Smart biomedical signal analysis systems allow Artificial Intelligence (AI) and Internet of Medical Things (IoMT) to provide near constant monitoring of disease progression, bringing more awareness about patients’ conditions than ever before. Traditionally, AI has been used in cloud computing after sensor data is transferred from the bedside. Increasingly, lightweight processing, tailored algorithms, and sensor capabilities are enabling AI-computing before reaching the cloud. Bringing AI to the edge of the data pipeline, away from the cloud, can help optimize IoMT for patient care by alleviating bandwidth issues and improving patient data security. With machine intelligence, multimodality in bio-signals can bring more understanding in human health, physiology, and disease progression (and more).
The focus of this Research Topic is decentralizing AI to the origin of multimodal waveform data, towards developing new machine intelligence-based smart systems (software, hardware, and/or firmware) for addressing disease diagnosis, prognosis, and treatment response analysis using multimodal biomedical signals. This Research Topic is open to applications in the biomedical field ranging from environment to wearable to in vivo sensing. It is also open to concerns in the field ranging from accuracy and effectiveness to integration and security.
The scope ranges from signal processing, control, machine learning, sensor networks, bioinstrumentation, and beyond. The mission of this issue is to help bring research that will lay the groundwork for future innovation in biomedical sensing to the forefront. We welcome manuscripts from Original Research works to review-based works which analyze various human diseases with multimodal 1-dimensional waveforms and signals, signal denoising and quality assessment, signal clustering and classification for patients, early prediction and prognosis, treatment recovery analysis, wearable sensing, stimulation issues, and beyond. We believe this domain will surely bring new advancements and perspectives in understandability, generalizability, and robustness in healthcare.
Smart biomedical signal analysis systems allow Artificial Intelligence (AI) and Internet of Medical Things (IoMT) to provide near constant monitoring of disease progression, bringing more awareness about patients’ conditions than ever before. Traditionally, AI has been used in cloud computing after sensor data is transferred from the bedside. Increasingly, lightweight processing, tailored algorithms, and sensor capabilities are enabling AI-computing before reaching the cloud. Bringing AI to the edge of the data pipeline, away from the cloud, can help optimize IoMT for patient care by alleviating bandwidth issues and improving patient data security. With machine intelligence, multimodality in bio-signals can bring more understanding in human health, physiology, and disease progression (and more).
The focus of this Research Topic is decentralizing AI to the origin of multimodal waveform data, towards developing new machine intelligence-based smart systems (software, hardware, and/or firmware) for addressing disease diagnosis, prognosis, and treatment response analysis using multimodal biomedical signals. This Research Topic is open to applications in the biomedical field ranging from environment to wearable to in vivo sensing. It is also open to concerns in the field ranging from accuracy and effectiveness to integration and security.
The scope ranges from signal processing, control, machine learning, sensor networks, bioinstrumentation, and beyond. The mission of this issue is to help bring research that will lay the groundwork for future innovation in biomedical sensing to the forefront. We welcome manuscripts from Original Research works to review-based works which analyze various human diseases with multimodal 1-dimensional waveforms and signals, signal denoising and quality assessment, signal clustering and classification for patients, early prediction and prognosis, treatment recovery analysis, wearable sensing, stimulation issues, and beyond. We believe this domain will surely bring new advancements and perspectives in understandability, generalizability, and robustness in healthcare.