Improving facilities lifecycle management using RFID localization and BIM-based visual analytics
Bibliographic record
Abstract
Indoor localization has gained importance as it has the potential to improve various processes related to the lifecycle management of facilities, such as the manual search to find assets.In the operation and maintenance phase, the lack of standards for interoperability and the difficulties related to the processing of large amount of accumulated data from different sources cause several process inefficiencies.For example, identifying failure cause-effect patterns in order to prepare maintenance plans is difficult due to the complex interactions and interdependencies between different building components and the existence of the related data in multiple, fragmented sources.Building Information Modelling (BIM) is emerging as a method for creating, sharing, exchanging and managing the information throughout the lifecycle of buildings.Radio Frequency Identification (RFID), on the other hand, has emerged as an automatic data collection technology, and has been used in different applications for the lifecycle management of facilities.The previous research of the author proposed permanently attaching RFID tags to assets where the memory of the tags is populated with their accumulated lifecycle information taken from a standard BIM database to enhance various lifecycle processes.This thesis builds on this framework and investigates several methods for supporting lifecycle management processes of assets by using BIM, RFID iv and visual analytics.It investigates the usage of location-related data that can be retrieved from a BIM and are stored on RFID tags.It also investigates the usage of RFID technology for indoor localization of RFID-equipped assets using handheld readers.The research proposes using the location data saved on the tags attached to fixed assets to locate them on the floor plan.These tags also act as reference tags to locate moveable assets using received signal pattern matching and clustering algorithms.Additionally, the research investigates extending BIM to incorporate RFID information.It provides the opportunity to interrelate BIM and RFID data using predefined relationships.For this purpose, a requirements' gathering is performed to add new entities, data types, relationships, and property sets to the BIM.Moreover, the research investigates the potential of BIM visualization to help facilities managers make better decisions in the operation and maintenance phase of the lifecycle.It proposes a knowledge-assisted BIMbased visual analytics approach for failure root-cause detection in facilities management where various sources of lifecycle data are integrated with a BIM and used for interactive visualization exploiting the heuristic problem solving ability of field experts.v ACNOWLEDGEMENT My greatest appreciation goes to my supervisor, Dr. Amin Hammad for his intellectual and personal support, encouragement and patience.His guidance, advice and criticism was my most valuable asset during my studies.Overall, I feel very fortunate having the opportunity to know him and work with him.I would like to thank my research colleagues for their kind support in developing the simulation environment, preparing 3D models and performing field tests.I would like to acknowledge the contributions of Mr. Mohammad Soltani for developing the simulation environment, software programming of the RFID data logger application, and his help performing RFID localization field tests.His enthusiasm in conducting research was a great asset in our collaboration.I appreciate his recommendations related to RFID localization and BIM extension modules of my research.Mr. Shayan Setayeshgar has contributed to this research by developing several 3D models for the BIM extension project.His technical knowledge together with his teamwork skills made our collaboration very successful.Mr. Yoosef Asen developed the BIM model for the Genomics Research Center and assisted in developing the case study for FM visual analytics project.Mr. Kehinde Adetiloye helped in developing the mobile application for fixed asset localization.The
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".