The Internet of Medical Things (IoMT) paradigm is becoming mainstream in multiple clinical trials and healthcare procedures. Cardiovascular diseases monitoring, usually involving electrocardiogram (ECG) traces analysis, is one of the most promising and high-impact applications. Nevertheless, to fully exploit the potential of IoMT in this domain, some steps forward are needed. First, the edge-computing paradigm must be added to the picture. A certain level of near-sensor processing has to be enabled, to improve the scalability, portability, reliability, responsiveness of the IoMT nodes. Second, novel, increasingly accurate, data analysis algorithms, such as those based on artificial intelligence and Deep Learning, must be exploited. To reach these objectives, designers and programmers of IoMT nodes, have to face challenging optimization tasks, in order to execute fairly complex computing tasks on low-power wearable and portable processing systems, with tight power and battery lifetime budgets. In this work, we explore the implementation of a cognitive data analysis algorithm, based on a convolutional neural network trained to classify ECG waveforms, on a resource-constrained microcontroller-based computing platform. To minimize power consumption, we add an adaptivity layer that dynamically manages the hardware and software configuration of the device to adapt it at runtime to the required operating mode. Our experimental results show that adapting the node setup to the workload at runtime can save up to 50% power consumption. Our optimized and quantized neural network reaches an accuracy value higher than 97% for arrhythmia disorders detection on MIT-BIH Arrhythmia dataset.
With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume. The Edge Intelligence (EI) has led to the emergence of edge devices in various application domains. The EI can provide efficient services to delay-sensitive applications, where the edge devices are deployed as edge nodes to host the majority of execution, which can effectively manage services and improve service discovery efficiency. The multilevel index model is a well-known model used for indexing service, such a model is being introduced and optimized in the edge environments to efficiently services discovery whilst managing large volumes of data. However, effectively updating the multilevel index model by adding new services timely and precisely in the dynamic Edge Computing environments is still a challenge. Addressing this issue, this paper proposes a designated key selection method to improve the efficiency of adding services in the multilevel index models. Our experimental results show that in the partial index and the full index of multilevel index model, our method reduces the service addition time by around 84% and 76%, respectively when compared with the original key selection method and by around 78% and 66%, respectively when compared with the random selection method. Our proposed method significantly improves the service addition efficiency in the multilevel index model, when compared with existing state-of-the-art key selection methods, without compromising the service retrieval stability to any notable level.
While Moore's law has driven exponential computing power expectations, its nearing end calls for new avenues for improving the overall system performance. One of these avenues is the exploration of alternative brain-inspired computing architectures that aim at achieving the flexibility and computational efficiency of biological neural processing systems. Within this context, neuromorphic engineering represents a paradigm shift in computing based on the implementation of spiking neural network architectures in which processing and memory are tightly co-located. In this paper, we provide a comprehensive overview of the field, highlighting the different levels of granularity at which this paradigm shift is realized and comparing design approaches that focus on replicating natural intelligence (bottom-up) versus those that aim at solving practical artificial intelligence applications (top-down). First, we present the analog, mixed-signal and digital circuit design styles, identifying the boundary between processing and memory through time multiplexing, in-memory computation, and novel devices. Then, we highlight the key tradeoffs for each of the bottom-up and top-down design approaches, survey their silicon implementations, and carry out detailed comparative analyses to extract design guidelines. Finally, we identify necessary synergies and missing elements required to achieve a competitive advantage for neuromorphic systems over conventional machine-learning accelerators in edge computing applications, and outline the key ingredients for a framework toward neuromorphic intelligence.
Vibration patterns yield valuable information about the health state of a running machine, which is commonly exploited in predictive maintenance tasks for large industrial systems. However, the overhead, in terms of size, complexity and power budget, required by classical methods to exploit this information is often prohibitive for smaller-scale applications such as autonomous cars, drones or robotics. Here we propose a neuromorphic approach to perform vibration analysis using spiking neural networks that can be applied to a wide range of scenarios. We present a spike-based end-to-end pipeline able to detect system anomalies from vibration data, using building blocks that are compatible with analog-digital neuromorphic circuits. This pipeline operates in an online unsupervised fashion, and relies on a cochlea model, on feedback adaptation and on a balanced spiking neural network. We show that the proposed method achieves state-of-the-art performance or better against two publicly available data sets. Further, we demonstrate a working proof-of-concept implemented on an asynchronous neuromorphic processor device. This work represents a significant step towards the design and implementation of autonomous low-power edge-computing devices for online vibration monitoring.
