Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Biological tissues (1)
- Classification (1)
- Collaborative local models (1)
- Data-driven global model (1)
- Deep learning (1)
-
- Dielectrohoreisis (1)
- Distinct imaging features (1)
- Electric fields (1)
- Electrodes (1)
- Electronic equipment (1)
- Energy harvesting (1)
- Feature extraction (1)
- Federated learning (1)
- Global model shifts (1)
- Haar wavelets (1)
- Harmonic multiscale based (1)
- Harmonization (1)
- Harmonized image feature space (1)
- Health care (1)
- Histopathological images (1)
- Image classification (1)
- Image representation (1)
- Image segmentation (1)
- Imaging scanner protocols (1)
- Internet of things (1)
- Learning (artificial intelligence) (1)
- Local domain (1)
- Local model weight shift (1)
- Machine learning approach (1)
- Medical image processing (1)
Articles 1 - 4 of 4
Full-Text Articles in Biomedical
Recent Progress In Microrna Detection Using Integrated Electric Fields And Optical Detection Methods, Logeeshan Velmanickam, Dharmakeerthi Nawarathna
Recent Progress In Microrna Detection Using Integrated Electric Fields And Optical Detection Methods, Logeeshan Velmanickam, Dharmakeerthi Nawarathna
Electrical & Computer Engineering Faculty Publications
Low-cost, highly-sensitivity, and minimally invasive tests for the detection and monitoring of life-threatening diseases and disorders can reduce the worldwide disease burden. Despite a number of interdisciplinary research efforts, there are still challenges remaining to be addressed, so clinically significant amounts of relevant biomarkers in body fluids can be detected with low assay cost, high sensitivity, and speed at point-of-care settings. Although the conventional proteomic technologies have shown promise, their ability to detect all levels of disease progression from early to advanced stages is limited to a limited number of diseases. One potential avenue for early diagnosis is microRNA (miRNA). …
Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim
Adversarial Training Based Domain Adaptation Of Skin Cancer Images, Syed Qasim Gilani, Muhammad Umair, Maryam Naqvi, Oge Marques, Hee-Cheol Kim
Electrical & Computer Engineering Faculty Publications
Skin lesion datasets used in the research are highly imbalanced; Generative Adversarial Networks can generate synthetic skin lesion images to solve the class imbalance problem, but it can result in bias and domain shift. Domain shifts in skin lesion datasets can also occur if different instruments or imaging resolutions are used to capture skin lesion images. The deep learning models may not perform well in the presence of bias and domain shift in skin lesion datasets. This work presents a domain adaptation algorithm-based methodology for mitigating the effects of domain shift and bias in skin lesion datasets. Six experiments were …
Energy Harvesting Face Mask Using A Thermoelectric Generator For Powering Wearable Health Monitoring Sensors, Ugur Erturun, Cansu Yalim, James E. West
Energy Harvesting Face Mask Using A Thermoelectric Generator For Powering Wearable Health Monitoring Sensors, Ugur Erturun, Cansu Yalim, James E. West
Engineering Management & Systems Engineering Faculty Publications
A wearable energy harvester (EH) incorporating a face mask with a thermoelectric generator is demonstrated. The function of this device is to generate electrical power from the heat produced by the human body, particularly breath, with the specific aim of powering wearable sensor applications. A prototype was built using a commercially available N95 face mask, a thermoelectric generator, and a heatsink. The performance of this EH device was assessed using experimental and numerical methodologies. The experimentally tested power output of the prototype was found to be ≈100 µW, with a corresponding power density of ≈30 µW/cm3, for a temperature difference …
Wavelet-Based Harmonization Of Local And Global Model Shifts In Federated Learning For Histopathological Images, W. Farzana, A. Temtam, K. M. Iftekharuddin
Wavelet-Based Harmonization Of Local And Global Model Shifts In Federated Learning For Histopathological Images, W. Farzana, A. Temtam, K. M. Iftekharuddin
Electrical & Computer Engineering Faculty Publications
Federated Learning (FL) is a promising machine learning approach for development of data-driven global model using collaborative local models across multiple local institutions. However, the heterogeneity of medical imaging data is one of the challenges within FL. This heterogeneity is caused by the variation in imaging scanner protocols across institutions, which may result in weight shift among local models leading to deterioration in predictive accuracy of global model. The prevailing approaches involve applying different FL averaging techniques to enhance the performance of the global model, ignoring the distinct imaging features of the local domain. In this work, we address both …