Smart Edge Research Articles

Sustainable Manufacturing in Industry 4.0: Enhancing Safety and Rapid Response in Industrial Control Systems with Smart Edge IoT Devices

In This research, we delve into the dynamic synergy between sustainable energy and Industry 4.0 within the field of "Energy and Sustainable Engineering." It centers on integrating an emergency email generation system into a robust digitalization framework. The study prioritizes hands-on training, emphasizing practical applications that blend sustainable energy practices with the transformative principles of Industry 4.0. By focusing primarily on the intersection of sustainable energy, the project underscores the crucial role of digitization. This seamless integration aligns with the principles of automation, smart technologies, and the evolving landscape of digitization within industries committed to sustainable energy practices. The primary objective in this experiment is to integrate Industrial IoT into the realm of smart manufacturing, effectively incorporating our system into the framework of Industry 4.0, while prioritizing energy sustainability. Through this integration, our experimental results demonstrate that in the event of an emergency condition, instead of the automation system persisting under faulty conditions, an email notification is immediately sent to the operator, facilitated by IoT. This approach not only ensures swift response to critical situations but also contributes to energy conservation and overall sustainability. This initiative significantly contributes to ongoing discussions surrounding sustainable energy, digital transformation, and Industry 4.0, marking a significant step forward in promoting conscientious industrial practices for the future.

Smart edge segmentation and localization method for building detection in satellite imagery

The rapid advancements in satellite imaging technology have brought about an unprecedented influx of high-resolution satellite imagery. One of the critical tasks in this domain is the automated detection of buildings within satellite imagery. Building detection holds substantial significance for urban planning, disaster management, environmental monitoring, and various other applications. The challenges in this field are manifold, including variations in building sizes, shapes, orientations, and surrounding environments. Furthermore, satellite imagery often contains occlusions, shadows, and other artifacts that can hinder accurate building detection. The proposed method introduces a novel approach to improve the boundary detection of detected buildings in high-resolution remote sensed images having shadows and irregular shapes. It aims to enhance the accuracy of building detection and classification. The proposed algorithm is compared with Customized Faster R-CNNs and Single-Shot Multibox Detectors to show the significance of the results. We have used different datasets for training and evaluating the algorithm. Experimental results show that SESLM for Building Detection in Satellite Imagery can detect 98.5% of false positives at a rate of 8.4%. In summary, SESLM showcases high accuracy and improved robustness in detecting buildings, particularly in the presence of shadows.

Intelligent data-driven condition monitoring of power electronics systems using smart edge–cloud framework

The ongoing revolution in industrial production- Industry 4.0, is driven by transformative technologies such as the Industrial Internet of Things (IIoT), Artificial Intelligence (AI), single-board computers, and 5G communication. As the trend towards IIoT continues, an increasing number of industrial drive systems and their fleets are being connected to the cloud. This enables the manufacturers to perform condition monitoring (CM) and streamlined maintenance activities. At the heart of these drive systems are Power Electronics Systems (PESs), which operate at high switching frequencies (10 kHz–1 MHz) to efficiently transfer electrical power and deliver it to a load in a controlled manner. However, due to their functionalities and the presence of semiconductor switches, PESs are susceptible to failure, necessitating effective condition monitoring (CM) for fault detection and improved lifetime. Link to this issue, to enable CM based on high-frequency data, an industrial site with multiple electric drives is required to record data up to 15TB/week. Therefore, there is a demand from industrial partners to establish intelligent communication between a fleet of physical systems and the cloud to reduce transmission, storage, and bandwidth costs, as well as to enable real-time fault detection and learning from fleet operations. This paper proposes an intelligent edge–cloud computing methodology to address the challenge of high-frequency data monitoring for PESs, focusing on novelty detection and selective data transmission to reduce transmission costs. The methodology involves developing a novel edge–cloud framework that incorporates a neural network-based novelty detector for selective data transmission from physical systems to the cloud. The proposed methodology is evaluated through hardware tests, demonstrating a significant reduction in data transmission (94%) and potential cost savings of up to €5.9k/year for a single remote system. 95.6% detection accuracy of the PQ phase is obtained during experimental tests over 590 samples. Thus, this paper contributes to the vision of the smart grid and IIoT by analyzing the Power Quality (PQ) monitoring problem of a three-phase grid and showcasing the capability of the proposed framework in terms of novelty detection and data transmission cost reduction. To conclude, the proposed intelligent edge–cloud computing methodology offers a promising solution for effective condition monitoring of PESs, with potential cost savings and improved fault detection capabilities. By leveraging advanced technologies and intelligent data-driven approaches, this framework advances the goals of Industry 4.0 and paves the way for efficient and reliable industrial operations in the digital age.

