SI - Tiny Machine Learning in Biomedical Imaging - Journal of Intelligent Systems, Open Access

TMLBI 2022

Artificial Intelligence

* Prof. Deepak Khazanchi, University of Nebraska at Omaha, Nebraska
* Dr. Celestine Iwendi, School of Creative Technologies, University of Bolton, UK
* Dr. Kamal Kant Hiran, Aalborg University, Copenhagen, Denmark (Lead Guest Editor)
In recent years, the development of biomedical imaging techniques, integrative sensors, deep learning, and machine learning brings many benefits to healthcare. Deep Learning and tiny Machine Learning (tinyML) are both quickly growing in the industry and are becoming more
accessible to companies. We can collect, measure, and analyze vast volumes of health-related data using the technologies of computing and networking, leading to tremendous opportunities for the health and biomedical community. Because of the increasing number of microcontrollers, there are now chips that do only one task on a device. More efficient, less expensive, and faster are the standard design goals of embedded devices today. Machines learn how to perform calculations and gather data by directly interacting with the microcontroller. Now, manufacturers want to increase what machines can do by introducing them to microcontrollers. Now biomedical
devices can be equipped with low-latency, low power, and low bandwidth inference models.
The intersection of embedded Machine Learning (ML) applications, algorithms, hardware, and software makes tinyML a pivotal platform for various ML uses. In contrast to machine learning that relies on software, such as the cloud, or hardware, such as servers, tinyML necessitates both embedded hardware expertise and software expertise This special issue will overview the state-of-the-art methods and algorithms at the forefront of biomedical and health informatics data. We are open to novelty ideas and significant results in the spirit of low-latency, low-power embedded machine learning model development utilizing tinyML and deep learning techniques.
We seek contributions that include, but are not limited to:
- Novel applications of tinyML in biomedical imaging acquisition, reconstruction, and analysis.
- Challenges in deploying tinyML in Ultra-Low-Power Microcontrollers.
- Development of low-latency tinyML and Deep-Learning model for diagnosis of disease.
- Energy optimization of embedded hardware implementing tiny algorithms.
- Cloud-edge computing systems for biomedical applications employingtinyML.
- Computational efficient biomedical image synthesis, segmentation, registration, and reconstruction.
- Un/Semi/Supervised tinyML model in biomedical image computing.
- TinyML and Deep-Learning model under limited, sparse, incomplete andhighly imbalanced inputs.
- tinyML and deep learning techniques for real-time wearable sensor dataanalytics.
- New datasets and benchmarks for tinyML and Deep-Learning techniques.
- The submitted article must be original, unpublished, and not currently reviewed by other journals.
- Authors must mention in their cover letter for each Special Issue manuscript that the particular manuscript is for the theme and name of Guest Editors of Special Issue consideration so that the Guest Editors can be notified separately.
Please visit, when submitting your paper please select the article type "S.I.: tiny Machine Learning in Biomedical imaging"
We are looking forward to your submission!
In case of any further questions please contact:
Editorial Office -