Machine Learning Applications for IoT Healthcare

Agarwal, Neha; Singh, Pushpa; Singh, Narendra; Singh, Krishna Kant; Jain, Rohit

doi:10.1002/9781119761884.ch6

Cited by 3 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IoT 2022, 3 ZigBee is an IEEE 802.15.4-based specification for high-level communication protocols that enables the creation of small, low-power, low data rate, low-bandwidth, and close proximity digital radio networks, such as those created for home automation applications [1]. As one of the most popular IoT protocols [2], ZigBee is specialized for building home automation applications. The protocol can be found in IKEA Smart Lighting, Philips Hue Lights, Xiaomi Mijia, and many other smart home solutions.…”

Section: Introductionmentioning

confidence: 99%

Living in the Dark: MQTT-Based Exploitation of IoT Security Vulnerabilities in ZigBee Networks for Smart Lighting Control

Hussein

Nhlabatsi

2022

IoT

View full text Add to dashboard Cite

The Internet of Things (IoT) has provided substantial enhancements to the communication of sensors, actuators, and their controllers, particularly in the field of home automation. Home automation is experiencing a huge rise in the proliferation of IoT devices such as smart bulbs, smart switches, and control gateways. However, the main challenge for such control systems is how to maximize security under limited resources such as low-processing power, low memory, low data rate, and low-bandwidth IoT networks. In order to address this challenge the adoption of IoT devices in automation has mandated the adoption of secure communication protocols to ensure that compromised key security objectives, such as confidentiality, integrity, and availability are addressed. In light of this, this work evaluates the feasibility of MQTT-based Denial of Service (DoS) attacks, Man-in-the-Middle (MitM), and masquerade attacks on a ZigBee network, an IoT standard used in wireless mesh networks. Performed through MQTT, the attacks extend to compromise neighboring Constrained Application Protocol (CoAP) nodes, a specialized service layer protocol for resource-constrained Internet devices. By demonstrating the attacks on an IKEA TRÅDFRI lighting system, the impact of exploiting ZigBee keys, the basis of ZigBee security, is shown. The reduction of vulnerabilities to prevent attacks is imperative for application developers in this domain. Two Intrusion Detection Systems (IDSs) are proposed to mitigate against the proposed attacks, followed by recommendations for solution providers to improve IoT firmware security. The main motivation and purpose of this work is to demonstrate that conventional attacks are feasible and practical in commercial home automation IoT devices, regardless of the manufacturer. Thus, the contribution to the state-of-the-art is the design of attacks that demonstrate how known vulnerabilities can be exploited in commercial IoT devices for the purpose of motivating manufacturers to produce IoT systems with improved security.

show abstract

Section: Introductionmentioning

confidence: 99%

Living in the Dark: MQTT-Based Exploitation of IoT Security Vulnerabilities in ZigBee Networks for Smart Lighting Control

Hussein

Nhlabatsi

2022

IoT

View full text Add to dashboard Cite

show abstract

Recent Advances in Artificial Intelligence and Wearable Sensors in Healthcare Delivery

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) and wearable sensors are gradually transforming healthcare service delivery from the traditional hospital-centred model to the personal-portable-device-centred model. Studies have revealed that this transformation can provide an intelligent framework with automated solutions for clinicians to assess patients’ general health. Often, electronic systems are used to record numerous clinical records from patients. Vital sign data, which are critical clinical records are important traditional bioindicators for assessing a patient’s general physical health status and the degree of derangement happening from the baseline of the patient. The vital signs include blood pressure, body temperature, respiratory rate, and heart pulse rate. Knowing vital signs is the first critical step for any clinical evaluation, they also give clues to possible diseases and show progress towards illness recovery or deterioration. Techniques in machine learning (ML), a subfield of artificial intelligence (AI), have recently demonstrated an ability to improve analytical procedures when applied to clinical records and provide better evidence supporting clinical decisions. This literature review focuses on how researchers are exploring several benefits of embracing AI techniques and wearable sensors in tasks related to modernizing and optimizing healthcare data analyses. Likewise, challenges concerning issues associated with the use of ML and sensors in healthcare data analyses are also discussed. This review consequently highlights open research gaps and opportunities found in the literature for future studies.

show abstract

Machine Learning in Healthcare

Hamad

Ali

Saeed

2022

AI Applications for Disease Diagnosis and Treatment

View full text Add to dashboard Cite

Due to the increase in healthcare data provided by IoT, there is a need to use new methods for data analysis. Machine learning (ML) techniques promise solutions for many challenges facing the IoT-based healthcare services. MLs provide significant improvement in different IoT aspects related to storage size, computational power, and data transfer speeds. In addition, MLs provide a number of solutions for medical imaging, resources, medical data processing, detection, diagnosis, and prediction. Recently, many applications have appeared in the field of medicine and healthcare, which are closely related to the IoT. This chapter presents basic concepts related to the use of ML techniques, in addition to some algorithms used in the medical field and healthcare technology based on IoT devices and systems. Moreover, the chapter will discuss the ML opportunities and challenges in healthcare and future trends as well. The chapter gives the reader full perception of the possibility of using ML techniques in the medical and healthcare fields, with a systematic description of their applications.

show abstract

Machine Learning Applications for IoT Healthcare

Cited by 3 publications

References 33 publications

Living in the Dark: MQTT-Based Exploitation of IoT Security Vulnerabilities in ZigBee Networks for Smart Lighting Control

Living in the Dark: MQTT-Based Exploitation of IoT Security Vulnerabilities in ZigBee Networks for Smart Lighting Control

Recent Advances in Artificial Intelligence and Wearable Sensors in Healthcare Delivery

Machine Learning in Healthcare

Contact Info

Product

Resources

About