1 code implementation • 12 Oct 2023 • Zhendong Wang, Ioanna Miliou, Isak Samsten, Panagiotis Papapetrou
In this paper, we formulate the novel problem of counterfactual generation for time series forecasting, and propose an algorithm, called ForecastCF, that solves the problem by applying gradient-based perturbations to the original time series.
no code implementations • 25 Jul 2023 • Andrew Aquilina, Sean Diacono, Panagiotis Papapetrou, Maria Movin
The consumption of podcast media has been increasing rapidly.
1 code implementation • Artificial Intelligence in Medicine 2023 • Zhendong Wang, Isak Samsten, Vasiliki Kougia, Panagiotis Papapetrou
In this paper, we propose a counterfactual solution MedSeqCF for preventing the mortality of three cohorts of ICU patients, by representing their electronic health records as medical event sequences, and generating counterfactuals by adopting and employing a text style-transfer technique.
1 code implementation • 30 May 2022 • Lena Mondrejevski, Ioanna Miliou, Annaclaudia Montanino, David Pitts, Jaakko Hollmén, Panagiotis Papapetrou
Thus, the federated approach can be seen as a valid and privacy-preserving alternative to centralized machine learning for classifying ICU mortality when sharing sensitive patient data between hospitals is not possible.
no code implementations • 2 Nov 2021 • Amin Azari, Fateme Salehi, Panagiotis Papapetrou, Cicek Cavdar
There is a lack of research on the analysis of per-user traffic in cellular networks, for deriving and following traffic-aware network management.
1 code implementation • International Conference on Discovery Science 2021 • Zhendong Wang, Isak Samsten, Rami Mochaourab, Panagiotis Papapetrou
Counterfactual explanations can provide sample-based explanations of features required to modify from the original sample to change the classification result from an undesired state to a desired state; hence it provides interpretability of the model.
1 code implementation • International Conference on Artificial Intelligence in Medicine 2021 • Zhendong Wang, Isak Samsten, Panagiotis Papapetrou
In recent years, machine learning methods have been rapidly implemented in the medical domain.
no code implementations • 7 Feb 2021 • Rami Mochaourab, Sugandh Sinha, Stanley Greenstein, Panagiotis Papapetrou
For such classifiers, counterfactual explanations need to be robust against the uncertainties in the SVM weights in order to ensure, with high confidence, that the classification of the data instance to be explained is different than its explanation.
no code implementations • 22 Jun 2020 • John Pavlopoulos, Panagiotis Papapetrou
We show that a neural language model can achieve as high as 51. 3% accuracy in radiology reports (one out of two words predicted correctly).
1 code implementation • 11 Jun 2020 • Vasiliki Kougia, John Pavlopoulos, Panagiotis Papapetrou, Max Gordon
This paper introduces RTEx, a novel methodology for a) ranking radiography exams based on their probability to contain an abnormality, b) generating abnormality tags for abnormal exams, and c) providing a diagnostic explanation in natural language for each abnormal exam.
no code implementations • 13 Jul 2019 • Maria Bampa, Panagiotis Papapetrou
The challenge in this work is to aggregate heterogeneous data types involving diagnosis codes, drug codes, as well as lab measurements.
no code implementations • 3 Jun 2019 • Amin Azari, Panagiotis Papapetrou, Stojan Denic, Gunnar Peters
In this paper, we study the problem of network traffic traffic prediction and classification by employing standard machine learning and statistical learning time series prediction methods, including long short-term memory (LSTM) and autoregressive integrated moving average (ARIMA), respectively.
no code implementations • 9 May 2019 • Amin Azari, Panagiotis Papapetrou, Stojan Denic, Gunnar Peters
Traffic prediction plays a vital role in efficient planning and usage of network resources in wireless networks.
1 code implementation • 13 Sep 2018 • Isak Karlsson, Jonathan Rebane, Panagiotis Papapetrou, Aristides Gionis
We show that the problem is NP-hard, and focus on two instantiations of the problem, which we refer to as reversible and irreversible time series tweaking.
1 code implementation • 27 Dec 2016 • Andreas Henelius, Kai Puolamäki, Henrik Boström, Panagiotis Papapetrou
In this study, we propose a technique for quantifying the instability of a clustering solution and for finding robust clusters, termed core clusters, which correspond to clusters where the co-occurrence probability of each data item within a cluster is at least $1 - \alpha$.