CN111033411A - Coarse-grained multi-layer flow information dynamics for multi-scale monitoring - Google Patents

Coarse-grained multi-layer flow information dynamics for multi-scale monitoring Download PDF

Info

Publication number
CN111033411A
CN111033411A CN201880052092.4A CN201880052092A CN111033411A CN 111033411 A CN111033411 A CN 111033411A CN 201880052092 A CN201880052092 A CN 201880052092A CN 111033411 A CN111033411 A CN 111033411A
Authority
CN
China
Prior art keywords
region
interest
cluster
controlling
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201880052092.4A
Other languages
Chinese (zh)
Inventor
倪康宇
T-C·卢
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
HRL Laboratories LLC
Original Assignee
HRL Laboratories LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by HRL Laboratories LLC filed Critical HRL Laboratories LLC
Publication of CN111033411A publication Critical patent/CN111033411A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • G05B19/0426—Programming the control sequence
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B15/00—Systems controlled by a computer
    • G05B15/02—Systems controlled by a computer electric
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
    • G05B23/0216—Human interface functionality, e.g. monitoring system providing help to the user in the selection of tests or in its configuration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G06V10/422—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation for representing the structure of the pattern or shape of an object therefor
    • G06V10/426—Graphical representations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Automation & Control Theory (AREA)
  • Multimedia (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • Discrete Mathematics (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • Complex Calculations (AREA)
  • Traffic Control Systems (AREA)

Abstract

A system for multi-scale monitoring is described. During operation, the system receives monitoring data for a scene having a plurality of zones. The monitoring data includes an object flow tensor V representing a plurality of objects flowing from one region to another region at time t and an object communication tensor C representing a plurality of communications transmitted from one region to another region at time t. The system then determines cluster members for the plurality of zones. Dependency links between the communication and the flow are then determined. Based on the dependency links, at least one cluster of one or more regions is designated as a region of interest, which allows the system to control the device based on the designated region of interest.

