Growing neural gas for temporal clustering

Sledge, Isaac J.; Keller, James M.

doi:10.1109/icpr.2008.4761768

Cited by 25 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, 32 different features are computed from the unprocessed data, which help to locate short-term changes and long-term activity trends that correlate with different states of health. Although incremental, temporal approaches have shown prom-ise in locating the activity clusters (Sledge and Keller 2008;Sledge et al 2008c, d), the data are rather noisy and should help highlight areas for improving cluster count extraction. Utilizing three participants' feature data, the n ¼ 428; 851; 588 VAT images, shown in Fig.…”

Section: Real World Data Experimentsmentioning

confidence: 97%

Finding the number of clusters in ordered dissimilarities

et al. 2009

Self Cite

View full text Add to dashboard Cite

As humans, we have innate faculties that allow us to efficiently segment groups of objects. Computers, to some degree, can be programmed with similar categorical capabilities, which stem from exploratory data analysis. Out of the various subsets of data reasoning, clustering provides insight into the structure and relationships of input samples situated in a number of distributions. To determine these relationships, many clustering methods rely on one or more human inputs; the most important being the number of distributions, c, to seek. This work investigates a technique for estimating the number of clusters from a general type of data called relational data. Several numerical examples are presented to illustrate the effectiveness of the proposed method.

show abstract

Section: Real World Data Experimentsmentioning

confidence: 97%

Finding the number of clusters in ordered dissimilarities

et al. 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…T par ≈ 520/p = const/p (14) we can conclude that our parallel algorithm is scalable in the selected range with a more or less constant efficiency E. To have a measure of the speed-up of the WR WM PSOM, we draw in Fig. 12 its efficiency.…”

Section: Processing Time and Convergence Speedmentioning

confidence: 98%

Mining massive datasets by an unsupervised parallel clustering on a GRID: Novel algorithms and case study

Faro

Giordano

Maiorana

2011

Future Generation Computer Systems

View full text Add to dashboard Cite

“…These pattern deviations may take the form of a sudden change as a result of a specific health event, or in the form of a gradual change as a result of a deteriorating condition. One approach for detecting such changes is a new algorithm for temporal clustering [40][41][42]. A baseline cluster is established for a resident, using 32 features extracted from the motion and bed sensors data, such as time to wake up, time to bed, in bed and out of bed time, and activity density in each room.…”

Section: Passive Physiological Sensor Network and Supporting Componentsmentioning

confidence: 99%

A smart home application to eldercare: Current status and lessons learned

Skubic

Alexander

Popescu

et al. 2009

THC

202

100

View full text Add to dashboard Cite

To address an aging population, we have been investigating sensor networks for monitoring older adults in their homes. In this paper, we report ongoing work in which passive sensor networks have been installed in 17 apartments in an aging in place eldercare facility. The network under development includes simple motion sensors, video sensors, and a bed sensor that captures sleep restlessness and pulse and respiration levels. Data collection has been ongoing for over two years in some apartments. This longevity in sensor data collection is allowing us to study the data and develop algorithms for identifying alert conditions such as falls, as well as extracting typical daily activity patterns for an individual. The goal is to capture patterns representing physical and cognitive health conditions and then recognize when activity patterns begin to deviate from the norm. In doing so, we strive to provide early detection of potential problems which may lead to serious health events if left unattended. We describe the components of the network and show examples of logged sensor data with correlated references to health events. A summary is also included on the challenges encountered and the lessons learned as a result of our experiences in monitoring aging adults in their homes.

show abstract

Growing neural gas for temporal clustering

Cited by 25 publications

References 12 publications

Finding the number of clusters in ordered dissimilarities

Finding the number of clusters in ordered dissimilarities

Mining massive datasets by an unsupervised parallel clustering on a GRID: Novel algorithms and case study

A smart home application to eldercare: Current status and lessons learned

Contact Info

Product

Resources

About