Localization is one of the current challenges in indoor navigation research. The conventional global positioning system (GPS) is affected by weak signal strengths due to high levels of signal interference and fading in indoor environments. Therefore, new positioning solutions tailored for indoor environments need to be developed. In this paper, we propose a deep learning approach for indoor localization. However, the performance of a deep learning system depends on the quality of the feature representation. This paper introduces two novel feature set extractions based on the continuous wavelet transforms (CWT) of the received signal strength indicators’ (RSSI) data. The two novel CWT feature sets were augmented with additive white Gaussian noise. The first feature set is CWT image-based, and the second is composed of the CWT PSD numerical data that were dimensionally equalized using principal component analysis (PCA). These proposed image and numerical data feature sets were both evaluated using CNN and ANN models with the goal of identifying the room that the human subject was in and estimating the precise location of the human subject in that particular room. Extensive experiments were conducted to generate the proposed augmented CWT feature set and numerical CWT PSD feature set using two analyzing functions, namely, Morlet and Morse. For validation purposes, the performance of the two proposed feature sets were compared with each other and other existing feature set formulations. The accuracy, precision and recall results show that the proposed feature sets performed better than the conventional feature sets used to validate the study. Similarly, the mean localization error generated by the proposed feature set predictions was less than those of the conventional feature sets used in indoor localization. More particularly, the proposed augmented CWT-image feature set outperformed the augmented CWT-PSD numerical feature set. The results also show that the Morse-based feature sets trained with CNN produced the best indoor positioning results compared to all Morlet and ANN-based feature set formulations.

Forest carbon sinks significantly contribute to mitigation of atmospheric concentrations of carbon dioxide. Thus, estimating forest carbon is becoming important to develop policies for mitigating climate change and trading carbon credits. However, a great challenge is how to quantify uncertainties in estimation of forest carbon. This study investigated uncertainties of mapping aboveground forest carbon due to location errors of sample plots for Lin-An County of China. National forest inventory plot data and Landsat TM images were combined using co-simulation algorithm. The findings show that randomly perturbing plot locations within 10 distance intervals statistically did not result in biased population mean predictions of aboveground forest carbon at a significant level of 0.05, but increased root mean square errors of the maps. The perturbations weakened spatial autocorrelation of aboveground forest carbon and its correlation with spectral variables. The perturbed distances of 800 m or less did not obviously change the spatial distribution of predicted values. However, when the perturbed distances were 1600 m or larger, the correlation coefficients of the predicted values from the perturbed locations with those from the true plot locations statistically did not significantly differ from zero at a level of 0.05 and the spatial distributions became random.

Objectives. We conducted a case–control study of adulthood asthma and point-source respirable particulate air pollution with asthma-diagnosed case patients (n = 3717) and gastroenteritis-diagnosed control patients (n = 4129) to determine effects of particulate air pollution on public health. Methods. We used hospitalization data from Buffalo, NY, neighborhoods for a 5-year period (1996 through 2000), geographic information systems techniques, the Diggle method, and statistical analysis to compare the locations of case patients and control patients in terms of proximity to different known pollution sources in the study area. Results. We found a clustering of asthma cases in close proximity to the Peace Bridge Complex and the freeways and a dose–response relationship indicating a decreased risk of asthma prevalence the farther an individual resides from the source of exposure. Conclusions. These findings provide a basis for the development of new hypotheses relating to the spatial distribution of asthma prevalence and morbidity in this community.

Lead poisoning remains a major environmental health threat and a persistent source of health disparities in the United States. In this retrospective study, statistical and geospatial approaches were used to evaluate age- and gender-specific differences in childhood lead prevalence across Chicago, assess the spatiotemporal dynamics of the disease, and identify the socioeconomic and racial composition of high-risk communities. Elevated blood lead levels (≥ 10 μ g/dL of lead) decreased significantly during the study period but disparities persisted across neighborhoods. A significant association was observed between high-risk neighborhoods and housing age, low income, and minority populations. These findings provide insights into the complex geographies of lead exposure and could serve as a basis for developing more targeted health intervention programs.

While tsunami characteristics and effects are not fully understood in the countries around the Indian Ocean, there are reports suggesting that mangroves, acting as a barrier, significantly reduce the devastation caused by the waves. This study proposes a creative approach to investigating the impact of the 2004 tsunami on mangrove vegetation. The approach involves a combination of Geographic Information System (GIS) proximity analyses and change detection methods in remote sensing to delineate multiple buffer distances from the coastline into four homogeneous subregions. The changes in land cover are then assessed in these subregions before and after the tsunami event. The proposed approach provides a more reliable and accurate means than conventional methods to evaluate spatial patterns of damaged areas through different land characteristics along the coastline. There are major damages to land cover, representing an average of 26.87% change, in those geographic locations with low mangrove coverage that are in close proximity to the coastline in all four subregions, whereas less damage is apparent in locations with high mangrove coverage, representing an average of only 2.77% change. The optimum distance between 1000 and 1500 m of mangrove buffer would be favourable and most effective for reducing the damage by potential tsunami waves. The findings support the need for mangrove replantation and management in the future and may serve as a prototype for studying impacts of tsunamis in other affected countries.