We propose a theoretically and practically improved density-based, hierarchical clustering method, providing a clustering hierarchy from which a simplified tree of significant clusters can be constructed. For obtaining a “flat” partition consisting of only the most significant clusters (possibly corresponding to different density thresholds), we propose a novel cluster stability measure, formalize the problem of maximizing the overall stability of selected clusters, and formulate an algorithm that computes an optimal solution to this problem. We demonstrate that our approach outperforms the current, state-of-the-art, density-based clustering methods on a wide variety of real world data.

Density-based clustering based on hierarchical density estimates

Multi-feature, multi-modal, and multi-source social event detection: A comprehensive survey

Monitoring the change of land use and land cover (LULC) and land surface temperature (LST) at different spatio-temporal scales is vital for evaluating landscape dynamics and thermal environment. This study investigates the decadal change of LULC and winter LST on Pabna municipality over the period between 1990 and 2020 using Landsat images (TM, ETM+ and OLI). The study further explores LST distribution for different LULC classes and the explanatory power of various land surface indicators for change in LST. A supervised maximum likelihood classification (MLC) technique was used for LULC mapping of the study area. The results showed that built-up areas were increasing rapidly while water bodies, bare lands and vegetation decreased. The built-up area expanded by 358% between 1990 and 2020, with the occupied area rising from 1.44 km2 to 6.60 km2. To obtain reliable LST results, average values of LST obtained from multiple Landsat images for each year were used. The mean LST in the winter season has risen by 0.63 °C over the last 30 years. The variation in LST between separate days of the same year increased significantly, although the change in mean LST was small. Statistical analysis of land surface indicators revealed that NDVI, NDBI and NDBaI have significant explanatory power to describe LST scenarios. The explanatory power of NDBI and NDBaI to explain the rise of LST is increasing over time while the cooling capacity of NDVI is declining. LST had a moderate positive correlation with NDBI and NDBI and a weak negative correlation with NDVI.

Assessment of land surface temperature and land cover variability during winter: A spatio-temporal analysis of Pabna municipality in Bangladesh

The best possible way for brick-and-mortar retailers to maximise engagement with personalised shoppers is capitalising on intelligent insights. The retailer operates differently with diversified items and services, but influencing retail atmospheric on personalised shoppers, the perception remains the same across industries. Retail atmospherics stimuli such as design, smell and others create behavioural modifications. The purpose of this study is to explore the atmospheric effects on brick-and-mortar store performance and personalised shopper's behaviour using cognitive computing based in-store analytics in the context of emerging market.,The data are collected from 35 shoppers of a brick-and-mortar retailer through questionnaire survey and analysed using quantitative method.,The result of the analysis reveals month-on-month growth in footfall count (46%), conversation rate (21%), units per transaction (27%), average order value (23%), dwell time (11%), purchase intention (29%), emotional experience (40%) and a month-on-month decline in remorse (20%). The retailers need to focus on three control gates of shopper behaviour: entry, browsing and exit. Attention should be paid to the cognitive computing solution to judge the influence of retail atmospherics on store performance and behaviour of personalised shoppers. Retail atmospherics create the right experience for individual shoppers and forceful use of it has an adverse impact.,The paper focuses on strategic decisions of retailers, the tactical value of personalised shoppers and empirically identifies the retail atmospherics effect on brick-and-mortar store performance and personalised shopper behaviour.

Retail atmospherics effect on store performance and personalised shopper behaviour: A cognitive computing approach

Targeting occupant feedback using digital twins: Adaptive spatial-temporal thermal preference sampling to optimize personal comfort models

An increase in the size of data repositories of spatiotemporal data has opened up new challenges in the fields of spatiotemporal data analysis and data mining. Foremost among them is “spatiotemporal clustering,” a subfield of data mining that is increasingly becoming popular because of its applications in wide-ranging areas such as engineering, surveillance, transportation, environmental and seismology studies, and mobile data analysis. This review paper presents a comprehensive review of spatiotemporal clustering approaches and their applications as well as a brief tutorial on the taxonomy of data types in the spatiotemporal domain and patterns. Additionally, the data pre-processing techniques, access methods, cluster validation, space–time scan statistics, software tools, and datasets used by various spatiotemporal clustering algorithms are highlighted.

Spatiotemporal clustering: a review

The various sources generate large volume of spatiotemporal data of different types including crime events. In order to detect crime spot and predict future events, their analysis is important. Crime events are spatiotemporal in nature; therefore a distance function is defined for spatiotemporal events and is used in Fuzzy C-Means algorithm for crime analysis. This distance function takes care of both spatial and temporal components of spatiotemporal data. We adopt sum of squared error (SSE) approach and Dunn index to measure the quality of clusters. We also perform the experimentation on real world crime data to identify spatiotemporal crime clusters.

https://publications.drdo.gov.in/ojs/index.php/dsj/article/download/12518/6231

Application of Spatiotemporal Fuzzy C-Means Clustering for Crime Spot Detection

Spatial technologies generate large datasets quickly and continuously. The purpose of this study is to develop a clustering algorithm to mine spatiotemporal co-location events in trajectory datasets. We present a spatiotemporal algorithm for sub-trajectory clustering that divides a trajectory into line segments and groups theses sub-trajectories on the basis of both spatial and temporal aspects by extending DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm. We adopt the concepts of entropy and silhouette index to validate the clusters. Experiments conducted on two different real datasets demonstrate that the proposed clustering algorithm effectively discovers optimal clusters. Furthermore, experimental results reveal hidden and useful clusters and demonstrate that the proposed algorithm outperforms the CorClustST (Correlation-based Clustering of Big Spatiotemporal Datasets), and the ST-OPTICS (Spatiotemporal-Ordering Points to Identify Clustering Structure) algorithms.

Spatiotemporal trajectory clustering: A clustering algorithm for spatiotemporal data

Effective-coverage and connectivity in WSN

Technology today has made available plenty of seismic data. Their study regarding associated risks and hazards is very important for sustainable development. The use of density based clustering algorithm enables the identification of the seismic cluster formation and its evolution. The current work applies a density based clustering algorithm (DBSCAN) to the earthquake point data of India and thereby divides the region into the various seismic zones depending on the analysis of the various clusters formed. The obtained results are in conformance with seismic map of India as per Bureau of Indian Standards IS 1893:2002.

Mohd Yousuf Ansari

Papers

Spatiotemporal clustering: a review

Application of Spatiotemporal Fuzzy C-Means Clustering for Crime Spot Detection

Spatiotemporal trajectory clustering: A clustering algorithm for spatiotemporal data

Effective-coverage and connectivity in WSN

Identification of Seismic Zones of India using DBSCAN