The Past, Present, and Prospective Future of XAI: A Comprehensive Review

Islam, Muhammad Usama; Mottalib, Md. Mozaharul; Hassan, Mehedi; Alam, Zubair Ibne; Zobaed, SM; Rabby, Md. Fazle

doi:10.1007/978-3-030-96630-0_1

Cited by 14 publications

(7 citation statements)

References 103 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several components of XAI are currently available that has the ability to explain the results to user [71], [72]. Feature importance, feature dependencies, what-if analysis, partial dependence, feature interaction, correlation, decision trees are to name a few components that can be used to explain the insights, the technical details of which is described through evolution of XAI research through SHAP, PDP, LIME, SHA-PASH and so forth [71], [73].…”

Section: B Insight Explanationmentioning

confidence: 99%

A Framework to Enhance User Experience of Older Adults With Speech-Based Intelligent Personal Assistants

Islam

Chaudhry

2023

IEEE Access

View full text Add to dashboard Cite

Speech-based Intelligent Personal Assistants (sIPAs) available in the market are evolving towards the needs of older adults. They are currently being used for entertainment, generic tasks, and reminders primarily. We conducted a semi-structured interview study with fourteen older adults to understand whether they found sIPA useful or not. The collected data were analyzed using inductive and deductive coding. In accordance with our insights generated from the interview, we propose a future research framework, including permission to store data, using explainable artificial intelligence principles, dialect and accent recognition, and humanized communication to improve virtual assistants in the design to make them efficient and fruitful for older adults daily use.INDEX TERMS Older adults, virtual assistants, usability, text tagging, inductive and deductive coding

show abstract

Section: B Insight Explanationmentioning

confidence: 99%

A Framework to Enhance User Experience of Older Adults With Speech-Based Intelligent Personal Assistants

Islam

Chaudhry

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Several methods are available in explaining the results of which SHapley Additive exPlanations (SHAP) is a wellknown XAI method [34]. Other XAI techniques include LIME, DeepLIFT, as well as layer-wise relevance propagation.…”

Section: Explainable Ai Visualizationmentioning

confidence: 99%

Advanced Persistent Threat Identification with Boosting and Explainable AI

2023

Self Cite

View full text Add to dashboard Cite

Advanced persistent threat (APT) is a serious concern in cyber-security that has matured and grown over the years with the advent of technology. The main aim of this study is to establish an effective identification model for APT attacks to prevent and reduce their influence. Machine learning has the potential as well as substantial background to detect and predict cyber-security threats including APT. This study utilized several boosting-based machine learning methods to predict various types of APTs that are consistent in cyber-security domain. Furthermore, Explainable Artificial Intelligence (XAI) was coupled with the predictions to provide actionable insights to the domain stakeholders as well as practitioners in this domain. The results, particularly XGBoost with weighted F1 score of 0.97 and SHapley Additive exPlanations (SHAP)-based explanation, prove that boosting methods as well as machine learning models paired with XAI are indeed promising in handling cyber-security-related dataset problems which can be extrapolated towards new avenues of challenging research by effectively deploying boosting-based XAI models.

show abstract

“…XAI techniques can be used to verify the trustworthiness of models and gain insight into how they can be improved. In NLP, there are several options for explaining the inner workings of models, which can be categorized based on their approaches, such as surrogate model, example-driven, induction, provenance, and feature-importance [ 28 ]. Surrogate model XAI techniques involve training a second model to explain predictions, while example-driven XAI techniques provide comparable examples to explain predictions.…”

Section: Related Workmentioning

confidence: 99%

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

et al. 2023

View full text Add to dashboard Cite

Understanding the diagnostic goal of medical reports is valuable information for understanding patient flows. This work focuses on extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring. We investigate the performance of domain-dependent and general state-of-the-art language models and their alignment with domain expertise. To this end, eXplainable Artificial Intelligence (XAI) techniques are used to acquire insight into the inner workings of the model, which are verified on their trustworthiness. The verified XAI explanations are then compared with explanations from a domain expert, to indirectly determine the reliability of the model. BERTje, a Dutch Bidirectional Encoder Representations from Transformers (BERT) model, outperforms RobBERT and MedRoBERTa.nl in both accuracy and reliability. The latter model (MedRoBERTa.nl) is a domain-specific model, while BERTje is a generic model, showing that domain-specific models are not always superior. Our validation of BERTje in a small prospective study shows promising results for the potential uptake of the model in a practical setting.

show abstract

The Past, Present, and Prospective Future of XAI: A Comprehensive Review

Cited by 14 publications

References 103 publications

A Framework to Enhance User Experience of Older Adults With Speech-Based Intelligent Personal Assistants

A Framework to Enhance User Experience of Older Adults With Speech-Based Intelligent Personal Assistants

Advanced Persistent Threat Identification with Boosting and Explainable AI

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

Contact Info

Product

Resources

About