Pub Date : 2024-09-02DOI: 10.1038/s44287-024-00097-8
Lishu Wu
An article in IEEE Journal on Selected Areas in Communications presents a cooperative framework that integrates satellite routing and frequency assignment to avoid self-interference in large satellite constellations.
电气和电子工程师学会通信选区期刊》（IEEE Journal on Selected Areas in Communications）上的一篇文章介绍了一种合作框架，该框架将卫星路由和频率分配整合在一起，以避免大型卫星星座中的自干扰。
{"title":"Mitigating interference within satellite megaconstellations","authors":"Lishu Wu","doi":"10.1038/s44287-024-00097-8","DOIUrl":"10.1038/s44287-024-00097-8","url":null,"abstract":"An article in IEEE Journal on Selected Areas in Communications presents a cooperative framework that integrates satellite routing and frequency assignment to avoid self-interference in large satellite constellations.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"568-568"},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-02DOI: 10.1038/s44287-024-00078-x
Saptadeep Pal, Arindam Mallik, Puneet Gupta
Advanced integration and packaging will drive the scaling of computing systems in the next decade. Diversity in performance, cost and scale of the emerging systems implies that system technology co-optimization (STCO) would be essential to develop these integration technologies for future systems. Such STCO would need to comprehend not only integration technology, circuits, architectures and software but also their interactions with the power delivery, cooling and system costs. In this Review, we present a perspective on what would be needed from these STCO approaches with exemplar case studies covering the current state of the art and the future outlook. This Review discusses system technology co-optimization across the technology–hardware–software stack to guide broader research and development efforts towards the realization of future heterogeneously integrated computing systems.
{"title":"System technology co-optimization for advanced integration","authors":"Saptadeep Pal, Arindam Mallik, Puneet Gupta","doi":"10.1038/s44287-024-00078-x","DOIUrl":"10.1038/s44287-024-00078-x","url":null,"abstract":"Advanced integration and packaging will drive the scaling of computing systems in the next decade. Diversity in performance, cost and scale of the emerging systems implies that system technology co-optimization (STCO) would be essential to develop these integration technologies for future systems. Such STCO would need to comprehend not only integration technology, circuits, architectures and software but also their interactions with the power delivery, cooling and system costs. In this Review, we present a perspective on what would be needed from these STCO approaches with exemplar case studies covering the current state of the art and the future outlook. This Review discusses system technology co-optimization across the technology–hardware–software stack to guide broader research and development efforts towards the realization of future heterogeneously integrated computing systems.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"569-580"},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-27DOI: 10.1038/s44287-024-00082-1
Leon O. Chua
Rather than echoing the vision and perspectives proffered by numerous previous publications, this Review focuses on the recent resolution of four unsolved classic problems — Galvani’s ‘irritability’, the Hodgkin–Huxley ‘all-or-none’ mystery, the Turing instability and the Smale paradox — the oldest dating back 243 years to Galvani in 1781. Unlike advances reported previously, which tend to be ephemeral, our resolution of these problems is timeless, because they are a manifestation of a new law of nature, called the ‘principle of local activity’, which, within a certain relatively small parameter space, could harbour a physical state dubbed the ‘edge of chaos’. In this Review, we provide an explicit formula for calculating, via matrix algebra, the precise parameter range where a nonlinear device, or system, is locally active or operating on the edge of chaos. Unlike numerous unsuccessful attempts by luminaries, such as Boltzmann’s assay for decreasing entropy, Schrödinger’s futile search for negentropy, Prigogine’s quest for the ‘instability of the homogeneous’ and Gell-Mann’s musing on ‘amplification of fluctuations’, the principle of local activity provides an explicit formula to identify the parameter space where the edge of chaos reigns supreme. This Review resolves the age-old problems of Galvani’s irritability, the Hodgkin–Huxley ‘all-or-none’ mystery, the Turing instability and the Smale paradox, by applying the findings in 2023 that memristors operating on the ‘edge of chaos’ can model the nonlinear dynamics of these problems, complementing the second law of thermodynamics.