Description

Coarse-grained multi-layer flow information dynamics for multi-scale monitoring
Government rights
The invention was made with government support under U.S. government contract number PC 1141899 signed by the national reconnaissance office via the boeing company. The government has certain rights in the invention.
Cross Reference to Related Applications
This application is a continuation-in-part application of U.S. application No.15/497,202 filed on 25.4.2017, which is a non-provisional application of U.S. provisional application No.62/376,220 filed on 17.8.2016, the entire contents of which are incorporated herein by reference.
This application is also a non-provisional patent application of U.S. provisional application No.62/557,733 filed on 12.9.2017, which is incorporated herein by reference in its entirety.
Background of the invention
(1) Field of the invention
The present invention relates to monitoring systems, and more particularly, to systems for dynamic multi-scale monitoring using coarse-grained multi-layer flow information.
(2) Description of the related Art
Monitoring systems are commonly used to observe and monitor a wide variety of complex systems. While monitoring a single data source appears to be simple, monitoring a large scale heterogeneous data source is exceptionally complex and error prone. Some prior art techniques (see list of incorporated references, reference No.4) were developed to provide new capabilities for analyzing multiple heterogeneous data sources using a multi-layered information dynamic framework, while other prior art techniques (see reference nos. 2 and 5) only consider a single data source.
While attempts have been made to understand large-scale heterogeneous data, the prior art still lacks the ability to extend a multi-tiered information dynamic framework to model multiple scales (e.g., spatial scales) so that limited computing resources can be efficiently utilized. Therefore, there is a continuing need for a system that dynamically performs multi-scale monitoring using coarse-grained multi-layer flow information to allow efficient resource allocation.
Disclosure of Invention
The present disclosure provides a system for multi-scale monitoring. In various aspects, the system includes a memory and one or more processors, the memory being a non-transitory computer-readable medium encoded with executable instructions such that, when the instructions are executed, the one or more processors perform operations such as receiving monitoring data of a scene having a plurality of zones, the monitoring data having an object flow tensor V representing a plurality of objects flowing from one zone to another zone at a time t and an object communication tensor C representing a plurality of communications sent from one zone to another zone at the time t; determining cluster members for the plurality of zones; determining a dependency link between the communication and the flow; designating at least one cluster of one or more regions as a region of interest based on the dependency links; and controlling the device based on the region of interest.
In another aspect, determining cluster members for the plurality of zones further comprises: constructing an adjacency matrix A based on the object flow tensor V; the adjacent matrix A is symmetrical; solving a non-negative matrix factorization of the symmetric adjacency matrix; and assigning a cluster member of the object in each of the plurality of zones to generate the cluster member.
In yet another aspect, determining a dependency link between a communication and a flow further comprises the operations of: constructing a low resolution stream tensor based on the cluster members by merging ship streams V within each cluster; determining a stream transfer entropy; and identifying the dependency links and dependent clusters by thresholding.
Additionally, designating at least one cluster of one or more regions as a region of interest based on the dependency links comprises: designating the subordinate cluster as a region of interest.
In another aspect, controlling the apparatus based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
Further, controlling the apparatus based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
Finally, the present invention also includes a computer program product and a computer-implemented method. The computer program product includes computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having one or more processors such that, when the instructions are executed, the one or more processors perform the operations listed herein. Alternatively, the computer-implemented method includes acts that cause a computer to execute such instructions and perform the resulting operations.
Drawings
The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the office upon request and payment of the necessary fee.
The objects, features and advantages of the present invention will be apparent from the following detailed description of the various aspects of the invention, taken in conjunction with the accompanying drawings in which:
FIG. 1 is a block diagram depicting components of a system according to various embodiments of the invention;
FIG. 2 is an exemplary diagram of a computer program product embodying an aspect of the present invention;
FIG. 3 is a flow diagram depicting a process for multi-scale monitoring according to various embodiments of the invention;
FIG. 4 is a multi-layer information dynamics model for finding cross-layer active dependencies, in accordance with various embodiments of the present invention;
FIG. 5 is a schematic illustration of a hybrid coarse-scale multi-layer network;
FIG. 6 is an illustrative diagram depicting how multiple spatial scales of a multi-layered information dynamic framework provide the ability to zoom into a region of interest;
FIG. 7 is a schematic illustration of discovering inter-layer dependencies;
FIG. 8 is an illustration showing that flow clustering summarizes ship flows and reduces the number of flows;
FIG. 9A is an example of a ship flowsheet at full resolution;
FIG. 9B is an example of a ship flowsheet at low resolution;
FIG. 9C is an example of a ship flowsheet depicting a multi-scale version; and
fig. 10 is a block diagram depicting control of an apparatus according to various embodiments.
Detailed Description
The present invention relates to monitoring systems, and more particularly, to systems for dynamic multi-scale monitoring using coarse-grained multi-layer flow information. The following description is presented to enable any person skilled in the art to make and use the invention and is incorporated in the context of a particular application. Various modifications, as well as numerous uses of various aspects, will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to a wide variety of aspects. Thus, the present invention is not intended to be limited to the aspects shown, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
In the following detailed description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. However, it will be apparent to one skilled in the art that the present invention may be practiced without necessarily being limited to these specific details. In other instances, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring the present invention.
The reader is also directed to all documents and documents which are filed concurrently with this specification and which are open to public inspection with this specification, the contents of all such documents and documents being incorporated herein by reference. All the features disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Thus, unless expressly stated otherwise, each feature disclosed is one example only of a generic series of equivalent or similar features.
Moreover, any element in the claims that does not explicitly recite "a means for performing a specified function" or "a step for performing a particular function" should not be construed as an "means" or "a step" clause as specified in section 6 of 35 u.s.c.112. In particular, use of "step … …" or "action of … …" in the claims herein should not trigger the provisions of section 6 of 35 u.s.c.112.
Prior to describing the present invention in detail, a list of cited references is first provided. Next, a description is provided of various main aspects of the present invention. The introduction then provides the reader with a general understanding of the present invention. Finally, specific details of various embodiments of the invention are provided to enable an understanding of the specific aspects.
(1) List of incorporated references
The following references are cited throughout this application. For clarity and convenience, these references are listed herein as the central resource of the reader. The following references are incorporated by reference as if fully set forth herein. These references are incorporated by reference in the present application by reference to the corresponding reference numbers:
1.Batty,Michael,et al."Entropy,complexity,and spatial information."Journal of geographical systems 16.4(2014):363-385.
2.J.Borge-Holthefer,N.Perra,B.Goncalves,S.Gonzalez-Bailon,A.Arenas,Y.Moreno,and A.Vespignani.The dynamics of information-driven coordinationphenomena:A transfer entropy analysis,Science Advance,2:5,e1501158,2016.