FE-Net: Feature enhancement segmentation network

Semantic segmentation is one of the directions in image research. It aims to obtain the contours of objects of interest, facilitating subsequent engineering tasks such as measurement and feature selection. However, existing segmentation methods still lack precision in class edge, particularly in multi-class mixed region. To this end, we present the Feature Enhancement Network (FE-Net), a novel approach that leverages edge label and pixel-wise weights to enhance segmentation performance in complex backgrounds. Firstly, we propose a Smart Edge Head (SE-Head) to process shallow-level information from the backbone network. It is combined with the FCN-Head and SepASPP-Head, located at deeper layers, to form a transitional structure where the loss weights gradually transition from edge labels to semantic labels and a mixed loss is also designed to support this structure. Additionally, we propose a pixel-wise weight evaluation method, a pixel-wise weight block, and a feature enhancement loss to improve training effectiveness in multi-class regions. FE-Net achieves significant performance improvements over baselines on publicly datasets Pascal VOC2012, SBD, and ATR, with best mIoU enhancements of 15.19%, 1.42% and 3.51%, respectively. Furthermore, experiments conducted on Pole&Hole match dataset from our laboratory environment demonstrate the superior effectiveness of FE-Net in segmenting defined key pixels.

A decentralised federated learning scheme for heterogeneous devices in cognitive IoT

Cognitive Internet of Things (IoT) technologies typically rely on substantial data collected from edge devices for data analysis and decision-making. However this reliance often leads to the inadvertent exposure of private data from smart edge devices. Federated learning (FL) is a distributed machine learning framework that protects user privacy by performing collaborative training without uploading private data. Nevertheless, applying classical FL to cognitive IoT systems to preserve privacy preservation faces significant challenges, such as central server failure and communication burden. Furthermore, when edge devices with heterogeneous data and systems participate in federated training, the learning process becomes slow and the performance of edge devices is compromised. To address these challenges, we propose a decentralised FL framework for cognitive IoT, termed DFL–MKF. In DFL– MKF, the centralised server is eliminated and each edge device is dynamically connected. We initialised models for edge devices based on computational and storage capabilities to accommodate system heterogeneity. Edge devices learned from the knowledge of multiple neighbours via knowledge transfer, and knowledge fusion was employed to aggregate the knowledge of multiple neighbours, thereby improving the performance of local models, and addressing data heterogeneity. Comprehensive experiments were performed on three image classification tasks. The results of these experiments demonstrate that the proposed method achieved superior performance compared to various baselines and improved communication efficiency.

Mutual Knowledge Distillation based Personalized Federated Learning for Smart Edge Computing

Mutual Knowledge Distillation based Personalized Federated Learning for Smart Edge Computing

Edge-AI: IoT Request Service Provisioning in Federated Edge Computing Using Actor-Critic Reinforcement Learning

Edge computing plays a critical role in the Internet of Things (IoT) environment as it potentially supports the time-critical IoT applications’ resources as well as latency requirements. In the near future, most edge service providers are envisioned to receive revenue from deploying these applications with the expenditures proportional to placing the offloaded requests from IoT devices and allocating the required resources. One way to maximize the edge profit and minimize the response latency is to integrate the edge nodes and form the edge federation. Therefore, edge service providers can have interoperability to distribute the IoT requests on the appropriate edge nodes in the light of providing satisfactory service levels to meet their objectives. Since the edge nodes are volatile and IoT time-critical applications are increasing, the edge nodes are envisioned to face massive traffic from IoT devices. Therefore, exploiting the traditional dynamic requests placement approaches cannot meet the SLA requirement of both IoT devices and edge service providers. In this article, we designed an intelligent reinforcement learning-based request service provisioning system (i.e., here, we call Edge-AI) as part of a smart edge orchestrator in the edge federation. We implement the proposed method, which is called DRL-Dispatcher, and compare it with greedy and random algorithms in edge federation. The experimental results show that the proposed DRL-Dispatcher performs better in terms of profit and low response latency as compared with the baseline approaches.

