Nonnegative Matrix Factorization-Based Spatial-Temporal Clustering for Multiple Sensor Data Streams

Abstract

Cyber physical systems have grown exponentially and have been attracting a lot of attention over the last few years. To retrieve and mine the useful information from massive amounts of sensor data streams with spatial, temporal, and other multidimensional information has become an active research area. Moreover, recent research has shown that clusters of streams change with a comprehensive spatial-temporal viewpoint in real applications. In this paper, we propose a spatial-temporal clustering algorithm (STClu) based on nonnegative matrix trifactorization by utilizing time-series observational data streams and geospatial relationship for clustering multiple sensor data streams. Instead of directly clustering multiple data streams periodically, STClu incorporates the spatial relationship between two sensors in proximity and integrates the historical information into consideration. Furthermore, we develop an iterative updating optimization algorithm STClu. The effectiveness and efficiency of the algorithm STClu are both demonstrated in experiments on real and synthetic data sets. The results show that the proposed STClu algorithm outperforms existing methods for clustering sensor data streams.

In vivo imaging in the oral cavity by endoscopic optical coherence tomography

“…43 Although a variety of impressive EOCT solutions are proposed in flexible catheter-based configuration, 44,45 especially for intravascular, 46 bronchial 47 as well as gastrointestinal diagnosis, 48,49 in rigid implementation, in particular, for otorhinolaryngology [50][51][52] and in needle-like design for intratissue examinations in cancer diagnosis, [53][54][55][56] developments of intraoral OCT probes adapted to the oral cavity can only be found occasionally. [57][58][59] So far, rigid handheld endoscopic probes, 20,[60][61][62][63] miniaturized probes, 64,65 and rotary pullback catheters 66,67 are developed in forward and side viewing configuration, as well as in contact and noncontact mode for intraoral measurements, which is a crucial step for the application of OCT methodology in clinical practice. In our judgment, most of the reported rigid OCT systems allow the imaging of the well accessible buccal mucosa, the hard and anterior soft palate as well as different parts of the tongue, but none of them has demonstrated contactless OCT images of different areas of the posterior oral mucosa (e.g., palatoglossal arch and fold) with highly resolved structures of the connective tissue and molars in vivo.…”

A non-negative matrix factorization based clustering to identify potential tuna fishing zones

“…Pauca et al [16] have been used an effective NMF algorithm with novel smoothness constraints for unmixing spectral reflectance data for space object identification. Sun and Sang [17] proposed an algorithm spatial-temporal clustering (STClu) based on nonnegative matrix factorization for grouping the data that flows continuously in time series. STClu algorithm works by combining two adjacent sensor data which are then integrated with spatial and temporal information as consideration for clustering.…”

“…In this research, we wanted to know the clustering result of tuna fish catch data using sparse nonnegative matrix factorization (SNMF) [17] and non-negative matrix factorization with sparse constraints (NMFSC) [13], both are the development of the NMF algorithm with the addition of sparseness constraints. Essentially, NMF is an algorithm used to perform dimension reduction (features) such as principal component analysis (PCA).…”

Geo-Visualisation and Visual Analytics for Smart Cities: A Survey

“…Moreover, the geospatial data is a geographical entity which is georeferenced and is represented in terms of location, dimensions, attributes and comprises of points, lines, areas, surfaces, volumes as well as includes time as data of higher dimension (Papadimitriou et al, 1999, Feng et al, 2012, Stasch et al, 2012, Bröring and Reitz, 2014, Gong et al, 2015, Songnian Li et al, 2016. The geo-spatial data visualisation is a powerful instrument for interactive Visual Analytics (VA) and places the geo-spatial data in a visual context by identifying trends, patterns, that usually go unrecognised in the text-based data (Nittel, 2014, Sun and Sang, 2014, Sun and Li, 2016. Further, Geo-Visualisation (GV) techniques help in representing the geo-spatial data beyond the typical spreadsheets, charts and graphs along with presenting it in more sophisticated formats using infographics, maps, detailed bars, pie and fever charts, sparklines, heat maps and 3D globes to * Corresponding author communicate relationships between the geo-spatial data values.…”