The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2–17 and using acute kidney injury—a common and potentially life-threatening condition18—as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment. A deep learning approach that predicts the risk of acute kidney injury may help to identify patients at risk of health deterioration within a time window that enables early treatment.

A clinically applicable approach to continuous prediction of future acute kidney injury

Visible Light Positioning (VLP) provides a promising means to achieve indoor localization with sub-meter accuracy. We observe that the Visible Light Communication (VLC) methods in existing VLP systems rely on intensity-based modulation, and thus they require a high pulse rate to prevent flickering. However, the high pulse rate adds an unnecessary and heavy burden to receiving devices. To eliminate this burden, we propose the polarization-based modulation, which is flicker-free, to enable a low pulse rate VLC. In this way, we make VLP light-weight enough even for resourceconstrained wearable devices, e.g. smart glasses. Moreover, the polarization-based VLC can be applied to any illuminating light sources, thereby eliminating the dependency on LED. This paper presents the VLP system PIXEL, which realizes our idea. In PIXEL, we develop three techniques, each of which addresses a design challenge: 1) a novel color-based modulation scheme to handle users’ mobility, 2) an adaptive downsampling algorithm to tackle the uneven sampling problem of wearables’ low-cost camera and 3) a computational optimization method for the positioning algorithm to enable real-time processing. We implement PIXEL’s hardware using commodity components and develop a software program for both smartphone and Google glass. Our experiments based on the prototype show that PIXEL can provide accurate realtime VLP for wearables and smartphones with camera resolution as coarse as 60 pixel 80 pixel and CPU frequency as low as 300MHz.

/pdf/wearables-can-afford-light-weight-indoor-positioning-with-54z10zkb1f.pdf

Wearables Can Afford: Light-weight Indoor Positioning with Visible Light (Best Paper Candidate, Best Video Presentation Award)

The Internet of Things (IoT) is basically like a system for connecting computer devices, mechanical and digital machines, objects, or individuals provided with the unique system (UIDs) and without transfer to transmit data over an ability human-to-human or computer-to-human relation. Another thing on the internet is that the items in the IoT are like a connected manner with humans and computers to which internet protocol addresses can be assigned and which can transfer data over the network or another man-made object. In this paper, we describe the utilization of IoT in the cloud, fog, IoT technologies with applications and security. Specifically, we provide IoT architecture for design and development with sensors in 6G. Finally, we discuss the current research, solutions, and present open issues of future research in IoT.

A Review and State of Art of Internet of Things (IoT)

Blockchain based solutions to secure IoT: Background, integration trends and a way forward

The Internet of Medical Things (IoMT) couples IoT technologies with healthcare services in order to support real-time, remote patient monitoring and treatment. However, the interconnectivity of critical medical devices with other systems in various network layers creates new opportunities for remote adversaries. Since most of the communication protocols have not been specifically designed for the needs of connected medical devices, there is a need to classify the available IoT communication technologies in terms of security. In this paper we classify IoT communication protocols, with respect to their application in IoMT. Then we describe the main characteristics of IoT communication protocols used at the perception, network and application layer of medical devices. We examine the inherent security characteristics and limitations of IoMT-specific communication protocols. Based on realistic attacks we identify available mitigation controls that may be applied to secure IoMT communications, as well as existing research and implementation gaps.

