Internet of Things and Big Data Technologies for Next Generation Healthcare

The Internet of Things (IoT) is a physical device along with other items network that embedded with software, electronics, network connectivity, and sensors to collect objects in order to exchange data. The IoT impact in healthcare is still in its initial development phases. The IoT system has several layers that lead to implementation challenges where many engaged devices have sensors to collect data. Each has its manufacturer own exclusive protocols. These protocols using software environment associated with privacy and security raise new challenges in the IoT technology. This current chapter attempts to understand and review the IoT concept and healthcare applications to realize superior healthcare with affordable costs. The chapter included in brief the IoT functionality and its association with the sensing and wireless techniques to implement the required healthcare applications.

The next era will be the connection between the physical things and internet. The things include goods, machine, appliances even we also become the part of it. The reason for integrating healthcare with Internet of Things features into medical devices improves the quality and effectiveness of service, bringing especially high value for elderly, patients with chronic conditions and those that require consistent supervision. Now research is going on-how to transform healthcare industry by increasing efficiency, lowering costs and put the focus back on better patient care. The Internet of Things will be a game changer for the healthcare industry. With an intelligent system and powerful algorithms, one can obtain an unprecedented level of real-time, life-critical data which is captured and analyzed to drive people in advance research, management and critical care. Taking care of patient’s health at very low cost is an important factor. The main idea of applying IoT in healthcare is move out from traditional area to visit hospitals and thus waiting will come to an end. The concept here is that it can be able to sense, process and communicate with biomedical and physical parameters so that they can work on it. Many applications and devices have been designed for healthcare purpose and have been put for people to use. The view is to connect the doctors, patients and nurses via smart device and each entity can roam without any restrictions. The idea is 24 * 7 monitoring of patient.

Internet of Things (IoT) is the emerging technology, that holds huge number of internet enabled devices and allows to share the data globally. IoT technology provides effective healthcare service by constant monitoring and reporting the chronic conditions of patients. IoT is highly greeted by healthcare sectors. IoT devices are smart in nature but constrained by energy, because most of the IoT applications uses battery operated smart devices. Hence energy is considered as valuable resource in energy constrained IoT environment. In this chapter energy efficient network architecture is proposed for IoT health care applications. Proposed network architecture describes the suitable combination of two different techniques such as, routing technique and node placement technique. In routing technique energy level of the nodes are monitored, to transmit the data in energy efficient path. In node placement technique, data traffic is balanced by varying the density of the nodes. This chapter describes the major factors that affect energy efficiency and it elaborates the suitable techniques to improve energy efficiency in IoT network.

This chapter proposes a novel strategic framework and computationally intelligent model to measure possible vulnerabilities for security context in e-health. In order to keep track of security of e-health paradigm, the chapter conceives a bio-inspired model comprising the collective intelligence of social insects e.g. ant colony. Ant colony optimization is a computationally intelligent meta-heuristics, which takes care-off the different random and uncertain behavior of different sensors deployed towards e-health measures. The essential input is provided from interconnected wireless sensors under Internet of Things (IoT) paradigm and intelligent social insects that could sense the possibility of threats for a patient moving in different physical locations during his medical diagnosis. Social insect ants can sense and communicate through a chemical, known as pheromone, remotely from their nest towards collection of food. The intensity of pheromone measured for different interconnected graphs of e-health could lead to a consolidated algorithm and finally the differences of intensities can infer on the affected or safe path for propagation of medical information. Modelling the pheromone dynamics can be a precise measure to quantify the different e-health security issues like Sinkhole threat or sybil attack under IoT environment. The proposed pheromone alert is presented and compared statistically in terms of precision to identify the classification of possible vulnerabilities.

Since last two decade robotics is one of the emerging, challenging, developing and innovative fields of research among researchers, industries universities. It is very difficult to distinguish robots from other machines; robots can be defined as machines that are capable of perform variety of task with more autonomy and degree of freedom (DoF) than humans. Nowadays healthcare services and systems become very complex and encompass a vast number of entities that are characterized by shared, distributed, and heterogeneous devices, sensors, and information and communication technology. With the advent of Internet of Things (IoT), robots are integrated as a ‘thing’ and establish connections with other things over the Internet. This chapter clearly indicates the long term benefits of human being in healthcare sector, medical emergencies, e-health, etc. using robotics and IoT. Also, the phase of adoption, interaction, challenges for future is to be discussed.

