no code implementations • 28 Jan 2024 • Jasin Machkour, Michael Muma, Daniel P. Palomar
In recent years, multivariate false discovery rate (FDR) controlling methods have emerged, providing guarantees even in high-dimensional settings where the number of variables surpasses the number of samples.
no code implementations • 26 Jan 2024 • Jasin Machkour, Daniel P. Palomar, Michael Muma
In high-dimensional data analysis, such as financial index tracking or biomedical applications, it is crucial to select the few relevant variables while maintaining control over the false discovery rate (FDR).
no code implementations • 18 Jan 2024 • Taulant Koka, Jasin Machkour, Michael Muma
Unfortunately, well-established estimators, such as the graphical lasso or neighborhood selection, are known to be susceptible to a high prevalence of false edge detections.
no code implementations • 16 Jan 2024 • Jasin Machkour, Arnaud Breloy, Michael Muma, Daniel P. Palomar, Frédéric Pascal
Sparse principal component analysis (PCA) aims at mapping large dimensional data to a linear subspace of lower dimension.
1 code implementation • 2 Dec 2023 • Aylin Tastan, Michael Muma, Abdelhak M. Zoubir
The block diagonal structure of an affinity matrix is a commonly desired property in cluster analysis because it represents clusters of feature vectors by non-zero coefficients that are concentrated in blocks.
1 code implementation • European Signal Processing Conference 2023 • Jonas Emrich, Taulant Koka, Sebastian Wirth, Michael Muma
Further acceleration is obtained by adopting the computationally efficient horizontal visibility graph, which has not yet been used for R-peak detection.
1 code implementation • 25 May 2023 • Christian A. Schroth, Christian Eckrich, Ibrahim Kakouche, Stefan Fabian, Oskar von Stryk, Abdelhak M. Zoubir, Michael Muma
The large number and scale of natural and man-made disasters have led to an urgent demand for technologies that enhance the safety and efficiency of search and rescue teams.
no code implementations • 14 Dec 2022 • Taulant Koka, Manolis C. Tsakiris, Michael Muma, Benjamín Béjar Haro
Assuming that we have a sensing matrix for the underlying signals, we show that the problem is equivalent to a structured unlabeled sensing problem, and establish sufficient conditions for unique recovery.
no code implementations • 1 Apr 2022 • Stefan Vlaski, Christian Schroth, Michael Muma, Abdelhak M. Zoubir
This is followed by an aggregation step, which traditionally takes the form of a (weighted) average.
no code implementations • 12 Oct 2021 • Jasin Machkour, Michael Muma, Daniel P. Palomar
The T-Rex selector controls a user-defined target false discovery rate (FDR) while maximizing the number of selected variables.
no code implementations • 26 Jul 2021 • Aylin Tastan, Michael Muma, Abdelhak M. Zoubir
The Fiedler vector of a connected graph is the eigenvector associated with the algebraic connectivity of the graph Laplacian and it provides substantial information to learn the latent structure of a graph.
1 code implementation • 18 Nov 2020 • Aylin Tastan, Michael Muma, Abdelhak M. Zoubir
We compare the performance to popular graph and cluster-based community detection approaches on a variety of benchmark network and cluster analysis data sets.
1 code implementation • 30 Jun 2020 • Christian A. Schroth, Michael Muma
This article proposes a new class of Real Elliptically Skewed (RESK) distributions and associated clustering algorithms that allow for integrating robustness and skewness into a single unified cluster analysis framework.
3 code implementations • 4 May 2020 • Christian A. Schroth, Michael Muma
Robustly determining the optimal number of clusters in a data set is an essential factor in a wide range of applications.
no code implementations • 29 Nov 2018 • Freweyni K. Teklehaymanot, Michael Muma, Abdelhak M. Zoubir
Hence, we propose a two-step cluster enumeration algorithm that uses the expectation maximization algorithm to partition the data and estimate cluster parameters prior to the calculation of one of the robust criteria.
1 code implementation • 22 Oct 2017 • Freweyni K. Teklehaymanot, Michael Muma, Abdelhak M. Zoubir
We derive a new Bayesian Information Criterion (BIC) by formulating the problem of estimating the number of clusters in an observed data set as maximization of the posterior probability of the candidate models.
no code implementations • 31 Aug 2017 • Patricia Binder, Michael Muma, Abdelhak M. Zoubir
The cluster enumeration exploits the fact that the highest attraction on the mobile mass units is exerted by regions with a high density of feature vectors, i. e., gravitational clusters.
no code implementations • 2017 25th European Signal Processing Conference (EUSIPCO) 2017 • Tim Schäck, Michael Muma, Abdelhak M. Zoubir
Wearable devices that acquire photoplethysmographic (PPG) signals are becoming increasingly popular to monitor the heart rate during physical exercise.
Ranked #5 on Heart rate estimation on PPG-DaLiA