Application of artificial intelligence in wearable devices: Opportunities and challenges
Author links open overlay panelDarius Nahavandi a, Roohallah Alizadehsani a, Abbas Khosravi (Senior IEEE) a, U Rajendra Acharya (Senior IEEE) b c d
Show more
Share
Cite https://doi.org/10.1016/j.cmpb.2021.106541Get rights and content
•
Different types of wearable devices are introduced.
•
The body parts on which the wearable devises are installed are investigated.
•
Distribution of existing wearable devices based on target body parts and their applications is presented.
•
Comprehensive treatment of domain-specific applications of wearable devices such as sports, healthcare, industrial and manufacturing is provided.
• Wearable technologies challenges such as data collection, data transmission, etc. are pointed out.
•
Future directions regarding application of artificial intelligence methods in wearable devices are discussed.
Abstract Background and objectives
: Wearable technologies have added completely new and fast emerging tools to the popular field of personal gadgets. Aside from being fashionable and equipped with advanced hardware technologies such as communication modules and networking, wearable devices have the potential to fuel artificial intelligence (AI) methods with a wide range of valuable data. Methods
: Various AI techniques such as supervised, unsupervised, semi-supervised and reinforcement learning (RL) have already been used to carry out various tasks. This paper reviews the recent applications of wearables that have leveraged AI to achieve their objectives. Results
: Particular example applications of supervised and unsupervised learning for medical diagnosis are reviewed. Moreover, examples combining the internet of things, wearables, and RL are reviewed. Application examples of wearables will be also presented for specific domains such as medical, industrial, and sport. Medical applications include fitness, movement disorder, mental health, etc. Industrial applications include employee performance improvement with the aid of wearables. Sport applications are all about providing better user experience during workout sessions or professional gameplays. Conclusion
: The most important challenges regarding design and development of wearable devices and the computation burden of using AI methods are presented. Finally, future challenges and opportunities for wearable devices are presented.
Introduction
Wearables are small electronic and mobile devices, or computers with wireless communication capabilities incorporated into gadgets, accessories, or clothes, which can be worn on the human body. There are also invasive versions of the wearables such as micro-chips or smart tattoos [1]. Nowadays, different types of wearable devices have been invented. Some of the most common wearable devices are smart glasses and smart watches. The consumer market of the wearable devices is increasing steadily. The wearables are used to collect, transmit and even analyze the data commonly collected from the body of a human or animal. They are purely mechanical devices or intelligent mechatronic systems which are commonly built using sensors, actuators, and computation parts. They can be used for early diagnosis and management of medical conditions as well as measuring the vital signs such as body and skin temperature, blood pressure [2], heart rate, electrocardiogram (ECG) [3], and electroencephalogram (EEG) [4]. All these wearable devices are implemented with various technologies, capabilities and costs. People who use these technologies may need some skills to work with them.
Wearable devices are classified based on their requirement and usage. Some of them are used according to the instructions of physicians to avoid serious problems. However, some wearables are not used in medical fields [5], [6], [7]. In [8], a comprehensive review of wearable devices was done in which, smart wearable devices such as watches, eyewear, headsets, jewelry, rings, chains, garments, and bracelets were described. The list of these devices can be seen in Fig. 1 [9].
Wearable devices are made in different forms to meet their usage requirements. They are commonly in small size while they are expected to sense continuously. They should be able to collect data and process them to improve the quality of life. Therefore, wearables need to communicate in a secure way while keeping their power consumption as low as possible. The security of wearable devices is a big challenge. They may be able to collect the data locally or send them to an external device. In both cases, the data should be encrypted to enforce their privacy. Given that wearable devices usually have low computational power, a lightweight authentication test is needed. In addition, wearable devices must be able to communicate in real-time; such requirement impacts on the challenge of power consumption management.
The motivation behind this review is the fact that the emerging field of wearable devices has the potential to open new application opportunities in various domains. The focus of this review is on medical, industrial, and sport applications. We focused on the medical domain since it is directly related to the lives of people. With enough development, wearables have the potential to revolutionize the medical domain leading to cost-effective healthcare services and longer lifetimes. In the industrial domain, wearable devices can make workstations more ergonomic. To this end, the workers can be equipped with appropriate wearable devices in order to accelerate the industrial processes leading to shortened working hours and better psychological health. The sport domain is also important since it can be used for medical diagnosis and treatment. Additionally, sport is directly related to the general well-being of society. Therefore, sport domain is also an important domain that is worth reviewing.
