A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image upsampling are currently trained using either resize or sub-pixel convolution to learn kernels that generate high fidelity images with minimal artifacts. However, performing inference with these learned convolution kernels requires memory-intensive feature map transformations that dominate time and energy costs in real-time applications. To alleviate this pressure on memory bandwidth, we confine the use of resize or sub-pixel convolution to training in the cloud by transforming learned convolution kernels to deconvolution kernels before deploying them for inference as a functionally equivalent deconvolution. These kernel transformations, intended as a one-time cost when shifting from training to inference, enable a systems designer to use each algorithm in their optimal context by preserving the image fidelity learned when training in the cloud while minimizing data transfer penalties during inference at the edge. We also explore existing variants of deconvolution inference algorithms and introduce a novel variant for consideration. We analyze and compare the inference properties of convolution-based upsampling algorithms using a quantitative model of incurred time and energy costs and show that using deconvolution for inference at the edge improves both system latency and energy efficiency when compared to their sub-pixel or resize convolution counterparts.
Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyper-parameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyper-parameters and genetically modifies the parameters cluster-wise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyper-parameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data.
The development of lightweight object detectors is essential due to the limited computation resources. To reduce the computation cost, how to generate redundant features plays a significant role. This paper proposes a new lightweight Convolution method Cross-Stage Lightweight (CSL) Module, to generate redundant features from cheap operations. In the intermediate expansion stage, we replaced Pointwise Convolution with Depthwise Convolution to produce candidate features. The proposed CSL-Module can reduce the computation cost significantly. Experiments conducted at MS-COCO show that the proposed CSL-Module can approximate the fitting ability of Convolution-3x3. Finally, we use the module to construct a lightweight detector CSL-YOLO, achieving better detection performance with only 43% FLOPs and 52% parameters than Tiny-YOLOv4.
Feature selection refers to the process of selecting useful features for machine learning tasks, and it is also a key step for structural health monitoring (SHM). This paper proposes a fast feature selection algorithm by efficiently computing the sum of squared canonical correlation coefficients between monitored features and target variables of interest in greedy search. The proposed algorithm is applied to both synthetic and real datasets to illustrate its advantages in terms of computational speed, general classification and regression tasks, as well as damage-sensitive feature selection tasks. Furthermore, the performance of the proposed algorithm is evaluated under varying environmental conditions and on an edge computing device to investigate its applicability in real-world SHM scenarios. The results show that the proposed algorithm can successfully select useful features with extraordinarily fast computational speed, which implies that the proposed algorithm has great potential where features need to be selected and updated online frequently, or where devices have limited computing capability.
The capabilities of natural neural systems have inspired new generations of machine learning algorithms as well as neuromorphic very large-scale integrated (VLSI) circuits capable of fast, low-power information processing. However, it has been argued that most modern machine learning algorithms are not neurophysiologically plausible. In particular, the workhorse of modern deep learning, the backpropagation algorithm, has proven difficult to translate to neuromorphic hardware. In this study, we present a neuromorphic, spiking backpropagation algorithm based on synfire-gated dynamical information coordination and processing, implemented on Intel's Loihi neuromorphic research processor. We demonstrate a proof-of-principle three-layer circuit that learns to classify digits from the MNIST dataset. To our knowledge, this is the first work to show a Spiking Neural Network (SNN) implementation of the backpropagation algorithm that is fully on-chip, without a computer in the loop. It is competitive in accuracy with off-chip trained SNNs and achieves an energy-delay product suitable for edge computing. This implementation shows a path for using in-memory, massively parallel neuromorphic processors for low-power, low-latency implementation of modern deep learning applications.
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.
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.
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.
Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-Of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3x. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5x in memory efficiency improvement) and mitigate OOM problems during GNN inference.
Online algorithms for detecting changepoints, or abrupt shifts in the behavior of a time series, are often deployed with limited resources, e.g., to edge computing settings such as mobile phones or industrial sensors. In these scenarios it may be beneficial to trade the cost of collecting an environmental measurement against the quality or "fidelity" of this measurement and how the measurement affects changepoint estimation. For instance, one might decide between inertial measurements or GPS to determine changepoints for motion. A Bayesian approach to changepoint detection is particularly appealing because we can represent our posterior uncertainty about changepoints and make active, cost-sensitive decisions about data fidelity to reduce this posterior uncertainty. Moreover, the total cost could be dramatically lowered through active fidelity switching, while remaining robust to changes in data distribution. We propose a multi-fidelity approach that makes cost-sensitive decisions about which data fidelity to collect based on maximizing information gain with respect to changepoints. We evaluate this framework on synthetic, video, and audio data and show that this information-based approach results in accurate predictions while reducing total cost.
