A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Enhancing digital twin efficiency in indoor environments: Virtual sensor-driven optimization of physical sensor combinations
Abstract Multiple sensor nodes are preferred for the development of digital twins in indoor environments; however, it poses significant financial burdens. Therefore, considering both cost-effectiveness and information richness, optimal physical sensor placement and efficient virtual sensor operation must be balanced. Data-driven techniques for sensor placement prioritize locations via statistical metrics, information fidelity, and signal strength. When extending spatial sensing through virtual sensors, the indirectly determined physical sensor sites encounter challenges like multicollinearity and overfitting, hampering the reliability of predictive models (virtual sensors). To address this, this study introduces an algorithm that selects optimal physical sensor combinations based exclusively on virtual sensor performance. The results highlight the superiority of our proposed algorithm over conventional methods for virtual sensor development. Notably, our approach reduces computational workload compared to brute-force methods. This algorithm provides an economical means to manage extensive data and holds substantial promise for advancing digital twin capabilities in indoor environments.
Highlights Algorithm to optimize physical sensor placement for virtual sensor performance. Error rates below 2% obtained in various test scenarios. Outperformed other data-driven methodologies in virtual sensor performance. An economical solution for effective digital twin development in indoor environments.
Enhancing digital twin efficiency in indoor environments: Virtual sensor-driven optimization of physical sensor combinations
Abstract Multiple sensor nodes are preferred for the development of digital twins in indoor environments; however, it poses significant financial burdens. Therefore, considering both cost-effectiveness and information richness, optimal physical sensor placement and efficient virtual sensor operation must be balanced. Data-driven techniques for sensor placement prioritize locations via statistical metrics, information fidelity, and signal strength. When extending spatial sensing through virtual sensors, the indirectly determined physical sensor sites encounter challenges like multicollinearity and overfitting, hampering the reliability of predictive models (virtual sensors). To address this, this study introduces an algorithm that selects optimal physical sensor combinations based exclusively on virtual sensor performance. The results highlight the superiority of our proposed algorithm over conventional methods for virtual sensor development. Notably, our approach reduces computational workload compared to brute-force methods. This algorithm provides an economical means to manage extensive data and holds substantial promise for advancing digital twin capabilities in indoor environments.
Highlights Algorithm to optimize physical sensor placement for virtual sensor performance. Error rates below 2% obtained in various test scenarios. Outperformed other data-driven methodologies in virtual sensor performance. An economical solution for effective digital twin development in indoor environments.
Enhancing digital twin efficiency in indoor environments: Virtual sensor-driven optimization of physical sensor combinations
Shin, Hakjong (author) / Kwak, Younghoon (author)
2024-02-06
Article (Journal)
Electronic Resource
English
Digital twin , Virtual sensor , Physical sensor placement , Data-driven method , BIM , Building Information Modeling , CN , Challenging Node , EBM , Error-Based Method , HBM , HSIC-based method , HSIC , Hilbert-Schmidt Independence Criterion , HVAC , Heating, Ventilation, and Air Conditioning , IEQ , Indoor Environmental Quality , IoT , Internet of Things , MAPE , Mean Absolute Percent Error , OC , Optimal Combination , PC , Promising Combination , PS , Parameter Set , RSSI , Received Signal Strength Indicator , VPPC , Virtual sensor Performance-based Physical sensor Combination
A physical-virtual based digital twin robotic hand
| Springer Verlag | 2024
A physical-virtual based digital twin robotic hand
| Springer Verlag | 2024