Contextual Importance and Utility: A Theoretical Foundation

Främling, Kary

doi:10.1007/978-3-030-97546-3_10

Cited by 10 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third model-agnostic algorithm, influenced by Decision Theory and Multiple Criteria Decision Making (MCDM), separates measured importance and attribute utility, emphasizing contextual importance (CI) based on feature relevance [48,50].…”

Section: Ciu In Detailmentioning

confidence: 99%

See 1 more Smart Citation

XplAInable: Explainable AI Smoke Detection at the Edge

Lehnert,

Gawantka,

During

et al. 2024

BDCC

View full text Add to dashboard Cite

Wild and forest fires pose a threat to forests and thereby, in extension, to wild life and humanity. Recent history shows an increase in devastating damages caused by fires. Traditional fire detection systems, such as video surveillance, fail in the early stages of a rural forest fire. Such systems would see the fire only when the damage is immense. Novel low-power smoke detection units based on gas sensors can detect smoke fumes in the early development stages of fires. The required proximity is only achieved using a distributed network of sensors interconnected via 5G. In the context of battery-powered sensor nodes, energy efficiency becomes a key metric. Using AI classification combined with XAI enables improved confidence regarding measurements. In this work, we present both a low-power gas sensor for smoke detection and a system elaboration regarding energy-efficient communication schemes and XAI-based evaluation. We show that leveraging edge processing in a smart way combined with buffered data samples in a 5G communication network yields optimal energy efficiency and rating results.

show abstract

Section: Ciu In Detailmentioning

confidence: 99%

“…C by comparing it to the overall range of predictions across all contexts and feature sets. For a more comprehensive understanding, refer to the paper by Kary Främling [48,50,51].…”

Section: Ciu In Detailmentioning

confidence: 99%

XplAInable: Explainable AI Smoke Detection at the Edge

Lehnert,

Gawantka,

During

et al. 2024

BDCC

View full text Add to dashboard Cite

show abstract

“…Based on the relevance of the features, the focus lies on contextual importance (CI). This is described in [19,25] as follows:…”

Section: Ciumentioning

confidence: 99%

“…The functions absmax j and absmin j determine the highest and lowest prediction from the given data set. More details are provided in [19,25,26].…”

Section: Ciumentioning

confidence: 99%

See 1 more Smart Citation

A Novel Metric for Evaluating the Stability of XAI Explanations

Gawantka,

Just,

Savelyeva

et al. 2024

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Automated systems are increasingly exerting influence on our lives, evident in scenarios like AI-driven candidate screening for jobs or loan applications. These scenarios often rely on eXplainable Artificial Intelligence (XAI) algorithms to meet legal requirements and provide understandable insights into critical processes. However, a significant challenge arises when some XAI methods lack determinism, resulting in the generation of different explanations for identical inputs (i.e., the same data instances and prediction model). The question of explanation stability becomes paramount in such cases. In this study, we introduce two intuitive methods for assessing the stability of XAI algorithms. A taxonomy was developed to categorize the evaluation criteria and the ideas were expanded to create an objective metric to classify the XAI algorithms based on their explanation stability.

show abstract

Integration of Local and Global Features Explanation with Global Rules Extraction and Generation Tools

Contreras

Schumacher

Calvaresi

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Widely used in a growing number of domains, Deep Learning predictors are achieving remarkable results. However, the lack of transparency (i.e., opacity) of their inner mechanisms has raised trust and employability concerns. Nevertheless, several approaches fostering models of interpretability and explainability have been developed in the last decade. This paper combines approaches for local feature explanation (i.e., Contextual Importance and Utility -CIU) and global feature explanation (i.e., Explainable Layers) with a rule extraction system, namely ECLAIRE. The proposed pipeline has been tested in four scenarios employing a breast cancer diagnosis dataset. The results show improvements such as the production of more human-interpretable rules and adherence of the produced rules with the original model.

show abstract

Contextual Importance and Utility: A Theoretical Foundation

Cited by 10 publications

References 6 publications

XplAInable: Explainable AI Smoke Detection at the Edge

XplAInable: Explainable AI Smoke Detection at the Edge

A Novel Metric for Evaluating the Stability of XAI Explanations

Integration of Local and Global Features Explanation with Global Rules Extraction and Generation Tools

Contact Info

Product

Resources

About