A mobile health (mHealth) system is responsible to support and provision of healthcare services using mobile communication devices, such as mobile phones and tablet computers. Although mHealth system development for Internet of Things (IoT) environments is still in the early stage, the existing research shows the essential potential impact on the healthcare service industry. This chapter overviews important IoT use cases in healthcare focusing on the proposed IoT solutions for smart services provided by an mHealth system. The study discusses recent experience on development of smart space based mHealth systems. IoT-aware opportunities and properties of healthcare services are considered, including our vision on service intelligence in the mHealth case. Smart spaces based methods are described for mHealth system development, including multi-agent architectures, semantics-oriented information sharing, and operation with multisource heterogeneous data.

The health care systems are rapidly adopting large amounts of data, driven by record keeping, compliance and regulatory requirements, and patient care. The advances in healthcare system will rapidly enlarge the size of the health records that are accessible electronically. Concurrently, fast progress has been made in clinical analytics. For example, new techniques for analyzing large size of data and gleaning new business insights from that analysis is part of what is known as big data. Big data also hold the promise of supporting a wide range of medical and healthcare functions, including among others disease surveillance, clinical decision support and population health management. Hence, effective big data based knowledge management system is needed for monitoring of patients and identify the clinical decisions to the doctor. The chapter proposes a big data based knowledge management system to develop the clinical decisions. The proposed knowledge system is developed based on variety of databases such as Electronic Health Record (EHR), Medical Imaging Data, Unstructured Clinical Notes and Genetic Data. The proposed methodology asynchronously communicates with different data sources and produces many alternative decisions to the doctor.

Smart data analysis has become a challenging task in today’s environment where disparate data set is generated across the globe with enormous volume. So there is an absolute need of parallel and distributed framework along with appropriate algorithms which can handle these challenges. Various machine learning algorithms can be deployed effectively in this environment as they can work with minimal manual intervention. The objective of this chapter is first to present various issues faced in storing and processing big data and available tools, technologies and algorithms to deal with those problems along with one case study which describes an application in healthcare analytics. In the subsequent section it discusses few distributed algorithms which are widely used in the data mining domain. Finally it focuses on various machine learning algorithms and their roles in the big data analytics world.

Co-creation of scientific knowledge based on new technologies and big data sources is one of the main challenges for the digital society in the XXI century. Data management and the analysis of patterns among datasets based on machine learning and artificial intelligence has become essential for many sectors nowadays. The development of real time health-related climate services represents an example where abundant structured and unstructured information and transdisciplinary research are needed. The study of the interactions between atmospheric processes and human health through a big data approach can reveal the hidden value of data. The Oxyalert technological platform is presented as an example of a digital biometeorological infrastructure able to forecast, at an individual level, oxygen changes impacts on human health.

Information and communication technology (ICT) has contributed a lot of things to support the health system in many aspects and has an impact positively. Information technology even changed on how hospital order stocks activities. E-health system is a stage that uses the ICT to interface different clients; it was intended to convey social insurance. Mobile health information system and internet support public health and clinical care-offers and also it is widely available and can enhancing electronic health for healthcare organization at different level; such as regional, community, and individual levels. Telematics has ease people from afar to do medical check via media usually. One part of e-Health is electronic medical record that contains patients information and accessible by healthcare staff. Clinical decision support system is a system that helps to make a decision regarding their patients matter. Management and maintenance of server should also be watch after as it affects many things in the information technology. Administrative staff also record their patients clinical record and organizing their financial management by using IT. Even robots have replaced some of the position such as doing surgery in health organizations. This study is an attempt to provide a picture of preferences over the information and communication emerging technology to enabling healthcare innovation through big data perspective. The results are interesting. Healthcare innovation through ICT and big data are indispensable elements of a multifaceted approach to forestall medication errors and enhance the patient safety. Clinical staff play a major role in the health organizations as information system in health organization. Improvisation of uniformity and recognition of the design aside from implementation of such systems should also be advantageous to the ICT though big data. Likewise, generating an economic and policy environment conducive to the financial intention of hospitals and physicians will facilitate wider adoption of such technology in the health information system sector.