{"title":"Memristors on ‘edge of chaos’","authors":"Leon O. Chua","doi":"10.1038/s44287-024-00082-1","DOIUrl":"10.1038/s44287-024-00082-1","url":null,"abstract":"Rather than echoing the vision and perspectives proffered by numerous previous publications, this Review focuses on the recent resolution of four unsolved classic problems — Galvani’s ‘irritability’, the Hodgkin–Huxley ‘all-or-none’ mystery, the Turing instability and the Smale paradox — the oldest dating back 243 years to Galvani in 1781. Unlike advances reported previously, which tend to be ephemeral, our resolution of these problems is timeless, because they are a manifestation of a new law of nature, called the ‘principle of local activity’, which, within a certain relatively small parameter space, could harbour a physical state dubbed the ‘edge of chaos’. In this Review, we provide an explicit formula for calculating, via matrix algebra, the precise parameter range where a nonlinear device, or system, is locally active or operating on the edge of chaos. Unlike numerous unsuccessful attempts by luminaries, such as Boltzmann’s assay for decreasing entropy, Schrödinger’s futile search for negentropy, Prigogine’s quest for the ‘instability of the homogeneous’ and Gell-Mann’s musing on ‘amplification of fluctuations’, the principle of local activity provides an explicit formula to identify the parameter space where the edge of chaos reigns supreme. This Review resolves the age-old problems of Galvani’s irritability, the Hodgkin–Huxley ‘all-or-none’ mystery, the Turing instability and the Smale paradox, by applying the findings in 2023 that memristors operating on the ‘edge of chaos’ can model the nonlinear dynamics of these problems, complementing the second law of thermodynamics.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"614-627"},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44287-024-00082-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-23DOI: 10.1038/s44287-024-00095-w
Silvia Conti
An article in Nature Communications introduces the use of acoustic holograms in direct remote printing.
自然-通讯》上的一篇文章介绍了声全息图在直接远程打印中的应用。
{"title":"Remote distance printing through acoustic holograms","authors":"Silvia Conti","doi":"10.1038/s44287-024-00095-w","DOIUrl":"10.1038/s44287-024-00095-w","url":null,"abstract":"An article in Nature Communications introduces the use of acoustic holograms in direct remote printing.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"567-567"},"PeriodicalIF":0.0,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-22DOI: 10.1038/s44287-024-00086-x
Bo Hou, Qiushui Chen, Luying Yi, Paul Sellin, Hong-Tao Sun, Liang Jie Wong, Xiaogang Liu
X-ray detection is critical for applications in medical diagnosis, industrial inspection, security checks, scientific inquiry and space exploration. Recent advances in materials science, electronics, manufacturing and artificial intelligence have greatly propelled the field forward. In this Review we examine fundamental principles and recent breakthroughs in X-ray detection and imaging technologies, with a focus on the interplay between electrical engineering techniques and X-ray-responsive materials. We highlight two primary approaches: semiconductor-based direct detection and scintillator-based indirect detection. We then discuss innovations such as photon-counting detectors and heterojunction phototransistors and emphasize the critical contributions of electrical engineering in the development of these cutting-edge detectors. Subsequently, we provide an overview of X-ray detection applications, ranging from biomedical imaging and resonant X-ray techniques for material analysis to nanometre-resolution circuit imaging. Finally, the Review summarizes future research directions, which encompass 3D and 4D X-ray imaging sensors, multispectral X-ray imaging and artificial intelligence-assisted medical image diagnosis. This Review examines fundamental principles and recent breakthroughs in X-ray detection and imaging technologies, with a focus on the interplay between electrical engineering techniques and materials science.
