Search Results for author: Komminist Weldemariam

Found 8 papers, 0 papers with code

Domain-agnostic and Multi-level Evaluation of Generative Models

no code implementations20 Jan 2023 Girmaw Abebe Tadesse, Jannis Born, Celia Cintas, William Ogallo, Dmitry Zubarev, Matteo Manica, Komminist Weldemariam

To this end, we propose a framework for Multi-level Performance Evaluation of Generative mOdels (MPEGO), which could be employed across different domains.

BON: An extended public domain dataset for human activity recognition

no code implementations12 Sep 2022 Girmaw Abebe Tadesse, Oliver Bent, Komminist Weldemariam, Md. Abrar Istiak, Taufiq Hasan, Andrea Cavallaro

Body-worn first-person vision (FPV) camera enables to extract a rich source of information on the environment from the subject's viewpoint.

Human Activity Recognition

Pattern Detection in the Activation Space for Identifying Synthesized Content

no code implementations26 May 2021 Celia Cintas, Skyler Speakman, Girmaw Abebe Tadesse, Victor Akinwande, Edward McFowland III, Komminist Weldemariam

Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise.

Image Generation Misinformation

DeepMI: Deep Multi-lead ECG Fusion for Identifying Myocardial Infarction and its Occurrence-time

no code implementations31 Mar 2021 Girmaw Abebe Tadesse, Hamza Javed, Yong liu, Jin Liu, Jiyan Chen, Komminist Weldemariam, Tingting Zhu

We propose an end-to-end deep learning approach, DeepMI, to classify MI from normal cases as well as identifying the time-occurrence of MI (defined as acute, recent and old), using a collection of fusion strategies on 12 ECG leads at data-, feature-, and decision-level.

Transfer Learning

Prediction of neonatal mortality in Sub-Saharan African countries using data-level linkage of multiple surveys

no code implementations25 Nov 2020 Girmaw Abebe Tadesse, Celia Cintas, Skyler Speakman, Komminist Weldemariam

Existing datasets available to address crucial problems, such as child mortality and family planning discontinuation in developing countries, are not ample for data-driven approaches.

Analyzing Bias in Sensitive Personal Information Used to Train Financial Models

no code implementations9 Nov 2019 Reginald Bryant, Celia Cintas, Isaac Wambugu, Andrew Kinai, Komminist Weldemariam

Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models.

Fairness Management

Preservation of Anomalous Subgroups On Machine Learning Transformed Data

no code implementations9 Nov 2019 Samuel C. Maina, Reginald E. Bryant, William O. Goal, Robert-Florian Samoilescu, Kush R. Varshney, Komminist Weldemariam

Our evaluation confirmed that the approach was able to produce synthetic datasets that preserved a high level of subgroup differentiation as identified initially in the original dataset.

BIG-bench Machine Learning Subgroup Discovery

Subset Scanning Over Neural Network Activations

no code implementations19 Oct 2018 Skyler Speakman, Srihari Sridharan, Sekou Remy, Komminist Weldemariam, Edward McFowland

This is the first work to introduce "Subset Scanning" methods from the anomalous pattern detection domain to the task of detecting anomalous input of neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.