Deep learning has become one of the trendiest fields in recent years. Nonetheless, it is an appealing and hard undertaking to do tasks related to computer vision, natural language processing, speech recognition, bioinformatics, and smart health care. Acquiring information and significant knowledge from complex, high-dimensional, and heterogeneous biomedical data sources remains a critical test in changing health care. Different kinds of data have been arising in present-day biomedical exploration, including electronic health records, imaging, sensor data, and information, which are perplexing, heterogeneous, inadequately explained and for the most part unstructured. Conventional data mining and machine learning approaches regularly need to initially perform feature designing to acquire robust and more vigorous features from those data and afterward build prediction or clustering models on top of them. There are several severe difficulties on the two stages in the case of complex data and lacking adequate domain information. Based on machine learning, medical IoT devices, detection and diagnosis through imaging, automated surgeries and other several techniques have been in use in real-world and some are still under development. A few potential issues like security, QoS improvement, and arrangement demonstrate the vital piece of deep learning. We reveal working principle, deep learning for health care including images and text, smart devices and privacy issues in health care data.

Role of Deep Learning for Smart Health Care

Calimeri F.
2022

Abstract

Deep learning has become one of the trendiest fields in recent years. Nonetheless, it is an appealing and hard undertaking to do tasks related to computer vision, natural language processing, speech recognition, bioinformatics, and smart health care. Acquiring information and significant knowledge from complex, high-dimensional, and heterogeneous biomedical data sources remains a critical test in changing health care. Different kinds of data have been arising in present-day biomedical exploration, including electronic health records, imaging, sensor data, and information, which are perplexing, heterogeneous, inadequately explained and for the most part unstructured. Conventional data mining and machine learning approaches regularly need to initially perform feature designing to acquire robust and more vigorous features from those data and afterward build prediction or clustering models on top of them. There are several severe difficulties on the two stages in the case of complex data and lacking adequate domain information. Based on machine learning, medical IoT devices, detection and diagnosis through imaging, automated surgeries and other several techniques have been in use in real-world and some are still under development. A few potential issues like security, QoS improvement, and arrangement demonstrate the vital piece of deep learning. We reveal working principle, deep learning for health care including images and text, smart devices and privacy issues in health care data.
978-3-030-96428-3
978-3-030-96429-0
Deep learning
Internet of medical things
Privacy issues
Smart health care
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/339128
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact