Body Sensor Networking, Design and Algorithms. Saeid Sanei

Чтение книги онлайн.

СКАЧАТЬ of supercomputers, availability of large memory clusters, and accessibility of the cloud have been crucial to the expansion of sensor networks. Moreover, new data processing and machine learning methods based on tensor factorisation, cooperative learning, graph theory, kernel-based classification, deep learning neural networks, and distributed systems together with pervasive computing have revolutionised the assessment of the information collected from multisensor networks, particularly when the dataset is large. Network communication, on the other hand, involves network topology design [50], channel characterization [51], channel access control [52, 53], routing algorithm design [54], lightweight communication protocols design, energy harvesting in a network, and many other issues related to short- and long-range communications. These key technologies must be considered and further developed for building a complete BSN system.

      To enable long-term data collection from the human body, biocompatible sensors and devices need to be designed. This field of research brings new areas of engineering researchers in biotechnology, biomaterials, bioelectronics, and biomechanics together to develop practical sensors.

      The demand for a green environment pushes for the optimization of energy harvesting and an effective solution to energy consumption together with enhancing the QoS. For WSNs the plethora of battery technologies available today enables system designers to tailor their energy storage devices to the needs of their applications. The latest lithium battery technologies allow optimization for any operating lifetime or environment. For applications with small temperature variation and short lifetime, lithium manganese dioxide (LiMnO₂) batteries provide solid performance at cost-effective prices, while applications demanding large temperature ranges and multidecade lifetimes are satisfied with batteries based on lithium thionyl chloride (LiSOCL₂) chemistry [7].

      While batteries represent the preferred low-cost energy storage technology, energy harvesting/scavenging devices are beginning to emerge as viable battery replacements in some applications. For example, power can be generated from temperature differences through thermoelectric and pyroelectric effects, kinetic motion of piezoelectric materials, photovoltaic cells that capture sunlight, or even the direct conversion of RF (radio frequency) energy through specialised antennas and rectification. Examples of energy scavenging/harvesting devices coming to market today include piezoelectric light, solar batteries, and doorbell switches. Although the above technology can solve BSN problems, further research is needed for designing biologically powered systems and biocompatible batteries which can last longer while being attached to body internal tissues.

      Finally, secure connections and data security are vital, particularly when personal information is analysed or communicated. In parallel with increasing complexity in data hacking algorithms, there is great demand for producing more sophisticated data encryption and network security.

In dealing with BSNs, machine-centric and human-centric challenges confront researchers. The machine-centric problems, as mentioned before, include security [55], compatibility or interoperability; sensor design and sensor validity; data consistency, as the data residing on multiple mobile devices and wireless patient notes need to be collected and analysed in a seamless fashion; interference; and data management [56, 57].

      Besides hardware-centric challenges, human-centric challenges include cost, constant monitoring, deployment constraints, and performance limitations [13, 58–61], which need to be taken care of in any BSN design. After all, the wearable system should be acceptable, convenient, and user friendly.

1.4 Layout of the Book

      This monograph consists of 15 chapters and has been designed to cover all aspects of BSNs, starting with human body measurable or recordable biomarkers. Chapter 2 is dedicated to understanding these biomarkers, including physical, physiological, and biological measurable quantities. In Chapter 3, sensors, sensor classification, and the quantities measured by different sensors are described. In this chapter, the structures of the sensors for the applications listed in Chapter 2 are detailed. In Chapter 4, more popular and ambulatory sensor systems used in clinical departments and intensive care units are discussed and some examples of their recordings and analysis explained. This discussion continues in Chapter 5, where sleep, as a specific state of human body, is analysed. This chapter includes discussion of various sleep measurement modalities which are more popular and of interest today to researchers. Chapter 6 covers the area of noninvasive, intrusive, and nonintrusive measurement approaches. The objective of this chapter is to introduce the techniques and sensors for nonintrusive or contactless monitoring of major human vital signs, such as breathing, heart rate, and blood oxygen saturation level.

      Next, Chapter 7, covers the important concept of gait analysis, recognition, and monitoring. The outcome of this study has a major application in assistive technology, rehabilitation, and assistive robotics. Chapter 8 brings together a wide range of techniques and research approaches in health monitoring. These address the important daily assisted living problems of disabled and older people, and patients with degenerative diseases, and the solutions being currently researched. In Chapter 9 numerous machine learning techniques used for both sensor networks and bioinformatics are explained. This chapter includes most popular, advanced, and very recent machine learning methods for clustering, classification, and feature learning. Support vector machines, reinforcement learning, and different deep neural networks are also included in this chapter. Some examples of machine learning for sensor networks conclude this chapter.

Signal processing techniques and their wide range of applications are covered in Chapter 10. This long chapter explains useful approaches in time, frequency, and multidimensional spaces. Multiresolution analysis, synchro-squeezing wavelet transform, and adaptive cooperative filtering are addressed. At the end of this chapter various signal processing platforms established recently are reviewed. Chapter 11 is devoted to communication systems for BSNs. Short-range communication methods, limitations, and barriers; problems with communication channels and their modelling; linking between body and public networks; and routing methods for BSNs are extensively explained in this chapter. The important topic of energy harvesting for sensor networks is covered in Chapter 12. Advanced techniques in harvesting kinetic, radiant, thermal, chemical, and biochemical energy are explored. At the end of this chapter, topology control and energy prediction, two hot research topics, are introduced.

      Chapter 13 covers a wide range of studies of and practical approaches to solving information and network security problems. In addition to general security and privacy preserving techniques, some problems related to patient and clinical data and their importance are discussed in this chapter. QoS, as the major requirement for BSNs are emphasised in this chapter. In Chapter 14 various hardware and software platforms for developing sensor networks currently employed for BSN design are discussed and some practical examples reviewed. Finally, in Chapter 15, the book is summarised, the main topics highlighted, and some suggestions for future research in BSN proposed.

References

      1 1 СКАЧАТЬ