Association between Macroscopic-factors and Identified HIV/AIDS Cases among Injecting Drug Users: An Analysis Using Geographically Weighted Regression Model

Drug use （DU）, particularly injecting drug use （IDU） has been the main route of transmission and spread of Human Immunodeficiency Virus （HIV）/Acquired Immune Deficiency Syndrome （AIDSJ among injecting drug users （IDUs）[1]. Previous studies have proven that needles or cottons sharing during drug injection were major risk factors for HIV/AIDS transmission at the personal level[z4]. Being a social behavioral issue, HIV/AIDS related risk factors should be far beyond the personal level. Therefore, studies on HIV/AIDS related risk factors should focus not only on the individual factors, but also on the association between HIV/AIDS cases and macroscopic-factors, such as economic status, transportation, health care services, etc[1]. The impact of the macroscopic-factors on HIV/AIDS status might be either positive or negative, which are potentially reflected in promoting, delaying or detecting HIV/AIDS epidemics.

Travel Behaviours of Sharing Bicycles in the Central Urban Area Based on Geographically Weighted Regression: The Case of Guangzhou, China

Mobile information and communication technologies(MICTs) have fully penetrated everyday life in smart societies;this has greatly compressed time, space, and distance, and consequently, reshaped residents’ travel behaviour patterns. As a new mode of shared mobility, the sharing bicycle offers a variety of options for the daily travel of urban residents. Extant studies have mainly examined the travel characteristics and influencing factors of public bicycles with piles, while the travel patterns for sharing bicycles and their driving mechanisms have been largely ignored. Using one week’s travel data for Mobike, this study investigated the spatial and temporal distribution patterns of sharing bicycle travel behaviours in the central urban area of Guangzhou, China;furthermore, it identified the influences of built environment density factors on sharing bicycle travel behaviours based on the geographically weighted regression method. Obvious morning and evening peaks were observed in the sharing bicycle travel patterns for both weekdays and weekends. The old urban area, which had a high degree of mixed function, dense road networks, and cycling-friendly built environments, was the main travel area that attracted sharing bicycles on both weekdays and weekends. Furthermore, factors including the point of interest(POI) for the density of public transport stations, the functional mixing degree, and the density of residential POIs significantly affected residents’ travel behaviours. These findings could enrich discourse regarding shared mobility with a Chinese case characterised by rapidly developing MICTs and also provide references to local authorities for improving slow traffic environments.

Prototyping an open environment for sharing geographical analysis models on cloud computing platform

The sharing of geographical analysis models is of crucial importance for simulating geographic processes and phenomena in the current geographical information systems(e.g.Digital Earth),but there remain some issues that have not been completely resolved.The challenges include,eliminating model heterogeneity and searching for suitable infrastructures to support the open sharing and effective execution of models.Taking advantage of cloud computing,this article aims to address the above issues and develop an open environment for geographical analysis model sharing.On the basis of the analysis of the applicability of cloud computing,the architecture of the open environment is proposed.More importantly,key strategies designed for heterogeneous model description,model encapsulating as well as model deploying and transparent accessing in the cloud are discussed in detail to establish such an environment.Finally,the prototype environment is implemented,and experiments were conducted to verify the environment’s feasibility to support the sharing of geographical analysis models.

A new framework for GEOBIA: accurate individual plant extraction and detection using high-resolution RGB data from UAVs

Citrus(Citrus reticulata),which is an important economic crop worldwide,is often managed in a labor-intensive and inefficient manner in developing countries,thereby necessitating more rapid and accurate alternatives tofield surveys for improved crop management.In this study,we propose a novel method for individual tree segmentation from unmanned aerial vehicle remote sensing(RS)using a combination of geographic object-based image analysis(GEOBIA)and layer-adaptive Euclidean distance transformation-based watershed segmentation(LAEDT-WS).First,we use a GEOBIA support vector machine classifier that is optimized for features and parameters to identify the boundaries of citrus tree canopies accurately by generating mask images.Thereafter,our LAEDT workflow separates connected canopies and facilitates the accurate segmentation of individual canopies using WS.Our method exhibited an F1-score improvement of 10.75%compared to the traditional WS method based on the canopy height model.Furthermore,it achieved 0.01%and 1.38%higher F1-scores than the state-of-the-art deep learning detection networks YOLOX and YOLACT,respectively,on the test plot.Our method can be extended to detect larger-scale or more complex structured crops or economic plants by introducing morefinely detailed and transferable RS images,such as high-resolution or LiDAR-derived images,to improve the mask base map.

Deep learning for land use and land cover classification from the Ecuadorian Paramo.

The paramo,plays an important role in our ecosystems as They balance the water resources and can retain substantial quantities of carbon.This research was carried out in the province of Tungurahua,specifically the Quero district.The aim is to develop a classification of the land use land cover(LULC)in the paramo using satellite imagery using several classifiers and determine which one obtains the best performance,for which three different approaches were applied:Pixel-Based Image Analysis(PBIA),Geographic Object-Based Image Analysis(GEOBIA),and a Deep Neural Network(DNN).Various parameters were used,such as the Normalized Difference Vegetation Index(NDVI),the Bare Soil Index(BSI),texture,altitude,and slope.Seven classes were used:paramo,pasture,crops,herbaceous vegetation,urban,shrubrainland,and forestry plantations.The data was obtained with the help of onsite technical experts,using geo-referencing and reference maps.Among the models used the highest-ranked was DNN with an overall precision of 87.43%,while for the paramo class specifically,GEOBIA reached a precision of 95%.