Article
Engineering, Electrical & Electronic
Davide Borsatti, Gianluca Davoli, Walter Cerroni, Carla Raffaelli
Summary: The combination of Industrial IoT and emerging cloud computing architectures has the potential to revolutionize industrial processes. This potential can be maximized by deploying IoT services near factory premises on demand. An architecture based on the ETSI MEC framework is proposed for the automated deployment of Industrial IoT applications, utilizing edge and fog computing environments. A proof-of-concept implementation shows that transforming Industrial IoT applications into MEC-based services is not only feasible, but can achieve full deployment within seconds.
IEEE COMMUNICATIONS MAGAZINE
(2021)
Article
Chemistry, Analytical
Qinghua Sheng, Haixiang Sheng, Peng Gao, Zhu Li, Haibing Yin
Summary: This study proposes a real-time detection scheme for cook assistant overalls based on the Hi3559A embedded processor, which improves the network reasoning speed on embedded devices through optimizing the network model and parallel processing technology. This allows for accurate image recognition and effective application in the scene of identifying kitchen overalls.
Article
Chemistry, Analytical
Laura Erhan, Mario Di Mauro, Ashiq Anjum, Ovidiu Bagdasar, Wei Song, Antonio Liotta
Summary: The article discusses the use of machine learning at sensor nodes for data cleaning and imputation to prevent the transmission of corrupted data to the cloud. Experimental results demonstrate the accuracy and computational efficiency of edge-learning methods in filling missing data values in corrupted data series.
Review
Computer Science, Information Systems
Praveen Joshi, Mohammed Hasanuzzaman, Chandra Thapa, Haithem Afli, Ted Scully
Summary: In recent years, deep learning models have achieved remarkable success in tasks like speech recognition, image processing, and natural language understanding. However, computing DL training and inference remains a challenge, with issues like high latency and privacy concerns. To address these challenges, efforts have been made to push DL processing to edge servers, giving rise to the concept of edge intelligence (EI). This survey paper focuses on the all in-edge level of EI, where DL training and deployment are performed solely by edge servers, and discusses architectures, enabling technologies, model adaptation techniques, performance metrics, and research challenges in this area.
Article
Computer Science, Information Systems
Kenneth Li-Minn Ang, Jasmine Kah Phooi Seng
Summary: This article provides a comprehensive survey and review of embedded intelligence research in the field of smart cities, covering enabling technologies, applications, and challenges. The aim is to offer useful insights to researchers and inspire the development of practical EI solutions for smart cities.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Hardware & Architecture
Yaohua Sun, Jianmin Chen, Zeyu Wang, Mugen Peng, Shiwen Mao
Summary: This article introduces the application of virtual reality technology in gaming and operation training, and points out the problems of existing VR solutions. To address these issues, they design a mobile VR system that utilizes 5G and fog computing to provide high bandwidth and low latency service. By using artificial intelligence and interfaces to adjust parameters, they demonstrate the improvement of system performance and identify future research directions.
Article
Engineering, Electrical & Electronic
Yuepeng Li, Deze Zeng, Lin Gu, Andong Zhu, Quan Chen, Shui Yu
Summary: This article addresses the security issues of offloading tasks to edge servers and proposes a Priority-aware Secure Task Offloading (PASTO) algorithm based on TrustZone. Experimental results show that PASTO effectively reduces the total task completion time compared to other approaches.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Chemistry, Analytical
Carlos Resende, Duarte Folgado, Joao Oliveira, Bernardo Franco, Waldir Moreira, Antonio Oliveira-Jr, Armando Cavaleiro, Ricardo Carvalho
Summary: Industry 4.0, AI, and IoT are driving the digitization and automation of industrial processes, with maintenance being a key area of improvement. Predictive maintenance, using sensors and machine learning algorithms, offers benefits such as reduced downtime, improved equipment effectiveness, and lower costs. The TIP4.0 platform showcases the use of edge computing for predictive maintenance, with competitive performance and speed compared to traditional models.
Review
Computer Science, Artificial Intelligence
Weixing Su, Linfeng Li, Fang Liu, Maowei He, Xiaodan Liang
Summary: This paper focuses on the combination of edge computing and artificial intelligence to form edge intelligence. It explores the technologies and implementations for edge training and edge inference, as well as the challenges and future directions in this field.
ARTIFICIAL INTELLIGENCE REVIEW
(2022)
Article
Computer Science, Information Systems
Jose-Luis Poza-Lujan, Pedro Uribe-Chavert, Juan-Jose Saenz-Penafiel, Juan-Luis Posadas-Yague
Summary: This article discusses the paradigm shift in embedded devices in the context of the Internet of Things, where intelligence and data distribution have become possible. It introduces a distributed modular architecture to support this new paradigm and validates its effectiveness.
