Full metadata record
|Department:||Department of Computing||en_US|
|Title:||Activity recognition for health care and individual safety using wireless technologies and smartphones||en_US|
|Abstract:||In recent years, human activity recognition has attracted increasing attention. Technologies and systems have been prepared for various kinds of applications. Among them, health care and individual safety are two important domains. Conventionally, researchers utilize specialized sensors which are not only expensive, but also obtrusive to human bodies. The emergence of smartphone sensing and wireless technologies provides researchers with novel platforms and makes it possible to develop low-priced and unobtrusive activity recognition systems. However, despite the promising capacities of smartphone sensing and wireless technologies, several challenging issues still arise. First, a majority of smartphones equipped with a limited number of sensors and wireless transceivers can only collect coarse physical signals, which poses an obstacle to highly accurate activity recognition. Second, although a smartphone may be able to gather various kinds of physical signals from different sensors, how to incorporate those heterogeneous signals efficiently remains a difficult task. Third, activity recognition systems should not incur excessive obtrusiveness and intrude users’ privacy, which poses more constraints to system development. In this thesis, we investigate activity recognition for health care and individual safety using smartphone sensing and wireless technologies. Specifically, we propose a system architecture and based on which, we implement two activity recognition systems, one for the safety of pedestrian mobile phone users and another for contact-less WiFi breath detection system. We identify and describe the the challenging issues when developing the systems and describe our corresponding solutions.||en_US|
|Abstract:||For the safety of mobile phone pedestrian users, it is well recognized that walking while using mobile phones tends to make people more susceptible at various risks. Existing works for improving smartphone users’ safety are mainly focused on detecting incoming vehicles, but not able to address more common and equally dangerous accidents such as trips, falling from stairs and platforms or falling into an open manhole. These hazards are generally caused by sudden change of ground level. We design and implement InfraSee, a system that is able to detect sudden change of ground level while mobile phone users walk. InfraSee augments smartphones with a small infrared sensor which measures the distance of the ground surface from the sensor. The temporal variation of distance can provide information about the change of ground surface ahead. InfraSee also leverages the information of smartphone sensors to improve detection accuracy, reduce energy consumption, and avoid unnecessary alarms. We have carried out extensive experiments in different scenarios and with different users. The results show that InfraSee is able to reliably detect about 80% change of ground surfaces. In addition, InfraSee can reduce unnecessary alarms by distinguishing among different modes of the smartphone user. Second, we use WiFi technology to implement a health care system that retrieves fine-grained sleep information like respiration, sleeping postures and rollovers. We develop Wi-Sleep, the first sleep monitoring system based on WiFi signals. Wi-Sleep adopts off-the-shelf WiFi devices and is able to continuously collect the fine-grained wireless channel state information (CSI) around a person. From the CSI, Wi-Sleep extracts rhythmic patterns associated with respiration and abrupt changes due to the body movement. Compared to existing sleep monitoring systems that usually require special devices attached to human body (i.e. probes, head belt, and wrist band), Wi-Sleep is completely contact-less. In addition, different from many vision-based sleep monitoring systems, Wi-Sleep is robust to low-light environments and does not raise privacy concerns. Preliminary testing results show that the Wi-Sleep can reliably track an individual’s respiration and sleeping postures in different conditions.||en_US|
|Pages:||xvi, 123 pages : color illustrations||en_US|
|Subject:||Hong Kong Polytechnic University -- Dissertations||en_US|
|Subject:||Human activity recognition||en_US|
Files in This Item:
|991021962222703411.pdf||For All Users||7.52 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: