The emergence of nodding syndrome (NS) in Northern Uganda has generated controversial views with respect to patterns, natural history, and aetiology of the disease which is yet unknown. This study explored spatial pat...The emergence of nodding syndrome (NS) in Northern Uganda has generated controversial views with respect to patterns, natural history, and aetiology of the disease which is yet unknown. This study explored spatial patterns of NS using spatial-temporal methods to establish its clustering patterns across both space and time. Village and year of NS onset for individual patients between the years 1990 and 2014 were entered as input for spatial and temporal analysis in the 6 districts in northern Uganda where it is prevalent. Our temporal results showed that NS onset started before the population was moved in Internally Displaced People’s (IDPs) camps. It also shows that NS continued to be reported during the IDPs and after people had left the IDPs. Our spatial and spatiotemporal analysis showed that two periods had persistent NS clusters. These were 2000-2004 and 2010-2014, coinciding with the period when the population was in the IDP camps and when the population was already out of the camps, respectively. Our conclusion is that the view of associating NS outbreak with living conditions in IDP camps is thus coincidental. We, therefore, contend that the actual aetiological factor of NS is still at large.展开更多
Extracting information about emerging events in large study areas through spatiotemporal and textual analysis of geotagged tweets provides the possibility of monitoring the current state of a disaster.This study propo...Extracting information about emerging events in large study areas through spatiotemporal and textual analysis of geotagged tweets provides the possibility of monitoring the current state of a disaster.This study proposes dynamic spatio-temporal tweet mining as a method for dynamic event extraction from geotagged tweets in large study areas.It introduces the use of a modified version of ordering points to identify the clustering structure to address the intrinsic heterogeneity of Twitter data.To precisely calculate the textual similarity,three state-of-theart text embedding methods of Word2vec,GloVe,and Fast Text were used to capture both syntactic and semantic similarities.The impact of selected embedding algorithms on the quality of the outputs was studied.Different combinations of spatial and temporal distances with the textual similarity measure were investigated to improve the event detection outcomes.The proposed method was applied to a case study related to 2018 Hurricane Florence.The method was able to precisely identify events of varied sizes and densities before,during,and after the hurricane.The feasibility of the proposed method was qualitatively evaluated using the Silhouette coefficient and qualitatively discussed.The proposed method was also compared to an implementation based on the standard density-based spatial clustering of applications with noise algorithm,where it showed more promising results.展开更多
文摘The emergence of nodding syndrome (NS) in Northern Uganda has generated controversial views with respect to patterns, natural history, and aetiology of the disease which is yet unknown. This study explored spatial patterns of NS using spatial-temporal methods to establish its clustering patterns across both space and time. Village and year of NS onset for individual patients between the years 1990 and 2014 were entered as input for spatial and temporal analysis in the 6 districts in northern Uganda where it is prevalent. Our temporal results showed that NS onset started before the population was moved in Internally Displaced People’s (IDPs) camps. It also shows that NS continued to be reported during the IDPs and after people had left the IDPs. Our spatial and spatiotemporal analysis showed that two periods had persistent NS clusters. These were 2000-2004 and 2010-2014, coinciding with the period when the population was in the IDP camps and when the population was already out of the camps, respectively. Our conclusion is that the view of associating NS outbreak with living conditions in IDP camps is thus coincidental. We, therefore, contend that the actual aetiological factor of NS is still at large.
文摘Extracting information about emerging events in large study areas through spatiotemporal and textual analysis of geotagged tweets provides the possibility of monitoring the current state of a disaster.This study proposes dynamic spatio-temporal tweet mining as a method for dynamic event extraction from geotagged tweets in large study areas.It introduces the use of a modified version of ordering points to identify the clustering structure to address the intrinsic heterogeneity of Twitter data.To precisely calculate the textual similarity,three state-of-theart text embedding methods of Word2vec,GloVe,and Fast Text were used to capture both syntactic and semantic similarities.The impact of selected embedding algorithms on the quality of the outputs was studied.Different combinations of spatial and temporal distances with the textual similarity measure were investigated to improve the event detection outcomes.The proposed method was applied to a case study related to 2018 Hurricane Florence.The method was able to precisely identify events of varied sizes and densities before,during,and after the hurricane.The feasibility of the proposed method was qualitatively evaluated using the Silhouette coefficient and qualitatively discussed.The proposed method was also compared to an implementation based on the standard density-based spatial clustering of applications with noise algorithm,where it showed more promising results.
