arXiv subjects

Manav Mahan Singh

Publications and source records attributed to Manav Mahan Singh.

3 recordsLinked to original sources

arXiv2024

Explainable AI for Engineering Design: A Unified Approach of Systems Engineering and Component- Based Deep Learning Demonstrated by Energy- Efficient Building Design

Data-driven models created by machine learning, gain in importance in all fields of design and engineering. They, have high potential to assist decision-makers in creating novel, artefacts with better performance and sustainability. However,, limited generalization and the black-box nature of these models, lead to limited explainability and reusability. To overcome this, situation, we propose a component-based approach to create, partial component models by machine learning (ML). This, component-based approach aligns deep learning with systems, engineering (SE). The key contribution of the component-based, method is that activations at interfaces between the components, are interpretable engineering quantities. In this way, the, hierarchical component system forms a deep neural network, (DNN) that a priori integrates information for engineering, explainability. The, approach adapts the model structure to engineering methods of, systems engineering and to domain knowledge. We examine the, performance of the approach by the field of energy-efficient, building design: First, we observed better generalization of the, component-based method by analyzing prediction accuracy, outside the training data. Especially for representative designs, different in structure, we observe a much higher accuracy, (R2 = 0.94) compared to conventional monolithic methods, (R2 = 0.71). Second, we illustrate explainability by exemplary, demonstrating how sensitivity information from SE and rules, from low-depth decision trees serve engineering. Third, we, evaluate explainability by qualitative and quantitative methods, demonstrating the matching of preliminary knowledge and data-driven, derived strategies and show correctness of activations at, component interfaces compared to white-box simulation results, (envelope components: R2 = 0.92..0.99; zones: R2 = 0.78..0.93).

cs.LG↗

arXiv2023

Utilizing Domain Knowledge: Robust Machine Learning for Building Energy Prediction with Small, Inconsistent Datasets

The demand for a huge amount of data for machine learning (ML) applications is currently a bottleneck in an empirically dominated field. We propose a method to combine prior knowledge with data-driven methods to significantly reduce their data dependency. In this study, component-based machine learning (CBML) as the knowledge-encoded data-driven method is examined in the context of energy-efficient building engineering. It encodes the abstraction of building structural knowledge as semantic information in the model organization. We design a case experiment to understand the efficacy of knowledge-encoded ML in sparse data input (1% - 0.0125% sampling rate). The result reveals its three advanced features compared with pure ML methods: 1. Significant improvement in the robustness of ML to extremely small-size and inconsistent datasets; 2. Efficient data utilization from different entities' record collections; 3. Characteristics of accepting incomplete data with high interpretability and reduced training time. All these features provide a promising path to alleviating the deployment bottleneck of data-intensive methods and contribute to efficient real-world data usage. Moreover, four necessary prerequisites are summarized in this study that ensures the target scenario benefits by combining prior knowledge and ML generalization.

cs.LG↗

arXiv2022

Introducing causal inference in the energy-efficient building design process

"What-if" questions are intuitively generated and commonly asked during the design process. Engineers and architects need to inherently conduct design decisions, progressing from one phase to another. They either use empirical domain experience, simulations, or data-driven methods to acquire consequential feedback. We take an example from an interdisciplinary domain of energy-efficient building design to argue that the current methods for decision support have limitations or deficiencies in four aspects: parametric independency identification, gaps in integrating knowledge-based and data-driven approaches, less explicit model interpretation, and ambiguous decision support boundaries. In this study, we first clarify the nature of dynamic experience in individuals and constant principal knowledge in design. Subsequently, we introduce causal inference into the domain. A four-step process is proposed to discover and analyze parametric dependencies in a mathematically rigorous and computationally efficient manner by identifying the causal diagram with interventions. The causal diagram provides a nexus for integrating domain knowledge with data-driven methods, providing interpretability and testability against the domain experience within the design space. Extracting causal structures from the data is close to the nature design reasoning process. As an illustration, we applied the properties of the proposed estimators through simulations. The paper concludes with a feasibility study demonstrating the proposed framework's realization.

stat.ME↗