Next-Generation Personal Memory Aids

Computer Vision for Assistive Healthcare

Sun

Smeaton

et al. 2018

Section: Typical Applications In Assistive Livingmentioning

confidence: 88%

Computer Vision for Lifelogging

Computer Vision for Assistive Healthcare

Sun

Smeaton

et al. 2018

“…They demonstrated that one reason people have trouble with remembering is the poor encoding process. Vemuri and Bender [Vemuri and Bender, 2004] concluded that people encode information in a summary form without filling out the details. People tend not to dedicate much effort to the initial encoding process, which sometimes results in memory failure.…”

Section: Poor Encodingmentioning

confidence: 99%

Exploring the role of prospective memory in location-based reminders

Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication

Pérez-Quiñones

2014

Location-based reminder systems (LBRs) are typically used to remind people to complete a to-do task at a particular location. People use their prospective memory to remember future to-do tasks. However, the current design of LBRs fails to take advantage of human prospective memory theory. In this dissertation, I propose a framework connecting human prospective memory theory with LBRs. My work applies human prospective memory into the technical design of LBRs. The goal of my work is to make the reminder work more consistently with how human memory works.Prospective memory research suggests that encoding of the location and familiarity with the location have an impact on prospective remembering. I conducted two empirical studies to test how this theoretical knowledge applies to LBRs. In one experiment, Ihypothesized that if the encoding stage provides a closer match to the retrieval stage in LBRs, then location recognition and task recall should improve at retrieval time. The results indicate that providing a first-person view (street view of the desired location) at the encoding stage benefits prospective remembering the most.Prospective memory theory also suggests that the familiarity with the external cue has a significant influence on prospective remembering. In the second experiment, I hypothesized that familiarity with a location has an impact on the location recognition at the retrieval.The results show that the encoding interface is used differently for familiar and unfamiliar cities and businesses to support recognizing a target location.The findings have implications for the design of future LBRs. I designed an LBR prototype by applying these empirical research findings and conducted a usability evaluation. Future designers of LBR should consider 1) providing more support in matching the encoding stage to the eventual cue in retrieval stage and 2) involving user's familiarity level with the places at the encoding stage to provide a better user experience. My work showed the importance of using prospective memory theory in the design of LBR systems. Exploring the Role of Prospective Memory in Location-Based Reminders Yao Wang General Audience AbstractPeople use location-based mobile reminder systems to complete a to-do task at a particular location. My work studied how people memorize the locations at the reminder set up stage, as well as how they recognize the locations and remember the associated to-do tasks at the reminder retrieval stage. People see a location from a first-person view while completing a to-do task in the real life. However, current interface designs of location-based reminders do not support that. My research results contributed to the future interface design of location-based mobile reminder system. That is, future encoding interface design of location-based reminders could possibly apply a street view of the location to make the reminder more usable and more user-friendly. DedicationDedicated to my husband Bo Li, who is always there with me.

“…At MIT, an experiment was carried out using Bluetooth-enabled mobile telephones to measure information context in order to identify the deep social patterns in user activities [7]. In [17], Vemuri and Bender presented a memory re-finding use of lifelogging which is called "iRemember". In their research they recorded audio clips as the main information to navigate memory.…”

Section: Introductionmentioning

confidence: 99%

Aggregating semantic concepts for event representation in lifelogging

Proceedings of the International Workshop on Semantic Web Information Management

Smeaton

2011

The performance of automatic detection of concepts in image and video data has been improved to a satisfactory level for some generic concepts like indoor, outdoor, faces, etc. on high quality data from broadcast TV or movies. However it remains a challenge to apply this to interpreting the high-level semantics of events as they occur in visual lifelogs from wearable cameras. This is because poorer quality image data and the activities of the wearer make it difficult to automatically categorise them. In this paper, we propose an interestingness-based semantic aggregation and representation algorithm, to tackle the problem of event management and representation in visual lifelogging. Semantic concept interestingness is calculated by fusing image-level concepts which are then exploited to select a representation for the semantic event correlated to various event topics. Experimental results show the efficacy of our algorithm in fusing semantics at the event level, and in selecting representations for event management in visual lifelogging.