Affect detection from non-stationary physiological data using ensemble classifiers

AlZoubi, Omar; Fossati, Davide; D’Mello, Sidney K.; Calvo, Rafael A.

doi:10.1007/s12530-014-9123-z

Cited by 12 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Integrating the above, we highlight several implications for developing a future emotion regulation system: Non-stationarity of sensor data: Similar to prior affective computing datasets that included multi-days of sampling (e.g. [ 46 , 47 ],), we report that sensor data values exhibit day-to-day differences that must be accounted for across the population. A core challenge with this non-stationarity data is accounting for the effects of sensor-skin interface variation (influencing indicator values), and physiological/psychological contextual change (affecting the indicand-indicator relationship).…”

Section: Application Design: Implications For Emotion Regulation Systemsmentioning

confidence: 71%

“…However, real drift where the posterior probability P(y|x) of emotion labels changes over time relative to PPG values, points to the contextual challenge of PPG alone defining anger classes (i.e., a specific PPG data point may be attributed to anger at one point in time and non-anger in another). In this case, non-stationary models would have to be developed to account for these changes, such as ensemble approaches that adapt to shifting days of data [ 47 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Towards PPG-based anger detection for emotion regulation

How

Green

Mihailidis

2023

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

Background Anger dyscontrol is a common issue after traumatic brain injury (TBI). With the growth of wearable physiological sensors, there is new potential to facilitate the rehabilitation of such anger in the context of daily life. This potential, however, depends on how well physiological markers can distinguish changing emotional states and for such markers to generalize to real-world settings. Our study explores how wearable photoplethysmography (PPG), one of the most widely available physiological sensors, could be used detect anger within a heterogeneous population. Methods This study collected the TRIEP (Toronto Rehabilitation Institute Emotion-Physiology) dataset, which comprised of 32 individuals (10 TBI), exposed to a variety of elicitation material (film, pictures, self-statements, personal recall), over two day sessions. This complex dataset allowed for exploration into how the emotion-PPG relationship varied over changes in individuals, endogenous/exogenous drivers of emotion, and day-to-day differences. A multi-stage analysis was conducted looking at: (1) times-series visual clustering, (2) discriminative time-interval features of anger, and (3) out-of-sample anger classification. Results Characteristics of PPG are largely dominated by inter-subject (between individuals) differences first, then intra-subject (day-to-day) changes, before differentiation into emotion. Both TBI and non-TBI individuals showed evidence of linear separable features that could differentiate anger from non-anger classes within time-interval analysis. However, what is more challenging is that these separable features for anger have various degrees of stability across individuals and days. Conclusion This work highlights how there are contextual, non-stationary challenges to the emotion-physiology relationship that must be accounted for before emotion regulation technology can perform in real-world scenarios. It also affirms the need for a larger breadth of emotional sampling when building classification models.

show abstract

Section: Application Design: Implications For Emotion Regulation Systemsmentioning

confidence: 71%

Section: Discussionmentioning

confidence: 99%

Towards PPG-based anger detection for emotion regulation

How

Green

Mihailidis

2023

J NeuroEngineering Rehabil

View full text Add to dashboard Cite

show abstract

“…Finally, after the next phase of experiments, we hope to have enough multi-modal affective data to build basic classifiers of emotions. We are starting with the replication of findings in the literature [54,81,82,83,84,85,86,87,88,89,90], although the experimental setup differs with every experiment. As such, there is a need to build our own classifiers, aligned with our configuration.…”

Section: Discussion Of the Approachmentioning

confidence: 99%

Analysis and Use of the Emotional Context with Wearable Devices for Games and Intelligent Assistants

Nalepa

Kutt

Giżycka

et al. 2019

Sensors

View full text Add to dashboard Cite

In this paper, we consider the use of wearable sensors for providing affect-based adaptation in Ambient Intelligence (AmI) systems. We begin with discussion of selected issues regarding the applications of affective computing techniques. We describe our experiments for affect change detection with a range of wearable devices, such as wristbands and the BITalino platform, and discuss an original software solution, which we developed for this purpose. Furthermore, as a test-bed application for our work, we selected computer games. We discuss the state-of-the-art in affect-based adaptation in games, described in terms of the so-called affective loop. We present our original proposal of a conceptual design framework for games, called the affective game design patterns. As a proof-of-concept realization of this approach, we discuss some original game prototypes, which we have developed, involving emotion-based control and adaptation. Finally, we comment on a software framework, that we have previously developed, for context-aware systems which uses human emotional contexts. This framework provides means for implementing adaptive systems using mobile devices with wearable sensors.

show abstract

“…[14], [15] depicts the research application on management and strategic planning domain. The authors of [16], [17] works state the use of application in personal assistance field. The authors of [18], [19] refers application in the ubiquitous environmental information domain.…”

Section: Review Of the Literaturementioning

confidence: 99%

“…The tabular representation of the contemporary models reviewed in this section follows (see Table 1). [10], [11] Field-of-medicine; [12], [13] Monitoring-and-control sector; [14], [15] Management-and-strategic-planning domain; [16], [17] Personal-assistance-field; [18], [19] Ubiquitous-environmental-information-domain. [2], [7], [22] Surveys [27] Network-intrusion-detection field Unsupervised [23] Univariate Outlier-detection [24], [25], [26] Multivariate By example models, can't react to the changes occurred in the correlated components considered [27], [28] Multivariate solo monitoring of components using ensemble scalar CDT, every single component of the data stream is inspected to detect concept drift in a multivariate data, can't react to the changes occurred in the correlated components considered [29], [30] Multivariate nonparametric density models [31], [32], [26] Multivariate 'Pure' detectors, outperform with a low volume of data Supervised [33] Machine learning Uses commonly selected sequences as Hidden Markov Models, limits to define simple patterns.…”

Section: Review Of the Literaturementioning

confidence: 99%

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Kumar¹,

Kumar²,

Prasanna³

2018

IJET

View full text Add to dashboard Cite

Concept drift is defined as the distributed data across multiple data streams that change over the time. Concept drift is visible only when the type of collected data changes after some stable period. The emergence of concept drift in data streams leads to increase misclassification and performing degradation of data streams. In order to obtain accurate results, identification of such concept drifts must be visible. This paper focused on a review of the issues related to identifying the changes occurred in the various multivariate high dimensional data streams. The insight of the manuscript is probing the inbuilt difficulties of existing contemporary change-detection methods when they encounter during data dimensions scales.

show abstract

Affect detection from non-stationary physiological data using ensemble classifiers

Cited by 12 publications

References 43 publications

Towards PPG-based anger detection for emotion regulation

Towards PPG-based anger detection for emotion regulation

Analysis and Use of the Emotional Context with Wearable Devices for Games and Intelligent Assistants

Data Mining Models of High Dimensional Data Streams, and Contemporary Concept Drift Detection Methods: a Comprehensive Review

Contact Info

Product

Resources

About