Browsing by Subject "explainable AI"

Now showing 1 - 2 of 2

Access status: Open Access ,
Developing explainable machine-learning model using augmented concept activation vector
(Wydawnictwa AGH, 2025) Hassanpour, Reza; Oztoprak, Kasim; Netten, Niels; Busker, Tony; Bargh, Mortaza S.; Choenni, Sunil; Kizildag, Beyza; Kilinc, Leyla Sena
Machine-learning models use high-dimensional feature spaces to map their inputs to the corresponding class labels; however, these features often do not have a one-to-one correspondence with the physical concepts that are understandable by humans. This hinders the ability to provide meaningful explanations for the decisions that are made by these models. We propose a method for measuring the correlation between high-level concepts and the decisions that are made by machine-learning models. Our method can isolate the impact of a given high-level concept and accurately measure it quantitatively. Additionally, this study aims to determine the prevalence of frequent patterns in machine-learning models that often occur in imbalanced data sets. We successfully applied the proposed method to fundus images and managed to quantitatively measure the impacts of the radiomic patterns on the model’s decisions.
Access status: Open Access ,
Explainable deep neural network-based analysis on intrusion-detection systems
(Wydawnictwa AGH, 2023) Pande, Sagar Dhanraj; Khamparia, Aditya
The research on intrusion-detection systems (IDSs) has been increasing in recent years. Particularly, this research widely utilizes machine-learning concepts, and it has proven that these concepts are effective with IDSs - particularly, deep neural network-based models have enhanced the rates of the detection of IDSs. In the same instance, these models are turning out to be very complex, and users are unable to track down explanations for the decisions that are made, this indicates the necessity of identifying the explanations behind those decisions to ensure the interpretability of the framed model. In this aspect, this article deals with a proposed model that can explain the obtained predictions. The proposed framework is a combination of a conventional IDS with the aid of a deep neural network and the interpretability of the model predictions. The proposed model utilizes Shapley additive explanations (SHAPs) that mixes the local explainability as well as the global explainability for the enhancement of interpretations in the case of IDS. The proposed model was implemented by using popular data sets (NSL-KDD and UNSW-NB15), and the performance of the framework was evaluated by using their accuracy. The framework achieved accuracy levels of 99.99 and 99.96%, respectively. The proposed framework can identify the top-4 features using local explainability and the top-20 features using global explainability.