Creating human digital memories with the aid of pervasive mobile devices

Dobbins, Chelsea; Merabti, Madjid; Fergus, Paul; Llewellyn‐Jones, David

doi:10.1016/j.pmcj.2013.10.009

Cited by 16 publications

(14 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dobbins et al . [ 51 ] provide more detail about the state of the art of lifelogging systems. We designed these visualizations following Starner’s suggestion [ 52 ]: Besides being physically light, consumer wearables must be visually lightweight.…”

Section: Implementation and Evaluationmentioning

confidence: 99%

Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches

Rawassizadeh

Tomitsch

Nourizadeh

et al. 2015

Sensors

View full text Add to dashboard Cite

As the availability and use of wearables increases, they are becoming a promising platform for context sensing and context analysis. Smartwatches are a particularly interesting platform for this purpose, as they offer salient advantages, such as their proximity to the human body. However, they also have limitations associated with their small form factor, such as processing power and battery life, which makes it difficult to simply transfer smartphone-based context sensing and prediction models to smartwatches. In this paper, we introduce an energy-efficient, generic, integrated framework for continuous context sensing and prediction on smartwatches. Our work extends previous approaches for context sensing and prediction on wrist-mounted wearables that perform predictive analytics outside the device. We offer a generic sensing module and a novel energy-efficient, on-device prediction module that is based on a semantic abstraction approach to convert sensor data into meaningful information objects, similar to human perception of a behavior. Through six evaluations, we analyze the energy efficiency of our framework modules, identify the optimal file structure for data access and demonstrate an increase in accuracy of prediction through our semantic abstraction method. The proposed framework is hardware independent and can serve as a reference model for implementing context sensing and prediction on small wearable devices beyond smartwatches, such as body-mounted cameras.

show abstract

Section: Implementation and Evaluationmentioning

confidence: 99%

Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches

Rawassizadeh

Tomitsch

Nourizadeh

et al. 2015

Sensors

View full text Add to dashboard Cite

show abstract

“…has been answered, using the decision tree (TREEC) classifier. This algorithm has been chosen because, during initial tests, it has produced good results [11]. Table 1 illustrates the resulting confusion matrix from this test.…”

Section: The Digmem Systemmentioning

confidence: 99%

A user-centred approach to reducing sedentary behaviour

Dobbins

Merabti

Fergus

et al. 2014

2014 IEEE 11th Consumer Communications and Networking Conference (CCNC)

Self Cite

View full text Add to dashboard Cite

Abstract-The use of digital technologies in the administration of healthcare is growing at a rapid rate. However, such platforms are often expensive. As people are living longer, the strain placed on hospitals is increasing. It is evident that a usercentric approach is needed, which aims to prevent illness before a hospital visit is required. As such, with the levels of obesity rising, preventing this illness before such resources are required has the potential to save an enormous amount of time and money, whilst promoting a healthier lifestyle. New and novel approaches are needed, which are inexpensive and pervasive in nature. One such approach is to use human digital memories. This outlet provides visual lifelogs, composed of a variety of data, which can be used to identify periods of inactivity. This paper explores how the DigMem system is used to successfully recognise activity and create temporal memory boxes of human experiences, which can be used to monitor sedentary behaviour.

show abstract

“…HDM systems need to be able to cope with searching a vast pool of data so that relevant information can be extracted and visualised. Machine learning algorithms are seen as a way to alleviate this problem, as large datasets are capable of being processed (Dobbins et al 2013c). As HDM vectors increase in size, it becomes progressively more difficult to keep track of accumulated data, especially from 10 or 20 years ago.…”

Section: Research Challengesmentioning

confidence: 99%

“…Therefore, when defining explicit queries, it is easy to overlook pieces of information. However, using a matrix representation of the data, allows the searching of this information to be treated as a machine learning problem, based on the similarities in a vector object (Dobbins et al 2013c). Consequently, a wider range of information can be included in the memory, as searching by similarity allows the desired information to be retrieved, as well as associated data that the user might not be aware of.…”

Section: Research Challengesmentioning

confidence: 99%

“…Since this data is highly heterogeneous, an intelligent way of searching this information is also needed. As previously stated, machine learning is seen as a way to alleviate this problem (Dobbins et al 2013c). Treating the searching of these documents as a machine learning problem also eliminates the need to produce complex and exact queries.…”

Section: Research Challengesmentioning

confidence: 99%

See 1 more Smart Citation

Advances in Physiological Computing

Fairclough¹,

Gilleade²

2014

Human–Computer Interaction Series

View full text Add to dashboard Cite

HCI is a multidisciplinary field focused on human aspects of the development of computer technology. As computer-based technology becomes increasingly pervasive-not just in developed countries, but worldwide-the need to take a human-centered approach in the design and development of this technology becomes ever more important. For roughly 30 years now, researchers and practitioners in computational and behavioral sciences have worked to identify theory and practice that influences the direction of these technologies, and this diverse work makes up the field of human-computer interaction. Broadly speaking it includes the study of what technology might be able to do for people and how people might interact with the technology. The HCI series publishes books that advance the science and technology of developing systems which are both effective and satisfying for people in a wide variety of contexts. Titles focus on theoretical perspectives (such as formal approaches drawn from a variety of behavioral sciences), practical approaches (such as the techniques for effectively integrating user needs in system development), and social issues (such as the determinants of utility, usability and acceptability).

show abstract

Creating human digital memories with the aid of pervasive mobile devices

Cited by 16 publications

References 55 publications

Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches

Energy-Efficient Integration of Continuous Context Sensing and Prediction into Smartwatches

A user-centred approach to reducing sedentary behaviour

Advances in Physiological Computing

Contact Info

Product

Resources

About