The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure. Upcoming 5G systems are evolving to support exploding mobile traffic volumes, real-time extraction of fine-grained analytics, and agile management of network resources, so as to maximize user experience. Fulfilling these tasks is challenging, as mobile environments are increasingly complex, heterogeneous, and evolving. One potential solution is to resort to advanced machine learning techniques, in order to help manage the rise in data volumes and algorithm-driven applications. The recent success of deep learning underpins new and powerful tools that tackle problems in this space. In this paper, we bridge the gap between deep learning and mobile and wireless networking research, by presenting a comprehensive survey of the crossovers between the two areas. We first briefly introduce essential background and state-of-the-art in deep learning techniques with potential applications to networking. We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems. Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains. Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.

/pdf/deep-learning-in-mobile-and-wireless-networking-a-survey-ct8cy2kuqi.pdf

Deep Learning in Mobile and Wireless Networking: A Survey

More than a decade of research in the field of thermal, motion, vibration and electromagnetic radiation energy harvesting has yielded increasing power output and smaller embodiments. Power management circuits for rectification and DC-DC conversion are becoming able to efficiently convert the power from these energy harvesters. This paper summarizes recent energy harvesting results and their power management circuits.

Micropower energy harvesting

The impact of the Internet of Things (IoT) on the advancement of the healthcare industry is immense. The ushering of the Medicine 4.0 has resulted in an increased effort to develop platforms, both at the hardware level as well as the underlying software level. This vision has led to the development of Healthcare IoT (H-IoT) systems. The basic enabling technologies include the communication systems between the sensing nodes and the processors; and the processing algorithms for generating an output from the data collected by the sensors. However, at present, these enabling technologies are also supported by several new technologies. The use of Artificial Intelligence (AI) has transformed the H-IoT systems at almost every level. The fog/edge paradigm is bringing the computing power close to the deployed network and hence mitigating many challenges in the process. While the big data allows handling an enormous amount of data. Additionally, the Software Defined Networks (SDNs) bring flexibility to the system while the blockchains are finding the most novel use cases in H-IoT systems. The Internet of Nano Things (IoNT) and Tactile Internet (TI) are driving the innovation in the H-IoT applications. This paper delves into the ways these technologies are transforming the H-IoT systems and also identifies the future course for improving the Quality of Service (QoS) using these new technologies.

The Future of Healthcare Internet of Things: A Survey of Emerging Technologies

Wearable devices are becoming widespread in a wide range of applications, from healthcare to biomedical monitoring systems, which enable continuous measurement of critical biomarkers for medical diagnostics, physiological health monitoring and evaluation. Especially as the elderly population grows globally, various chronic and acute diseases become increasingly important, and the medical industry is changing dramatically due to the need for point-of-care (POC) diagnosis and real-time monitoring of long-term health conditions. Wearable devices have evolved gradually in the form of accessories, integrated clothing, body attachments and body inserts. Over the past few decades, the tremendous development of electronics, biocompatible materials and nanomaterials has resulted in the development of implantable devices that enable the diagnosis and prognosis through small sensors and biomedical devices, and greatly improve the quality and efficacy of medical services. This article summarizes the wearable devices that have been developed to date, and provides a review of their clinical applications. We will also discuss the technical barriers and challenges in the development of wearable devices, and discuss future prospects on wearable biosensors for prevention, personalized medicine and real-time health monitoring.

/pdf/evolution-of-wearable-devices-with-real-time-disease-1jg24fs3an.pdf

Evolution of Wearable Devices with Real-Time Disease Monitoring for Personalized Healthcare

A Survey on Wearable Technology: History, State-of-the-Art and Current Challenges

As smartphone penetration saturates, we are witnessing a new trend in personal mobile devices—wearable mobile devices or simply wearables as it is often called. Wearables come in many different forms and flavors targeting different accessories and clothing that people wear. Although small in size, they are often expected to continuously sense, collect, and upload various physiological data to improve quality of life. These requirements put significant demand on improving communication security and reducing power consumption of the system, fueling new research in these areas. In this paper, we first provide a comprehensive survey and classification of commercially available wearables and research prototypes. We then examine the communication security issues facing the popular wearables followed by a survey of solutions studied in the literature. We also categorize and explain the techniques for improving the power efficiency of wearables. Next, we survey the research literature in wearable computing. We conclude with future directions in wearable market and research.

