Reflective pervasive systems

Abstract

Pervasive adaptive systems are concerned with the construction of "smart" technologies capable of adapting to the needs of the individual in real time. In order to achieve this level of specificity, systems must be capable of monitoring the psychological status of the user and responding to these changes in real time and across multiple systems if necessary. This article describes a number of conceptual issues associated with this category of adaptive technology. The biocybernetic loop describes different approaches to monitoring the status of the user from physiological sensors to overt behavior. These data are used to drive real time system adaptation tailored to a specific user in a particular context. The rate at which the technology adapts to the individual user are described over three different phases of usage: awareness (short-term), adjustment (medium-term), and coevolution (long-term). An ontology is then proposed for the development of an adaptive software ar chitecture that embodies this approach and may be extended to encompass several distinct loops working in parallel. The feasibility of the approach is assessed through implemented case studies of their performance and functionality

Augmenting the Senses: A Review on Sensor-Based Learning Support

“…The second strategy identified on 11 of the prototypes, is similar to the first one; nonetheless this strategy instead of using sensors to track the learner's contexts, it uses sensors to track specific features of the learner such as the learning style [ 31 ], competences based on the score of predefined pre-tests [ 32 ], attention [ 33 – 35 ], emotional state [ 36 , 37 ], uncertainty while using a tutoring system [ 38 , 39 ], trouble solving problems [ 40 ] or driving style [ 41 ]. The information presented to the learner by these prototypes depends on the tracked values for these features.…”

Embedded multimodal interfaces in robotics: applications, future trends, and societal implications

“…The other possibility is that the adaptive response failed to reduce the mental workload of the human operator, in which case the multimodal interface must enter a second cycle of monitoring and adaptation in order to select another response, e.g., suggest a break. This latter process is called second-order adaptation or reflexive adaptation [Serbedzija and Fairclough 2012] because an adaptive response is based upon the closed-loop monitoring of the consequences of its own intervention on the state of the user.…”

A Closed-Loop Perspective on Symbiotic Human-Computer Interaction

“…Once the calming music has been activated for a short period, the system can perform a third check to assess whether frustration has been alleviated as expected. This process is called second-order adaptation or reflexive adaptation [25] because the loop monitors the consequences of its own intervention on the state of the user. This second-order level of adaptation fulfills two functions, it is a self-check (that the original adaptive response was effective) and represents an opportunity for a closed-loop system to collate information about user preferences based a long-term process of repeated interaction.…”

“…The evolving lifecycle of this reflexive technology has been described as a process of mutual adaptation with three main phases [25,26]. The initial encounters between the adaptive system and the user are characterised by a process of improvisation.…”