Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations
We develop a new model for spatial random field reconstruction of a binary-valued spatial phenomenon. In our model, sensors are deployed in a wireless sensor network across a large geographical region. Each sensor measures a non-Gaussian inhomogeneous temporal process which depends on the spatial ph...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176210 |
| _version_ | 1826123767678500864 |
|---|---|
| author | Sheng, Shunan Xiang, Qikun Nevat, Ido Neufeld, Ariel |
| author2 | School of Physical and Mathematical Sciences |
| author_facet | School of Physical and Mathematical Sciences Sheng, Shunan Xiang, Qikun Nevat, Ido Neufeld, Ariel |
| author_sort | Sheng, Shunan |
| collection | NTU |
| description | We develop a new model for spatial random field reconstruction of a binary-valued spatial phenomenon. In our model, sensors are deployed in a wireless sensor network across a large geographical region. Each sensor measures a non-Gaussian inhomogeneous temporal process which depends on the spatial phenomenon. Two types of sensors are employed: one collects point observations at specific time points, while the other collects integral observations over time intervals. Subsequently, the sensors transmit these time-series observations to a Fusion Center (FC), and the FC infers the spatial phenomenon from these observations. We show that the resulting posterior predictive distribution is intractable and develop a tractable two-step procedure to perform inference. Firstly, we develop algorithms to perform approximate Likelihood Ratio Tests on the time-series observations, compressing them to a single bit for both point sensors and integral sensors. Secondly, once the compressed observations are transmitted to the FC, we utilize a Spatial Best Linear Unbiased Estimator (S-BLUE) to reconstruct the binary spatial random field at any desired spatial location. The performance of the proposed approach is studied using simulation. We further illustrate the effectiveness of our method using a weather dataset from the National Environment Agency (NEA) of Singapore with fields including temperature and relative humidity. |
| first_indexed | 2024-10-01T06:09:43Z |
| format | Journal Article |
| id | ntu-10356/176210 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:09:43Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1762102024-05-14T01:41:04Z Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations Sheng, Shunan Xiang, Qikun Nevat, Ido Neufeld, Ariel School of Physical and Mathematical Sciences Mathematical Sciences Sensor networks Warped Gaussian process We develop a new model for spatial random field reconstruction of a binary-valued spatial phenomenon. In our model, sensors are deployed in a wireless sensor network across a large geographical region. Each sensor measures a non-Gaussian inhomogeneous temporal process which depends on the spatial phenomenon. Two types of sensors are employed: one collects point observations at specific time points, while the other collects integral observations over time intervals. Subsequently, the sensors transmit these time-series observations to a Fusion Center (FC), and the FC infers the spatial phenomenon from these observations. We show that the resulting posterior predictive distribution is intractable and develop a tractable two-step procedure to perform inference. Firstly, we develop algorithms to perform approximate Likelihood Ratio Tests on the time-series observations, compressing them to a single bit for both point sensors and integral sensors. Secondly, once the compressed observations are transmitted to the FC, we utilize a Spatial Best Linear Unbiased Estimator (S-BLUE) to reconstruct the binary spatial random field at any desired spatial location. The performance of the proposed approach is studied using simulation. We further illustrate the effectiveness of our method using a weather dataset from the National Environment Agency (NEA) of Singapore with fields including temperature and relative humidity. Nanyang Technological University The research was conducted under the Undergraduate Research Experience on Campus (URECA) project, supported by the School of Physical and Mathematical Sciences at Nanyang Technological University. AN gratefully acknowledges the financial support by his Nanyang Assistant Professorship Grant (NAP Grant) Machine Learning based Algorithms in Finance and Insurance. 2024-05-14T01:41:04Z 2024-05-14T01:41:04Z 2024 Journal Article Sheng, S., Xiang, Q., Nevat, I. & Neufeld, A. (2024). Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations. Journal of the Franklin Institute, 361(2), 612-636. https://dx.doi.org/10.1016/j.jfranklin.2023.12.016 0016-0032 https://hdl.handle.net/10356/176210 10.1016/j.jfranklin.2023.12.016 2-s2.0-85181142785 2 361 612 636 en NAP Grant Journal of the Franklin Institute © 2023 The Franklin Institute. Published by Elsevier Inc. All rights reserved. |
| spellingShingle | Mathematical Sciences Sensor networks Warped Gaussian process Sheng, Shunan Xiang, Qikun Nevat, Ido Neufeld, Ariel Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title | Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title_full | Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title_fullStr | Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title_full_unstemmed | Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title_short | Binary spatial random field reconstruction from non-Gaussian inhomogeneous time-series observations |
| title_sort | binary spatial random field reconstruction from non gaussian inhomogeneous time series observations |
| topic | Mathematical Sciences Sensor networks Warped Gaussian process |
| url | https://hdl.handle.net/10356/176210 |
| work_keys_str_mv | AT shengshunan binaryspatialrandomfieldreconstructionfromnongaussianinhomogeneoustimeseriesobservations AT xiangqikun binaryspatialrandomfieldreconstructionfromnongaussianinhomogeneoustimeseriesobservations AT nevatido binaryspatialrandomfieldreconstructionfromnongaussianinhomogeneoustimeseriesobservations AT neufeldariel binaryspatialrandomfieldreconstructionfromnongaussianinhomogeneoustimeseriesobservations |