RESUMEN
Air pollution has become the most important issue concerning human evolution in the last century, as the levels of toxic gases and particles present in the air create health problems and affect the ecosystems of the planet. Scientists and environmental organizations have been looking for new ways to combat and control the air pollution, developing new solutions as technologies evolves. In the last decade, devices able to observe and maintain pollution levels have become more accessible and less expensive, and with the appearance of the Internet of Things (IoT), new approaches for combating pollution were born. The focus of the research presented in this paper was predicting behaviours regarding the air quality index using machine learning. Data were collected from one of the six atmospheric stations set in relevant areas of Bucharest, Romania, to validate our model. Several algorithms were proposed to study the evolution of temperature depending on the level of pollution and on several pollution factors. In the end, the results generated by the algorithms are presented considering the types of pollutants for two distinct periods. Prediction errors were highlighted by the RMSE (Root Mean Square Error) for each of the three machine learning algorithms used.
Asunto(s)
Contaminantes Atmosféricos , Contaminación del Aire , Contaminantes Atmosféricos/análisis , Contaminación del Aire/análisis , Contaminación del Aire/prevención & control , Ciudades , Ecosistema , Monitoreo del Ambiente , Humanos , Aprendizaje Automático , Tiempo (Meteorología)RESUMEN
As standard practice in orthopedic surgery, the information gathered by analyzing Computer Tomography (CT) 2D images is used for patient diagnosis and planning surgery. Lately, these virtual slices are the input for generating 3D virtual models using DICOM viewers, facilitating spatial orientation, and diagnosis. Virtual Reality (VR) and 3D printing (3DP) technologies are also reported for use in anatomy visualization, medical training, and diagnosis. However, it has not been yet investigated whether the surgeons consider that the advantages offered by 3DP and VR outweigh their development efforts. Moreover, no comparative evaluation for understanding surgeon's preference in using these investigation tools has been performed so far. Therefore, in this paper, a pilot usability test was conducted for collecting surgeons' opinions. 3D models of knee, hip and foot were displayed using DICOM 3D viewer, two VR environments and as 3D-printed replicas. These tools adequacy for diagnosis was comparatively assessed in three cases scenarios, the time for completing the diagnosis tasks was recorded and questionnaires filled in. The time for preparing the models for VR and 3DP, the resources needed and the associated costs were presented in order to provide surgeons with the whole context. Results showed a preference in using desktop DICOM viewer with 3D capabilities along with the information provided by Unity-based VR solution for visualizing the virtual model from various angles challenging to analyze on the computer screen. 3D-printed replicas were considered more useful for physically simulating the surgery than for diagnosis. For the VR and 3DP models, the lack of information on bone quality was considered an important drawback. The following order of using the tools was preferred: DICOM viewer, followed by Unity VR and 3DP.
Asunto(s)
Procedimientos Ortopédicos , Cirujanos Ortopédicos , Ortopedia , Realidad Virtual , Humanos , Impresión TridimensionalRESUMEN
The current paper presents the design of a glass panels recycling flow and the method used for establishing the optimal processing installation architecture. In the solution provided in the current research, a novel approach centred on applying digital twinning in the design of the requested processing architecture is presented. It involves designing the virtual prototype of the diffused processing architecture and modelling the glass waste flow as a hybrid material flow. Dedicated analysis and simulation software is then used for establishing installation architecture and the specific parameters for each processing and transport capacity. The assessment of different processing scenarios by virtual modelling and simulations can also be used for exploring options to increase productivity and profit for other different recycling architectures. The main practical value of the study consists of creating the means to improve the waste recycling of automotive windshields, float glass or construction glass panels with metallic meshes, all representing categories of waste insufficiently recycled in Romania. The simulation results of the study were validated by tests made on the glass panel recycling installation. Also, a recovery glass rate of minimum 85% of the amount of waste loaded into the recycling system was achieved, obtaining a waste recycling quantity three times higher than initially anticipated.