With advancement of health monitoring systems and healthcare techniques, the reach of cheaper, sustainable and personalized healthcare is becoming a reality. Many developed countries have put forth standards and procedures that enable citizens to available medical services not only in designated hospitals or clinics, but also in their homes. Information and Communication Technology (ICT) has been leveraged to the fullest to achieve greater coherence in medical services. In developing countries, though there is a desire to increase reach of medical services, the infrastructure, policies and other factors create road blocks. The expectation in such countries can be met if there is a solution that is cheaper, reachable and easy to collaborate. Cloud computing paradigm can solve these issues. By leveraging cloud, developing countries can operationalize health informatics systems and enable all stakeholders to focus on refining of patient care services rather than worrying about the infrastructure for the solutions. But this requires a clear understanding of expectations from such solutions. This chapter aims at providing insights into the eHealth models that exist and challenges arising from those. The concept of HIaaS in cloud has been detailed out along with cloud based architecture for hosting eHealth services. It also illustrates application scenarios from developing countries where proposed architecture can be applied.

There has been a constant surge of Electronic medical applications in this modern era developed to enhance the health care services. As a result, wireless technology has emerged as a prime medium in not only monitoring and coordinating various processes effectively in this domain but also ensuring real time data delivery in a precise and reliable way. The electronics miniaturization and information proliferation in healthcare for energy retention and energy scavenging, have made it feasible the application of wireless networks especially Wireless Body Area Networks (WBAN) into medical sector. These advances herald in a new era for patient monitoring, healthcare procedures and several other critical sectors in modern age healthcare. This chapter illustrates a detail architectural analysis of WBAN in healthcare domain. A hybrid combination of Privacy Preserving Scalar Product for Computation Protocol (PPSPC) with Cascading Information Retrieval by Controlling Access with Distributed Slot Assignment Protocol (CICADA) is studied along with its stages of operation to provide secure, reliable and energy efficient data transmission in wireless body area sensor networks. Its performance is evaluated in terms of some critical parameters and it has been demonstrated that it generates a reasonable throughput thereby proving to be efficient. Thus this chapter deals with discussion of WBASN and its implementation in health status monitoring of patients residing in remote areas at any time.

Ever since the launch of Facebook and Twitter Social Networking has been booming. Healthcare is improving mainly due to services provided by social media websites such as Sermo, Ozmosis and MomMD. This chapter’s main objective is to broaden the understanding of healthcare services provided by social media. The reader will be able to understand the means by which medical information is exchanged online and how to interpret this information with some specific examples. In addition to describing the architecture behind social media further insights to mobile applications has been given. Big data in healthcare and risks involved in using social media for healthcare have been discussed to caution its usage.

Graphic Processing Units (GPU) and kinetic sensors are promising devices of Internet of Things (IoT) computing environments in various application domains, including mobile healthcare. In this chapter a novel training/testing process for building/testing a classification model for unusual human activities (UHA) using ensembles of Neural Networks running on NVIDIA GPUs is proposed. Traditionally, UHA is done by a classifier that learns what activities a person is doing by training with skeletal data obtained from a motion sensor such as Microsoft Kinect [1]. These skeletal data are the spatial coordinates (x, y, z) of different parts of the human body. The numeric information forms time series, temporal records of movement sequences that can be used for training an ensemble of Neural Networks. In addition to the spatial features that describe current positions in the skeletal data, new features called shadow features are used to improve the supervised learning efficiency of the ensemble of Neural Networks running on an NVIDIA GPU card. Shadow features are inferred from the dynamics of body movements, thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterizing activities in the classification process and thus significantly improving the accuracy. We show that the accuracy of using a Neural Network as a classifier on a data set with shadow features can still be further increased when more than one Neural Network is used, forming an ensemble of networks. In order to accelerate the processing speed of an ensemble of Neural Networks, the model proposed is designed and optimized to run on NIVDIA GPUs with CUDA.