Isabell Lehmann

Isabell Lehmann

Auto-generated profile, based on publicly available information

Isabell Lehmann

Signal and System Theory Group, Paderborn University, Germany

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2024 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
BGBen Gabrielson
Ben Gabrielson
MAMohammad Abu Baker Siddique Akhonda
Mohammad Abu Baker Siddique Akhonda
ILIsabell Lehmann
Isabell Lehmann
TATülay Adali
Tülay Adali
Joint blind source separation (JBSS) is a powerful methodology for analyzing multiple related datasets, able to jointly extract sources that describe statistical dependencies across the datasets. However, JBSS can be computationally prohibitive with high-dimensional data, thus there exists a key need for more efficient JBSS algorithms. JBSS algorithms typically rely on numerical solutions, which may be expensive due to their iterative nature. In contrast, analytic solutions follow consistent procedures that are often less expensive. In this paper, we introduce an efficient analytic solution for JBSS. Denoting a set of sources dependent across the datasets as a “source component vector” (SCV), our solution minimizes correlation among separate SCVs by minimizing distance of the SCV cross-covariance’s eigenvector matrix from a block diagonal matrix. Under the orthogonality constraint, this leads to a system of linear equations wherein each subproblem has an analytic solution. We derive identifiability conditions of our solution’s estimator, and demonstrate estimation performance and time efficiency in comparison with other JBSS algorithms that exploit source correlation across datasets. Results demonstrate that our solution achieves the lowest asymptotic computational complexity among JBSS algorithms, and is capable of superior estimation performance compared with algorithms of similar complexity.

29 July 2024 in IEEE Access
Verified
Journal Article
Open access
ILIsabell Lehmann
Isabell Lehmann
THTanuj Hasija
Tanuj Hasija
BGBen Gabrielson
Ben Gabrielson
MAMohammad A. B. S. Akhonda
Mohammad A. B. S. Akhonda
VCVince Calhoun
Vince Calhoun
TATülay Adali
Tülay Adali
Identifying relationships among multiple datasets is an effective way to summarize information and has been growing in importance. In this paper, we propose a robust 3-step method for identifying the relationship structure among multiple datasets based on Independent Vector Analysis (IVA) and bootstrap-based hypothesis testing. Unlike previous approaches, our theory-backed method eliminates the need for user-defined thresholds and can effectively handle non-Gaussian data. It achieves this by incorporating higher-order statistics through IVA and employing an eigenvalue decomposition-based feature extraction approach without distributional assumptions. This way, our method estimates more interpretable components and effectively identifies the relationship structure using hierarchical clustering. Simulation results demonstrate the effectiveness of our method, as it achieves perfect Adjusted Mutual Information (AMI) for different values of the correlation between the components. When applied to multi-task fMRI data from patients with schizophrenia and healthy controls, our method successfully reveals activated brain regions associated with the disorder, and identifies the relationship structure of task datasets that matches our prior knowledge of the experiment. Moreover, our proposed method extends beyond task datasets, offering broad applicability in subgroup identification in neuroimaging and other domains.

24 October 2025 in IEEE Transactions on Signal Processing
Verified
Journal Article
Open access
ILIsabell Lehmann
Isabell Lehmann
BGBen Gabrielson
Ben Gabrielson
THTanuj Hasija
Tanuj Hasija
TATülay Adali
Tülay Adali
Multiset Canonical Correlation Analysis (mCCA), also called Generalized Canonical Correlation Analysis (GCCA), is a technique to identify correlated variables across multiple datasets, which can be used for feature extraction in fields like neuroscience, cross-language information retrieval, and recommendation systems, among others. Besides its wide use, there is still a lack of comprehensive understanding of its theory and implementation with different objective functions all under one umbrella. In this paper, we review the five commonly used mCCA methods sumcor, maxvar, minvar, genvar, and ssqcor. We provide a concise overview of their optimization problems along with their solutions and pseudocodes. After this, we discuss the application of mCCA for estimating underlying latent components in the Joint Blind Source Separation (JBSS) problem and propose the source identification conditions of the different mCCA methods, i.e., the conditions under which they are able to achieve JBSS. We substantiate the proposed theoretical conditions with numerical results and test the statistical efficiency of the methods for finite samples. We observe in our experiments that genvar appears to have the least restrictive source identification conditions and to be more statistically efficient that the other methods. This suggests that genvar is generally the best-performing mCCA method for JBSS except for special cases, which is an important finding, as the most commonly used mCCA methods are maxvar and sumcor.