Pervasive AI for IoT Applications: Resource-efficient Distributed Artificial Intelligence

Abstract

Artificial intelligence (AI) has witnessed a substantial breakthrough in a variety of Internet of Things (IoT) applications and services, spanning from recommendation systems and speech processing applications to robotics control and military surveillance. This is driven by the easier access to sensory data and the enormous scale of pervasive/ubiquitous devices that generate zettabytes (ZB) of real-time data streams. Designing accurate models using such data streams, to predict future insights and revolutionize the decision-taking process, inaugurates pervasive systems as a worthy paradigm for a better quality-oflife. The confluence of pervasive computing and artificial intelligence, Pervasive AI, expanded the role of ubiquitous IoT systems from mainly data collection to executing distributed computations with a promising alternative to centralized learning, presenting various challenges, including privacy concerns, scalability, and latency requirements. In this context, a wise cooperation and resource scheduling should be envisaged among IoT devices (e.g., smartphones, smart vehicles) and infrastructure (e.g. edge nodes, and base stations) to avoid communication and computation overheads and ensure maximum performance. In this paper, we conduct a comprehensive survey of the recent techniques and strategies developed to overcome these resource challenges in pervasive AI systems. Specifically, we first present an overview of the pervasive computing, its architecture, and its intersection with artificial intelligence. We then review the background, applications and performance metrics of AI, particularly Deep Learning (DL) and online learning, running in a ubiquitous system. Next, we provide a deep literature review of communication-efficient techniques, from both algorithmic and system perspectives, of distributed inference, training and online learning tasks across the combination of IoT devices, edge devices and cloud servers. Finally, we discuss our future vision and research challenges.

Utilising Emotion Monitoring for Developing Music Interventions for People with Dementia: A State-of-the-Art Review

“…With the growing interest in monitoring systems, both in academia and industry, it becomes increasingly more important to assess the ethics and consider privacy preserving techniques. Sensors are able to collect sensitive data (e.g., images, GPS coordinates, or vital signs of a subject [90]) invisibly and continuously. Wu et al [35] mentions that one should carefully think about privacy issues from the start of the design process to produce good and safe technology.…”

“…Moreover, they stress it is important to guarantee the user's privacy when recruiting participants for experiments. One of the methods by which attackers gain sensitive data is by training classifiers to predict private data belonging to a known community [90].…”

“…Saxena et al [91] proposed a secure and privacy-preserving data aggregation scheme using encryption and a cryptosystem. Several other data privacy techniques are addressed by Baccour et al [90]. Moreover, Esch recommends to use a privacy-by-design approach, meaning the privacy requirements are collected first, after which the design should adhere to these.…”

RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for Low Latency IoT Systems

“…The nexus between IoT devices motivates the research community to push the DNN computation in close proximity of data source, in order to reduce the inference latency, minimize the network cost, and avoid bandwidth bottlenecks [14], [15]. Particularly, the trained DNN network is split into segments that are assigned to different helpers.…”

FDRL Approach for Association and Resource Allocation in Multi-UAV Air-To-Ground IoMT Network

“…Furthermore, machine learning (ML) methods have been applied in the healthcare industry to provide smart health services, optimizing system parameters, monitoring populations, and controlling chronic diseases [6]. In particular, the reinforcement learning (RL) and deep RL (DRL) methods are used in the healthcare industry to maximize energy efficiency, minimize communication latency, and allocate efficient resources [7] [8]. Federated learning (FL) is a recent ML paradigm that allows heterogeneous edge nodes to train data models and perform aggregation centrally, protecting data privacy.…”