Interpretable Model-Agnostic Explanations Based on Feature Relationships for High-Performance Computing

Chen, Zhouyuan; Lian, Zhichao; Xu, Zhe

doi:10.3390/axioms12100997

Cited by 3 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study of interpretable neural networks, Zhang et al [10] classified interpretable models according to three dimensions: type of engagement (passive and active interpretation methods), the type of explanation, and the focus (from local to global explainability). Chen et al [11] proposed a post-event locally interpretable model applied to image data, obtained the disturbed samples to be classified through local Mask sampling, and trained a simple linear model to interpret the field of interest of the local output labels of complex models. Tejaswini et al [12] proposed using decision tree to construct a model equivalent to neural network, which is a global rule extraction method.…”

Section: Introductionmentioning

confidence: 99%

Coupling Fault Diagnosis Based on Dynamic Vertex Interpretable Graph Neural Network

Wang,

Jing,

Pan

et al. 2024

Preprint

View full text Add to dashboard Cite

Mechanical equipment is composed of several parts, the interaction between the parts exists throughout whole life cycle leads to the widespread phenomenon of fault coupling and the diagnosis of independent faults cannot meet the requirements of the health management of mechanical equipment under actual working conditions. In this paper, the topological structure of graph neural network is used to describe the correlation of coupling faults and multiple fault types are regarded as network nodes respectively. The fault features are fused and extracted by graph convolution to achieve the classification of coupling faults. In this paper, dynamic vertexes are defined in data topology and the parameters of DIGNN classification model are optimized by changing the fault type of dynamic vertexes during training stage. The data is loaded into dynamic vertexes for classification and analysis during testing stage. The one-dimensional vibration data is converted into two-dimensional time-frequency domain data by wavelet transform making the input features of the model interpretable to reduce the uncertainty of model training. The data topology is then fed into DIGNN for fault classification, and GCN's node aggregation gives interpretability to each layer of network data processing. The method proposed in this paper can realize accurate diagnosis of independent faults on the data set, and can effectively judge the coupling mode of coupling faults, which is suitable for coupling fault analysis of mechanical equipment.

show abstract

Section: Introductionmentioning

confidence: 99%

Coupling Fault Diagnosis Based on Dynamic Vertex Interpretable Graph Neural Network

Wang,

Jing,

Pan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Recent Applications of Explainable AI (XAI): A Systematic Literature Review

Saarela,

Podgorelec

2024

Applied Sciences

View full text Add to dashboard Cite

This systematic literature review employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of explainable AI (XAI) over the past three years. From an initial pool of 664 articles identified through the Web of Science database, 512 peer-reviewed journal articles met the inclusion criteria—namely, being recent, high-quality XAI application articles published in English—and were analyzed in detail. Both qualitative and quantitative statistical techniques were used to analyze the identified articles: qualitatively by summarizing the characteristics of the included studies based on predefined codes, and quantitatively through statistical analysis of the data. These articles were categorized according to their application domains, techniques, and evaluation methods. Health-related applications were particularly prevalent, with a strong focus on cancer diagnosis, COVID-19 management, and medical imaging. Other significant areas of application included environmental and agricultural management, industrial optimization, cybersecurity, finance, transportation, and entertainment. Additionally, emerging applications in law, education, and social care highlight XAI’s expanding impact. The review reveals a predominant use of local explanation methods, particularly SHAP and LIME, with SHAP being favored for its stability and mathematical guarantees. However, a critical gap in the evaluation of XAI results is identified, as most studies rely on anecdotal evidence or expert opinion rather than robust quantitative metrics. This underscores the urgent need for standardized evaluation frameworks to ensure the reliability and effectiveness of XAI applications. Future research should focus on developing comprehensive evaluation standards and improving the interpretability and stability of explanations. These advancements are essential for addressing the diverse demands of various application domains while ensuring trust and transparency in AI systems.

show abstract

BIM Integration with XAI Using LIME and MOO for Automated Green Building Energy Performance Analysis

Khan,

Tariq,

Rehman

et al. 2024

Energies

View full text Add to dashboard Cite

Achieving sustainable green building design is essential to reducing our environmental impact and enhancing energy efficiency. Traditional methods often depend heavily on expert knowledge and subjective decisions, posing significant challenges. This research addresses these issues by introducing an innovative framework that integrates building information modeling (BIM), explainable artificial intelligence (AI), and multi-objective optimization. The framework includes three main components: data generation through DesignBuilder simulation, a BO-LGBM (Bayesian optimization–LightGBM) predictive model with LIME (Local Interpretable Model-agnostic Explanations) for energy prediction and interpretation, and the multi-objective optimization technique AGE-MOEA to address uncertainties. A case study demonstrates the framework’s effectiveness, with the BO-LGBM model achieving high prediction accuracy (R-squared > 93.4%, MAPE < 2.13%) and LIME identifying significant HVAC system features. The AGE-MOEA optimization resulted in a 13.43% improvement in energy consumption, CO2 emissions, and thermal comfort, with an additional 4.0% optimization gain when incorporating uncertainties. This study enhances the transparency of machine learning predictions and efficiently identifies optimal passive and active design solutions, contributing significantly to sustainable construction practices. Future research should focus on validating its real-world applicability, assessing its generalizability across various building types, and integrating generative design capabilities for automated optimization.

show abstract

Interpretable Model-Agnostic Explanations Based on Feature Relationships for High-Performance Computing

Cited by 3 publications

References 32 publications

Coupling Fault Diagnosis Based on Dynamic Vertex Interpretable Graph Neural Network

Coupling Fault Diagnosis Based on Dynamic Vertex Interpretable Graph Neural Network

Recent Applications of Explainable AI (XAI): A Systematic Literature Review

BIM Integration with XAI Using LIME and MOO for Automated Green Building Energy Performance Analysis

Contact Info

Product

Resources

About