data scenarios is relatively low and it is difficult to obtain the true intention of user queries, we propose a gazetteer retrieval method which takes into account the spatial relationship semantics. Firstly, the multivariable geo-location retrieval pattern of gazetteer service is defined as the basis for constructing the spatial relationship semantic model. Secondly, a measurement formula is given for calculating attribute similarity and spatial relationship similarity. In particular, we propose a similarity measurement approach that reconstructs geographical name entity so as to adapt the characteristics of non-point objects' spatial relationship. Finally, our proposal is evaluated on real-world datasets against traditional methods. The results reveal that the proposed method can not only enrich user's geo-location retrieval pattern, but also improve the effectiveness and quality of gazetteer services under the background of big data.

The relevance of geographic entities has always been the focus of research on geographic information retrieval, geographic knowledge graph and recommendation systems. Traditional research methods, which use spatial or semantic similarity to calculate the correlation between regions, have certain one-sidedness and limitations. The network topology can clearly represent the relationship between entities. However, semantic relationships are difficult to define, so there are few cases where network-related algorithms are used to solve the relevance of geographic entities. With the development of the Internet, web pages provide people with a huge amount of information, and geographical names as a key element are often ignored by researchers, and the rich semantic information contained in it needs further research. This study attempts to explore the geographic entity relevance of integrated semantics and spatial factors based on textual data from a network perspective. Based on the community mining algorithm, the experiment studies the aggregation characteristics of geographic entities and can find areas that are close to each other and tightly related, which is more satisfied with people's common sense.

In this paper, we propose a novel outlier detection method for robust manifold learning. First, we assume that the input high-dimensional data can be represented by an integration of local linear patches, and each patch consists of samples in the local neighborhood that maintains a linear relationship. Then, we use a hierarchical divisive clustering method to seek maximum linear patches (MLPs) and present a local density based scheme to detect outliers in each MLP. In order to evaluate the performance of outlier detection, we also propose an improved outlier detection evaluation method based on manifold distance, which is suitable for robust manifold learning. Last, we give several experiments to demonstrate the effectiveness of the proposed outlier detection method and evaluation method.

Rotation, anisotropic scaling, translation, outliers and noise are common problems in point set registration. In order to solve the point set registration under the above conditions, a robust weighted scaled iterative nearest point (WSICP) algorithm is proposed in this paper. Based on the Euclidean distance between point pairs, a weighted strategy of point pairwise is designed to reduce the influence of outliers and noise points on the solution of transformation matrix. Next, the brief and clear registration transform matrices of rotation, scale and translation are given. Experiments result show that our algorithm performs better than others on registration accuracy and convergence quality under scale stretching, outliers and noise case.

Robot is a research focus at present, and how to build and design a robot, the related model building is difficult. In this paper, a 10-DOF gymnastic robot is proposed and designed, which includes the head of the robot, the left and right two-DOF arm structure, the two-DOF waist structure and the left and right two-DOF leg structure. By establishing the dynamic model of a typical two-degree-of-freedom joint robot, a reasonable overall structure and model of the robot are designed, and the actual object of the robot is made. In this paper, the ATmega32 is used as the main controller. Through the software design, the corresponding gymnastic movements of the gymnastic robot are compiled, including two-handed push-ups, one-handed push-ups, handstand, roll forward and a series of actions. Through the application analysis of the actual robot, the feasibility and validity of the 10-DOF gymnastic robot model designed in this paper are verified. It can be widely used in teaching platform, scientific research and competitions.

Mine ventilation control system is an essential link in the mining and mining industry, especially in the working face which requires strict gas concentration. The ventilation state and gas content in the well are very important for the staff. Therefore, the control of mine ventilation has important theoretical significance and practical significance, especially the control of remote mine ventilation system has received special attention in recent years. In this paper, the network control technology is applied to study the control of the remote mine ventilation system, and the network scheduling algorithm is used to reduce the influence of network induced delay. The air flow state is controlled by the speed regulation of the ventilator, the stability of the air volume under the mine is guaranteed, and the safety and reliability of the mine are raised.

Satellite task planning not only plans the observation tasks to collect images of the earth surface, but also schedules the transmission tasks to download images to the ground station for users’ using, which plays an important role in improving the efficiency of the satellite observation system. However, most of the work to our knowledge, scheduling the observation and transmission tasks separately, ignores the correlation between them in resource (e.g., energy and memory) consumption and acquisition. In this paper, we study the single-satellite observation and transmission task planning problem under a more accurate resource usage model. Two preprocessing strategies including graph partition and nondominated subpaths selection are used to decompose the problem, and an improved label-setting algorithm with the lower bound cutting strategy is proposed to maximize the total benefit. Finally, we compare the proposed method with other three algorithms based on three data sets, and the experimental result shows that our method can find the near-optimal solution in much less time.