A smart edge computing infrastructure for air quality monitoring using LPWAN and MQTT technologies

A smart edge computing infrastructure for air quality monitoring using LPWAN and MQTT technologies

A Case Study of Edge Computing Implementations: Multi-access Edge Computing, Fog Computing and Cloudlet

With the explosive growth of intelligent and mobile devices, the current centralized cloud computing paradigm is encountering difficult challenges. Since the primary requirements have shifted towards implementing real-time response and supporting context awareness and mobility, there is an urgent need to bring resources and functions of centralized clouds to the edge of networks, which has led to the emergence of the edge computing paradigm. Edge computing increases the responsibilities of network edges by hosting computation and services, therefore enhancing performances and improving quality of experience (QoE). Fog computing, multi-access edge computing (MEC), and cloudlet are three typical and promising implementations of edge computing. Fog computing aims to build a system that enables cloud-to-thing service connectivity and works in concert with clouds, MEC is seen as a key technology of the fifth generation (5G) system, and Cloudlet is a micro-data center deployed in close proximity. In terms of deployment scenarios, Fog computing focuses on the Internet of Things (IoT), MEC mainly provides mobile RAN application solutions for 5G systems, and cloudlet offloads computing power at the network edge. In this paper, we present a comprehensive case study on these three edge computing implementations, including their architectures, differences, and their respective application scenario in IoT, 5G wireless systems, and smart edge. We discuss the requirements, benefits, and mechanisms of typical co-deployment cases for each paradigm and identify challenges and future directions in edge computing.

Dynamic robust analysis of IoV link delay in cellular Telematics and smart edge networking base on deep reinforcement learning

Applications for the Internet of Vehicles (IoV) are progressing from more fundamental ones like those for traffic efficiency, road safety, and information services to more sophisticated ones like autonomous driving and intelligent mobility that have a variety of connectivity requirements. Therefore, IoV communication systems must overcome various obstacles in order to enable a variety of IoV applications. Attacks on TSP servers are the major target of telematics attack threat events. This article analyses data security monitoring from the vehicle end to the TSP platform, as well as gathering and analysing the status and intelligence of linked vehicles, in order to develop a Telematics TSP server attack monitoring system. Experiments show that the error detection rate of the benchmark algorithms decreases significantly as the error rate of vehicle speed data increases, with the exponential smoothing algorithm showing the largest decrease in the error detection rate. However, the proposed combined model is very close to the error detection rate of the benchmark algorithm at the later stages when the error rate is high, with an error detection rate of more than 80%.It provides great assistance for anomaly detection and data recovery, especially in researching key technologies for remote information processing data security and reliability, greatly improving their performance.

Design of Smart Edge Sharpening and Enhancement Algorithm for the Complex Panoramic Image of City Landscape Architecture

Abstract When using the current method to sharpen and enhance the edge of panoramic image, it is affected by the noise in panoramic image, resulting in large image standard deviation and mean square error, low signal-to-noise ratio and peak signal-to-noise ratio, high brightness distortion, and visual information distortion. Therefore, an edge sharpening and enhancement algorithm for the complex panoramic image of landscape architecture is proposed. The principal component analysis method is used to denoise the complex panoramic image of landscape architectures. According to the surface points and detail areas of plant landscape, the panoramic image’s super-resolution reconstruction and template matching are carried out, the overall histogram distribution model of panoramic image is reconstructed, and the self-similarity coefficient of edge sharpened surface points of panoramic image is obtained by tone mapping and color feature decomposition, so that the image edge sharpening is completed. Finally, NLEMD algorithm and Retinex algorithm are combined to enhance the complex panoramic image of landscape architecture. Experimental results show that the proposed algorithm has small image standard deviation and mean square error, high signal-to-noise ratio, and peak signal-to-noise ratio, as well as low brightness distortion and visual information distortion.

Cooperative and Comprehensive Multi-Task Surveillance Sensing and Interaction System Empowered by Edge Artificial Intelligence

Numerous sensors were introduced to intelligent transportation systems (ITS) in the past decade. Consequently, new sensing technologies and the generated data attracted more and more attention, which brought new challenges, such as redundant sensors, huge maintenance costs, and data explosion, to ITS. To satisfy the core demands of traffic agencies in a more effective and efficient way, therefore, this paper proposes the idea of “Sensing as a Service” (SaaS) and implements it in the Cooperative and Comprehensive Smart Edge Node for Sensing and OpeRation (COCO SENSOR) system for practical deployments. COCO SENSOR is an innovative multi-task sensing system, which was developed to address key practical applications, including real-time vehicle counting and recognition, road-surface-condition classification, visibility estimation, and live communication among traffic controllers and road users in a single unit. COCO SENSOR introduced customized cooperative sensing and a parallel computation mechanism to increase perception accuracy and efficiency with limited computation resources on the edge device. In collaboration with the Washington State Department of Transportation and the City of Bellevue, a field experiment was conducted to test the system’s performance. The results of the experiment show that the COCO SENSOR effectively fills the gap between sensing and traffic services and that it successfully executed four practical applications, including traffic-volume counting by vehicle type, traffic-status detection, road-visibility estimation, and road-surface-condition classification, with high accuracy. Additionally, a mobile app was developed for both traffic managers and users to access comprehensive traffic information and live warning messages.