Article
Computer Science, Theory & Methods
Ruikun Luo, Hai Jin, Qiang He, Song Wu, Xiaoyu Xia
Summary: In the MEC environment, deploying edge servers with storage and computing resources at base stations near users extends cloud computing capabilities to the network edge. However, the limited storage capacities of edge servers result in high data storage overheads, which is a challenge for ensuring application performance on an ESS. Data deduplication offers a solution to reduce data redundancy in ESSs, but the unique characteristics of MEC render traditional cloud data deduplication mechanisms obsolete. This article proposes the balanced edge data deduplication (BEDD) problem, models it formally, and presents optimal and sub-optimal approaches for solving it in small-scale and large-scale scenarios respectively, with significant performance improvements demonstrated in experiments.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2023)
Article
Computer Science, Information Systems
Usman Mahmood Malik, Muhammad Awais Javed
Summary: This paper proposes an ambient intelligence-assisted computing technique for Industrial IoT, aiming to maximize the number of served tasks and improve computational resource utilization at fog nodes by utilizing contextual information and adaptive computing resource unit sizing.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Multidisciplinary
Shunpu Tang, Lunyuan Chen, Ke He, Junjuan Xia, Lisheng Fan, Arumugam Nallanathan
Summary: This paper investigates the deployment of computational intelligence and deep learning in edge-enabled industrial IoT networks. A multi-exit-based federated edge learning framework is proposed to address the limited resources issue. Simulation experiments show that the proposed framework achieves significant accuracy improvement in industrial IoT networks.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Anran Du, Yicheng Shen, Qinzi Zhang, Lewis Tseng, Moayad Aloqaily
Summary: Industry 5.0 is emerging as a result of advancements in networking and communication technologies, artificial intelligence, distributed computing, and beyond 5G. This article proposes a framework to integrate federated learning, industrial edge computing, and Byzantine-tolerant machine learning, and introduces a novel Byzantine-tolerant federated learning algorithm called CRACAU.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Automation & Control Systems
Mingjin Zhang, Jiannong Cao, Yuvraj Sahni, Qianyi Chen, Shan Jiang, Lei Yang
Summary: In this study, a blockchain-based collaborative edge intelligence (BCEI) approach is designed for trustworthy and real-time video surveillance. In BCEI, geo-distributed edge devices form a peer-to-peer network to maintain a permissioned blockchain and share data and computation resources to perform computation-intensive video analytics tasks. By leveraging collaboration among edge devices, BCEI exhibits superior performance in latency reduction and system throughput improvement.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Koutarou Yamamoto, Akihiro Fukuhara, Hiroaki Nishi
Summary: This study proposed a hardware implementation of an MQTT broker and evaluated the accuracy of an MQTT-based time synchronization method. The research confirmed that the proposed MQTT architecture achieved high throughput, low latency, and low jitter MQTT broker, satisfying the response time requirements for smart city services.
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Jifei Deng, Jie Sun, Wen Peng, Dianhua Zhang, Valeriy Vyatkin
Summary: In this paper, a method for addressing imbalanced multiclass problems is proposed by combining synthetic minority oversampling technique with active learning based on deep belief network. Experimental results show that the proposed method outperforms conventional methods in tackling imbalanced multiclass problems.
KNOWLEDGE-BASED SYSTEMS
(2022)
Editorial Material
Automation & Control Systems
Jiehan Zhou, Qinghua Lu, Wenbin Dai, Ray Y. Zhong
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Nikolai Galkin, Michail Ruchkin, Valeriy Vyatkin, Chen-Wei Yang, Viktor Dubinin
Summary: Data centres are essential in our society's infrastructure, however, their growing number is leading to increased energy consumption. This paper proposes a new concept of generating a digital twin system for data centres, which can aid decision-making and virtual commissioning through simulation, machine learning, and reasoning. The IEC 61850 standard is used as a starting point for generating the digital twin, combining a simulation model and decentralized control logic.
Article
Automation & Control Systems
Wenbin Dai, Yingyue Zhang, Yunpeng Zhang, Jiale Kang, Dan Huang
Summary: This article proposes an automatic information model generation method that can significantly reduce the development time for distributed information models and provide strong support for dynamic reconfiguration.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Nikolai Galkin, Chen-Wei Yang, Valeriy Vyatkin
Summary: The wide propagation of electric vehicle (EV) charging infrastructure integrated into the energy distribution network poses challenges that require advanced control, predictions, and virtual commissioning. Integrating EV-specific standards and protocols with other electrical standards can automate the design and simulation of new charging stations, improve compatibility between standards, and promote the development of EV infrastructure. A virtual commissioning method for electrical charging stations is proposed, which uses the IEC 61850 standard as input for a software tool that builds a digital twin of the charging station and generates communication code primitives for control and management using the open charge point protocol. The method's application is illustrated through a case study.