3.Ding,Chris,Xiaofeng He,and Horst D.Simon."On the equivalence ofnonnegative matrix factorization and spectral clustering."Proceedings of the2005SIAM International Conference on Data Mining.Society for Industrial andApplied Mathematics,2005.
U.S. patent application No.15/497,202 entitled "Multi layer Information Dynamics for Activity and Behavior Detection" filed on 25.4.4. 4.2017
5.N-K.Ni and T-C.Lu,Information Dynamic Spectrum Characterizes SystemInstability toward Critical Transitions,EPJ Data Science,3:28,2014
6.T.Schreiber,Measuring information transfer.Phys Rev Lett 2000,85(2):461–464.10.1103/PhysRevLett.85.461
7.C.E.Shannon,A Mathematical Theory of Communication".Bell SystemTechnical Journal 27(3):379–423,1948.
8.Shi,Lei,Hanghang Tong,Jie Tang,and Chuang Lin."Vegas:Visualinfluence graph summarization on citation networks."IEEE Transactions onKnowledge and Data Engineering 27.12(2015):3417-3431.
9.Vandaele,A.,Gillis,N.,Lei,Q.,Zhong,K.,&Dhillon,I."Efficient andnon-convex coordinate descent for symmetric nonnegative matrixfactorization."IEEE Transactions on Signal Processing 64.21(2016):5571-5584.
(2) Main aspects of the invention
Various embodiments of the present invention include three "primary" aspects. The first main aspect is a system for multi-scale monitoring. The system typically takes the form of the operating software of a computer system or the form of a "hard-coded" instruction set. The system may be incorporated into a wide variety of devices that provide different functions. The second main aspect is a method, usually in the form of software, operating with a data processing system (computer). A third main aspect is a computer program product. The computer program product generally represents computer readable instructions stored on a non-transitory computer readable medium such as an optical storage device (e.g., a Compact Disc (CD) or a Digital Versatile Disc (DVD)) or a magnetic storage device (e.g., a floppy disk or a magnetic tape). Other non-limiting examples of computer readable media include: hard disks, Read Only Memories (ROMs), and flash memory type memories. These aspects will be described in more detail below.
A block diagram illustrating an example of the system of the present invention, namely computer system 100, is provided in fig. 1. The computer system 100 is configured to perform calculations, processes, operations, and/or functions associated with a program or algorithm. In one aspect, certain processes and steps discussed herein are implemented as a series of instructions (e.g., a software program) residing in a computer readable memory unit and executed by one or more processors of the computer system 100. When executed, the instructions cause the computer system 100 to perform particular actions and exhibit particular behaviors, as described herein.
Computer system 100 may include an address/data bus 102 configured to communicate information. In addition, one or more data processing units, such as a processor 104 (or multiple processors), are coupled to the address/data bus 102. The processor 104 is configured to process information and instructions. In an aspect, the processor 104 is a microprocessor. Alternatively, the processor 104 may be a different type of processor, such as a parallel processor, an Application Specific Integrated Circuit (ASIC), a Programmable Logic Array (PLA), a Complex Programmable Logic Device (CPLD), or a Field Programmable Gate Array (FPGA).
Computer system 100 is configured to utilize one or more data storage units. The computer system 100 may include a volatile memory unit 106 (e.g., random access memory ("RAM"), static RAM, dynamic RAM, etc.) coupled to the address/data bus 102, wherein the volatile memory unit 106 is configured to store information and instructions for the processor 104. The computer system 100 may also include a non-volatile memory unit 108 (e.g., read only memory ("ROM"), programmable ROM ("PROM"), erasable programmable ROM ("EPROM"), electrically erasable programmable ROM ("EEPROM"), flash memory, etc.) coupled to the address/data bus 102, wherein the non-volatile memory unit 108 is configured to store static information and instructions for the processor 104. Alternatively, the computer system 100 may execute instructions retrieved from an online data storage unit, such as in "cloud" computing. In an aspect, computer system 100 may also include one or more interfaces, such as interface 110, coupled to address/data bus 102. The one or more interfaces are configured to enable computer system 100 to connect with other electronic devices and computer systems. The communication interfaces implemented by the one or more interfaces may include wired (e.g., serial cable, modem, network adapter, etc.) and/or wireless (e.g., wireless modem, wireless network adapter, etc.) communication technologies.
In one aspect, computer system 100 may include an input device 112 coupled to address/data bus 102, wherein input device 112 is configured to communicate information and command selections to processor 100. According to one aspect, the input device 112 is an alphanumeric input device (e.g., a keyboard) that may include alphanumeric and/or function keys. Alternatively, the input device 112 may be other input devices besides alphanumeric input devices. In one aspect, the computer system 100 may include a cursor control device 114 coupled with the address/data bus 102, wherein the cursor control device 114 is configured to communicate user input information and/or command selections to the processor 100. In one aspect, cursor control device 114 is implemented with a device such as a mouse, a trackball, a trackpad, an optical tracking device, or a touch screen. Nonetheless, in one aspect, cursor control device 114 is directed and/or enabled via input from input device 112, for example, in response to using special keys and key sequence commands associated with input device 112. In another aspect, cursor control device 114 is configured to be directed or guided by voice commands.
In an aspect, computer system 100 may also include one or more optional computer usable data storage devices, such as storage device 116, coupled to address/data bus 102. Storage device 116 is configured to store information and/or computer-executable instructions. In one aspect, storage device 116 is a storage device such as a magnetic or optical disk drive (e.g., hard disk drive ("HDD"), floppy disk, compact disk read only memory ("CD-ROM"), digital versatile disk ("DVD")). According to one aspect, a display device 118 is coupled with the address/data bus 102, wherein the display device 118 is configured to display video and/or graphics. In one aspect, display device 118 may include: a cathode ray tube ("CRT"), a liquid crystal display ("LCD"), a field emission display ("FED"), a plasma display, or any other display device suitable for displaying video and/or graphic images, as well as alphanumeric characters recognizable to a user.
Computer system 100 presented herein is an example computing environment in accordance with an aspect. However, a non-limiting example of computer system 100 is not strictly limited to being a computer system. For example, one aspect provides that computer system 100 represents a type of data processing analysis that may be used in accordance with various aspects described herein. Other computing systems may also be implemented. Indeed, the spirit and scope of the present technology is not limited to any single data processing environment. Thus, in one aspect, computer-executable instructions (e.g., program modules) executed by a computer are used to control or implement one or more operations of the various aspects of the technology. In one implementation, such program modules include routines, programs, objects, components, and/or data structures that are configured to perform particular tasks or implement particular abstract data types. In addition, one aspect provides for implementing one or more aspects of the technology by utilizing one or more distributed computing environments, where tasks are performed by remote processing devices that are linked through a communications network, for example, or where various program modules are located in both local and remote computer storage media including memory-storage devices.
An illustrative diagram of a computer program product (i.e., a storage device) embodying the present invention is shown in FIG. 2. The computer program product is shown as a floppy disk 200 or an optical disk 202 such as a CD or DVD. However, as previously mentioned, the computer program product generally represents computer readable instructions stored on any compatible non-transitory computer readable medium. The term "instructions," as used with respect to the present invention, generally indicates a set of operations to be performed on a computer, and may represent a fragment of an entire program or a single, separable software module. Non-limiting examples of "instructions" include computer program code (source or object code) and "hard-coded" electronic devices (i.e., computer operations encoded into a computer chip). "instructions" are stored on any non-transitory computer readable medium, such as on a floppy disk, CD-ROM, and flash drive or in the memory of a computer. Regardless, the instructions are encoded on a non-transitory computer readable medium.
(3) Introduction to the design reside in