Although zero-watermarking can provide an effective and distortion-free scheme for image copyright protection, its robustness and discriminability do not meet expectations in existing methods. Some cannot resist effectively geometric attacks, others do not consider the discriminability and equalization. For that reason, this paper proposes a robust and distinguishable color image zero-watermarking algorithm based on polar harmonic transforms (PHTs) and compound chaotic map. In the proposed algorithm, firstly three PHTs moments of an image are computed simultaneously and accurate moments are selected for the robustness. Then, content-based binary feature sequence is acquired by judging the relation between magnitudes of adjacent moments for the discriminability. Finally, compound chaotic map is employed to encrypt copyright logo for ensuring security and scramble binary feature sequence for improving the equalization. Experimental results show that the proposed zero-watermarking algorithm has good equalization and discriminability, and an advantage in robustness compared with other zero-watermarking and traditional watermarking.

With the rapid development of satellite sensor technology and aerial photography technology, spatial and temporal resolution of the remote sensing image has been greatly improved. To speed up the visualization of remote sensing images, pyramid building technology is the best choice at present. However, the performance of existing methods is not as good as expected. Considering the load imbalance problem caused by the uneven data distribution problem, this paper proposes a fast tile-pyramid construction algorithm based on multilevel task parallelism. Our method changed the traditional parallel tile generation algorithm which is generated layer by layer and implemented a new algorithm that generated multiple layers at the same time by using the entire tile pyramid as a whole. Experimental results on real-life datasets show that our new algorithm can improve the construction speed of tile-pyramids.

Buffer and overlay analysis are fundamental operations which are widely used in Geographic Information Systems (GIS) for resource allocation, land planning, and other relevant fields. Real-time buffer and overlay analysis for large-scale spatial data remains a challenging problem because the computational scales of conventional data-oriented methods expand rapidly with data volumes. In this paper, we present HiBO, a visualization-oriented buffer-overlay analysis model which is less sensitive to data volumes. In HiBO, the core task is to determine the value of pixels for display. Therefore, we introduce an efficient spatial-index-based buffer generation method and an effective set-transformation-based overlay optimization method. Moreover, we propose a fully optimized hybrid-parallel processing architecture to ensure the real-time capability of HiBO. Experiments on real-world datasets show that our approach is capable of handling ten-million-scale spatial data in real time. An online demonstration of HiBO is provided (http://www.higis.org.cn: 8080/hibo).

Unmanned aerial vehicles (UAVs) have been increasingly used in earth observation, public safety, military and civilian applications due to its portability, high mobility and flexibility. In some GPS-denied environments, accurate drone position cannot be obtained due to occlusion, multi-path interference and other factors. While understanding and localization the content of the images is vital for earth observation, map revision, multi-source image fusion, disaster relief, smart city and other applications. The progress of computer vision and convolutional neural networks(CNNs) in image processing provide a promising solution to locate UAVs aerial image and mapping to the large-scale reference image. Firstly, key localization techniques based on image retrieval-----image description, image matching and position mapping are summarized considering the characteristics of UAVs aerial images. And then, image localization based on extracting deep semantic features and image localization based on classification method by subdividing areas are recommended. Throughout this paper, we will have an insight into the prospect of the UAVs image localization and the challenges to be faced.

Buffer analysis, a fundamental function in a geographic information system (GIS), identifies areas by the surrounding geographic features within a given distance. Real-time buffer analysis for large-scale spatial data remains a challenging problem since the computational scales of conventional data-oriented methods expand rapidly with increasing data volume. In this paper, we introduce HiBuffer, a visualization-oriented model for real-time buffer analysis. An efficient buffer generation method is proposed which introduces spatial indexes and a corresponding query strategy. Buffer results are organized into a tile-pyramid structure to enable stepless zooming. Moreover, a fully optimized hybrid parallel processing architecture is proposed for the real-time buffer analysis of large-scale spatial data. Experiments using real-world datasets show that our approach can reduce computation time by up to several orders of magnitude while preserving superior visualization effects. Additional experiments were conducted to analyze the influence of spatial data density, buffer radius, and request rate on HiBuffer performance, and the results demonstrate the adaptability and stability of HiBuffer. The parallel scalability of HiBuffer was also tested, showing that HiBuffer achieves high performance of parallel acceleration. Experimental results verify that HiBuffer is capable of handling 10-million-scale data.

