Filtern
Erscheinungsjahr
- 2019 (18) (entfernen)
Dokumenttyp
Sprache
- Englisch (18)
Volltext vorhanden
- ja (18)
Gehört zur Bibliographie
- nein (18)
Schlagworte
- Maschinelles Lernen (3)
- machine learning (3)
- Künstliche Intelligenz (2)
- Personenkraftwagen (2)
- Rückenschmerz (2)
- Sport (2)
- back pain (2)
- sports (2)
- Aguascalientes (Staat) (1)
- Analyse (1)
Institut
- FB Umweltplanung/-technik (UCB) (7)
- FB Informatik + Therapiewissenschaft (5)
- ISS - Institut für Softwaresysteme in Wirtschaft, Umwelt und Verwaltung (2)
- FB Bauen + Leben (1)
- FB Wirtschaft (1)
- IfaS - Institut für angewandtes Stoffstrommanagement (1)
- LaROS - Labor für Radiotechnologie und optische Systeme (1)
Following a quantitative analysis of adequate feedstock, comprising 11 woody biomass species, four biochars were generated using a Kon-Tiki flame curtain kiln in the state of Aguascalientes, Mexico. Despite the high quality (certified by European Biochar Certificate), the biochars contain substantial quantities of hazardous substances, such as polycyclic aromatic hydrocarbons, polychlorinated dibenzo-p-dioxins and dibenzofurans, polychlorinated biphenyls, and heavy metals, which can induce adverse effects if wrongly applied to the environment. To assess the toxicity of biochars to non-target organisms, toxicity tests with four benthic and zooplanktonic invertebrate species, the ciliate Paramecium caudatum, the rotifer Lecane quadridentata, and the cladocerans Daphnia magna and Moina macrocopa were performed using biochar elutriates. In acute and chronic toxicity tests, no acute toxic effect to ciliates, but significant lethality to rotifers and cladocerans was detected. This lethal toxicity might be due to ingestion/digestion by enzymatic/mechanic processes of biochar by cladocerans and rotifers of toxic substances present in the biochar. No chronic toxicity was found where biochar elutriates were mixed with soil. These data indicate that it is instrumental to use toxicity tests to assess biochars’ toxicity to the environment, especially when applied close to sensitive habitats, and to stick closely to the quantitative set-point values.
Background: High numbers of consumable medical materials (eg, sterile needles and swabs) are used during the daily routine of intensive care units (ICUs) worldwide. Although medical consumables largely contribute to total ICU hospital expenditure, many hospitals do not track the individual use of materials. Current tracking solutions meeting the specific requirements of the medical environment, like barcodes or radio frequency identification, require specialized material preparation and high infrastructure investment. This impedes the accurate prediction of consumption, leads to high storage maintenance costs caused by large inventories, and hinders scientific work due to inaccurate documentation. Thus, new cost-effective and contactless methods for object detection are urgently needed.
Objective: The goal of this work was to develop and evaluate a contactless visual recognition system for tracking medical consumable materials in ICUs using a deep learning approach on a distributed client-server architecture.
Methods: We developed Consumabot, a novel client-server optical recognition system for medical consumables, based on the convolutional neural network model MobileNet implemented in Tensorflow. The software was designed to run on single-board computer platforms as a detection unit. The system was trained to recognize 20 different materials in the ICU, while 100 sample images of each consumable material were provided. We assessed the top-1 recognition rates in the context of different real-world ICU settings: materials presented to the system without visual obstruction, 50% covered materials, and scenarios of multiple items. We further performed an analysis of variance with repeated measures to quantify the effect of adverse real-world circumstances.
Results: Consumabot reached a >99% reliability of recognition after about 60 steps of training and 150 steps of validation. A desirable low cross entropy of <0.03 was reached for the training set after about 100 iteration steps and after 170 steps for the validation set. The system showed a high top-1 mean recognition accuracy in a real-world scenario of 0.85 (SD 0.11) for objects presented to the system without visual obstruction. Recognition accuracy was lower, but still acceptable, in scenarios where the objects were 50% covered (P<.001; mean recognition accuracy 0.71; SD 0.13) or multiple objects of the target group were present (P=.01; mean recognition accuracy 0.78; SD 0.11), compared to a nonobstructed view. The approach met the criteria of absence of explicit labeling (eg, barcodes, radio frequency labeling) while maintaining a high standard for quality and hygiene with minimal consumption of resources (eg, cost, time, training, and computational power).
Conclusions: Using a convolutional neural network architecture, Consumabot consistently achieved good results in the classification of consumables and thus is a feasible way to recognize and register medical consumables directly to a hospital’s electronic health record. The system shows limitations when the materials are partially covered, therefore identifying characteristics of the consumables are not presented to the system. Further development of the assessment in different medical circumstances is needed.