The present disclosure provides a unique multi-scale multi-layer graph framework for information dynamics that analyzes and monitors different types of activities and dynamic relationships. Based on time series of different types of observables (or measurements), multi-scale multi-layer graph representations for information dynamics can be used to detect and infer their dependencies, which cannot be directly observed (or measured). The multiple spatial scale equations of the framework allow the construction of activity and dynamics adaptive multi-layer maps to reduce measurement requirements while maintaining analysis performance. A key aspect of implementing the multiple spatial scales within the information dynamic framework is a flow rate optimization method that merges graph nodes into clusters. The activity can then be summarized on a coarse-grained graph derived from a derived cluster of multiscale, which in turn allows the system to hint the region of interest for multiscale monitoring of the system's dynamics.
It is an object of the present invention to efficiently direct computing resources to monitor and analyze activity occurring from multiple sources at multiple scales. On the basis of the multi-layer information dynamic framework of the team, the new characteristics of the multi-scale multi-layer dynamic information have two advantages: 1) it reduces the amount of computation without losing the ability to find active dependencies. Coarse resolution corresponds to sparse activity dependency; thus, it provides better abstraction and enables overlay of larger graphs. 2) It has the ability to zoom in or out on the region of interest to provide better feasible insight for analysts or other system operations.
The system described herein may be deployed in cloud computing infrastructure as an embedded decision support module, or as an independent system for the application domain of complex systems, such as intelligence monitoring and reconnaissance (ISR) for perceiving maritime activity situations (as shown), crisis management, social turbulence, and financial markets. Successful deployment of this technology is expected to bring about detection and inference of system behavior, activity, and dependencies. More detailed information is provided below.
(4) Details of various embodiments
(4.1) method overview: multi-layer information dynamics with multiple (spatial) scales
The present disclosure provides a multi-scale multi-layer graph representation for information dynamics that detects and infers their dependencies from a time series of different observable (or measurement) modalities that cannot be directly observed (or measured). Multiple spatial scales within the information dynamics framework are developed using a flow rate optimization model that merges graph nodes into clusters. This process is further illustrated in fig. 3. More specifically, fig. 3 illustrates a flow diagram depicting a process for multi-scale monitoring including a stream clustering process 300 that receives inputs as ship stream tensors and generates cluster members, followed by a multi-scale multi-tier information dynamic process 302 that provides dependency links, dependent clusters, and corresponding multi-scale streams. More detailed information on these processes is provided below.
(4.2) mixed coarse-scale multilayer network: example scene (maritime affairs activity)
For further understanding, the following provides example scenarios related to monitoring maritime activity. As shown in fig. 4, at the top level 400 of a multi-layer network, signals are communication activities between nodes 402 (or zones). Node 402 represents a region or area of certain locations, such as a dedicated economic zone, a port, etc. These are time series of each pair of nodes 402 that measure the amount of collective communication activity between those zones (all vessels within each zone). On the bottom layer 404, the signal is the ship flow between nodes, representing the number of ships flowing from one zone to another over a period of time. How communication activity affects ship flow can be modeled as follows:
Figure BDA0002381929590000081
wherein G is1Showing a ship's view, G2The communication diagram is shown, t represents time, epsilon represents reaction time delay, V represents ship density, α represents diffusion constant, and β represents a coefficient for weighting communication information.
The semi-discrete (time continuous and space discrete) partial differential equation describes the variation of vessel density (left side) as a function of 1) with a vessel map G1The graph laplacian of, and 2) diffusion of the vessel with the graph from communication graph G2With a small reaction time delay epsilon. The number of the model generatedIn a manner whereby ship flow between certain zones is dependent on communication activity.
The goal of this multi-layered information framework is to discover hidden dependencies between ship flows and communication activities (input data is a time series of these) without knowing the model (the equations above) that generated the data. This approach is demonstrated using stream passing entropy (defined below in the stream passing entropy section) to detect hidden dependencies, i.e., the identification of ship streams that depend on certain communication activities.
The multi-layered information dynamic framework extends to multiple spatial scales. As described above, the advantage of extending the framework to multiple spatial scales is that the framework is simplified and the computational effort is reduced without losing the ability to find dependencies (as shown in FIG. 5) and providing the ability to enlarge the region of interest (as shown in FIG. 6). In particular, fig. 5 provides a schematic illustration of a hybrid coarse-scale multilayer network. The original scale 500 of the multi-layer network on the left is processed by a novel stream clustering algorithm to maximize the observed stream rate (middle) and generate clusters 502 (rectangular boxes), which clusters 502 in turn enable cross-layer dependency computation between the stream dependencies of the clustered entities (simplified edges on the right).
The region of interest 504 is identified by a cross-layer dependency link 506 (directed edge). As shown on the right side of FIG. 5, all regions adjacent to the cross-layer dependency link 506 are identified as regions of interest 504. In this simplified illustration, the only region that is not a region of interest is the lower right region 508.
Additionally, FIG. 6 provides a schematic illustration of the zoom in and zoom out capabilities. The coarse-scale multi-layer network 504 also enables zooming in to a specified node, such as a selected square node 600, which enables the zoomed-in selected node 602. As shown, in this example, the enlarged selected node 602 contains 7 nodes. Based on this, stream clustering process 604 may continue to provide another level of finer-grained clusters 606.
(4.3) ship flow clustering:
assume ship flowsheet G1Is A ═ aij)i,j＝1,…,NI.e. aijRepresenting the amount of vessel flowing from zone i to zone j. One approach to multiple spatial scales is to apply stream clustering to merge nodes into k clusters picAnd c 1,2, …, k, which emphasizes the largest within and across clusters
Figure BDA0002381929590000091
A stream ξs，
Figure BDA0002381929590000092
Stream ξsIs from the cluster pic(s)Node-to-cluster pi in (1)d(s)Set of all links of the node in flow ξsThe flow rate of (a) is defined as:
Figure BDA0002381929590000101
wherein v represents a node, c(s) represents a starting node, d(s) represents a final node, i and j represent zones i and j, respectively, wherein aijRepresenting the amount of vessel flowing from zone i to zone j. The stream clustering problem is proposed to find k clusters, which makes
Figure BDA0002381929590000109
The sum of the flow rates in the largest intra-cluster or inter-cluster flows is maximized. Number of clusters k and number of streams
Figure BDA00023819295900001010
Is predefined. The flow rate maximization problem is an optimization problem as follows:
Figure BDA0002381929590000102
the solution to this problem can be approximated using kernel k-means clustering (see reference No.8), since both aim to maximize the weighted sum of the graph adjacency matrix entries. The kernel k-means clustering is equivalent to symmetric Nonnegative Matrix Factorization (NMF) (see reference No.3), and can be efficiently solved by a coordinate descent method (see reference No. 9).
Let M be the symmetric matrix of the ship flow adjacency matrix a: m is A + AT. The aim of the symmetrical NMF is to find
Figure BDA0002381929590000103
Minimized with non-negative entry HijA ≧ 0 Nxk matrix H (where k < N), wherein |FRepresenting the Frobenius norm.
The difference between the problem addressed here and that in reference No.8 is as follows: the problem summarizes the more general directed graph, and reference No.8 summarizes the impact flow from a single source node in the reverse publication citation graph. In the problem addressed by the present disclosure, the number of sources may be arbitrary.
(4.4) stream transfer entropy
For ships and communication, from region RiTo the region RjThe streams of (a) are respectively represented as:
Figure BDA0002381929590000104
and
Figure BDA0002381929590000105
