Filtern
Erscheinungsjahr
Dokumenttyp
Volltext vorhanden
- ja (183)
Gehört zur Bibliographie
- nein (183)
Schlagworte
- Deutschland (14)
- Nachhaltigkeit (11)
- Rückenschmerz (11)
- COVID-19 (7)
- Digitalisierung (7)
- Maschinelles Lernen (7)
- China (6)
- Gesundheitswesen (6)
- Künstliche Intelligenz (6)
- Pandemie (6)
Institut
- FB Bauen + Leben (49)
- FB Umweltplanung/-technik (UCB) (44)
- FB Informatik + Therapiewissenschaft (30)
- FB Technik (13)
- FB Umweltwirtschaft/-recht (UCB) (11)
- IfaS - Institut für angewandtes Stoffstrommanagement (10)
- InDi - Institut für Internationale und Digitale Kommunikation (7)
- LaROS - Labor für Radiotechnologie und optische Systeme (6)
- ISS - Institut für Softwaresysteme in Wirtschaft, Umwelt und Verwaltung (5)
- FB Wirtschaft (3)
Driven by decreasing PV and energy storage prices, increasing electricity costs and policy supports from Thai government (self-consumption era), rooftop PV and energy storage systems are going to be deployed in the country rapidly that may disrupt existing business models structure of Thai distribution utilities due to revenue erosion and lost earnings opportunities. The retail rates that directly affect ratepayers (non-solar customers) are expected to increase. This paper focuses on a framework for evaluating impacts of PV with and without energy storage systems on Thai distribution utilities and ratepayers by using cost-benefit analysis (CBA). Prior to calculation of cost/benefit components, changes in energy sales need to be addressed. Government policies for the support of PV generation will also help in accelerating the rooftop PV installation. Benefit components include avoided costs due to transmission losses and deferring distribution capacity with appropriate PV penetration level, while cost components consist of losses in revenue, program costs, integration costs and unrecovered fixed costs. It is necessary for Thailand to compare total costs and total benefits of rooftop PV and energy storage systems in order to adopt policy supports and mitigation approaches, such as business model innovation and regulatory reform, effectively.
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.
1. Recent reports on insect decline have highlighted the need for long-term data on insect communities towards identifying their trends and drivers.
2. With the launch of many new insect monitoring schemes to investigate insect communities over large spatial and temporal scales, Malaise traps have become one of the most important tools due to the broad spectrum of species collected and reduced capture bias through passive sampling of insects day and night. However, Malaise traps can vary in size, shape, and colour, and it is unknown how these differences affect biomass, species richness, and composition of trap catch, making it difficult to compare results between studies.
3. We compared five Malaise trap types (three variations of the Townes and two variations of the Bartak Malaise trap) to determine their effects on biomass and species richness as identified by metabarcoding.
4. Insect biomass varied by 20%–55%, not strictly following trap size but varying with trap type. Total species richness was 20%–38% higher in the three Townes trap models compared to the Bartak traps. Bartak traps captured lower richness of highly mobile taxa but increased richness of ground-dwelling taxa. The white roofed Townes trap captured a higher richness of pollinators.
5. We find that biomass, total richness, and taxa group specific richness are all sensitive to Malaise trap type. Trap type should be carefully considered and aligned to match monitoring and research questions. Additionally, our estimates of trap type effects can be used to adjust results to facilitate comparisons across studies.