Performance and Accuracy Comparisons of Classification Methods and Perspective Solutions for UAV-Based Near-Real-Time "Out of the Lab" Data Processing.

Today, integration into automated systems has become a priority in the development of remote sensing sensors carried on drones. For this purpose, the primary task is to achieve real-time data processing. Increasing sensor resolution, fast data capture and the simultaneous use of multiple sensors is one direction of development. However, this poses challenges on the data processing side due to the increasing amount of data. Our study intends to investigate how the running time and accuracy of commonly used image classification algorithms evolve using Altum Micasense multispectral and thermal acquisition data with GSD = 2 cm spatial resolution. The running times were examined for two PC configurations, with a 4 GB and 8 GB DRAM capacity, respectively, as these parameters are closer to the memory of NRT microcomputers and laptops, which can be applied "out of the lab". During the accuracy assessment, we compared the accuracy %, the Kappa index value and the area ratio of correct pixels. According to our results, in the case of plant cover, the Spectral Angles Mapper (SAM) method achieved the best accuracy among the validated classification solutions. In contrast, the Minimum Distance (MD) method achieved the best accuracy on water surface. In terms of temporality, the best results were obtained with the individually constructed decision tree classification. Thus, it is worth developing these two directions into real-time data processing solutions.

Clinical symptoms and blood concentration of new psychoactive substances (NPS) in intoxicated and hospitalized patients in the Budapest region of Hungary (2018-19).

BACKGROUND: New Psychoactive Substances (NPS) impose a new challenge on the legal and health care system, yet, there is little information available about how new substances spread based on hospitalization of intoxicated patients. The aims of this study were: (i) to investigate the frequency of NPS among suspected drug intoxicated patients, (ii) to study the connection between blood concentration and clinical symptoms, (iii) to determine their half-life with a time-series blood sampling protocol. METHODS: During the observation period, 116 suspected drug intoxicated patients were sampled. The samples were analyzed for alcohol, 20 classical illicit and licit drugs, and for 78 NPS. Clinical symptoms were registered on-site (by the Emergency Medical Services) and (also) at hospital admittance. RESULTS: NPS were detected in 51 patients of which cathinones were found in 4, the synthetic cannabinoids (SCs) 5 F-MDMB-PINACA and 5 F-MDMB-PICA in 23-23, and CUMYL-CH-MEGACLONE in 2 cases. Poison severity scores (PSS) showed mild to moderate intoxications overall. Connection between blood concentration and severity of clinical symptoms were inconclusive. The calculated half-life of 5 F-MDMB-PINACA and 5 F-MDMB-PICA was 2.50 and 2.68 h, respectively. CONCLUSION: The ratio of SCs among the selected intoxicated patients was higher than expected from seizure data which could be the consequence of targeted patient selection. The clinical symptoms and the severity of intoxication cannot be characterized simply by NPS blood levels. The short half-life of SCs can explain the relatively rapid consolidation of intoxication symptoms.HighlightsIn the Budapest region, the majority of hospitalized NPS intoxications was caused by the synthetic cannabinoids 5F-MDMB-PINACA and 5F-MDMB-PICA in 2018-19.No correlation between blood concentration and symptoms severity could be established.The clinical symptoms of synthetic cannabinoid users improved quickly and no ICU treatment was necessary.The half-life of 5F-MDMB-PINACA and 5F-MDMB-PICA was proved to be 2.50 hours and 2.68 hours, respectively.