A Speculative Computation Approach for Energy-Efficient Deep Neural Network

Deep neural networks (DNNs) have been widely used for data processing and analysis nowadays. Many computational techniques have been proposed to improve the energy efficiency of executing DNNs, which is critical for emerging smart edge applications. This article presents a speculative computation approach to improving the energy efficiency of DNN computations. The proposed approach employs the techniques of input channel partitioning and threshold-based negative masking to predict and eliminate unnecessary computations. Moreover, a systematic procedure of threshold optimization is proposed to achieve the best tradeoff between the energy and accuracy performance. Finally, an energy-efficient DNN processor architecture was designed and implemented to support the proposed speculative computation approach. The experimental results show that the proposed DNN processor with speculative computation can enhance the energy efficiency of the processor by 22.8%, with only 0.96% accuracy degradation and 1% implementation overhead.

Smart Edge Detection Technique in X-ray Images for Improving PSNR using Robert Edge Detection Algorithm with Gaussian Filter in Comparison with Laplacian Algorithm

Aim: This study aims to propose smart edge detection techniques in x-ray images for improving PSNR using the Robert edge detection algorithm and compared it with the laplacian algorithm. Materials and Methods: For the design of edge detection technique to improve PSNR Robert edge detection algorithm is used along with the gaussian filter and it is compared with the laplacian algorithm. Robert edge detection algorithm and laplacian algorithm are the two groups considered in this study. For each group, the sample size is 20 and the total sample size is 40. Sample size calculation was done using clinicalc.com by keeping g-power at 80%, confidence interval at 95%, and the threshold at 0.05%. Result: When comparing the two algorithms, it is clear that the Robert edge detection algorithm has a higher mean PSNR value of 43.83 db than the laplacian algorithm 43.33 db. It is observed that the Robert edge detection algorithm has statistically insignificant difference from the laplacian algorithm by performing an independent sample t-test with p value greater than 0.05. Conclusion: Robert edge detection has significantly greater PSNR when compared to the Laplacian algorithm

Smart Edge Detection Technique in X-ray Images for Improving PSNR using Sobel Edge Detection Algorithm with Gaussian Filter in Comparison with Laplacian Algorithm

Aim: The aim of this study is to propose smart edge detection techniques in x-ray images for improving PSNR using the sobel edge detection algorithm and comparing it with the laplacian algorithm. Materials and methods: For the design of edge detection technique to improve PSNR Sobel edge detection algorithm is used along with the gaussian filter and it is compared with the laplacian algorithm. Sobel edge detection algorithm and laplacian algorithm are the two groups considered in this study. For each group, the sample size is 20 and the total sample size is 40. Sample size calculation was done using clinicalc. com by keeping g-power at 80%, confidence interval at 95%, and the threshold at 0.05%. Result: When comparing the two algorithms, it is clear that the Sobel edge detection algorithm has a higher mean PSNR value of 39.15db than the laplacian algorithm 36.79db. It is observed that the Sobel edge detection algorithm performed better than the laplacian algorithm by performing an independent sample t-test. The p value is 0.09 which is greater than the normal value(p>0.05). Conclusion: Sobel edge detection has insignificantly greater PSNR when compared to the Laplacian algorithm.

Smart Edge Detection Technique in X-ray Images for Improving PSNR using Prewitt Edge Detection Algorithm with Gaussian Filter in Comparison with Laplacian Algorithm

Aim: This study aims to propose smart edge detection techniques in x-ray images for improving PSNR using the Prewitt edge detection algorithm and comparing it with the laplacian algorithm. Materials and methods: For the design of edge detection technique to improve PSNR Prewitt edge detection algorithm is used along with a gaussian filter and it is compared with the laplacian algorithm. Prewitt edge detection algorithm and laplacian algorithm are the two groups considered in this study. For each group, the sample size is 20 and the total sample size is 40. Sample size calculation was done using clinicalc. com by keeping g-power at 80%, confidence interval at 95%, and the threshold at 0.05%. Result: When comparing the two algorithms, it is clear that the Prewitt edge detection algorithm has a higher mean PSNR value of 39.19 db than the laplacian algorithm of 37.56 db. It is observed that the Prewitt edge detection algorithm is statistically significant p<0.05 than the laplacian algorithm by performing an independent sample t-test. Conclusion: Prewitt edge detection has insignificantly greater PSNR when compared to the Laplacian algorithm.

