About this Research Topic
In the past two decades, machine learning (ML) has been dramatically developed and is still experiencing a fast and ever-lasting change in paradigm, methodology, application, and other aspects. In particular, deep learning (DL), a popular and emerging technique in machine learning, is currently leading a revolution for the domain of artificial intelligence and its applications (e.g. healthcare and biomedical engineering).
On one hand, recent breakthroughs in Big Data, Internet of Things (IoT), 5G, Cloud Computing, High Performance Computing (HPC), Wearable Devices, etc., will significantly benefit the relevant studies on ML/DL for non/less-invasive methods applied to the field of health informatics (e.g. diagnosis, treatment, and management of diseases, assistive technologies in daily life, AI-based rehabilitation apparatuses, etc.). On the other hand, there are numerous challenges and issues ranging from technical and ethical points of view that need to be addressed.
To this end, we are calling for contributions to this Research Topic to explore how we can leverage the power of AI to facilitate non/less-invasive methods for early diagnosis of serious diseases, monitoring of chronic diseases and management of clinical practice (e.g. patient-centered health records). The Research Topic aims to answer the following questions:
a. How can we compare and combine the advantages of classical ML and DL?
b. How can we overcome data scarcity (e.g. limited annotated data) in health informatics?
c. How can we build explainable and responsible AI-based systems for healthcare and social well-being applications?
d. What are the current findings and limitations for real-world applications?
e. Are ethical issues a critical point in AI for healthcare, and how can we solve it?
f. How can we use the cutting-edge AI methods to benefit the diagnosis and treatment in not only physiological but also mental diseases?
In conjunction with the 8th China Sound and Music Technology Conference CSMT2020, we welcome prospective authors from multidisciplinary backgrounds (engineering, medical, technical, and even social scholars are very welcome) to submit Original Research articles, Short Communications in recent breakthroughs or findings, Comprehensive or Mini Reviews, Perspectives and Opinions. Please note this Research Topic is open to public submissions, as well as those based on talks given at the conference.
Relevant topics include but are not limited to:
• Signal processing and machine learning for non/less-invasive methods in health informatics;
• Deep learning technologies in fast and efficient diagnosis and monitoring of diseases;
• Smart wearable devices that applied to daily life;
• IoT-based intelligent system for healthcare and social well-being;
• General AI-based applications for elderly, children and special needs;
• AI-related ethical issues in health informatics;
• ML and DL for diagnosis, treatment, and management of mental diseases.
We would like to acknowledge that Dr. Lin Song has acted as coordinator and contributed to the preparation of the proposal for this Research Topic.
On one hand, recent breakthroughs in Big Data, Internet of Things (IoT), 5G, Cloud Computing, High Performance Computing (HPC), Wearable Devices, etc., will significantly benefit the relevant studies on ML/DL for non/less-invasive methods applied to the field of health informatics (e.g. diagnosis, treatment, and management of diseases, assistive technologies in daily life, AI-based rehabilitation apparatuses, etc.). On the other hand, there are numerous challenges and issues ranging from technical and ethical points of view that need to be addressed.
To this end, we are calling for contributions to this Research Topic to explore how we can leverage the power of AI to facilitate non/less-invasive methods for early diagnosis of serious diseases, monitoring of chronic diseases and management of clinical practice (e.g. patient-centered health records). The Research Topic aims to answer the following questions:
a. How can we compare and combine the advantages of classical ML and DL?
b. How can we overcome data scarcity (e.g. limited annotated data) in health informatics?
c. How can we build explainable and responsible AI-based systems for healthcare and social well-being applications?
d. What are the current findings and limitations for real-world applications?
e. Are ethical issues a critical point in AI for healthcare, and how can we solve it?
f. How can we use the cutting-edge AI methods to benefit the diagnosis and treatment in not only physiological but also mental diseases?
In conjunction with the 8th China Sound and Music Technology Conference CSMT2020, we welcome prospective authors from multidisciplinary backgrounds (engineering, medical, technical, and even social scholars are very welcome) to submit Original Research articles, Short Communications in recent breakthroughs or findings, Comprehensive or Mini Reviews, Perspectives and Opinions. Please note this Research Topic is open to public submissions, as well as those based on talks given at the conference.
Relevant topics include but are not limited to:
• Signal processing and machine learning for non/less-invasive methods in health informatics;
• Deep learning technologies in fast and efficient diagnosis and monitoring of diseases;
• Smart wearable devices that applied to daily life;
• IoT-based intelligent system for healthcare and social well-being;
• General AI-based applications for elderly, children and special needs;
• AI-related ethical issues in health informatics;
• ML and DL for diagnosis, treatment, and management of mental diseases.
We would like to acknowledge that Dr. Lin Song has acted as coordinator and contributed to the preparation of the proposal for this Research Topic.
Keywords: Machine Learning, Deep Learning, Wearable Devices, Healthcare, Non/Less-Invasive Methods
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