the present approach aims to capture the dependencies of these flows (edges) and their variation across different types of flows. Sensor data (e.g., from aircraft, satellites, etc.) may be used to obtain a time series of in-layer edges observed for each layer (e.g., vessel flow over a fixed time interval varies over time). For i ═ j, the time series will be the density of vessels and communications in each region of the layer:
Figure BDA0002381929590000106
and
Figure BDA0002381929590000107
from these stream time series, the 0 break-off inter-layer relationships. Since this method aims to find the dependency of the flows from one layer to another, the inter-layer edge is between a pair of flows from different layers (as shown in fig. 7). The dependencies are determined by computing the ATE:
Figure BDA0002381929590000108
therefore, these are called stream transfer entropy.
FIG. 7 provides a schematic illustration of discovering inter-layer dependencies: the communication flow between node 1 and node 12 in the upper panel 700 affects the ship flow on the path of node 1 → 4 → 8 → 12 in the bottom panel 702. ATE methods automatically infer such flow dependencies (edges) between layers.
(4.5) stream clustering algorithm
As shown in fig. 3, the stream clustering process 300 receives inputs as ship stream tensors and generates cluster members based thereon. This process is provided below and further depicted in fig. 3:
inputs V and k: NxNxT ship flow tensor V, wherein each entry VijtRepresenting the amount of the vessel flowing from node i to node j at time t. The number of clusters k.
1. The N × N adjacency matrix a is obtained by summing over time: a. theij＝∑tVijt。
2. By M ═ A + ATThe matrix a is symmetric.
3. Solving symmetric NMF problems
Figure BDA0002381929590000111
H is an N × k matrix.
4. Assigning cluster members, represented by an Nx 1 vector d, where the ith entry is di＝argmaxjHi(j) I.e. Hi(line i of H) the argument of the largest entry.
And (3) outputting d: an N1 vector d representing cluster members with entries from {1,2, …, k }.
(4.6) Ship flow clustering example results
A ship stream clustering process is performed using a set of data to validate the system and process. Examples are provided below illustrating stream clustering to summarize ship streams and reduce the number of streams. The example diagram in fig. 8 is a 10 x 10 regular grid (thus 100 nodes) 800 with three primary communications from node 3 to node 77, from node 35 to node 77, and from node 59 to node 77. The communication frequency of these is 5%, i.e. if the sampling rate is per minute, there are on average 5 active states per 100 minutes. There is also noisy communication at a frequency of 2%, with a pair of nodes randomly selected at a time. The vessel flow is simulated using the partial differential equations described above and the vessel density at each node is randomly initialized. Grid 800 shows the corresponding ship flows for the primary communication. Fig. 8 also depicts a ship stream clustering result 802 with 10 clusters, where each cluster is color-coded (nodes with the same color are clusters). A ship flow summary 804 is also depicted, which shows a generalized version of the ship flow in the grid 800. A ship flow summary 804 is indicated by a directed edge, indicating that the number of flows is decreasing.
(4.7) Multi-Scale Multi-layer information dynamic Algorithm
The system described herein utilizes low resolution to detect communication and vessel flow dependencies and TE to hint the region of interest for multi-scale monitoring (depicted as element 302 in fig. 3). This process will be described in further detail below:
inputs V, C and k: NxNxT ship flow tensor V, wherein the item VijtRepresenting the amount of the vessel flowing from node i to node j at time t. NxNxT communication tensor C, where entry CijtRepresenting the amount of communication from node i to node j at time t. The number of clusters is k.
1. The cluster member vector d is obtained using the stream clustering algorithm above.
2. By merging the ship flows V within each cluster, a low-resolution ship flow tensor W (having a size of k × k × T) is constructed from the cluster member vectors d.
3. Calculating the flow passing entropy from C to W:
Figure BDA0002381929590000121
4. by thresholding ATEij→klDependency links are identified to obtain dependent clusters.
5. The dependent clusters (to which the dependency links point) are enlarged (e.g., back to the original high resolution) and the low resolution of the independent clusters is maintained.
And outputting the dependency links, the dependent clusters and the corresponding multi-scale streams.
The output provides a unique abstraction and representation of the stream dependencies that enables decision tools (e.g., situational awareness tools that monitor vessel ingress and egress to disputed waters) to support exploratory analysis (e.g., exploring to high flow entropy regions based on dependent cluster depth) to refine the analysis unit for tracking purposes (e.g., using corresponding multi-scale streams and corresponding dependency links).
(4.8) multiscale multi-layer information dynamic example results
Multi-scale multi-tier information dynamic processing is performed with the clustered data to further validate the system and process. Fig. 9A-9C depict examples of multi-scale multi-layer information dynamic frameworks. Specifically, fig. 9A is a snapshot of a ship flow 900 with a full resolution 10 x 10 grid (100 nodes), where the thickness of the links represents the amount of ships flowing from one node to another. Fig. 9B is a snapshot of the generalized ship flow 902 on the flow cluster map, where 100 nodes are reduced to 10 clusters, providing a low resolution flow (after clustering). As shown in fig. 9C, after the ATE is applied to the low resolution ship flow, a multi-scale ship flow graph 904 is generated. In this regard, the region of interest may be prompted for multi-scale vessel flow monitoring. For example, the system may zoom into a region of interest while maintaining adequate monitoring of low regions of interest. Fig. 9C provides a snapshot of the multi-scale ship flow 904, with the dependent clusters (depending on the communication) having the original resolution, and the rest having a low resolution.
And (4.9) controlling the device.
As shown in fig. 10, the processor 104 may be used to control a device 1000 (e.g., a mobile device display, a virtual reality display, an augmented reality display, a computer monitor, a motor, a machine, a drone, a camera, etc.) based on generating a multi-scale ship flow graph. For example, movement of a drone or other autonomous vehicle to an area in a multi-scale vessel flow graph may be controlled based on identified dependent flows/clusters or their changes over time. For example, prior to deploying drones to a disputed body of water, the system may generate a multi-scale ship map by applying an algorithm to data collected via satellites, determine regions of interest with thresholds (e.g., significant deviations/changes in flow dependencies within an a priori determined time window), and dispatch drones to the regions of interest to collect finer grained data, or perform monitoring and tracking at a desired coverage level (e.g., zone size) for a given constraint (e.g., number of drones available, processing power, etc.). In still other embodiments, the camera may be controlled to be oriented toward the region of interest and zoomed in as desired. In other words, the actuator or motor is activated to move or zoom the camera (or sensor) over the region of interest. For example, the system may be connected to or otherwise incorporated into a satellite as a primary monitoring (more comprehensive, passive) so that upon identifying a region of interest, a monitoring device (camera, sensor, etc.) may be focused or otherwise zoomed into the region of interest. In the drone example, the drone is more active and provides fine grained monitoring (especially in occlusion states according to opponent's intentions and actions). Thus, a drone or unmanned aerial vehicle may be caused to pilot or otherwise move to an area of interest for further monitoring.
Finally, while the invention has been described in terms of several embodiments, those of ordinary skill in the art will readily recognize that the invention can have other applications in other environments. For example, although the system is described in relation to an ocean-going vessel, the system is not intended to be so limited, but may be equally applied to areas where objects may move, such as cars on the street, people on the battlefield, and the like. It should be noted that many embodiments and implementations are possible. Furthermore, the following claims are in no way intended to limit the scope of the present invention to the specific embodiments described above. Additionally, any use of the term "means" for … … is intended to induce an element and a device-plus-function interpretation of the claims, and any element not specifically used with the term "means" for … … should not be interpreted as a device-plus-function element, even if the claims otherwise include the term "means". Moreover, although specific method steps have been set forth in a particular order, these method steps may occur in any desired order and fall within the scope of the invention.

Claims (24)

1. A system for multi-scale monitoring, the system comprising:
a memory and one or more processors, the memory being a non-transitory computer-readable medium encoded with executable instructions such that, when the instructions are executed, the one or more processors perform operations comprising:
receiving monitoring data of a scene having a plurality of regions, the monitoring data having an object flow tensor V representing a plurality of objects flowing from one region to another region at a time t and an object communication tensor C representing a plurality of communications transmitted from one region to another region at the time t;
determining cluster members for the plurality of zones;
determining a dependency link between the communication and the flow;
designating at least one cluster of one or more regions as a region of interest based on the dependency links; and
controlling the device based on the region of interest.
2. The system of claim 1, wherein determining cluster members for the plurality of zones further comprises:
constructing an adjacency matrix a based on the object flow tensor V;
symmetrizing the adjacency matrix A;
solving a non-negative matrix factorization of the symmetric adjacency matrix; and
assigning a cluster member of the object in each of the plurality of zones to generate the cluster member.
3. The system of claim 2, wherein determining a dependency link between a communication and a flow further comprises the operations of:
constructing a low resolution stream tensor based on the cluster members by merging ship streams V within each cluster;
determining a stream transfer entropy; and
dependency links and dependent clusters are identified by thresholding.
4. The system of claim 3, wherein designating at least one cluster of one or more regions as a region of interest based on the dependency links comprises: designating the subordinate cluster as a region of interest.
5. The system of claim 4, wherein controlling a device based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
6. The system of claim 4, wherein controlling a device based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
7. The system of claim 1, wherein controlling a device based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
8. The system of claim 1, wherein controlling a device based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
9. A computer program product for multi-scale monitoring, the computer program product comprising:
a non-transitory computer-readable medium encoded with executable instructions such that, when the instructions are executed by one or more processors, the one or more processors perform the following:
receiving monitoring data of a scene having a plurality of regions, the monitoring data having an object flow tensor V representing a plurality of objects flowing from one region to another region at a time t and an object communication tensor C representing a plurality of communications transmitted from one region to another region at the time t;
determining cluster members for the plurality of zones;
determining a dependency link between the communication and the flow;
designating at least one cluster of one or more regions as a region of interest based on the dependency links; and
controlling the device based on the region of interest.
10. The computer program product of claim 9, wherein determining cluster members for the plurality of zones further comprises:
constructing an adjacency matrix a based on the object flow tensor V;
symmetrizing the adjacency matrix A;
solving a non-negative matrix factorization of the symmetric adjacency matrix; and
assigning a cluster member of the object in each of the plurality of zones to generate the cluster member.
11. The computer program product of claim 10, wherein determining a dependency link between a communication and a flow further comprises:
constructing a low resolution stream tensor based on the cluster members by merging ship streams V within each cluster;
determining a stream transfer entropy; and
dependency links and dependent clusters are identified by thresholding.
12. The computer program product of claim 11, wherein designating at least one cluster of one or more regions as a region of interest based on the dependency links comprises: designating the subordinate cluster as a region of interest.
13. The computer program product of claim 12, wherein controlling an apparatus based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
14. The computer program product of claim 12, wherein controlling an apparatus based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
15. The computer program product of claim 9, wherein controlling an apparatus based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
16. The computer program product of claim 9, wherein controlling an apparatus based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
17. A computer-implemented method for multi-scale monitoring, the method comprising the acts of:
causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium such that, when executed, the one or more processors perform the following:
receiving monitoring data of a scene having a plurality of regions, the monitoring data having an object flow tensor V representing a plurality of objects flowing from one region to another region at a time t and an object communication tensor C representing a plurality of communications transmitted from one region to another region at the time t;
determining cluster members for the plurality of zones;
determining a dependency link between the communication and the flow;
designating at least one cluster of one or more regions as a region of interest based on the dependency links; and
controlling the device based on the region of interest.
18. The method of claim 17, wherein determining cluster members for the plurality of zones further comprises:
constructing an adjacency matrix a based on the object flow tensor V;
symmetrizing the adjacency matrix A;
solving a non-negative matrix factorization of the symmetric adjacency matrix; and
assigning a cluster member of the object in each of the plurality of zones to generate the cluster member.
19. The method of claim 18, wherein determining a dependency link between a communication and a flow further comprises:
constructing a low resolution stream tensor based on the cluster members by merging ship streams V within each cluster;
determining a stream transfer entropy; and
dependency links and dependent clusters are identified by thresholding.
20. The method of claim 19, wherein designating at least one cluster of one or more regions as a region of interest based on the dependency links comprises: designating the subordinate cluster as a region of interest.
21. The method of claim 20, wherein controlling a device based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
22. The method of claim 20, wherein controlling a device based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
23. The method of claim 17, wherein controlling a device based on the region of interest further comprises: moving the unmanned aerial vehicle to the region of interest.
24. The method of claim 17, wherein controlling a device based on the region of interest further comprises: the monitoring device in the satellite is enlarged to the region of interest.
CN201880052092.4A 2017-09-12 2018-07-11 Coarse-grained multi-layer flow information dynamics for multi-scale monitoring Pending CN111033411A (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201762557733P 2017-09-12 2017-09-12
US62/557,733 2017-09-12
PCT/US2018/041714 WO2019055112A1 (en) 2017-09-12 2018-07-11 Coarse- grained multilayer flow information dynamics for multiscale monitoring

