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}
Pub Date : 2024-08-01DOI: 10.1038/s44287-024-00068-z
Enzi Zhai, Tianyu Liang, Ruizi Liu, Mingyang Cai, Ran Li, Qiming Shao, Cong Su, Yuxuan Cosmi Lin
Semi-metals present unique transport properties due to their distinctive band structures and topological properties, leading to an emergence of semi-metal-based electronic applications. Specifically, these properties include intrinsic low density of states at the Fermi level, the linear dispersion electronic structure and the symmetry breaking in the momentum space, which can be harnessed for improved functionality, energy efficiency and form factor in electronic devices. In this Review, we examine the fundamental properties and devices based on semi-metals and their heterojunctions for electronics applications. We then discuss advanced logic, analogue, memory and interconnect technologies enabled by the physical properties of semi-metals and benchmark them against the state-of-the-art technologies. Finally, we outline the remaining challenges and future perspectives of practical applications of semi-metal heterojunction electronics. This Review examines the unique electronic properties of semi-metals and their microelectronics applications, highlighting recent advancements, challenges and future prospects for semi-metal-based technologies in logic, memory, interconnects and high-frequency devices.
{"title":"The rise of semi-metal electronics","authors":"Enzi Zhai, Tianyu Liang, Ruizi Liu, Mingyang Cai, Ran Li, Qiming Shao, Cong Su, Yuxuan Cosmi Lin","doi":"10.1038/s44287-024-00068-z","DOIUrl":"10.1038/s44287-024-00068-z","url":null,"abstract":"Semi-metals present unique transport properties due to their distinctive band structures and topological properties, leading to an emergence of semi-metal-based electronic applications. Specifically, these properties include intrinsic low density of states at the Fermi level, the linear dispersion electronic structure and the symmetry breaking in the momentum space, which can be harnessed for improved functionality, energy efficiency and form factor in electronic devices. In this Review, we examine the fundamental properties and devices based on semi-metals and their heterojunctions for electronics applications. We then discuss advanced logic, analogue, memory and interconnect technologies enabled by the physical properties of semi-metals and benchmark them against the state-of-the-art technologies. Finally, we outline the remaining challenges and future perspectives of practical applications of semi-metal heterojunction electronics. This Review examines the unique electronic properties of semi-metals and their microelectronics applications, highlighting recent advancements, challenges and future prospects for semi-metal-based technologies in logic, memory, interconnects and high-frequency devices.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"497-515"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141886594","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 : 2024-08-01DOI: 10.1038/s44287-024-00085-y
Yao Zhou, Jinliang He
Long-distance transmission of large-scale renewable energy calls for reliable and stable high-capacity power cables with improved environmental friendliness. Hierarchical structure regulation enables synergistic optimization of electrical, thermal and mechanical properties in polypropylene-based insulation materials, aiding the development of environmentally friendly power cables.
{"title":"Development of environmentally friendly high-capacity power cables","authors":"Yao Zhou, Jinliang He","doi":"10.1038/s44287-024-00085-y","DOIUrl":"10.1038/s44287-024-00085-y","url":null,"abstract":"Long-distance transmission of large-scale renewable energy calls for reliable and stable high-capacity power cables with improved environmental friendliness. Hierarchical structure regulation enables synergistic optimization of electrical, thermal and mechanical properties in polypropylene-based insulation materials, aiding the development of environmentally friendly power cables.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 9","pages":"565-566"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141886597","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 : 2024-08-01DOI: 10.1038/s44287-024-00087-w
Lishu Wu
An article in IEEE Journal on Selected Areas in Communications presents a vehicle-based vision–radar system designed for precise, real-time positioning of UAV clusters.
{"title":"Vehicle-based vision–radar fusion for real-time and accurate positioning of clustered UAVs","authors":"Lishu Wu","doi":"10.1038/s44287-024-00087-w","DOIUrl":"10.1038/s44287-024-00087-w","url":null,"abstract":"An article in IEEE Journal on Selected Areas in Communications presents a vehicle-based vision–radar system designed for precise, real-time positioning of UAV clusters.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"496-496"},"PeriodicalIF":0.0,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141886596","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 : 2024-07-31DOI: 10.1038/s44287-024-00083-0
Le Xie, Na Li, H. Vincent Poor
Sustainable electrification is essential for addressing climate change and leveraging artificial intelligence (AI). Electric grids have a fundamental role in decarbonizing the economy and enabling AI. Here we propose a comprehensive research agenda that integrates innovations in material discovery, computer architecture, smart grids and system theory to accelerate efficient, large-scale, low-carbon electrification.
