Hybrid Intelligent System for Medical Diagnosis in Health Care

Abstract

AbstractThe autonomous city implies a global vision that incorporates artificial intelligence, deep learning, big data, decision-making, ICT and the Internet of Things (IoT) to promote sustainable development. The ageing issue is that researchers, companies and the government should devote efforts to developing smart health care, innovative technology and applications. For an extended period, conventional intelligence systems have played a critical role in health care. However, with the increased popularity and widespread use of these hybrid intelligent computer systems, there is a significant shift in the healthcare sector. Diagnosis and detection of various diseases using several techniques can be resolved by using these techniques. Different novel methods are applied to biomedical engineering to diagnose diseases, and new models are being studied and compared with the existing technologies. Hybrid intelligence systems can be implied in decision-making, remote monitoring, healthcare logistics, medical diagnosis, and modern information system. This success's fundamental cause seems to be derived by different intelligent computational mechanisms, such as genetic algorithms, evolutionary computation, convolutional neural network (CNN), long short-term memory (LSTM), autoencoders, deep generative models and deep belief networks. To solve complex problems, we need domain knowledge that comprises the methodologies that provide hybrid systems with complementary reasoning and empirical data. This chapter will focus on the need for a hybrid intelligent system in the healthcare industry and their medical diagnosis applicability.KeywordsIntelligent systemDeep learningGenetic algorithmsNeural networksHybrid intelligence systemComputational intelligence