Publications (1)

Publication Number Publication Date
CN111033411A true CN111033411A (en) 2020-04-17

Family

ID=65723837

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880052092.4A Pending CN111033411A (en) 2017-09-12 2018-07-11 Coarse-grained multi-layer flow information dynamics for multi-scale monitoring

Country Status (3)

Country Link
EP (1) EP3682304A4 (en)
CN (1) CN111033411A (en)
WO (1) WO2019055112A1 (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090208054A1 (en) * 2008-02-20 2009-08-20 Robert Lee Angell Measuring a cohort's velocity, acceleration and direction using digital video
CN103583027A (en) * 2011-06-07 2014-02-12 高通股份有限公司 Multiple description coding with plural combined diversity
US20140097979A1 (en) * 2012-10-09 2014-04-10 Accipiter Radar Technologies, Inc. Device & method for cognitive radar information network
US20140180566A1 (en) * 2012-12-26 2014-06-26 Sap Ag Complex event processing for moving objects
US20140267723A1 (en) * 2013-01-30 2014-09-18 Insitu, Inc. Augmented video system providing enhanced situational awareness
US20150235143A1 (en) * 2003-12-30 2015-08-20 Kantrack Llc Transfer Learning For Predictive Model Development
US20150301208A1 (en) * 2014-04-22 2015-10-22 Westerngeco L.L.C. Seismic data processing
US20150379408A1 (en) * 2014-06-30 2015-12-31 Microsoft Corporation Using Sensor Information for Inferring and Forecasting Large-Scale Phenomena
US20160217692A1 (en) * 2015-01-22 2016-07-28 Electronics And Telecommunications Research Institute Vessel monitoring system and vessel monitoring method thereof
US20170090478A1 (en) * 2015-09-30 2017-03-30 Ants Technology (Hk) Limited. Systems and Methods for Autonomous Vehicle Navigation
WO2017068224A1 (en) * 2015-10-23 2017-04-27 Consejo Superior De Investigaciones Científicas Biomimetic and zoosemiotic unmanned aircraft guided by automatic pilot for precision and/or pursuit flights
US20170178524A1 (en) * 2015-05-06 2017-06-22 Ocula Corporation Swim Lap Counting and Timing System and Methods for Event Detection from Noisy Source Data
US9727976B1 (en) * 2015-09-08 2017-08-08 Sandia Corporation Geospatial-temporal semantic graph representations of trajectories from remote sensing and geolocation data
US20170225760A1 (en) * 2014-12-15 2017-08-10 Leidos, Inc. System and Method For Fusion of Sensor Data to Support Autonomous Maritime Vessels