X 射线探测在医疗诊断、工业检测、安全检查、科学探究和太空探索等领域的应用至关重要。材料科学、电子学、制造业和人工智能领域的最新进展极大地推动了这一领域的发展。在本综述中，我们将研究 X 射线探测和成像技术的基本原理和最新突破，重点关注电子工程技术与 X 射线响应材料之间的相互作用。我们重点介绍两种主要方法：基于半导体的直接探测和基于闪烁体的间接探测。然后，我们讨论了光子计数探测器和异质结光电晶体管等创新技术，并强调了电气工程在这些尖端探测器开发过程中的重要贡献。随后，我们概述了 X 射线探测的应用，从用于材料分析的生物医学成像和共振 X 射线技术到纳米分辨率电路成像。最后，综述总结了未来的研究方向，包括三维和四维 X 射线成像传感器、多光谱 X 射线成像和人工智能辅助医学影像诊断。
{"title":"Materials innovation and electrical engineering in X-ray detection","authors":"Bo Hou, Qiushui Chen, Luying Yi, Paul Sellin, Hong-Tao Sun, Liang Jie Wong, Xiaogang Liu","doi":"10.1038/s44287-024-00086-x","DOIUrl":"10.1038/s44287-024-00086-x","url":null,"abstract":"X-ray detection is critical for applications in medical diagnosis, industrial inspection, security checks, scientific inquiry and space exploration. Recent advances in materials science, electronics, manufacturing and artificial intelligence have greatly propelled the field forward. In this Review we examine fundamental principles and recent breakthroughs in X-ray detection and imaging technologies, with a focus on the interplay between electrical engineering techniques and X-ray-responsive materials. We highlight two primary approaches: semiconductor-based direct detection and scintillator-based indirect detection. We then discuss innovations such as photon-counting detectors and heterojunction phototransistors and emphasize the critical contributions of electrical engineering in the development of these cutting-edge detectors. Subsequently, we provide an overview of X-ray detection applications, ranging from biomedical imaging and resonant X-ray techniques for material analysis to nanometre-resolution circuit imaging. Finally, the Review summarizes future research directions, which encompass 3D and 4D X-ray imaging sensors, multispectral X-ray imaging and artificial intelligence-assisted medical image diagnosis. This Review examines fundamental principles and recent breakthroughs in X-ray detection and imaging technologies, with a focus on the interplay between electrical engineering techniques and materials science.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 10","pages":"639-655"},"PeriodicalIF":0.0,"publicationDate":"2024-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-21DOI: 10.1038/s44287-024-00080-3
Lei Zhu, Ming Zhang, Zichun Zhou, Wenkai Zhong, Tianyu Hao, Shengjie Xu, Rui Zeng, Jiaxing Zhuang, Xiaonan Xue, Hao Jing, Yongming Zhang, Feng Liu
Organic photovoltaic (OPV) technology is flexible, lightweight, semitransparent and ecofriendly, but it has historically suffered from low power conversion efficiency (PCE). However, since 2015, the materials design and PCE of OPV devices have been markedly optimized, and there is now an increasing understanding of OPV optoelectronic processes and blending morphology within the bulk heterojunction framework. In this Review, we survey OPV technology, discussing progress in enhancing the PCE and in understanding the relationship between structure and performance. This progress includes the development of emerging OPV materials and techniques for manipulation and characterization of thin-film morphology. Furthermore, we address the practical application issues ahead of OPV technology, showcasing strategies for improving device stability, fabricating large-area modules and realizing device encapsulation. Finally, we highlight future research directions, including the use of machine learning for material design and synthesis, device fabrication optimization, and prediction and optimization of device performance. Organic photovoltaics are flexible, lightweight and widely applicable, but they face commercialization challenges owing to stability and fabrication issues. This Review explores progress and technological bottlenecks in material innovation, morphology control, device stability and large-scale module fabrication for commercial use.
{"title":"Progress of organic photovoltaics towards 20% efficiency","authors":"Lei Zhu, Ming Zhang, Zichun Zhou, Wenkai Zhong, Tianyu Hao, Shengjie Xu, Rui Zeng, Jiaxing Zhuang, Xiaonan Xue, Hao Jing, Yongming Zhang, Feng Liu","doi":"10.1038/s44287-024-00080-3","DOIUrl":"10.1038/s44287-024-00080-3","url":null,"abstract":"Organic photovoltaic (OPV) technology is flexible, lightweight, semitransparent and ecofriendly, but it has historically suffered from low power conversion efficiency (PCE). However, since 2015, the materials design and PCE of OPV devices have been markedly optimized, and there is now an increasing understanding of OPV optoelectronic processes and blending morphology within the bulk heterojunction framework. In this Review, we survey OPV technology, discussing progress in enhancing the PCE and in understanding the relationship between structure and performance. This progress includes the development of emerging OPV materials and techniques for manipulation and characterization of thin-film morphology. Furthermore, we address the practical application issues ahead of OPV technology, showcasing strategies for improving device stability, fabricating large-area modules and realizing device encapsulation. Finally, we highlight future research directions, including the use of machine learning for material design and synthesis, device fabrication optimization, and prediction and optimization of device performance. Organic photovoltaics are flexible, lightweight and widely applicable, but they face commercialization challenges owing to stability and fabrication issues. This Review explores progress and technological bottlenecks in material innovation, morphology control, device stability and large-scale module fabrication for commercial use.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"581-596"},"PeriodicalIF":0.0,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-19DOI: 10.1038/s44287-024-00092-z
Ali Aliev, Mikhail Belogolovskii
Further progress in quantum technologies will require the hybridization of superconducting and photonic platforms. Transparent superconducting oxides would be an ideal solution to avoid substantial losses caused by photon absorption of the superconducting components. Here we present design principles for such materials and discuss the foreseeable prospects of transparent superconductor electronics.