https://www.mdpi.com/1424-8220/20/17/4828/pdf

Security in IoMT Communications: A Survey

Wearable devices are the significant ubiquitous technology of the Internet of Things in day-to-day life. The efficient data processing in various devices such as smart clothes, smart wristwear and medical wearables along with consumer-oriented service of the IoT technology becomes inevitable in smart healthcare systems. The wearable market is currently dominated by health, safety, interaction, tracker, identity, fitness etc. Wearables increase the convergence of physical and digital world which automatically bring people into the IoT. The popularity of wearable devices is growing exponentially since it entirely changes the way how the consumers interact with the environment. 74% people believe that the wearable sensors assist them in interacting with the physical objects around them. Henceforth, one out of three smartphone users will wear minimum 5 wearables in 2020. Moreover, 60% believe that wearables in the next five years will be used not only to track health related information, although it can be used to control objects, unlock doors, authenticate identity and transactions. Wearables must be evolved to cope with the future to meet the expectations of consumers, where the users will wear many devices that is connected with the internet to interact with the physical surroundings and receive data in a seamless secure way. By 2021, smartwatches are estimated to be sold to nearly 81 million units which signifies 16% sales of total wearable device. According to the latest figure of Gartner report, the global shipment of wearable devices are anticipated to raise by 25.8% every year to $225 million (GBP 176.3 million) in 2019. Researchers also forecasted that the usage of wearable devices by the end users will increase to $42 billion (GBP 32.9 million) in 2019. In recent years, the IoT based Smart Healthcare system has influenced greatly on growing demand of wearable devices. In fact, the Wearable IoT (WIoT) devices are generating huge volume of personal health data. Enabling technologies such as cloud computing, Fog computing and Big Data play vital role in leveraging WIoT services. These enabling services over the voluminous health data enhance clinical process at health care system at remote or local servers. The traditional remote healthcare information system involves data transfer, signal processing mechanism and naive machine learning models deployed on remote server to process the medical data of patients. This technique has several demerits like they are not suitable for resource constrained wearable IoT devices. The resources such as processing, memory, energy, networking capability are limited in WIoT devices. Traditional mechanism lacks optimization of resource usage, prediction of medical condition, and dynamic assessment based on available information. Further, the naive machine learning techniques does not perform knowledge generation, decision making and discover hidden valuable patterns from the available medical data. The integrated platform in which cloud computing serves as backend computing systems, Fog computing as edge computing and Big data as platform for data analysis, knowledge generation promise to provide valid solution to several issues of Wearable IoT devices. Next, the health data generated through WIoT devices are personal and sensitive. Hence, the security and privacy of such delicate data at all level of WIoT ecosystem is essential. This part of chapter will contribute towards understanding the recent research work, issues, challenges, and opportunities in applying enabling technologies for WIoT. Also, how well the security and privacy can be incorporated is also discussed.

Wearable Devices and IoT

Heart Disease Prediction using Exploratory Data Analysis

Black hole attack refers an attack by single or more number of malicious nodes which forcibly captures the route from source to destination by sending reply with largest sequence number and smallest hop count. In this paper, a novel technique using Localized Secure Architecture for MANET (LSAM) routing protocol is proposed to detect and prevent co-operative black hole attack. Security Monitoring Nodes (SMNs) would be activated only if the threshold value is exceeded. If malicious nodes are detected, other SMNs in its proximity area are intimated to isolate the malicious nodes. Network simulator tool is implemented to analyze the network performance of different scenarios with various number of nodes. Packet delivery ratio (PDR), routing overhead, control overhead, packet drop rate, throughput and end-to-end delay (EED) are the factors taken into consideration for performance analysis and it is shown that the proposed protocol is more secured and efficient. PDR is been increased by 27 % in the presence of 40 % misbehaving nodes, while it increases the percentage of overhead on proposed routing protocol from 1 to 4 %. EED is greatly reduced from 0.9 to 0.3 % in LSAM.

