scholarly journals ROOM-BASED ENERGY DEMAND CLASSIFICATION OF BIM DATA USING GRAPH SUPERVISED LEARNING

2021 ◽  
Vol XLVI-4/W4-2021 ◽  
pp. 97-100
Author(s):  
H. Kiavarz ◽  
M. Jadidi ◽  
A. Rajabifard ◽  
G. Sohn
Keyword(s):  
Energy Demand ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
3D City Model ◽  
Wide Range ◽  
Construction Step ◽  
Building Information ◽  
Topology Information ◽  
City Model ◽  
Demand Classification

Abstract. Nowadays, cities and buildings are increasingly interconnected with new modern data models like the 3D city model and Building Information Modelling (BIM) for urban management. In the past decades, BIM appears to have been primarily used for visualization. However, BIM has been recently used for a wide range of applications, especially in Building Energy Consumption Estimation (BECE). Despite extensive research, BIM is less used in BECE data-driven approaches due to its complexity in the data model and incompatibility with machine learning algorithms. Therefore, this paper highlights the potential opportunity to apply graph-based learning algorithms (e.g., GraphSAGE) using the enriched semantic, geometry, and room topology information extracted from BIM data. The preliminary results are demonstrated a promising avenue for BECE analysis in both pre-construction step (design) and post-construction step like retrofitting processes.

Smart City and Digital Twins

2021 ◽  
pp. 243-264
Author(s):  
Sara Giaveno
Keyword(s):  
Smart City ◽  
Building Information Modeling ◽  
Information Modeling ◽  
3D City Models ◽  
3D City Model ◽  
Digital Twins ◽  
Building Information ◽  
City Model ◽  
Technical Features

The chapter proposed aims at facing the various implications underlying the smart city concept based on digital twins. The structure of the text is articulated in three main themes: the use of the term “smart city” and the role that technologies had in its definition; the “3D city model” meaning and the integration procedures between BIM (building information modeling) and GIS (geographic information system); the classification of 3D city models by use cases. The chapter can provide researchers with a detailed dissertation aimed at clarifying both the theoretical and technical features belonging to smart city and its related innovative technologies.

scholarly journals 3D CITY MODEL AS A FIRST STEP TOWARDS DIGITAL TWIN OF SOFIA CITY

2021 ◽  
Vol XLIII-B4-2021 ◽  
pp. 23-30
Author(s):  
H. Dimitrov ◽  
D. Petrova-Antonova
Keyword(s):  
Urban Areas ◽  
Web Application ◽  
User Interaction ◽  
Digital Twin ◽  
3D City Model ◽  
Digital Twins ◽  
Starting Point ◽  
Wide Range ◽  
City Model ◽  
The City

Abstract. Semantic 3D city models are increasingly applied for a wide range of analysis and simulations of large urban areas. Such models are used as a foundation for development of city digital twins, representing with high accuracy the landscapes and urban areas as well as dynamic of the city in terms of processes and events. In this context, this paper presents a 3D city model, which is a starting point for development of digital twin of Sofia city. The 3D model is compliant with CityGML 2.0 in LOD1, supporting integration of the buildings and terrain and enriching the buildings’ attributes with address information. District Lozenets of Sofia city is chosen as a pilot area for modelling. An approach for 3D transformation of proprietary geospatial data into CityGML schemas is presented. The integration of the buildings and terrain is an essential part of it, since the buildings often partially float over or sink into the terrain. A web application for user interaction with the 3D city model is developed. Its main features include silhouetting a single building, showing relevant overlay content, displaying shadows and styling of buildings depending on their attributes.

scholarly journals WHAT IS THE NEED FOR BUILDING PARTS? – A COMPARISON OF CITYGML, INSPIRE BUILDING AND A SWEDISH BUILDING STANDARD

2018 ◽  
Vol XLII-4/W10 ◽  
pp. 27-32 ◽  
Author(s):  
H. Eriksson ◽  
L. Harrie ◽  
J. M. Paasch
Keyword(s):  
Industry Foundation Classes ◽  
3D City Models ◽  
Advantages And Disadvantages ◽  
3D City Model ◽  
Information Models ◽  
Building Information ◽  
Potential Applications ◽  
City Model ◽  
Definition Of ◽  
City Models

<p><strong>Abstract.</strong> The need for digital building information is increasing, both in the form of 3D city models (as geodata) and of more detailed building information models (BIM). BIM models are mainly used in the architecture, engineering and construction industry, but have recently become interesting also for municipalities. The overall aim of this paper is to study one way of dividing a building, namely the division of a building into building parts in both 3D city models and in BIM models. The study starts by an inventory of how building parts are defined in 3D city model standards (CityGML, the INSPIRE building specification and a Swedish national specification for buildings) and in BIM models (Industry Foundation Classes, IFC). The definition of building parts in these specifications are compared and evaluated. The paper also describes potential applications for the use of building parts, on what grounds a building could be divided into building parts, advantages and disadvantages of having building parts and what consequences it can have on the usage of the building information. One finding is that building parts is defined similar, but not identical in the studied geodata specifications and there are no requirements, only recommendations on how buildings should be divided into building parts. This can complicate the modelling, exchange and reuse of building information, and in a longer perspective, it would be desirable to have recommendations of how to define and use building parts in for example a national context.</p>

scholarly journals Review of machine learning algorithms' application in pharmaceutical technology

2021 ◽  
Vol 71 (4) ◽  
pp. 302-317
Author(s):  
Jelena Đuriš ◽  
Ivana Kurćubić ◽  
Svetlana Ibrić
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Data Science ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Formulation Development ◽  
Light Gradient ◽  
Pharmaceutical Technology ◽  
Wide Range

Machine learning algorithms, and artificial intelligence in general, have a wide range of applications in the field of pharmaceutical technology. Starting from the formulation development, through a great potential for integration within the Quality by design framework, these data science tools provide a better understanding of the pharmaceutical formulations and respective processing. Machine learning algorithms can be especially helpful with the analysis of the large volume of data generated by the Process analytical technologies. This paper provides a brief explanation of the artificial neural networks, as one of the most frequently used machine learning algorithms. The process of the network training and testing is described and accompanied with illustrative examples of machine learning tools applied in the context of pharmaceutical formulation development and related technologies, as well as an overview of the future trends. Recently published studies on more sophisticated methods, such as deep neural networks and light gradient boosting machine algorithm, have been described. The interested reader is also referred to several official documents (guidelines) that pave the way for a more structured representation of the machine learning models in their prospective submissions to the regulatory bodies.

scholarly journals THE USE OF 3D GEOVISUALIZATION AND CROWDSOURCING FOR OPTIMIZING ENERGY SIMULATION

2020 ◽  
Vol VI-4/W2-2020 ◽  
pp. 165-172
Author(s):  
S. K. Sini ◽  
R. Sihombing ◽  
P. M. Kabiro ◽  
T. Santhanavanich ◽  
V. Coors
Keyword(s):  
Energy Consumption ◽  
Building Energy ◽  
Energy Simulation ◽  
Historic Buildings ◽  
Missing Information ◽  
3D City Model ◽  
Building Information ◽  
City Model ◽  
Energy Simulations ◽  
Energy Information

Abstract. As the world continues in the quest to fight global warming and environmental pollution by gradually moving to renewable sources of energy, there is also a need to reduce building energy consumption by refurbishing old and historic buildings to meet the required energy standards. While this approach may differ from city to city across the globe, the refurbishment of old and historic buildings would make a significant impact. That is why it is necessary to educate building owners or occupants by simulating the existing energy consumption and proposing appropriate refurbishment strategies. Because the accuracy of energy simulation is directly proportional to the amount of data available and its reliability, there is a need to find creative ways of supplying incomplete or missing building information. The present paper describes a concept that enables individual building occupants or owners to provide this missing information. Implemented and tested with the 3D city model of Aachen, the proof-of-concept enables individual building owners or occupants to perform energy simulations based on energy information supplied.

scholarly journals Comparative analysis, applications, and interpretation of electronic health record-based stroke phenotyping methods

2020 ◽  
Author(s):  
Phyllis Thangaraj ◽  
Benjamin R Kummer ◽  
Tal Lorberbaum ◽  
Mitchell S.V. Elkind ◽  
Nicholas P Tatonetti
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Learning Algorithms ◽  
Case Control ◽  
Machine Learning Algorithms ◽  
Care Hospital ◽  
Diagnosis Codes ◽  
Wide Range ◽  
Electronic Health

Abstract Background: Accurate identification of acute ischemic stroke (AIS) patient cohorts is essential for a wide range of clinical investigations. Automated phenotyping methods that leverage electronic health records (EHRs) represent a fundamentally new approach cohort identification without current laborious and ungeneralizable generation of phenotyping algorithms. We systematically compared and evaluated the ability of machine learning algorithms and case-control combinations to phenotype acute ischemic stroke patients using data from an EHR.Materials and Methods: Using structured patient data from the EHR at a tertiary-care hospital system, we built and evaluated machine learning models to identify patients with AIS based on 75 different case-control and classifier combinations. We then estimated the prevalence of AIS patients across the EHR. Finally, we externally validated the ability of the models to detect AIS patients without AIS diagnosis codes using the UK Biobank.Results: Across all models, we found that the mean AUROC for detecting AIS was 0.963±0.0520 and average precision score 0.790±0.196 with minimal feature processing. Classifiers trained with cases with AIS diagnosis codes and controls with no cerebrovascular disease codes had the best average F1 score (0.832±0.0383). In the external validation, we found that the top probabilities from a model-predicted AIS cohort were significantly enriched for AIS patients without AIS diagnosis codes (60-150 fold over expected). Conclusions: Our findings support machine learning algorithms as a generalizable way to accurately identify AIS patients without using process-intensive manual feature curation. When a set of AIS patients is unavailable, diagnosis codes may be used to train classifier models.