Interpreting human actions requires understanding the spatial and temporal context of the scenes. State-of-the-art action detectors based on Convolutional Neural Network (CNN) have demonstrated remarkable results by adopting two-stream or 3D CNN architectures. However, these methods typically operate in a non-real-time, ofline fashion due to system complexity to reason spatio-temporal information. Consequently, their high computational cost is not compliant with emerging real-world scenarios such as service robots or public surveillance where detection needs to take place at resource-limited edge devices. In this paper, we propose ACDnet, a compact action detection network targeting real-time edge computing which addresses both efficiency and accuracy. It intelligently exploits the temporal coherence between successive video frames to approximate their CNN features rather than naively extracting them. It also integrates memory feature aggregation from past video frames to enhance current detection stability, implicitly modeling long temporal cues over time. Experiments conducted on the public benchmark datasets UCF-24 and JHMDB-21 demonstrate that ACDnet, when integrated with the SSD detector, can robustly achieve detection well above real-time (75 FPS). At the same time, it retains reasonable accuracy (70.92 and 49.53 frame mAP) compared to other top-performing methods using far heavier configurations. Codes will be available at https://github.com/dginhac/ACDnet.
Edge nodes are crucial for detection against multitudes of cyber attacks on Internet-of-Things endpoints and is set to become part of a multi-billion industry. The resource constraints in this novel network infrastructure tier constricts the deployment of existing Network Intrusion Detection System with Deep Learning models (DLM). We address this issue by developing a novel light, fast and accurate 'Edge-Detect' model, which detects Distributed Denial of Service attack on edge nodes using DLM techniques. Our model can work within resource restrictions i.e. low power, memory and processing capabilities, to produce accurate results at a meaningful pace. It is built by creating layers of Long Short-Term Memory or Gated Recurrent Unit based cells, which are known for their excellent representation of sequential data. We designed a practical data science pipeline with Recurring Neural Network to learn from the network packet behavior in order to identify whether it is normal or attack-oriented. The model evaluation is from deployment on actual edge node represented by Raspberry Pi using current cybersecurity dataset (UNSW2015). Our results demonstrate that in comparison to conventional DLM techniques, our model maintains a high testing accuracy of 99% even with lower resource utilization in terms of cpu and memory. In addition, it is nearly 3 times smaller in size than the state-of-art model and yet requires a much lower testing time.
The COVID-19 epidemic has been a significant healthcare challenge in the United States. According to the Centers for Disease Control and Prevention (CDC), COVID-19 infection is transmitted predominately by respiratory droplets generated when people breathe, talk, cough, or sneeze. Wearing a mask is the primary, effective, and convenient method of blocking 80% of all respiratory infections. Therefore, many face mask detection and monitoring systems have been developed to provide effective supervision for hospitals, airports, publication transportation, sports venues, and retail locations. However, the current commercial face mask detection systems are typically bundled with specific software or hardware, impeding public accessibility. In this paper, we propose an in-browser serverless edge-computing based face mask detection solution, called Web-based efficient AI recognition of masks (WearMask), which can be deployed on any common devices (e.g., cell phones, tablets, computers) that have internet connections using web browsers, without installing any software. The serverless edge-computing design minimizes the extra hardware costs (e.g., specific devices or cloud computing servers). The contribution of the proposed method is to provide a holistic edge-computing framework of integrating (1) deep learning models (YOLO), (2) high-performance neural network inference computing framework (NCNN), and (3) a stack-based virtual machine (WebAssembly). For end-users, our web-based solution has advantages of (1) serverless edge-computing design with minimal device limitation and privacy risk, (2) installation free deployment, (3) low computing requirements, and (4) high detection speed. Our WearMask application has been launched with public access at facemask-detection.com.
A conventional brain-computer interface (BCI) requires a complete data gathering, training, and calibration phase for each user before it can be used. In recent years, a number of subject-independent (SI) BCIs have been developed. Many of these methods yield a weaker performance compared to the subject-dependent (SD) approach, and some are computationally expensive. A potential real-world application would greatly benefit from a more accurate, compact, and computationally efficient subject-independent BCI. In this work, we propose a novel subject-independent BCI framework, named CCSPNet (Convolutional Common Spatial Pattern Network) that is trained on the motor imagery (MI) paradigm of a large-scale electroencephalography (EEG) signals database consisting of 400 trials for every 54 subjects who perform two-class hand-movement MI tasks. The proposed framework applies a wavelet kernel convolutional neural network (WKCNN) and a temporal convolutional neural network (TCNN) in order to represent and extract the spectral features of EEG signals. A common spatial pattern (CSP) algorithm is implemented for spatial feature extraction, and the number of CSP features is reduced by a dense neural network. Finally, the class label is determined by a linear discriminant analysis (LDA) classifier. The CCSPNet evaluation results show that it is possible to have a compact BCI that achieves both SD and SI state-of-the-art performance comparable to complex and computationally expensive models.
