Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level
Machine‐learning‐enhanced nanosensors are rapidly emerging as a promising solution in the field of sensor technology, as traditional sensors encounter limitations of data analysis in their development. Since the inception of machine‐learning algorithms being applied to enhance nanosensors, they have...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2024-04-01
|
| Series: | Small Structures |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/sstr.202300325 |
| _version_ | 1827291186577014784 |
|---|---|
| author | Zixuan Zhang Xinmiao Liu Hong Zhou Siyu Xu Chengkuo Lee |
| author_facet | Zixuan Zhang Xinmiao Liu Hong Zhou Siyu Xu Chengkuo Lee |
| author_sort | Zixuan Zhang |
| collection | DOAJ |
| description | Machine‐learning‐enhanced nanosensors are rapidly emerging as a promising solution in the field of sensor technology, as traditional sensors encounter limitations of data analysis in their development. Since the inception of machine‐learning algorithms being applied to enhance nanosensors, they have gained significant attention due to their adaptive and predictive capabilities, which promise to dramatically improve efficiency in data collection and processing applications. Herein, a comprehensive overview of technological innovation is provided by reviewing the latest developments in cloud computing, edge computing, and the burgeoning realm of neuromorphic computing. Cloud computing has emerged as a powerhouse, harnessing formidable computational capabilities to process vast volumes of high‐dimensional data. Then, the research directions for various applications of these cloud artificial intelligence (AI)‐enhanced nanosensors are outlined. Moreover, the integration of AI and nanosensor technology into chip‐level edge computing, although promising, still faces challenges such as energy‐efficient hardware development, algorithm optimization, and scalability for mass production. Finally, a forward‐looking perspective on the future of machine‐learning‐enhanced nanosensors is provided, delineating the challenges and opportunities for further research and innovation in this exciting field. |
| first_indexed | 2024-04-24T12:31:30Z |
| format | Article |
| id | doaj.art-319c6640424341f2ae7a811f7053c99e |
| institution | Directory Open Access Journal |
| issn | 2688-4062 |
| language | English |
| last_indexed | 2024-04-24T12:31:30Z |
| publishDate | 2024-04-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Small Structures |
| spelling | doaj.art-319c6640424341f2ae7a811f7053c99e2024-04-08T02:35:51ZengWiley-VCHSmall Structures2688-40622024-04-0154n/an/a10.1002/sstr.202300325Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip LevelZixuan Zhang0Xinmiao Liu1Hong Zhou2Siyu Xu3Chengkuo Lee4Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 SingaporeDepartment of Electrical and Computer Engineering National University of Singapore Singapore 117576 SingaporeDepartment of Electrical and Computer Engineering National University of Singapore Singapore 117576 SingaporeDepartment of Electrical and Computer Engineering National University of Singapore Singapore 117576 SingaporeDepartment of Electrical and Computer Engineering National University of Singapore Singapore 117576 SingaporeMachine‐learning‐enhanced nanosensors are rapidly emerging as a promising solution in the field of sensor technology, as traditional sensors encounter limitations of data analysis in their development. Since the inception of machine‐learning algorithms being applied to enhance nanosensors, they have gained significant attention due to their adaptive and predictive capabilities, which promise to dramatically improve efficiency in data collection and processing applications. Herein, a comprehensive overview of technological innovation is provided by reviewing the latest developments in cloud computing, edge computing, and the burgeoning realm of neuromorphic computing. Cloud computing has emerged as a powerhouse, harnessing formidable computational capabilities to process vast volumes of high‐dimensional data. Then, the research directions for various applications of these cloud artificial intelligence (AI)‐enhanced nanosensors are outlined. Moreover, the integration of AI and nanosensor technology into chip‐level edge computing, although promising, still faces challenges such as energy‐efficient hardware development, algorithm optimization, and scalability for mass production. Finally, a forward‐looking perspective on the future of machine‐learning‐enhanced nanosensors is provided, delineating the challenges and opportunities for further research and innovation in this exciting field.https://doi.org/10.1002/sstr.202300325cloud computingedge computingmemristorsneuromorphic computing |
| spellingShingle | Zixuan Zhang Xinmiao Liu Hong Zhou Siyu Xu Chengkuo Lee Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level Small Structures cloud computing edge computing memristors neuromorphic computing |
| title | Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level |
| title_full | Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level |
| title_fullStr | Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level |
| title_full_unstemmed | Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level |
| title_short | Advances in Machine‐Learning Enhanced Nanosensors: From Cloud Artificial Intelligence Toward Future Edge Computing at Chip Level |
| title_sort | advances in machine learning enhanced nanosensors from cloud artificial intelligence toward future edge computing at chip level |
| topic | cloud computing edge computing memristors neuromorphic computing |
| url | https://doi.org/10.1002/sstr.202300325 |
| work_keys_str_mv | AT zixuanzhang advancesinmachinelearningenhancednanosensorsfromcloudartificialintelligencetowardfutureedgecomputingatchiplevel AT xinmiaoliu advancesinmachinelearningenhancednanosensorsfromcloudartificialintelligencetowardfutureedgecomputingatchiplevel AT hongzhou advancesinmachinelearningenhancednanosensorsfromcloudartificialintelligencetowardfutureedgecomputingatchiplevel AT siyuxu advancesinmachinelearningenhancednanosensorsfromcloudartificialintelligencetowardfutureedgecomputingatchiplevel AT chengkuolee advancesinmachinelearningenhancednanosensorsfromcloudartificialintelligencetowardfutureedgecomputingatchiplevel |