Time Series are used in healthcare, meteorology, and many other fields. Rigorous research has been done to develop distance measures and classifying algorithms for time series. When a time series is classified, one can ask what changes should be made to the time series to classify it differently. A time series with the appropriate changes that make the classifier classify the time series as a different class is known as a counterfactual explanation. There exist model-dependent methods for creating counterfactual explanations. However, there exists a lack in the literature of a model agnostic method for creating counterfactual explanations for Time Series. This study aims to answer the following research question. ” How does a model agnostic method for counterfactuals for time series perform in terms of cost and compactness compared to model dependent algorithms for counterfactuals for time series?” To answer the research question, a model agnostic method for creating counterfactuals for time series was created named Multi-Objective Counterfactuals For Time Series. The Evaluation of the Multi-Objective Counterfactual Explanation For Time Series performed better than the modeldependent algorithms in Compactness but worse in Cost.

Explainable AI (XAI) has grown as an important field over the years. As more complicated AI systems are utilised in decision-making situations, the necessity for explanations for such systems is also increasing in order to ensure transparency and stakeholder trust. This study focuses on a specific type of explanation method, namely counterfactual explanations. Counterfactual explanations provide feedback that outlines what changes should be made to the input to reach a different outcome. This study expands on a previous dissertation in which a proof-of-concept tool was created for comparing several counterfactual explanation methods. This thesis investigates the properties of counterfactual explanation methods along with some appropriate metrics. The identified metrics are then used to evaluate and compare the desirable properties of the counterfactual approaches. The proof-of-concept tool is extended with a properties-metrics mapping module, and a user preference-based system is developed, allowing users to evaluate different counterfactual approaches depending on their preferences. This addition to the proof-of-concept tool is a critical step in providing field researchers with a standardised benchmarking tool.

Machine learning models are widely used in various industries. However, the black-box nature of the model limits users’ understanding and trust in its inner workings, and the interpretability of the model becomes critical. For example, when a person’s loan application is rejected, he may want to understand the reason for the rejection and seek to improve his personal information to increase his chances of approval. Counterfactual explanation is a method used to explain the different outcomes of a specific event or situation. It modifies or manipulates the original data to generate counterfactual instances to make the model make other decision results. This paper proposes a counterfactual explanation method based on Generative Adversarial Networks (GAN) and applies it to image recognition. Counterfactual explanation aims to make the model change the predictions by modifying the feature information of the input image. Traditional machine learning methods have apparent shortcomings in computational resources when training and have specific bottlenecks in practical applications. This article builds a counterfactual explanation model based on Deep Convolutional Generative Adversarial Network (DCGAN).The original random noise input of DCGAN is converted into an image, and the perturbation is generated by the generator in the GAN network, which is combined with the original image to generate counterfactual samples. The experimental results show that the counterfactual samples generated based on GAN are better than the traditional machine learning model regarding generation efficiency and accuracy, thus verifying the effectiveness and advancement of the method proposed in this article.