Smart Edge Detection Technique in X ray Images for Improving PSNR using Canny Edge Detection Algorithm with Gaussian Filter in Comparison with Laplacian Algorithm

Aim: The aim of this study is to propose smart edge detection techniques in x-ray images for improving PSNR using canny edge detection algorithm and compared with laplacian algorithm. Materials and Methods: Using the design of edge detection technique and to improve PSNR, canny edge detection algorithm is used along with gaussian filter and it is compared with laplacian algorithm. Canny edge detection algorithm and laplacian algorithm are the two groups considered in this study. For each group the sample size is 20 and the total sample size is 40. Sample size calculation was done using clinicalc. com by keeping g-power at 80%, confidence interval at 95% and threshold at 0.05%. Result: When comparing the two algorithms, it is clear that the canny edge detection algorithm has a higher mean PSNR value of 28.98db than the laplacian algorithm 27.08 db. It is observed that the canny edge detection algorithm performed better than the laplacian algorithm (p>0.05) by performing an independent sample t-test. Conclusion: Canny edge detection has insignificantly greater PSNR when compared to laplacian algorithm.

A 184-μW Error-Tolerant Real-Time Hand Gesture Recognition System With Hybrid Tiny Classifiers Utilizing Edge CNN

This article proposes a low-power real-time hand gesture recognition (HGR) system with high recognition accuracy for smart edge devices. This design balances accuracy and power consumption by utilizing computation-efficient hybrid classifiers assisted with a majority voting scheme. By combining the recognition results of consecutive frames, the HGR system shows improved immunity to misclassification. In addition, the compressed input data before high-level processing dramatically reduce the on- chip memory and computational load. The proposed Edge-convolutional neural network (CNN) core with interactable processing engines reduces the memory accessing and the feature register toggling rate by 27% and 50%, respectively. The sequence analyzer based on majority voting improves the static and dynamic gesture recognition accuracy by ~7% and ~8% only with 9.4% hardware overhead. The test chip was fabricated in 65-nm CMOS technology, occupying the area of 1 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\times $ </tex-math></inline-formula> 1.5 mm2. It consumes the lowest power of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$184~\mu \text{W}$ </tex-math></inline-formula> at 25 MHz and 0.6 V. The proposed HGR system can recognize six static gestures and 24 dynamic hand gestures with an average accuracy of 87.25%–95% and 85.4%–94.9%, respectively.

Tutorial on memristor-based computing for smart edge applications

Smart computing on edge-devices has demonstrated huge potential for various application sectors such as personalized healthcare and smart robotics. These devices aim at bringing smart computing close to the source where the data is generated or stored, while coping with the stringent resource budget of the edge platforms. The conventional Von-Neumann architecture fails to meet these requirements due to various limitations e.g., the memory-processor data transfer bottleneck. Memristor-based Computation-In-Memory (CIM) has the potential to realize such smart edge computing for data-dominated Artificial Intelligence (AI) applications by exploiting both the inherent properties of the architecture and the physical characteristics of the memristors. This paper discusses different aspects of CIM, including classification, working principle, CIM potentials and CIM design-flow. The design-flow is illustrated through two case studies to demonstrate the huge potential of CIM in realizing orders of magnitude improvement in energy-efficiency as compared to the conventional architectures. Finally future challenges and research directions of CIM are covered.

Structural plasticity‐based hydrogel optical Willshaw model for one‐shot on‐the‐fly edge learning

AbstractAutonomous one‐shot on‐the‐fly learning copes with the high privacy, small dataset, and in‐stream data at the edge. Implementing such learning on digital hardware suffers from the well‐known von‐Neumann and scaling bottlenecks. The optical neural networks featuring large parallelism, low latency, and high efficiency offer a promising solution. However, ex‐situ training of conventional optical networks, where optical path configuration and deep learning model optimization are separated, incurs hardware, energy and time overheads, and defeats the advantages in edge learning. Here, we introduced a bio‐inspired material‐algorithm co‐design to construct a hydrogel‐based optical Willshaw model (HOWM), manifesting Hebbian‐rule‐based structural plasticity for simultaneous optical path configuration and deep learning model optimization thanks to the underlying opto‐chemical reactions. We first employed the HOWM as an all optical in‐sensor AI processor for one‐shot pattern classification, association and denoising. We then leveraged HOWM to function as a ternary content addressable memory (TCAM) of an optical memory augmented neural network (MANN) for one‐shot learning the Omniglot dataset. The HOWM empowered one‐shot on‐the‐fly edge learning leads to 1000× boost of energy efficiency and 10× boost of speed, which paves the way for the next‐generation autonomous, efficient, and affordable smart edge systems.image