{"title":"Towards transparent superconductor electronics","authors":"Ali Aliev, Mikhail Belogolovskii","doi":"10.1038/s44287-024-00092-z","DOIUrl":"10.1038/s44287-024-00092-z","url":null,"abstract":"Further progress in quantum technologies will require the hybridization of superconducting and photonic platforms. Transparent superconducting oxides would be an ideal solution to avoid substantial losses caused by photon absorption of the superconducting components. Here we present design principles for such materials and discuss the foreseeable prospects of transparent superconductor electronics.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"563-564"},"PeriodicalIF":0.0,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142174380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-09DOI: 10.1038/s44287-024-00090-1
Emilio Calvanese Strinati
6G might integrate 5G and AI to merge physical, cyber and sapience spaces, transforming network interactions and enhancing AI-driven decision-making and automation. The semantic approach to communication will train AI while selectively informing on goal achievement, moving towards artificial general intelligence, presenting new challenges and opportunities.
{"title":"6G: the catalyst for artificial general intelligence","authors":"Emilio Calvanese Strinati","doi":"10.1038/s44287-024-00090-1","DOIUrl":"10.1038/s44287-024-00090-1","url":null,"abstract":"6G might integrate 5G and AI to merge physical, cyber and sapience spaces, transforming network interactions and enhancing AI-driven decision-making and automation. The semantic approach to communication will train AI while selectively informing on goal achievement, moving towards artificial general intelligence, presenting new challenges and opportunities.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"561-562"},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141921709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1038/s44287-024-00081-2
Junhyuk Bang, Seok Hwan Choi, Kyung Rok Pyun, Yeongju Jung, Sangwoo Hong, Dohyung Kim, Youngseok Lee, Daeyeon Won, Seongmin Jeong, Wooseop Shin, Seung Hwan Ko
Soft robots, capable of safe interaction with delicate objects through their flexibility and compliance, are attracting attention in various real-world applications as manipulators, biomedical devices and wearable tools. As these technologies advance, the ability to perform complex tasks in a robust and reliable way becomes essential. Thus, the incorporation of embedded intelligence in soft robots, which enables them to perceive external environments and generate appropriate actions, is increasingly important. Inspiration from sophisticated biological systems, which exhibit optimized behaviours through the acquisition of external information, promotes the development of intelligent soft robots. Here, we introduce biomimicry strategies for intelligent soft robotics and highlight progress in how soft robots interact with their environment and perform tasks. First, we discuss sensors inspired by the sensory nervous systems and soft actuators inspired by the musculoskeletal systems. Furthermore, we investigate various applications such as manipulation, exploration, wearable devices, biomedical devices and imperceptible devices. We conclude discussing the challenges and offering a perspective on the future direction of this field. Soft robots are evolving to perform increasingly complex tasks, with biomimicry having a fundamental role in their development. This Review details biomimetic strategies and pivotal advances in sensors, actuators and applications of intelligent soft robotics.
