AItalk: a tutorial to implement AI as IoT devices
In one of the recent trends of Internet of Things (IoT), the IoT data are manipulated by Artificial Intelligence (AI) techniques for smart applications. By including AI into existing IoT application programs, significant coding effort is required. This paper proposes a solution called AItalk to reso...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-05-01
|
Series: | IET Networks |
Subjects: | |
Online Access: | https://doi.org/10.1049/iet-net.2018.5182 |
id |
doaj-374d3ac28a9045428fc22f4dd5384d06 |
---|---|
record_format |
Article |
spelling |
doaj-374d3ac28a9045428fc22f4dd5384d062021-08-26T05:55:39ZengWileyIET Networks2047-49542047-49622019-05-018319520210.1049/iet-net.2018.5182AItalk: a tutorial to implement AI as IoT devicesYun‐Wei Lin0Yi‐Bing Lin1Chun‐You Liu2Department of Computer ScienceNational Chiao Tung UniversityHsinchu30010TaiwanDepartment of Computer ScienceNational Chiao Tung UniversityHsinchu30010TaiwanDepartment of Computer ScienceNational Chiao Tung UniversityHsinchu30010TaiwanIn one of the recent trends of Internet of Things (IoT), the IoT data are manipulated by Artificial Intelligence (AI) techniques for smart applications. By including AI into existing IoT application programs, significant coding effort is required. This paper proposes a solution called AItalk to resolve this issue. Unlike traditional AI‐based IoT applications that tightly integrate the AI mechanism within the network applications, the novel idea of AItalk is to treat the machine learning mechanism as a cyber IoT device. Our solution allows seamless inclusion of machine learning capability to the existing IoT applications without any programming effort. The advantage of this approach is that we can decompose a complex AI application into simplified distributed modules connected by using the IoT technology, and therefore the AI solution can be built more effectively. Also, in our approach, data can be easily processed in real time for an AI application. Supervised machine learning naturally fits the IoT applications, where the sensors provide the features to the AI algorithms, and the remote controllers serve as the labels. We show an example that the overhead of the IoT communication in AItalk is less than 30 ms and the AI prediction time is less than 2 ms.https://doi.org/10.1049/iet-net.2018.5182AItalkIoT devicesIoT dataArtificial Intelligence techniquessmart applicationssignificant coding effort |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yun‐Wei Lin Yi‐Bing Lin Chun‐You Liu |
spellingShingle |
Yun‐Wei Lin Yi‐Bing Lin Chun‐You Liu AItalk: a tutorial to implement AI as IoT devices IET Networks AItalk IoT devices IoT data Artificial Intelligence techniques smart applications significant coding effort |
author_facet |
Yun‐Wei Lin Yi‐Bing Lin Chun‐You Liu |
author_sort |
Yun‐Wei Lin |
title |
AItalk: a tutorial to implement AI as IoT devices |
title_short |
AItalk: a tutorial to implement AI as IoT devices |
title_full |
AItalk: a tutorial to implement AI as IoT devices |
title_fullStr |
AItalk: a tutorial to implement AI as IoT devices |
title_full_unstemmed |
AItalk: a tutorial to implement AI as IoT devices |
title_sort |
aitalk: a tutorial to implement ai as iot devices |
publisher |
Wiley |
series |
IET Networks |
issn |
2047-4954 2047-4962 |
publishDate |
2019-05-01 |
description |
In one of the recent trends of Internet of Things (IoT), the IoT data are manipulated by Artificial Intelligence (AI) techniques for smart applications. By including AI into existing IoT application programs, significant coding effort is required. This paper proposes a solution called AItalk to resolve this issue. Unlike traditional AI‐based IoT applications that tightly integrate the AI mechanism within the network applications, the novel idea of AItalk is to treat the machine learning mechanism as a cyber IoT device. Our solution allows seamless inclusion of machine learning capability to the existing IoT applications without any programming effort. The advantage of this approach is that we can decompose a complex AI application into simplified distributed modules connected by using the IoT technology, and therefore the AI solution can be built more effectively. Also, in our approach, data can be easily processed in real time for an AI application. Supervised machine learning naturally fits the IoT applications, where the sensors provide the features to the AI algorithms, and the remote controllers serve as the labels. We show an example that the overhead of the IoT communication in AItalk is less than 30 ms and the AI prediction time is less than 2 ms. |
topic |
AItalk IoT devices IoT data Artificial Intelligence techniques smart applications significant coding effort |
url |
https://doi.org/10.1049/iet-net.2018.5182 |
work_keys_str_mv |
AT yunweilin aitalkatutorialtoimplementaiasiotdevices AT yibinglin aitalkatutorialtoimplementaiasiotdevices AT chunyouliu aitalkatutorialtoimplementaiasiotdevices |
_version_ |
1721195981870989312 |