Distant1 supervised relation extraction is a commonly adopted technique to extract relations from unstructured text. In distant supervision, an existing database is heuristically aligned to text and the alignment results are processed as labeled data. Comparing to hand-labeled data, distant supervision data is available in large quantity, but contains much more errors. In the past few years, Convolutional Neural Networks (CNNs) are applied to distant relation extraction and achieved remarkable results. However, standard CNN architectures do not reflect the multi-granularity nature of linguistic data, and have difficulties capturing long-term dependencies. We propose an architecture named Multi-Path Convolutional Network to address this problem. Inspired by the Inception module used in image recognition systems, we apply multiple convolution layers with different kernel size in parallel and combine the output with another deeper CNN sub-network. In addition, we utilize two levels of attention to discern valuable information from irrelevant context: a word-level attention to capture important parts of a sentence, and a sentence-level attention to improve classification from multiple sentences. By experiments, we show that our approach achieves outstanding results on the NYT-Freebase dataset and outperforms several existing approaches.

With the development of aerospace technologies, the mission planning of agile earth observation satellites has to consider several objectives simultaneously, such as profit, observation task number, image quality, resource balance, and observation timeliness. In this paper, a five-objective mixed-integer optimization problem is formulated for agile satellite mission planning. Preference-based multi-objective evolutionary algorithms, i.e., T-MOEA/D-TCH, T-MOEA/D-PBI, and T-NSGA-III are applied to solve the problem. Problem-specific coding and decoding approaches are proposed based on heuristic rules. Experiments have shown the advantage of integrating preferences in many-objective satellite mission planning. A comparative study is conducted with other state-of-the-art preference-based methods (T-NSGA-II, T-RVEA, and MOEA/D-c). Results have demonstrated that the proposed T-MOEA/D-TCH has the best performance with regard to IGD and elapsed runtime. An interactive framework is also proposed for the decision maker to adjust preferences during the search. We have exemplified that a more satisfactory solution could be gained through the interactive approach.

The mission planning of agile earth observation satellite (AEOS) involves multiple objectives to be optimized simultaneously. Total profit, observed target number, averaged image quality, satellite usage balance and averaged timeliness are the five objectives considered in this paper. The problem is a mixed-integer problem with constraints and belongs to the class of NP-hard problems. Two preference-based evolutionary algorithms, i.e., T-NSGA-III and T-MOEA/D, are proposed with problem-specific coding and decoding strategies to solve the problem. Target region, which is defined by preferred range of each objective, is used for preference articulation. Experiments show that the proposed algorithms can obtain Pareto optimal solutions within the target region efficiently. They outperform Pareto-based T-NSGA-II with regard to Hypervolume indicator and CPU runtime.

Bike sharing system is widely used in many cities. However, the imbalanced usage pattern of bicycles causes over-demand issue which affects user experience. Bike demand prediction is necessary as it is the basis of bike pre-allocation which can satisfy people's demand in advance. In this paper, we propose a hierarchical traffic prediction model to predict bike check-out/in number of each station cluster. Firstly, we conduct station clustering with iterative spectral clustering algorithm, since the pattern of bike usage of several stations close to each other is more regular compared with that of a single station. Then, we adopt gradient boosting regression tree to predict the total check-out number of the whole bike sharing system. Thirdly, each cluster's check-out number is inferred based on its predicted proportion in the total check-out number. Fourthly, we propose inter-cluster transition proportion model which can describe the bike rent-return relationships between cluster pairs and predict check-in numbers of clusters. Finally, we evaluate our prediction model with data from Citi Bike System in New York City. Experiment results show that our prediction method can achieve more accurate and reasonable result compared with existing work.

We interpret the geographic world as a combination of geographic entities (such as city, road, river). Using these geographic entities as the basic granularity for description, storage and manipulation, therefore, can provide a bridge between conceptual understanding and practical application. However, the issue arises of how to design a data model that is generic enough for the geographic entities when the data can change spatially and temporally. This difficulty is compounded when there is a need for geographic inference. In this paper, we offer a feasible solution by presenting a Spatio-Temporal Data Model of Geographic Entities (STDMGE), which describes each geographic entity as geographic object part and geographic relation part, both of which are well designed to organize the multi-source data (traditional geospatial data, sensor data, relationship data among geographic entities, etc.). Spatial-temporal changes can be accurately expressed and efficiently implemented using this model. Moreover, the formal description of geographic rules and events are incorporated in the data model for the possible future requirements of geographic reasoning. We further illustrate the data model by applying it to the case study of the river data.