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9113590B2 (en) * 2012-08-06 2015-08-25 Superior Edge, Inc. Methods, apparatus, and systems for determining in-season crop status in an agricultural crop and alerting users

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150235143A1 (en) * 2003-12-30 2015-08-20 Kantrack Llc Transfer Learning For Predictive Model Development
US20090208054A1 (en) * 2008-02-20 2009-08-20 Robert Lee Angell Measuring a cohort's velocity, acceleration and direction using digital video
CN103583027A (en) * 2011-06-07 2014-02-12 高通股份有限公司 Multiple description coding with plural combined diversity
US20140097979A1 (en) * 2012-10-09 2014-04-10 Accipiter Radar Technologies, Inc. Device & method for cognitive radar information network
US20140180566A1 (en) * 2012-12-26 2014-06-26 Sap Ag Complex event processing for moving objects
US20140267723A1 (en) * 2013-01-30 2014-09-18 Insitu, Inc. Augmented video system providing enhanced situational awareness
US20150301208A1 (en) * 2014-04-22 2015-10-22 Westerngeco L.L.C. Seismic data processing
US20150379408A1 (en) * 2014-06-30 2015-12-31 Microsoft Corporation Using Sensor Information for Inferring and Forecasting Large-Scale Phenomena
US20170225760A1 (en) * 2014-12-15 2017-08-10 Leidos, Inc. System and Method For Fusion of Sensor Data to Support Autonomous Maritime Vessels
US20160217692A1 (en) * 2015-01-22 2016-07-28 Electronics And Telecommunications Research Institute Vessel monitoring system and vessel monitoring method thereof
US20170178524A1 (en) * 2015-05-06 2017-06-22 Ocula Corporation Swim Lap Counting and Timing System and Methods for Event Detection from Noisy Source Data
US9727976B1 (en) * 2015-09-08 2017-08-08 Sandia Corporation Geospatial-temporal semantic graph representations of trajectories from remote sensing and geolocation data
US20170090478A1 (en) * 2015-09-30 2017-03-30 Ants Technology (Hk) Limited. Systems and Methods for Autonomous Vehicle Navigation
WO2017068224A1 (en) * 2015-10-23 2017-04-27 Consejo Superior De Investigaciones Científicas Biomimetic and zoosemiotic unmanned aircraft guided by automatic pilot for precision and/or pursuit flights

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GIULIANA PALLOTTA,ET AL: "Vessel Pattern Knowledge Discovery from AIS Data: A Framework for Anomaly Detection and Route Prediction", 《ENTROPY》 *

Also Published As

Publication number Publication date
WO2019055112A1 (en) 2019-03-21
EP3682304A1 (en) 2020-07-22
EP3682304A4 (en) 2021-07-14

Similar Documents

Publication Publication Date Title
Soler et al. Lifted Wasserstein matcher for fast and robust topology tracking
CN108154222B (en) Deep neural network training method and system and electronic equipment
Zhang et al. Deep learning for detecting building façade elements from images considering prior knowledge
Villanueva-Domingo et al. Learning cosmology and clustering with cosmic graphs
US11954317B2 (en) Systems and method for a customizable layered map for visualizing and analyzing geospatial data
Gelbrecht et al. Neural partial differential equations for chaotic systems
Pu et al. Constrained least squares algorithms for nonlinear unmixing of hyperspectral imagery
CN113260986A (en) Machine learning framework for discovering materials with desired properties
US20180332256A1 (en) Coarse-grained multilayer flow information dynamics for multiscale monitoring
Chaudhuri et al. Application of image analytics for disaster response in smart cities
CN113158391A (en) Method, system, device and storage medium for visualizing multi-dimensional network node classification
Sun et al. α-Deep Probabilistic Inference (α-DPI): efficient uncertainty quantification from exoplanet astrometry to black hole feature extraction
Xing et al. A land use/land cover change geospatial cyberinfrastructure to integrate big data and temporal topology
Thomopoulos et al. Automated real-time risk assessment for airport passengers using a deep learning architecture
Farrah et al. An evolutionary paradigm for dusty active galaxies at low redshift
Mittermeier et al. A deep learning based classification of atmospheric circulation types over Europe: projection of future changes in a CMIP6 large ensemble
Li et al. Efficient regional seismic risk assessment via deep generative learning of surrogate models
Buzzicotti et al. Inferring turbulent environments via machine learning
US20220101120A1 (en) Interpretable visualization system for graph neural network
Khan et al. Detection of Dipole Modulation in CMB temperature anisotropy maps from WMAP and Planck using Artificial Intelligence
CN111033411A (en) Coarse-grained multi-layer flow information dynamics for multi-scale monitoring
Wu Big data classification of remote sensing image based on cloud computing and convolutional neural network
Budavári et al. Faint Object Detection in Multi-Epoch Observations via Catalog Data Fusion
Sharma et al. Image segmentation in Constrained IOT servers
Li Research on smart grid management and security guarantee of sports stadiums based on GCNN-GRU and self-attention mechanism

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200417