Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Subject: search.filters.subject.Data heterogeneity

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Data Format Heterogeneity in IoT-Based Ambient Assisted Living: A Survey
    (Springer Science and Business Media Deutschland GmbH, 2023) Sandeep, M.; Khatri, S.; Chandavarkar, B.R.
    Ambient Assisted Living (AAL) has become a significant component of the lives of the elderly in the present decade, allowing them to live independently by assisting their daily activities with automation. Different sensors from various manufacturers with proprietary data formats to detect environmental changes and monitor a person’s health metrics. These data formats are the root cause of the data Heterogeneity issue in AAL and, in turn, contribute to data interoperability challenges. In this paper, we have presented a survey on currently available state-of-the-art solutions to address data heterogeneity challenges in AAL and made a comparative study of suggested methods to overcome the data interoperability. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
  • No Thumbnail Available
    Item
    Enhancing Healthcare AI with Cross-Silo Personalized Federated Learning on Naturally Split Heterogeneous Data
    (Institute of Electrical and Electronics Engineers Inc., 2024) Mukeshbhai, A.N.; Annappa, B.; Sachin, D.N.
    The potential of Artificial Intelligence (AI) in health-care is unavoidable. However, its success depends on the availabil-ity of large, high-quality datasets. Because of data heterogeneity across institutions and privacy concerns, traditional centralized Machine Learning (ML) approaches often face difficulties in this field. Federated Learning (FL) allows collaborative model training without requiring the transfer of sensitive patient data from the original institution. Recent research in FL within the healthcare domain has predominantly relied on centralized datasets, which do not represent real-time data heterogeneity and made assumptions by random data splitting to different medical client institutions. Additionally, it may be challenging for a single global model to encompass the diverse characteristics of various healthcare settings accurately. This paper examines the application of Personalized Federated Learning (PFL) in realistic cross-silo healthcare scenarios with federated natural split datasets in different medical client institutions. This paper discusses the experiments conducted on brain segmentation, survival prediction, melanoma classification, and heart disease di-agnosis. Our experiments show that the proposed PFL techniques consistently improve local model performance over standard FL strategies by up to 10% in different medical use cases. © 2024 IEEE.