Visual Analysis of Relationships between Behavioral and Physiological Sensor Data

Kim, Jennifer G.; Snodgrass, Melinda R.; Pietrowicz, Mary; Karahalios, Karrie

doi:10.1109/ichi.2015.27

Cited by 9 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These changes are linked to the skin's production of sweat, which is itself linked to the sympathetic nervous system, often said to reflect changes in arousal. Researchers distinguish between 'phasic' data with lots of peaks that seem to mark arousal, and 'tonic' data that record gradual changes in engagement (Kim et al, 2013). The fact that there is always this differential element to the electric body helps us theorize a body that is charged, but never static or still -bodies are related rates of change, each rate itself changing (change of change …), involving 2 nd , 3 rd , and nth derivatives.…”

Section: Virtuality Intensity and The Futurity Of Mattermentioning

confidence: 99%

The biosocial subject: sensor technologies and worldly sensibility

Freitas

2017

Discourse: Studies in the Cultural Politics of Education

View full text Add to dashboard Cite

Sensor technologies are increasingly part of everyday life, embedded in buildings (movement, sound, temperature) and worn on persons (heart rate, electro-dermal activity, eye tracking). This paper presents a theoretical framework for research on computational sensor data. My approach moves away from theories of agent-centered perceptual synthesis (on behalf of a perceiving organism) and towards a more expansive understanding of the biosocial learning environment. The focus is on sensor technologies that track sensation below the bandwidth of human consciousness. I argue that there is an urgent need to reclaim this kind of biodata as part of an unequally distributed worldly sensibility, and to thereby undermine more narrow reductive readings of such data. The paper explores the biopolitical implications of recasting biodata in terms of transindividual inhuman forces, while continuing to track the distinctive power of humans.

show abstract

Section: Virtuality Intensity and The Futurity Of Mattermentioning

confidence: 99%

The biosocial subject: sensor technologies and worldly sensibility

Freitas

2017

Discourse: Studies in the Cultural Politics of Education

View full text Add to dashboard Cite

show abstract

“…Our work to display VWD builds on previous platforms that provide annotation of generic physiologic data such as AcqKnowledge, ChronoViz, and BEDA, which have exemplified how to perform annotation on temporally archived waveform data. (18,20,(43)(44)(45) APL's combined morphologic and metadata display functionality also builds upon several previous studies that have derived higher-level metadata from raw input streams for purposes of display and annotation. (26,(46)(47)(48)(49) Our work is limited by use of data and clinicians from a single center, and APL is presently limited to processing VWD from a single ventilator.…”

Section: Discussionmentioning

confidence: 96%

“…(7,10,17) Previous groups have developed waveform annotation software that can handle large volume data and output categorization results, but these efforts lack the specific functionality necessary for overcoming problems inherent with annotating VWD. (18)(19)(20)(21)(22)(23)(24)(25)(26)(27)(28)(29)(30). These challenges are: 1) consistent annotation workflows do not exist for VWD annotation, which has led to the creation of datasets that are potentially non-reproducible across medical centers (17), and 2) large, high-quality, multi-reviewer adjudicated datasets of VWD are highly timeconsuming to generate for expert clinicians.…”

Section: Introductionmentioning

confidence: 99%

An Analytic Platform for the Rapid and Reproducible Annotation of Ventilator Waveform Data

Rehm

Kühn

Lieng

et al. 2019

Preprint

View full text Add to dashboard Cite

Algorithmic classifiers are crucial components of clinical decision support (CDS) systems needed to advance healthcare delivery. Robust CDS systems must be derived and validated via creation of multi-reviewer adjudicated gold standard datasets. Manual annotation of physiologic data such as mechanical ventilator waveform data (VWD) can be time-consuming, and lacks methodological consistency in dataset development. To address these issues, we have created a system for annotating and adjudicating VWD called the Annotation PipeLine (APL) to optimize VWD annotation by expert reviewers. APL combines visual assessment of waveform characteristics with metadata display, enabling inclusion of quantitative thresholds into annotation decisions by reviewers. APL also includes specific features for resolving multireviewer disagreements and generating gold standard data sets. APL's unique combination of methods and open source framework may accelerate the creation of CDS algorithms for ventilator management, and may serve as a model for future research into physiologic waveform annotation systems.

show abstract

“…Somewhat similarly, the EventViewer developed by Beard et al (2007) is a framework for exploring data acquired from multiple environmental sensors, manipulating time granularities. The ChronoViz (Fouse, 2013), and the BEDA software (Kim et al, 2015) shows similar concerns, but are applied to the field of behavioral science. The already mentioned EventViewer (Beard et al, 2007) is also meant for exploring the geographical dimension of the data, allowing one to compare data of sensors placed in geographically distinct locations.…”

Section: Background: Visualization Decision Support Toolsmentioning

confidence: 99%

Decision Support Visualization Approach in Textile Manufacturing a Case Study From Operational Control in Textile Industry

Varela¹,

Amaral²,

Pereira³

et al. 2019

IJQR

View full text Add to dashboard Cite

Decision support visualization tools provide insights for solving problems by displaying data in an interactive, graphical format. Such tools can be effective for supporting decision-makers in finding new opportunities and in measuring decision outcomes. In this study, was used a visualization tool capable of handling multivariate time series for studying a problem of operational control in a textile manufacturing plant; the main goal was to identify sources of inefficiency in the daily production data of three machines. A concise rule-based model of the inefficiency measures (i.e. quantitative measures were transformed into categorical variables) was developed and then performed an in-depth visual analysis using a particular technique, the categorical time series plots stacked vertically. With this approach were identified a wide array of production inefficiency patterns, which were difficult to identify using standard quantitative reporting -temporal pattern of best and worst performing machines -and critically, along with most important sources of inefficiency and some interactions between them were revealed. The case study underlying this work was further contextualized within the state of the art, and demonstrates the effectiveness of adequate visual analysis as a decision support tool for operational control in manufacturing.

show abstract

Visual Analysis of Relationships between Behavioral and Physiological Sensor Data

Cited by 9 publications

References 23 publications

The biosocial subject: sensor technologies and worldly sensibility

The biosocial subject: sensor technologies and worldly sensibility

An Analytic Platform for the Rapid and Reproducible Annotation of Ventilator Waveform Data

Decision Support Visualization Approach in Textile Manufacturing a Case Study From Operational Control in Textile Industry

Contact Info

Product

Resources

About