A comprehensive review of existing wearables, their capabilities and shortcomings can shape future research directions. In this review, wearable devices as well as the role of AI methods to achieve various tasks with wearables are investigated. The employed paper collection strategy is outlined in Section 2. Various wearables are reviewed briefly in Section 3. Denoising methods used in wearables are explained in Section 4. Feature extraction, engineering and artificial intelligence methods used are described in Section 5. The applications of machine learning in wearable devices are presented in Section 6. Applications of wearables are explained in Section 7. The challenges of developing wearables are reported in Section 7.4. Discussion and future insights will be presented in Section 9 and the conclusion is given in Section 10. Access through your organization
Check access to the full text by signing in through your organization.
Section snippets Paper collection strategy
For reviewing previous papers in the field of wearables, all datasets supported by Google scholar such as IEEE, Science Direct, Springer, ACM Digital Library, and Hindawi were searched. The search query used in this work was:
(wearable technology healthcare OR wearable devices OR wearables OR smart wears OR wearable technology OR industrial wearable OR sports wearable) AND (artificial intelligence OR data mining OR deep learning OR machine learning).
Three authors inspected the papers collected Brief review of wearables
Wearables can be used for data collection in daily activities, sport performance, and health monitoring. There are different types of wearables such as smartwatches, hearing aids, electronic tattoos, wristbands, subcutaneous sensors, head-mounted displays, electronic textiles, and footwear as shown in Fig. 3(a) [10]. These devices are placed on different body parts to measure electrophysiological and biochemical signals or deliver drugs.
Wearable devices are used for augmented, virtual, and Denoising methods used in wearables
Signals, which have been gathered from wearable sensors, are commonly affected by noise. The noise sources are generated when the measuring element and the data collection system try to collect the signals. This section aims to introduce the AI-based hardware designed for denoising. As real information generated by biological systems, randomness of these systems are relatively low while the real information collected in time are often correlated.
For denoising, researchers have used different Artificial intelligence methods
In this section, at first, feature extraction and engineering is reviewed and then different categories of AI methods i.e. supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning are introduced. These learning methods and their main subfields are shown in Fig. 6. Application of machine learning algorithms in wearables
Various machine learning methods have been used in the field of wearables. In this section, some of existing works which combine wearable devices with machine learning algorithms are reviewed. The review has been categorized based on type of machine learning methods. The summary of works done using wearables and AI techniques are shown in Table 1. Wearable applications
Wearables have already emerged in various application domains such as eyewear, sport trackers, healthcare, industry, etc. The wearable technologies are not exclusive to medical applications and they share common hardware/software across different domains. Therefore, reviewing wearables in different domains provides a broader perspective about wearable technologies. To gain better insight on the potential applications of wearables, applications related to healthcare, manufacturing, and Wearable technologies challenges
Nowadays, wearable devices are often available in the form of smartwatches which can connect with smartphones. In the future, wearables are expected to be seen in various forms designed for different applications. The world of the future is the world of wearable devices that can help the humankind in doing his duties. They can market in the fastest possible time by sharing the collected data and help to maximize the profit. It can be generalized to other aspects of life like in medical, Discussion
Wearables provide various monitoring and scanning features such as biofeedback or other sensory physiological functions like biometry-related ones [137]. Moreover, wearables are portable and can be used hands-free. Wearable devices may improve life quality significantly but first, they have to be cost-effective.
According to [138], about half of people who purchase a wearable stop using it. One-third of them do this before six months. As reported in [139], elderly people have shown interest in Conclusion
Wearable technology is an essential building block in future information and communication technology (ICT) systems. However, wearable technology has not reached an acceptable level of maturity yet. Multiple challenges are still unaddressed with regard to data collection, data processing, communications, security, etc. The aim of this review was to give readers a broad overview of applications of wearable devices in sport, medical, and industrial domains. In the future, it will be useful to
BRN Price at posting:
31.0¢ Sentiment: Buy Disclosure: Held
(20min delay)