{"title":"Bioinspired electronics for intelligent soft robots","authors":"Junhyuk Bang, Seok Hwan Choi, Kyung Rok Pyun, Yeongju Jung, Sangwoo Hong, Dohyung Kim, Youngseok Lee, Daeyeon Won, Seongmin Jeong, Wooseop Shin, Seung Hwan Ko","doi":"10.1038/s44287-024-00081-2","DOIUrl":"10.1038/s44287-024-00081-2","url":null,"abstract":"Soft robots, capable of safe interaction with delicate objects through their flexibility and compliance, are attracting attention in various real-world applications as manipulators, biomedical devices and wearable tools. As these technologies advance, the ability to perform complex tasks in a robust and reliable way becomes essential. Thus, the incorporation of embedded intelligence in soft robots, which enables them to perceive external environments and generate appropriate actions, is increasingly important. Inspiration from sophisticated biological systems, which exhibit optimized behaviours through the acquisition of external information, promotes the development of intelligent soft robots. Here, we introduce biomimicry strategies for intelligent soft robotics and highlight progress in how soft robots interact with their environment and perform tasks. First, we discuss sensors inspired by the sensory nervous systems and soft actuators inspired by the musculoskeletal systems. Furthermore, we investigate various applications such as manipulation, exploration, wearable devices, biomedical devices and imperceptible devices. We conclude discussing the challenges and offering a perspective on the future direction of this field. Soft robots are evolving to perform increasingly complex tasks, with biomimicry having a fundamental role in their development. This Review details biomimetic strategies and pivotal advances in sensors, actuators and applications of intelligent soft robotics.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"597-613"},"PeriodicalIF":0.0,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141969126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1038/s44287-024-00076-z
Eli Chien, Mufei Li, Anthony Aportela, Kerr Ding, Shuyi Jia, Supriyo Maji, Zhongyuan Zhao, Javier Duarte, Victor Fung, Cong Hao, Yunan Luo, Olgica Milenkovic, David Pan, Santiago Segarra, Pan Li
Graph neural networks (GNNs) are a class of deep learning algorithms that learn from graphs, networks and relational data. They have found applications throughout the sciences and made significant strides in electrical engineering. GNNs can learn from various electrical and electronic systems, such as electronic circuits, wireless networks and power systems, and assist in solving optimization or inference tasks where traditional approaches may be slow or inaccurate. Robust learning algorithms and efficient computational hardware developed and tailored for GNNs have amplified their relevance to electrical engineering. We have entered an era in which the studies of GNNs and electrical engineering are intertwined, opening to opportunities and challenges to researchers in both fields. This Review explores applications of GNNs that might generate notable impacts on electrical engineering. We discuss how GNNs are used to address electrical automatic design, as well as the modelling and management of wireless communication networks. Additionally, we delve into GNNs for high-energy physics, materials science and biology. Presenting the applications, data and computational challenges, the need for innovative algorithms and hardware solutions becomes clear. Graph neural networks (GNNs) are an important technology for electrical engineering, physics, materials science and biology. This Review discusses how GNNs can help these research fields and how electrical engineering can resolve the technical challenges of GNNs.
{"title":"Opportunities and challenges of graph neural networks in electrical engineering","authors":"Eli Chien, Mufei Li, Anthony Aportela, Kerr Ding, Shuyi Jia, Supriyo Maji, Zhongyuan Zhao, Javier Duarte, Victor Fung, Cong Hao, Yunan Luo, Olgica Milenkovic, David Pan, Santiago Segarra, Pan Li","doi":"10.1038/s44287-024-00076-z","DOIUrl":"10.1038/s44287-024-00076-z","url":null,"abstract":"Graph neural networks (GNNs) are a class of deep learning algorithms that learn from graphs, networks and relational data. They have found applications throughout the sciences and made significant strides in electrical engineering. GNNs can learn from various electrical and electronic systems, such as electronic circuits, wireless networks and power systems, and assist in solving optimization or inference tasks where traditional approaches may be slow or inaccurate. Robust learning algorithms and efficient computational hardware developed and tailored for GNNs have amplified their relevance to electrical engineering. We have entered an era in which the studies of GNNs and electrical engineering are intertwined, opening to opportunities and challenges to researchers in both fields. This Review explores applications of GNNs that might generate notable impacts on electrical engineering. We discuss how GNNs are used to address electrical automatic design, as well as the modelling and management of wireless communication networks. Additionally, we delve into GNNs for high-energy physics, materials science and biology. Presenting the applications, data and computational challenges, the need for innovative algorithms and hardware solutions becomes clear. Graph neural networks (GNNs) are an important technology for electrical engineering, physics, materials science and biology. This Review discusses how GNNs can help these research fields and how electrical engineering can resolve the technical challenges of GNNs.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"529-546"},"PeriodicalIF":0.0,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141940769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：