A Survey of Wearable Devices and Challenges

Internet of Things (IoT) embraces the interconnection of identifiable devices that are capable of providing services through their cooperation. The cooperation among devices in such an IoT environment often requires reliable and trusted participating members in order to provide useful services to the end user. Consequently, an IoT environment or space needs to evaluate the trust levels of all devices in contact before admitting them as members of the space. Existing trust evaluation models are based on resources such as historical observations or recommendations information to evaluate the trust level of a device. However, these methods fail if there is no existing trust resource. This paper introduces a specific IoT environment called personal space IoT and proposes a novel trust evaluation model that performs a challenge-response trust assessment to evaluate the trust level of a device before allowing it to participate in the space. This novel challenge-response trust assessment model does not require the historical observation or previous encounter with the device or any existing trusted recommendation. The proposed challenge-response trust assessment model provides a reliable trust resource that can be used along with other resources such as direct trust, recommendation trust to get a comprehensive trust opinion on a specific device. It can also be considered as a new method for evaluating the trust value on a device.

Challenge-response trust assessment model for personal space IoT

Increasingly, trust has played a crucial role in the security of an IoT system from its inception to the end of its lifecycle A device has to earn some level of trust even before it is authenticated for admission to the system Furthermore, once the device is admitted to the system, it may behave maliciously over time; hence its behavior must be evaluated constantly in the form of trust to ensure the integrity of the system Currently, no mechanism exists to establish an initial trust on a device, without prior knowledge, before its admission to an IoT system Even when trust is applicable, trust evaluation models require direct/indirect observations over time, historical data on past encounters, or third party recommendations However, this type of past data is not available in the first encounter between the system and the device The question is how to establish whether a device can be trusted to a level that merits further evaluation for admission into a mobile and dynamic IoT system when it encounters the system for the first time? This paper addresses this challenge by proposing a challenge-response method and a trust assessment model to establish, without prior knowledge, the initial trust that a device places on another in a mobile and dynamic environment called personal space IoT The initial trust is established before further interaction can take place and under the assumption that only a limited window of time is available for the trust assessment The paper describes and evaluates the proposed model theoretically and by simulation It also describes a practical scheme for realizing the proposed solution

/pdf/initial-trust-establishment-for-personal-space-iot-systems-4eu4yfm04o.pdf

Initial trust establishment for personal space IoT systems

Traditional spam classification requires the end-user to reveal the content of its received email to the spam classifier which violates the privacy. Spam classification over encrypted emails enables the classifier to classify spam email without accessing the email, hence protects the privacy of email content. In this paper, we construct a spam classification framework that enables the classification of encrypted emails. Our classification model is based on a neural network with a quadratic network part and a multi-layer perception network part. The quadratic network architecture is compatible with the operation of an existing quadratic functional encryption scheme that enables our classification to predict the label of encrypted emails without revealing the associated plain-text email. The evaluation results on real-world spam datasets indicate that our proposed spam classification model achieves an accuracy of over 96%.

Privacy-Preserving Spam Filtering using Functional Encryption.

Trust has played a crucial role in enhancing the security of IoT systems over their lifecycles from creation to retirement. Particularly, in a personal space IoT system where devices join and leave the system dynamically, it is important to evaluate the device's behavior in the form of trust on its admission to the system to reduce the risk and uncertainty of the overall system. Currently, proposed trust evaluation models primarily rely on the historical knowledge or trusted recommendations. However, in many situations, such information is not available at the first encounter between the system and the device. The challenge tackled by this paper is how to establish whether a device can be trusted to a level that merits further evaluation for admission into an IoT system when it encounters the system for the first time. We propose a Dirichlet-based trust assessment model to establish the initial trust that the system places on a device in a mobile and dynamic environment called personal space IoT. The proposed scheme can also be used to affirm the trust of a device during its operation or when it is being re-admitted to the system after an interruption. We describe and evaluate our proposed model theoretically and by simulation.

/pdf/dirichlet-based-initial-trust-establishment-for-personal-z2dqag55s6.pdf

Tham Nguyen

Papers

A Survey of Wearable Devices and Challenges

Challenge-response trust assessment model for personal space IoT

Initial trust establishment for personal space IoT systems

Privacy-Preserving Spam Filtering using Functional Encryption.

Dirichlet-Based Initial Trust Establishment for Personal Space IoT Systems