Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability

Zafar, Muhammad Rehman; Khan, Naimul

doi:10.3390/make3030027

Cited by 151 publications

(68 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the LIME stability assessment, additional indicators may be helpful; they make it possible to increase confidence in the achieved results of calculations and to avoid cases when different explanations for the same forecasts are obtained [53]. One of the possible ways is to reduce instability in the obtained explanations, e.g., by replacing random perturbation of data with agglomerative hierarchical clustering (AHC) [54]. The robust model interpretability can sometimes be difficult due to the application of local approximation based on linear models, which may be inadequate for many analyzed problems.…”

Section: Resultsmentioning

confidence: 99%

Justifying Short-Term Load Forecasts Obtained with the Use of Neural Models

Grzeszczyk

2022

Energies

View full text Add to dashboard Cite

There is a lot of research on the neural models used for short-term load forecasting (STLF), which is crucial for improving the sustainable operation of energy systems with increasing technical, economic, and environmental requirements. Neural networks are computationally powerful; however, the lack of clear, readable and trustworthy justification of STLF obtained using such models is a serious problem that needs to be tackled. The article proposes an approach based on the local interpretable model-agnostic explanations (LIME) method that supports reliable premises justifying and explaining the forecasts. The use of the proposed approach makes it possible to improve the reliability of heuristic and experimental neural modeling processes, the results of which are difficult to interpret. Explaining the forecasting may facilitate the justification of the selection and the improvement of neural models for STLF, while contributing to a better understanding of the obtained results and broadening the knowledge and experience supporting the enhancement of energy systems security based on reliable forecasts and simplifying dispatch decisions.

show abstract

Section: Resultsmentioning

confidence: 99%

Justifying Short-Term Load Forecasts Obtained with the Use of Neural Models

Grzeszczyk

2022

Energies

View full text Add to dashboard Cite

show abstract

“…After deriving the SVM-based regression model for battery electrode mass loading prediction, to further explain these related predictions, the local interpretable model-agnostic explanation (LIME) is utilized. It should be known that LIME belongs to a model-agnostic solution which could mimic the underlying behaviors of a black box model for generating the explanation of the related prediction (Zafar and Khan, 2021).…”

Section: Local Interpretable Model-agnostic Explanationsmentioning

confidence: 99%

Battery Electrode Mass Loading Prognostics and Analysis for Lithium-Ion Battery–Based Energy Storage Systems

et al. 2021

View full text Add to dashboard Cite

With the rapid development of renewable energy, the lithium-ion battery has become one of the most important sources to store energy for many applications such as electrical vehicles and smart grids. As battery performance would be highly and directly affected by its electrode manufacturing process, it is vital to design an effective solution for achieving accurate battery electrode mass loading prognostics at early manufacturing stages and analyzing the effects of manufacturing parameters of interest. To achieve this, this study proposes a hybrid data analysis solution, which integrates the kernel-based support vector machine (SVM) regression model and the linear model–based local interpretable model-agnostic explanation (LIME), to predict battery electrode mass loading and quantify the effects of four manufacturing parameters from mixing and coating stages of the battery manufacturing chain. Illustrative results demonstrate that the derived hybrid data analysis solution is capable of not only providing satisfactory battery electrode mass loading prognostics with over a 0.98 R-squared value but also effectively quantifying the effects of four key parameters (active material mass content, solid-to-liquid ratio, viscosity, and comma-gap) on determining battery electrode properties. Due to the merits of explainability and data-driven nature, the design data–driven solution could assist engineers to obtain battery electrode information at early production cases and understand strongly coupled parameters for producing batteries, further benefiting the improvement of battery performance for wider energy storage applications.

show abstract

“…Nellithimaru proposed a new grape yield estimation method that combines instance segmentation and SLAM to obtain grape information [21], which improves the accuracy. However, the above mentioned deep neural network-based methods still have the problem of low robustness when analyzing characterization information such as the size of grape berries from dense and unconstrained grape images [22].…”

Section: Introductionmentioning

confidence: 99%

Grape Berry Detection and Size Measurement Based on Edge Image Processing and Geometric Morphology

Luo

et al. 2021

Machines

View full text Add to dashboard Cite

Counting grape berries and measuring their size can provide accurate data for robot picking behavior decision-making, yield estimation, and quality evaluation. When grapes are picked, there is a strong uncertainty in the external environment and the shape of the grapes. Counting grape berries and measuring berry size are challenging tasks. Computer vision has made a huge breakthrough in this field. Although the detection method of grape berries based on 3D point cloud information relies on scanning equipment to estimate the number and yield of grape berries, the detection method is difficult to generalize. Grape berry detection based on 2D images is an effective method to solve this problem. However, it is difficult for traditional algorithms to accurately measure the berry size and other parameters, and there is still the problem of the low robustness of berry counting. In response to the above problems, we propose a grape berry detection method based on edge image processing and geometric morphology. The edge contour search and the corner detection algorithm are introduced to detect the concave point position of the berry edge contour extracted by the Canny algorithm to obtain the best contour segment. To correctly obtain the edge contour information of each berry and reduce the error grouping of contour segments, this paper proposes an algorithm for combining contour segments based on clustering search strategy and rotation direction determination, which realizes the correct reorganization of the segmented contour segments, to achieve an accurate calculation of the number of berries and an accurate measurement of their size. The experimental results prove that our proposed method has an average accuracy of 87.76% for the detection of the concave points of the edge contours of different types of grapes, which can achieve a good edge contour segmentation. The average accuracy of the detection of the number of grapes berries in this paper is 91.42%, which is 4.75% higher than that of the Hough transform. The average error between the measured berry size and the actual berry size is 2.30 mm, and the maximum error is 5.62 mm, which is within a reasonable range. The results prove that the method proposed in this paper is robust enough to detect different types of grape berries.

show abstract

Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability

Cited by 151 publications

References 27 publications

Justifying Short-Term Load Forecasts Obtained with the Use of Neural Models

Justifying Short-Term Load Forecasts Obtained with the Use of Neural Models

Battery Electrode Mass Loading Prognostics and Analysis for Lithium-Ion Battery–Based Energy Storage Systems

Grape Berry Detection and Size Measurement Based on Edge Image Processing and Geometric Morphology

Contact Info

Product

Resources

About