With the development of the Internet and the enhanced rendering ability of browser end, electronic map based on the Internet, which is called web map, has been visited and plotted by more and more users. Normally, the representation of the plotting results such as the markers and curves are changed with the map level, and the traditional method is to take a strategy to select the composition points. In this paper, instead, an adaptive sampling method of plotting curves which preserves the characteristic points is proposed and a relationship between map level and the number of sampling points is established based on the Radical Law in cartography. Experiments are conducted to compare the proposed sampling method with others to validate the simplicity and accuracy. The result indicates that the proposed method can realize the sampling of plotting curves on the web map at different levels in terms of simplicity and accuracy for the multi-level representation.

With the increasing pervasiveness of basic facilitate of transportation and information, the need of multimodal route planning is becoming more essential in the fields of communication and transportation, urban planning, logistics management, etc. This article mainly described an OSM-oriented method of multimodal route planning. Firstly, it introduced how to extract the information we need from OSM data and build proper network model and storage model; then it analysed the accustomed cost standard adopted by most travellers; finally, we used shortest path algorithm to calculate the best route with multiple traffic means.

Incorporating decision makers' preferences is of great significance in multiobjective optimization. Target region-based multiobjective evolutionary algorithms (TMOEAs), aiming at a well-distributed subset of Pareto optimal solutions within the user-provided region(s), are extensively investigated in this paper. An empirical comparison is performed among three TMOEA instantiations: T-NSGA-II, T-SMS-EMOA and T-R2-EMOA. Experimental results show that T-SMS-EMOA has the best overall performance regarding the hypervolume indicator within the target region, while T-NSGA-II is the fastest algorithm. We also compare TMOEAs with other state-of-the-art preference-based approaches, i.e., DF-SMS-EMOA, RVEA, AS-EMOA and R-NSGA-II to show the advantages of TMOEAs. A case study in the mission planning of earth observation satellite is carried out to verify the capabilities of TMOEAs in the real-world application. Experimental results indicate that preferences can improve the searching ability of MOEAs, and TMOEAs can successfully find nondominated solutions preferred by the decision maker.

The buffer generation algorithm is a fundamental function in GIS, identifying areas of a given distance surrounding geographic features. Past research largely focused on buffer generation algorithms generated in a stand-alone environment. Moreover, dissolved buffer generation is data- and computing-intensive. In this scenario, the improvement in the stand-alone environment is limited when considering large-scale mass vector data. Nevertheless, recent parallel dissolved vector buffer algorithms suffer from scalability problems, leaving room for further optimization. At present, the prevailing in-memory cluster-computing framework—Spark—provides promising efficiency for computing-intensive analysis; however, it has seldom been researched for buffer analysis. On this basis, we propose a cluster-computing-oriented parallel dissolved vector buffer generating algorithm, called the HPBM, that contains a Hilbert-space-filling-curve-based data partition method, a data skew and cross-boundary objects processing strategy, and a depth-given tree-like merging method. Experiments are conducted in both stand-alone and cluster environments using real-world vector data that include points and roads. Compared with some existing parallel buffer algorithms, as well as various popular GIS software, the HPBM achieves a performance gain of more than 50%.

With the development of aerospace science and technology, Earth Observation Satellite cluster which consists of heterogeneous satellites with many kinds of payloads appears gradually. Compared with the traditional satellite systems, satellite cluster has some particular characteristics, such as large-scale, heterogeneous satellite platforms, various payloads, and the capacity of performing all the observation tasks. How to select a subset from satellite cluster to perform all observation tasks effectively with low cost is a new challenge arousing in the field of aerospace resource scheduling. This is the agent team formation problem for observation task-oriented satellite cluster. A mathematical scheduling model is built. Three novel algorithms, i.e., complete search algorithm, heuristic search algorithm, and swarm intelligence optimization algorithm, are proposed to solve the problem in different scales. Finally, some experiments are conducted to validate the effectiveness and practicability of our algorithms.

Point-of-interest (POI) recommendation is an important part of recommendation systems in location-based social networks. Most existing POI recommendation systems, such as collaborative filtering based and context-aware methods, usually use hand-designed or manually selected features to achieve the recommendation. However, the information in the location-based social networks has very complicated relationships with each other, e.g., the latent relationships among users, POIs and user preferences, thus leading to poor recommendation accuracy. We propose a two-stage method to address this problem. In the first stage, user and POI profiles are abstracted using statistical methods. Then in the second stage, a deep neural network (DNN) is used to predict ratings on these candidate POIs, and finally the topN list of POIs is obtained. Experimental results on the Gowalla and Brightkite dataset show the effectiveness of our DNN based recommendation method.