The emergence of technologies such as 5G and mobile edge computing has enabled provisioning of different types of services with different resource and service requirements to the vehicles in a vehicular network.The growing complexity of traffic mobility patterns and dynamics in the requests for different types of services has made service placement a challenging task. A typical static placement solution is not effective as it does not consider the traffic mobility and service dynamics. In this paper, we propose a reinforcement learning-based dynamic (RL-Dynamic) service placement framework to find the optimal placement of services at the edge servers while considering the vehicle's mobility and dynamics in the requests for different types of services. We use SUMO and MATLAB to carry out simulation experiments. In our learning framework, for the decision module, we consider two alternative objective functions-minimizing delay and minimizing edge server utilization. We developed an ILP based problem formulation for the two objective functions. The experimental results show that 1) compared to static service placement, RL-based dynamic service placement achieves fair utilization of edge server resources and low service delay, and 2) compared to delay-optimized placement, server utilization optimized placement utilizes resources more effectively, achieving higher fairness with lower edge-server utilization.
We consider the non-stationary multi-armed bandit (MAB) framework and propose a Kolmogorov-Smirnov (KS) test based Thompson Sampling (TS) algorithm named TS-KS, that actively detects change points and resets the TS parameters once a change is detected. In particular, for the two-armed bandit case, we derive bounds on the number of samples of the reward distribution to detect the change once it occurs. Consequently, we show that the proposed algorithm has sub-linear regret. Contrary to existing works, our algorithm is able to detect a change when the underlying reward distribution changes even though the mean reward remains the same. Finally, to test the efficacy of the proposed algorithm, we employ it in two case-studies: i) task-offloading scenario in wireless edge-computing, and ii) portfolio optimization. Our results show that the proposed TS-KS algorithm outperforms not only the static TS algorithm but also it performs better than other bandit algorithms designed for non-stationary environments. Moreover, the performance of TS-KS is at par with the state-of-the-art forecasting algorithms such as Facebook-PROPHET and ARIMA.
Extremely high data rates at modern synchrotron and X-ray free-electron laser light source beamlines motivate the use of machine learning methods for data reduction, feature detection, and other purposes. Regardless of the application, the basic concept is the same: data collected in early stages of an experiment, data from past similar experiments, and/or data simulated for the upcoming experiment are used to train machine learning models that, in effect, learn specific characteristics of those data; these models are then used to process subsequent data more efficiently than would general-purpose models that lack knowledge of the specific dataset or data class. Thus, a key challenge is to be able to train models with sufficient rapidity that they can be deployed and used within useful timescales. We describe here how specialized data center AI (DCAI) systems can be used for this purpose through a geographically distributed workflow. Experiments show that although there are data movement cost and service overhead to use remote DCAI systems for DNN training, the turnaround time is still less than 1/30 of using a locally deploy-able GPU.
We study optimization methods to train local (or personalized) models for decentralized collections of local datasets with an intrinsic network structure. This network structure arises from domain-specific notions of similarity between local datasets. Examples for such notions include spatio-temporal proximity, statistical dependencies or functional relations. Our main conceptual contribution is to formulate federated learning as generalized total variation (GTV) minimization. This formulation unifies and considerably extends existing federated learning methods. It is highly flexible and can be combined with a broad range of parametric models, including generalized linear models or deep neural networks. Our main algorithmic contribution is a fully decentralized federated learning algorithm. This algorithm is obtained by applying an established primal-dual method to solve GTV minimization. It can be implemented as message passing and is robust against inexact computations that arise from limited computational resources including processing time or bandwidth. Our main analytic contribution is an upper bound on the deviation between the local model parameters learnt by our algorithm and an oracle-based clustered federated learning method. This upper bound reveals conditions on the local models and the network structure of local datasets such that GTV minimization is able to pool (nearly) homogeneous local datasets.
Mm-wave radars have recently gathered significant attention as a means to track human movement and identify subjects from their gait characteristics. A widely adopted method to perform the identification is the extraction of the micro-Doppler signature of the targets, which is computationally demanding in case of co-existing multiple targets within the monitored physical space. Such computational complexity is the main problem of state-of-the-art approaches, and makes them inapt for real-time use. In this work, we present an end-to-end, low-complexity but highly accurate method to track and identify multiple subjects in real-time using the sparse point-cloud sequences obtained from a low-cost mm-wave radar. Our proposed system features an extended object tracking Kalman filter, used to estimate the position, shape and extension of the subjects, which is integrated with a novel deep learning classifier, specifically tailored for effective feature extraction and fast inference on radar point-clouds. The proposed method is thoroughly evaluated on an edge-computing platform from NVIDIA (Jetson series), obtaining greatly reduced execution times (reduced complexity) against the best approaches from the literature. Specifically, it achieves accuracies as high as 91.62%, operating at 15 frames per seconds, in identifying three subjects that concurrently and freely move in an unseen indoor environment, among a group of eight.
Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many time steps. As a method to overcome this difficulty, RNN pruning has attracted increasing attention in recent years, and it brings us benefits in terms of the reduction of computational cost as the time step progresses. However, most existing methods of RNN pruning are heuristic. The purpose of this paper is to study the theoretical scheme for RNN pruning method. We propose an appropriate pruning algorithm for RNNs inspired by "spectral pruning", and provide the generalization error bounds for compressed RNNs. We also provide numerical experiments to demonstrate our theoretical results and show the effectiveness of our pruning method compared with existing methods.
Deploying deep learning models in time-critical applications with limited computational resources, for instance in edge computing systems and IoT networks, is a challenging task that often relies on dynamic inference methods such as early exiting. In this paper, we introduce a novel architecture for early exiting based on the vision transformer architecture, as well as a fine-tuning strategy that significantly increase the accuracy of early exit branches compared to conventional approaches while introducing less overhead. Through extensive experiments on image and audio classification as well as audiovisual crowd counting, we show that our method works for both classification and regression problems, and in both single- and multi-modal settings. Additionally, we introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis, that can lead to a more fine-grained dynamic inference.
The Techtile measurement infrastructure is a multi-functional, versatile testbed for new communication and sensing technologies relying on fine-grained distributed resources. The facility enables experimental research on hyper-connected interactive environments and validation of new wireless connectivity, sensing and positioning solutions. It consists of a data acquisition and processing equipment backbone and a fabric of dispersed edge computing devices, Software-Defined Radios, sensors, and LED sources. These bring intelligence close to the applications and can also collectively function as a massive, distributed resource. Furthermore, the infrastructure allows exploring more degrees and new types of diversity, i.e., scaling up the number of elements, introducing `3D directional diversity' by deploying the distributed elements with different orientations, and `interface diversity' by exploiting multiple technologies and hybrid signals (RF, acoustic, and visible light).
We design a multi-purpose environment for autonomous UAVs offering different communication services in a variety of application contexts (e.g., wireless mobile connectivity services, edge computing, data gathering). We develop the environment, based on OpenAI Gym framework, in order to simulate different characteristics of real operational environments and we adopt the Reinforcement Learning to generate policies that maximize some desired performance.The quality of the resulting policies are compared with a simple baseline to evaluate the system and derive guidelines to adopt this technique in different use cases. The main contribution of this paper is a flexible and extensible OpenAI Gym environment, which allows to generate, evaluate, and compare policies for autonomous multi-drone systems in multi-service applications. This environment allows for comparative evaluation and benchmarking of different approaches in a variety of application contexts.
The health-care gets huge stress in a pandemic or epidemic situation. Some diseases such as COVID-19 that causes a pandemic is highly spreadable from an infected person to others. Therefore, providing health services at home for non-critical infected patients with isolation shall assist to mitigate this kind of stress. In addition, this practice is also very useful for monitoring the health-related activities of elders who live at home. The home health monitoring, a continuous monitoring of a patient or elder at home using visual sensors is one such non-intrusive sub-area of health services at home. In this article, we propose a transfer learning-based edge computing method for home health monitoring. Specifically, a pre-trained convolutional neural network-based model can leverage edge devices with a small amount of ground-labeled data and fine-tuning method to train the model. Therefore, on-site computing of visual data captured by RGB, depth, or thermal sensor could be possible in an affordable way. As a result, raw data captured by these types of sensors is not required to be sent outside from home. Therefore, privacy, security, and bandwidth scarcity shall not be issues. Moreover, real-time computing for the above-mentioned purposes shall be possible in an economical way.
The presented compact algorithm for recognizing handwritten digits of the MNIST database, created on the LogNNet reservoir neural network, reaches the recognition accuracy of 82%. The algorithm was tested on a low-memory Arduino board with 2 Kb static RAM low-power microcontroller. The dependences of the accuracy and time of image recognition on the number of neurons in the reservoir have been investigated. The memory allocation demonstrates that the algorithm stores all the necessary information in RAM without using additional data storage, and operates with original images without preliminary processing. The simple structure of the algorithm, with appropriate training, can be adapted for wide practical application, for example, for creating mobile biosensors for early diagnosis of adverse events in medicine. The study results are important for the implementation of artificial intelligence on peripheral constrained IoT devices and for edge computing.
Industrial Internet of Things (IIoT) applications can benefit from leveraging edge computing. For example, applications underpinned by deep neural networks (DNN) models can be sliced and distributed across the IIoT device and the edge of the network for improving the overall performance of inference and for enhancing privacy of the input data, such as industrial product images. However, low network performance between IIoT devices and the edge is often a bottleneck. In this study, we develop ScissionLite, a holistic framework for accelerating distributed DNN inference using the Transfer Layer (TL). The TL is a traffic-aware layer inserted between the optimal slicing point of a DNN model slice in order to decrease the outbound network traffic without a significant accuracy drop. For the TL, we implement a new lightweight down/upsampling network for performance-limited IIoT devices. In ScissionLite, we develop ScissionTL, the Preprocessor, and the Offloader for end-to-end activities for deploying DNN slices with the TL. They decide the optimal slicing point of the DNN, prepare pre-trained DNN slices including the TL, and execute the DNN slices on an IIoT device and the edge. Employing the TL for the sliced DNN models has a negligible overhead. ScissionLite improves the inference latency by up to 16 and 2.8 times when compared to execution on the local device and an existing state-of-the-art model slicing approach respectively.
