A survey of methods for data fusion and system adaptation using autonomic nervous system responses in physiological computing

Novak, Domen; Mihelj, Matjaž; Munih, Marko

doi:10.1016/j.intcom.2012.04.003

Cited by 157 publications

(177 citation statements)

References 105 publications

Supporting

Mentioning

149

Contrasting

Unclassified

Order By: Relevance

“…Since the film clips were approximately one minute long, the data formed temporal sequences. In affective computing, the feature-based approach to time sequence classification dominates (Novak et al 2012). We also found this method to be more suitable for a number of reasons.…”

Section: Data Mining and Extraction Of Featuresmentioning

confidence: 99%

“…With these algorithms, we would create prediction models for classification of psychological states. Five classification methods frequently used in affective computing (Novak et al 2012) were evaluated. K-nearest neighbor (kNN) is a simple algorithm that performs instance-based learning classifying an object based on the classes of its neighbors.…”

Section: Classification Algorithmsmentioning

confidence: 99%

“…The third classification method relied on a probabilistic model built with the naïve Bayes algorithm. The fourth approach was linear discriminant analysis (LDA) that is wellsuited for small data samples and is easy in implementation (Novak et al 2012).…”

Section: Classification Algorithmsmentioning

confidence: 99%

“…The reduction of dimensionality is achieved by keeping the components with highest variance. Second, LDA can be used for both the identification of important features and classification (Novak et al 2012).…”

Section: Classification Algorithmsmentioning

confidence: 99%

“…For instance, judging from the review provided in (Novak et al 2012), the studies that performed within-subjects recognition of psychological states achieved better results than the experiments where between-subjects approach were utilized.…”

Section: The First Column Reports the Categories Of The Film Clips Thmentioning

confidence: 99%

See 4 more Smart Citations

Beyond cognition and affect: sensing the unconscious

Ivonin

Chang

Díaz

et al. 2014

Behaviour & Information Technology

View full text Add to dashboard Cite

In the past decade, research on human-computer interaction has embraced psychophysiological user interfaces that enhance awareness of computers about conscious cognitive and affective states of users and increase their adaptive capabilities. Still, human experience is not limited to the levels of cognition and affect but extends further into the realm of universal instincts and innate behaviors that form the collective unconscious. Patterns of instinctual traits shape archetypes that represent images of the unconscious. This study investigated Further analysis suggested that classification performance could be improved up to 70.3 percent in the case of 7 archetypes by using within-subject models.

show abstract

Section: Data Mining and Extraction Of Featuresmentioning

confidence: 99%

Section: Classification Algorithmsmentioning

confidence: 99%

Section: Classification Algorithmsmentioning

confidence: 99%

Section: Classification Algorithmsmentioning

confidence: 99%

Section: The First Column Reports the Categories Of The Film Clips Thmentioning

confidence: 99%

See 3 more Smart Citations

Beyond cognition and affect: sensing the unconscious

Ivonin

Chang

Díaz

et al. 2014

Behaviour & Information Technology

View full text Add to dashboard Cite

show abstract

A Fresh Approach in the Optimization of Government Processes using Algorithms: A Case Study of Retirement Procedure in Cameroon

Etoundi

Aloo

Ndjodo

2016

E J Info Sys Dev Countries

View full text Add to dashboard Cite

Many works have been carried out in the field of business process re-engineering. Despite their abundance, there is still much to be done as not all the aspects have been taken into consideration. Most of the works are concentrated on the reduction of the number of tasks and do not take into consideration the reduction of resources needed to perform tasks. Among these resources are documents required for the processing of various tasks. Even when tasks reduction is concerned, there is no clear methodology that is proposed for task cancellation. Moreover, among business processes are administrative procedures, which are specific processes dealing with policy, legislation rules and regulation in the administration. The optimization of administrative procedures has become imperative in developing countries as these countries are working to improve the quality of services delivered to citizens. It is an important aspect to be considered in order to move ahead in their development. Procedures actually used in these countries have been developed just at the dawn of independences. Their effectiveness in terms of quality of service was not considered as these countries first wanted to deliver. Forty years after, the problem of the quality of service became crucial. Hence, these countries are seeking solutions to re-engineer their legacy administrative procedures. This paper presents a methodology associated with an algorithm for the reduction of documents required from citizens, and activities that are performed in the delivery of services. The methodology is based on the correlation among tasks and among documents. This methodology is applied to the management of the human resource retirement process in the public service in Cameroon.

show abstract

Engineering Issues in Physiological Computing

Novak

2014

Human–Computer Interaction Series

Self Cite

View full text Add to dashboard Cite

Prototypes of physiological computing systems have appeared in countless fields, but few have made the leap from research to widespread use. This is due to several practical problems that can be roughly divided into four major categories: hardware, signal processing, psychophysiological inference, and feedback loop design. This chapter explores these issues from an engineering point of view, discussing major weaknesses and suggesting directions for potential solutions. Specifically, some of the topics covered are: unobtrusiveness and robustness of the hardware, real-time signal processing capability, different approaches to design and validation of a psychophysiological classifier, and the desired complexity of the feedback rules. The chapter also briefly discusses the challenge of finding an appropriate practical application for physiological computing, then ends with a summary of recommendations for future research.

show abstract

A survey of methods for data fusion and system adaptation using autonomic nervous system responses in physiological computing

Cited by 157 publications

References 105 publications

Beyond cognition and affect: sensing the unconscious

Beyond cognition and affect: sensing the unconscious

A Fresh Approach in the Optimization of Government Processes using Algorithms: A Case Study of Retirement Procedure in Cameroon

Engineering Issues in Physiological Computing

Contact Info

Product

Resources

About