{"title":"Sustainable electrification in the era of AI","authors":"Le Xie, Na Li, H. Vincent Poor","doi":"10.1038/s44287-024-00083-0","DOIUrl":"10.1038/s44287-024-00083-0","url":null,"abstract":"Sustainable electrification is essential for addressing climate change and leveraging artificial intelligence (AI). Electric grids have a fundamental role in decarbonizing the economy and enabling AI. Here we propose a comprehensive research agenda that integrates innovations in material discovery, computer architecture, smart grids and system theory to accelerate efficient, large-scale, low-carbon electrification.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"493-494"},"PeriodicalIF":0.0,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141871105","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 : 2024-07-24DOI: 10.1038/s44287-024-00079-w
Tetsuya Ogata
Recent advancements in generative AI require multimodal information processing that incorporates images, videos and audio. This shift underscores the importance of integrating AI with robotics to address challenges such as Moravec’s paradox.
{"title":"Bridging the gap between AI and robotics","authors":"Tetsuya Ogata","doi":"10.1038/s44287-024-00079-w","DOIUrl":"10.1038/s44287-024-00079-w","url":null,"abstract":"Recent advancements in generative AI require multimodal information processing that incorporates images, videos and audio. This shift underscores the importance of integrating AI with robotics to address challenges such as Moravec’s paradox.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"491-492"},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141781668","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 : 2024-07-19DOI: 10.1038/s44287-024-00084-z
Silvia Conti
An article in Nature Electronics presents a low-thermal fabrication process for 3D integration of metal-oxide transistors.
自然-电子学》上的一篇文章介绍了一种用于金属氧化物晶体管三维集成的低热制造工艺。
{"title":"Metal oxide transistors 3D integration on low-thermal budget","authors":"Silvia Conti","doi":"10.1038/s44287-024-00084-z","DOIUrl":"10.1038/s44287-024-00084-z","url":null,"abstract":"An article in Nature Electronics presents a low-thermal fabrication process for 3D integration of metal-oxide transistors.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"495-495"},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141746153","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 : 2024-07-17DOI: 10.1038/s44287-024-00077-y
Yen-Ju Wu
Efficient heat dissipation is crucial for electronics. Interfacial thermal resistance (ITR) poses considerable challenges that require innovative solutions. Machine learning approaches could enhance ITR predictions by analysing large datasets to guide the development of inorganic, amorphous and 2D materials for advanced thermal management in next-generation electronic devices.
{"title":"Revolutionizing electronics with advanced interfacial heat management","authors":"Yen-Ju Wu","doi":"10.1038/s44287-024-00077-y","DOIUrl":"10.1038/s44287-024-00077-y","url":null,"abstract":"Efficient heat dissipation is crucial for electronics. Interfacial thermal resistance (ITR) poses considerable challenges that require innovative solutions. Machine learning approaches could enhance ITR predictions by analysing large datasets to guide the development of inorganic, amorphous and 2D materials for advanced thermal management in next-generation electronic devices.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 8","pages":"489-490"},"PeriodicalIF":0.0,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141719199","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 : 2024-07-16DOI: 10.1038/s44287-024-00071-4
Shih-Hsiang (Shane) Lin, Marko Simicic, Nicolas Pantano
2.5D/3D technologies require designers to reduce electrostatic discharge (ESD) protection of the internal I/O interfaces. To avoid over-design of ESD protection, designers require a more fundamental understanding of the ESD events that occur at this level. Here we present insights, practical guidelines and research directions for circuit designers and suppliers of bonding tools.
{"title":"Towards efficient ESD protection strategies for advanced 3D systems-on-chip","authors":"Shih-Hsiang (Shane) Lin, Marko Simicic, Nicolas Pantano","doi":"10.1038/s44287-024-00071-4","DOIUrl":"10.1038/s44287-024-00071-4","url":null,"abstract":"2.5D/3D technologies require designers to reduce electrostatic discharge (ESD) protection of the internal I/O interfaces. To avoid over-design of ESD protection, designers require a more fundamental understanding of the ESD events that occur at this level. Here we present insights, practical guidelines and research directions for circuit designers and suppliers of bonding tools.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 7","pages":"429-431"},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141631263","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 : 2024-07-15DOI: 10.1038/s44287-024-00073-2
Xiaoyu Ji, Wenjun Zhu, Shilin Xiao, Wenyuan Xu
Sensors are extensively used in the Internet of Things (IoT) applications, enhancing daily convenience but also raising concerns about privacy leakage. To address this, we advocate for protecting data privacy at the moment it is generated by sensors, rather than trying to secure it afterwards.
{"title":"Sensor-based IoT data privacy protection","authors":"Xiaoyu Ji, Wenjun Zhu, Shilin Xiao, Wenyuan Xu","doi":"10.1038/s44287-024-00073-2","DOIUrl":"10.1038/s44287-024-00073-2","url":null,"abstract":"Sensors are extensively used in the Internet of Things (IoT) applications, enhancing daily convenience but also raising concerns about privacy leakage. To address this, we advocate for protecting data privacy at the moment it is generated by sensors, rather than trying to secure it afterwards.","PeriodicalId":501701,"journal":{"name":"Nature Reviews Electrical Engineering","volume":"1 7","pages":"427-428"},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141631255","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：