In this position paper, we discuss the critical need for integrating zero trust (ZT) principles into next-generation communication networks (5G/6G). We highlight the challenges and introduce the concept of an intelligent zero trust architecture (i-ZTA) as a security framework in 5G/6G networks with untrusted components. While network virtualization, software-defined networking (SDN), and service-based architectures (SBA) are key enablers of 5G networks, operating in an untrusted environment has also become a key feature of the networks. Further, seamless connectivity to a high volume of devices has broadened the attack surface on information infrastructure. Network assurance in a dynamic untrusted environment calls for revolutionary architectures beyond existing static security frameworks. To the best of our knowledge, this is the first position paper that presents the architectural concept design of an i-ZTA upon which modern artificial intelligence (AI) algorithms can be developed to provide information security in untrusted networks. We introduce key ZT principles as real-time Monitoring of the security state of network assets, Evaluating the risk of individual access requests, and Deciding on access authorization using a dynamic trust algorithm, called MED components. To ensure ease of integration, the envisioned architecture adopts an SBA-based design, similar to the 3GPP specification of 5G networks, by leveraging the open radio access network (O-RAN) architecture with appropriate real-time engines and network interfaces for collecting necessary machine learning data. Therefore, this work provides novel research directions to design machine learning based components that contribute towards i-ZTA for the future 5G/6G networks.
Neuromorphic computing is a non-von Neumann computing paradigm that performs computation by emulating the human brain. Neuromorphic systems are extremely energy-efficient and known to consume thousands of times less power than CPUs and GPUs. They have the potential to drive critical use cases such as autonomous vehicles, edge computing and internet of things in the future. For this reason, they are sought to be an indispensable part of the future computing landscape. Neuromorphic systems are mainly used for spike-based machine learning applications, although there are some non-machine learning applications in graph theory, differential equations, and spike-based simulations. These applications suggest that neuromorphic computing might be capable of general-purpose computing. However, general-purpose computability of neuromorphic computing has not been established yet. In this work, we prove that neuromorphic computing is Turing-complete and therefore capable of general-purpose computing. Specifically, we present a model of neuromorphic computing, with just two neuron parameters (threshold and leak), and two synaptic parameters (weight and delay). We devise neuromorphic circuits for computing all the {\mu}-recursive functions (i.e., constant, successor and projection functions) and all the {\mu}-recursive operators (i.e., composition, primitive recursion and minimization operators). Given that the {\mu}-recursive functions and operators are precisely the ones that can be computed using a Turing machine, this work establishes the Turing-completeness of neuromorphic computing.
Introducing blockchain into Federated Learning (FL) to build a trusted edge computing environment for transmission and learning has attracted widespread attention as a new decentralized learning pattern. However, traditional consensus mechanisms and architectures of blockchain systems face significant challenges in handling large-scale FL tasks, especially on Internet of Things (IoT) devices, due to their substantial resource consumption, limited transaction throughput, and complex communication requirements. To address these challenges, this paper proposes ChainFL, a novel two-layer blockchain-driven FL system. It splits the IoT network into multiple shards within the subchain layer, effectively reducing the scale of information exchange, and employs a Direct Acyclic Graph (DAG)-based mainchain as the mainchain layer, enabling parallel and asynchronous cross-shard validation. Furthermore, the FL procedure is customized to integrate deeply with blockchain technology, and a modified DAG consensus mechanism is designed to mitigate distortion caused by abnormal models. To provide a proof-of-concept implementation and evaluation, multiple subchains based on Hyperledger Fabric and a self-developed DAG-based mainchain are deployed. Extensive experiments demonstrate that ChainFL significantly surpasses conventional FL systems, showing up to a 14% improvement in training efficiency and a threefold increase in robustness.
Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight quantization and pruning are usually applied before they can be accommodated onthe edge. It is generally believed that quantization leads to performance degradation, and plenty of existingworks have explored quantization strategies aiming at minimum accuracy loss. In this paper, we argue thatquantization, which essentially imposes regularization on weight representations, can sometimes help toimprove accuracy. We conduct comprehensive experiments on three widely used applications: fully con-nected network (FCN) for biomedical image segmentation, convolutional neural network (CNN) for imageclassification on ImageNet, and recurrent neural network (RNN) for automatic speech recognition, and experi-mental results show that quantization can improve the accuracy by 1%, 1.95%, 4.23% on the three applicationsrespectively with 3.5x-6.4x memory reduction.