Localized Secure Routing Architecture Against Cooperative Black Hole Attack in Mobile Ad Hoc Networks

Internet of Things (IoT) is an emerging technological paradigm where the things can be connected from different fields through the Internet. The rapid advancement in communication technologies, actuators and low-cost sensing devices leads to extensive deployment of IoT devices. Such devices can be deployed in any public spaces provide detailed information about the behavior of individuals such as personalization, behavior change and personal health monitoring. IoT technology which is being deployed is specially designed to make it invisible, such that the technology does not manifest its presence to the users it is monitoring. For the IoT based healthcare applications, the Wireless Body Area Network (WBAN) is gaining much popularity as wearable devices spring into the marketplace. Multiple sensor nodes can be deployed on different locations of the human body to measure the heartbeat, body temperature distribution, and detect falls. In addition to medical signals, the sensor nodes can be placed to track environmental conditions around the human body as well. Hence, wearable sensor systems afford valuable information about the impact of human health. These systems are not only limited for personal use, can be fitted on animal, car, etc. to construct a wireless sensor network. According to previous estimation, healthcare IoT solutions lay down the platform for extremely accessible, personalized and on-time services that will attain $1 trillion by 2025 hopefully. Wearable systems have emerged as a prominent area in healthcare for managing cardiovascular, neurological diseases etc. These sensors are used on the body surface or inside the human body non-invasively, however it is distinct from invasive implantable devices. This system will be particularly helpful for sensing information inside the human body as the sensors are designed and supported by flexible technologies. The sensing device collects data which is transmitted through wireless communication protocols to a server that is responsible to gather the datasets available for further analysis. WBAN comprised of heterogeneous nodes fixed in and around the human body which is connected to the network. It is characterized by IEEE 802.15 communication standard; generating huge volume of data and gathering it play a vital role in electronic healthcare. Data residing in multiple wireless devices need to be collected and analyzed effectively. Within WBAN datasets may be fragmented across many nodes and if practitioner’s node does not have the correct information then the quality of healthcare processing would be degraded. This chapter presents the overview of wearable sensors for tracking physiological and physical changes in daily life, their basics and applications. Wearable sensor based systems have enormous potentials to be completely explored and it is anticipated that advancement in technologies will afford the transformation how healthcare will be in future. It highlights the significance of localization in on-body area network and it gives an overview about evaluating the performance of localization systems. It also presents the several types of sensors and methodologies to fuse the data generated by sensors. Since we foreseen a future where the existence of miniature devices communicating through packet radio in both indoor and outdoor environments.

IoT Sensing Capabilities: Sensor Deployment and Node Discovery, Wearable Sensors, Wireless Body Area Network (WBAN), Data Acquisition

Performance and security are two critical functions of wireless ad-hoc networks (WANETs). Network security ensures the integrity, availability, and performance of WANETs. It helps to prevent critical service interruptions and increases economic productivity by keeping networks functioning properly. Since there is no centralized network management in WANETs, these networks are susceptible to packet drop attacks. In selective drop attack, the neighboring nodes are not loyal in forwarding the messages to the next node. It is critical to identify the illegitimate node, which overloads the host node and isolating them from the network is also a complicated task. In this paper, we present a resistive to selective drop attack (RSDA) scheme to provide effective security against selective drop attack. A lightweight RSDA protocol is proposed for detecting malicious nodes in the network under a particular drop attack. The RSDA protocol can be integrated with the many existing routing protocols for WANETs such as AODV and DSR. It accomplishes reliability in routing by disabling the link with the highest weight and authenticate the nodes using the elliptic curve digital signature algorithm. In the proposed methodology, the packet drop rate, jitter, and routing overhead at a different pause time are reduced to 9%, 0.11%, and 45%, respectively. The packet drop rate at varying mobility speed in the presence of one gray hole and two gray hole nodes are obtained as 13% and 14% in RSDA scheme.

/pdf/robust-defense-scheme-against-selective-drop-attack-in-2i3t5x63c8.pdf

T. Poongodi

Papers

Wearable Devices and IoT

Heart Disease Prediction using Exploratory Data Analysis

Localized Secure Routing Architecture Against Cooperative Black Hole Attack in Mobile Ad Hoc Networks

IoT Sensing Capabilities: Sensor Deployment and Node Discovery, Wearable Sensors, Wireless Body Area Network (WBAN), Data Acquisition

Robust Defense Scheme Against Selective Drop Attack in Wireless Ad Hoc Networks