東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT./
作者:	Jiang, Wenjun.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2022,
面頁冊數:	161 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
Contained By:	Dissertations Abstracts International83-09B.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28964847
ISBN:	9798790654855

Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT.
Jiang, Wenjun.

Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT. - Ann Arbor : ProQuest Dissertations & Theses, 2022 - 161 p.

Source: Dissertations Abstracts International, Volume: 83-09, Section: B.

Thesis (Ph.D.)--State University of New York at Buffalo, 2022.

This item must not be sold to any third party vendors.

Human sensing, such as activity recognition and pose estimation, aims to enable the computer systems to extract the information regarding the human in the environment. With the recent proliferation of mobile and wireless devices, mobile and wireless human sensing systems are attracting more and more interest from both academia and industry. The fundamental principle of the capability of using mobile and wireless devices to perform human sensing is that when a subject is carrying a mobile device or in the wireless channel, his movement will affect the in-built sensors (e.g., accelerometer, gyroscope etc.) on the mobile devices or the transmission pattern of the wireless signals. However, building a human sensing system with mobile or wireless devices is not trivial. First, in a mobile sensing system, although it is convenient to collect sensor data from mobile devices' in-built sensors, getting activity labels from the users is difficult. Second, wireless signals usually carry substantial environment specific and subject specific information, which would harm the transferability of the recognition model learned from them. Moreover, it is challenging to do fine-grained human sensing using commercial wireless devices. Therefore, it is crucial to build intelligent mobile and wireless human sensing systems that can overcome these challenges.In this thesis, we first propose a personalized learning framework in mobile sensing system, which deals with the scenario when the users provide insufficient or even no label information to the system. Then we investigate the environment dependency issue faced by current device-free human activity recognition systems and propose an effective and general framework, which can remove the environment specific information and extract transferable features of the activities. Finally, we push the limit of wireless sensing and investigate the possibility of using pervasive WiFi signals to reconstruct the 3D human pose and study how to improve its efficiency and extend it to cover the activity of a moving subject.

ISBN: 9798790654855Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Human-centered computing

Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT.
LDR:03222nmm a2200361 4500 001 2352181
005 20221118093835.5
008 241004s2022 ||||||||||||||||| ||eng d
020 $a 9798790654855
035 $a (MiAaPQ)AAI28964847
035 $a AAI28964847
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jiang, Wenjun. $3 3691805
245 1 0 $a Building Intelligent Mobile and Wireless Human Sensing Systems in the Era of IoT.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2022
300 $a 161 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-09, Section: B.
500 $a Advisor: Su, Lu.
502 $a Thesis (Ph.D.)--State University of New York at Buffalo, 2022.
506 $a This item must not be sold to any third party vendors.
520 $a Human sensing, such as activity recognition and pose estimation, aims to enable the computer systems to extract the information regarding the human in the environment. With the recent proliferation of mobile and wireless devices, mobile and wireless human sensing systems are attracting more and more interest from both academia and industry. The fundamental principle of the capability of using mobile and wireless devices to perform human sensing is that when a subject is carrying a mobile device or in the wireless channel, his movement will affect the in-built sensors (e.g., accelerometer, gyroscope etc.) on the mobile devices or the transmission pattern of the wireless signals. However, building a human sensing system with mobile or wireless devices is not trivial. First, in a mobile sensing system, although it is convenient to collect sensor data from mobile devices' in-built sensors, getting activity labels from the users is difficult. Second, wireless signals usually carry substantial environment specific and subject specific information, which would harm the transferability of the recognition model learned from them. Moreover, it is challenging to do fine-grained human sensing using commercial wireless devices. Therefore, it is crucial to build intelligent mobile and wireless human sensing systems that can overcome these challenges.In this thesis, we first propose a personalized learning framework in mobile sensing system, which deals with the scenario when the users provide insufficient or even no label information to the system. Then we investigate the environment dependency issue faced by current device-free human activity recognition systems and propose an effective and general framework, which can remove the environment specific information and extract transferable features of the activities. Finally, we push the limit of wireless sensing and investigate the possibility of using pervasive WiFi signals to reconstruct the 3D human pose and study how to improve its efficiency and extend it to cover the activity of a moving subject.
590 $a School code: 0656.
650 4 $a Computer science. $3 523869
650 4 $a Information science. $3 554358
650 4 $a Artificial intelligence. $3 516317
653 $a Human-centered computing
653 $a Mobile sensing
653 $a Wireless sensing
653 $a Machine learning
690 $a 0984
690 $a 0723
690 $a 0800
710 2 $a State University of New York at Buffalo. $b Computer Science and Engineering. $3 1035503
773 0 $t Dissertations Abstracts International $g 83-09B.
790 $a 0656
791 $a Ph.D.
792 $a 2022
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28964847