IEEE OPEN JOURNAL OF THE INDUSTRIAL ELECTRONICS SOCIETY
(2023)
Article
Computer Science, Information Systems
Yuiko Sakuma, Hiroaki Nishi
Summary: Short-term load forecasting is crucial for appliance control and demand response. To address security and data collection concerns, we propose a distributed framework that shares latent variables of household models.
Article
Computer Science, Information Systems
Mohammad Azangoo, Lotta Sorsamaki, Seppoa Sierla, Teemu Matasniemi, Miia Rantala, Kari Rainio, Valeriy Vyatkin
Summary: Digital twins are a top trend in Industry 4.0, used by companies to enhance digitalization, productivity, and reliability. However, their development is difficult, expensive, and time-consuming. This article proposes a semi-automated methodology to generate digital twins for process plants, using text and image processing techniques. It also introduces a methodology and toolchain for generating a digital twin of a brownfield process system.
Review
Computer Science, Information Systems
Rakshith Subramanya, Seppo A. Sierla, Valeriy Vyatkin
Summary: This article reviews the recent surge in papers applying reinforcement learning to optimize battery storage systems. It analyzes the optimization problem type, categorizing them into financial targets or energy efficiency approaches. The article also discusses methods for handling user comfort and battery degradation reduction. Furthermore, it categorizes the articles based on application context and identifies applications likely to attract significant research.
Article
Computer Science, Information Systems
Vladimir E. Zyubin, Andrei S. Rozov, Igor S. Anureev, Natalia O. Garanina, Valeriy Vyatkin
Summary: This paper presents the core concepts of the poST language, a process-oriented extension of the IEC 61131-3 Structured Text language, which aims to provide conceptual consistency between PLC source code and plant operating procedures. The language combines the advantages of FSM-based programming and the traditional syntax of ST, and describes its basic syntax and usage.
Article
Engineering, Electrical & Electronic
Nikolai Galkin, Chen-Wei Yang, Yulia Berezovskaya, Mattias Vesterlund, Valeriy Vyatkin
Summary: Green datacentres are not only consumers but also producers of power, making them important participants in the energy grid. Researchers have developed a microgrid simulation model based on a real edge datacentre, which has been validated through simulation and real-time tests. The model is then connected to the automation environment for online impact estimation and virtual commissioning purposes.
IEEE OPEN JOURNAL OF THE INDUSTRIAL ELECTRONICS SOCIETY
(2022)
Proceedings Paper
Engineering, Industrial
Shouichi Hatanaka, Hiroaki Nishi
Summary: Smart factory or Industry 4.0 is creating a new era for manufacturing by reducing total costs through monitoring and predicting expected faults in production lines and products. This study focuses on using deep generative models for unsupervised abnormality detection in a refrigeration system for large storage, achieving the highest accuracy with an Efficient GAN-based method while using low-cost microphone arrays for monitoring sounds and source locations.
PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2021)
Proceedings Paper
Automation & Control Systems
Hiroaki Nishi, Eugene Y. Song, Yuichi Nakamura, Kang B. Lee, Yucheng Liu, Kim Fung Tsang
Summary: This paper introduces time synchronization approaches to IEEE P1451.0 standard-based sensor networks for IoT applications, focusing on WAN time synchronization and providing two implementations to verify proper functioning. It also describes the time synchronization transducer electronic data sheets (TEDS) of IEEE P1451.1.6.
IECON 2021 - 47TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY
(2021)
Proceedings Paper
Automation & Control Systems
Shogo Shimahara, Hiroaki Nishi
Summary: As data services are provided to achieve Society 5.0, the use of personal data is expected to increase, necessitating privacy protection to keep pace with the growing data exchange. Stricter privacy regulations, starting from the enforcement of GDPR, are expanding globally, requiring personal data to be hidden or anonymized before propagation. Smart communities assume secondary data usage, calling for systems that can safeguard privacy to ensure secure network infrastructures.
IECON 2021 - 47TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY
(2021)
Proceedings Paper
Automation & Control Systems
Yuki Takayama, Saki Saito, Yuiko Sakuma, Hiroaki Nishi
Summary: This paper introduces a method of spatial recognition using stereo infrared array sensors to improve air-conditioning control efficiency by adjusting airflow based on room geometry to reduce temperature imbalance.
IECON 2021 - 47TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY
(2021)