scholarly journals Intelligent COVID-19 Forecasting, Diagnoses and Monitoring Systems: A Survey

2021 ◽  
Author(s):  
Nasreen Anjum ◽  
Amna Asif, ◽  
Mehreen Kiran ◽  
Fouzia Jabeen ◽  
Zhaohui Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Herd Immunity ◽  
Machine Learning Algorithms ◽  
Future Research ◽  
Monitoring Systems ◽  
Extensive Literature ◽  
Awareness Campaigns ◽  
Research Areas ◽  
Wide Range

<div>To date, the novel Corona virus (SARS-CoV-2) has infected millions and has caused the deaths of thousands of people around the world. At the moment, five antibodies, two from China, two from the U.S., and one from the UK, have already been widely utilized and numerous vaccines are under the trail process. In order to reach herd immunity, around 70% of the population would need to be inoculated. It may take several years to hinder the spread of SARS-CoV-2. Governments and concerned authorities have taken stringent measurements such as enforcing partial, complete, or smart lockdowns, building temporary medical facilities, advocating social distancing, and mandating masks in public as well as setting up awareness campaigns. Furthermore, there have been massive efforts in various research areas and a wide variety of tools, technologies and techniques have been explored and developed to combat the war against this pandemic. Interestingly, machine learning algorithms and internet of Things (IoTs) technology are the pioneers in this race. Up till now, several real-time and intelligent COVID-19 forecasting, diagnosing, and monitoring systems have been proposed to tackle the COVID-19 pandemic. In this article based on our extensive literature review, we provide a taxonomy based on the intelligent COVID-19 forecasting, diagnosing, and monitoring systems. We review the available literature extensively under the proposed taxonomy and have analyzed a significantly wide range of machine learning algorithms and IoTs which can be used in predicting the spread of COVID-19 and in diagnosing and monitoring the infected individuals. Furthermore, we identify the challenges and also provide our vision about the future research on COVID-19.</div>

scholarly journals Comparative analysis, applications, and interpretation of electronic health record-based stroke phenotyping methods

2020 ◽  
Author(s):  
Phyllis Thangaraj ◽  
Benjamin R Kummer ◽  
Tal Lorberbaum ◽  
Mitchell S.V. Elkind ◽  
Nicholas P Tatonetti
Keyword(s):  
Machine Learning ◽  
Ischemic Stroke ◽  
Acute Ischemic Stroke ◽  
Learning Algorithms ◽  
Case Control ◽  
Machine Learning Algorithms ◽  
Care Hospital ◽  
Diagnosis Codes ◽  
Wide Range ◽  
Electronic Health

Abstract Background: Accurate identification of acute ischemic stroke (AIS) patient cohorts is essential for a wide range of clinical investigations. Automated phenotyping methods that leverage electronic health records (EHRs) represent a fundamentally new approach cohort identification without current laborious and ungeneralizable generation of phenotyping algorithms. We systematically compared and evaluated the ability of machine learning algorithms and case-control combinations to phenotype acute ischemic stroke patients using data from an EHR.Materials and Methods: Using structured patient data from the EHR at a tertiary-care hospital system, we built and evaluated machine learning models to identify patients with AIS based on 75 different case-control and classifier combinations. We then estimated the prevalence of AIS patients across the EHR. Finally, we externally validated the ability of the models to detect AIS patients without AIS diagnosis codes using the UK Biobank.Results: Across all models, we found that the mean AUROC for detecting AIS was 0.963±0.0520 and average precision score 0.790±0.196 with minimal feature processing. Classifiers trained with cases with AIS diagnosis codes and controls with no cerebrovascular disease codes had the best average F1 score (0.832±0.0383). In the external validation, we found that the top probabilities from a model-predicted AIS cohort were significantly enriched for AIS patients without AIS diagnosis codes (60-150 fold over expected). Conclusions: Our findings support machine learning algorithms as a generalizable way to accurately identify AIS patients without using process-intensive manual feature curation. When a set of AIS patients is unavailable, diagnosis codes may be used to train classifier models.

Sign in / Sign up

Export Citation Format

Share Document