Multi-access Edge Computing (MEC) is an emerging computing paradigm that extends cloud computing to the network edge to support resource-intensive applications on mobile devices. As a crucial problem in MEC, service migration needs to decide how to migrate user services for maintaining the Quality-of-Service when users roam between MEC servers with limited coverage and capacity. However, finding an optimal migration policy is intractable due to the dynamic MEC environment and user mobility. Many existing studies make centralized migration decisions based on complete system-level information, which is time-consuming and also lacks desirable scalability. To address these challenges, we propose a novel learning-driven method, which is user-centric and can make effective online migration decisions by utilizing incomplete system-level information. Specifically, the service migration problem is modeled as a Partially Observable Markov Decision Process (POMDP). To solve the POMDP, we design a new encoder network that combines a Long Short-Term Memory (LSTM) and an embedding matrix for effective extraction of hidden information, and further propose a tailored off-policy actor-critic algorithm for efficient training. The extensive experimental results based on real-world mobility traces demonstrate that this new method consistently outperforms both the heuristic and state-of-the-art learning-driven algorithms and can achieve near-optimal results on various MEC scenarios.
There is growing interest in applying distributed machine learning to edge computing, forming federated edge learning. Federated edge learning faces non-i.i.d. and heterogeneous data, and the communication between edge workers, possibly through distant locations and with unstable wireless networks, is more costly than their local computational overhead. In this work, we propose DONE, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning. First, with strongly convex and smooth loss functions, DONE approximates the Newton direction in a distributed manner using the classical Richardson iteration on each edge worker. Second, we prove that DONE has linear-quadratic convergence and analyze its communication complexities. Finally, the experimental results with non-i.i.d. and heterogeneous data show that DONE attains a comparable performance to the Newton's method. Notably, DONE requires fewer communication iterations compared to distributed gradient descent and outperforms DANE and FEDL, state-of-the-art approaches, in the case of non-quadratic loss functions.
This paper presents Systolic-CNN, an OpenCL-defined scalable, run-time-flexible FPGA accelerator architecture, optimized for accelerating the inference of various convolutional neural networks (CNNs) in multi-tenancy cloud/edge computing. The existing OpenCL-defined FPGA accelerators for CNN inference are insufficient due to limited flexibility for supporting multiple CNN models at run time and poor scalability resulting in underutilized FPGA resources and limited computational parallelism. Systolic-CNN adopts a highly pipelined and paralleled 1-D systolic array architecture, which efficiently explores both spatial and temporal parallelism for accelerating CNN inference on FPGAs. Systolic-CNN is highly scalable and parameterized, which can be easily adapted by users to achieve up to 100% utilization of the coarse-grained computation resources (i.e., DSP blocks) for a given FPGA. Systolic-CNN is also run-time-flexible in the context of multi-tenancy cloud/edge computing, which can be time-shared to accelerate a variety of CNN models at run time without the need of recompiling the FPGA kernel hardware nor reprogramming the FPGA. The experiment results based on an Intel Arria/Stratix 10 GX FPGA Development board show that the optimized single-precision implementation of Systolic-CNN can achieve an average inference latency of 7ms/2ms, 84ms/33ms, 202ms/73ms, 1615ms/873ms, and 900ms/498ms per image for accelerating AlexNet, ResNet-50, ResNet-152, RetinaNet, and Light-weight RetinaNet, respectively. Codes are available at https://github.com/PSCLab-ASU/Systolic-CNN.
Monitoring the respiratory rate is crucial for helping us identify respiratory disorders. Devices for conventional respiratory monitoring are inconvenient and scarcely available. Recent research has demonstrated the ability of non-contact technologies, such as photoplethysmography and infrared thermography, to gather respiratory signals from the face and monitor breathing. However, the current non-contact respiratory monitoring techniques have poor accuracy because they are sensitive to environmental influences like lighting and motion artifacts. Furthermore, frequent contact between users and the cloud in real-world medical application settings might cause service request delays and potentially the loss of personal data. We proposed a non-contact respiratory rate monitoring system with a cooperative three-layer design to increase the precision of respiratory monitoring and decrease data transmission latency. To reduce data transmission and network latency, our three-tier architecture layer-by-layer decomposes the computing tasks of respiration monitoring. Moreover, we improved the accuracy of respiratory monitoring by designing a target tracking algorithm and an algorithm for eliminating false peaks to extract high-quality respiratory signals. By gathering the data and choosing several regions of interest on the face, we were able to extract the respiration signal and investigate how different regions affected the monitoring of respiration. The results of the experiment indicate that when the nasal region is used to extract the respiratory signal, it performs experimentally best. Our approach performs better than rival approaches while transferring fewer data.
To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded to the edge for processing by an accurate but resource-intensive model, and the rest are processed only by a less-accurate model on the device itself. Both models have computational costs that match available compute resources, and process inputs with low-latency. But offloading incurs network delays, and to manage these delays to meet application deadlines, we use a token bucket to constrain the average rate and burst length of transmissions from the device. We introduce a Markov Decision Process-based framework to make offload decisions under these constraints, based on the local model's confidence and the token bucket state, with the goal of minimizing a specified error measure for the application. Beyond isolated decisions for individual devices, we also propose approaches to allow multiple devices connected to the same access switch to share their bursting allocation. We evaluate and analyze the policies derived using our framework on the standard ImageNet image classification benchmark.