Common-sense knowledge for a computer vision system for human action recognition

This work presents a novel approach for human action recognition based on the combination of computer vision techniques and common-sense knowledge and reasoning capabilities. The emphasis of this work is on how common sense has to be leveraged to a vision-based human action recognition so that nonsensical errors can be amended at the understanding stage. The proposed framework is to be deployed in a realistic environment in which humans behave rationally, that is, motivated by an aim or a reason. © 2012 Springer-Verlag.

Episodic Reasoning for Vision-Based Human Action Recognition

Smart Spaces, Ambient Intelligence, and Ambient Assisted Living are environmental paradigms that strongly depend on their capability to recognize human actions. While most solutions rest on sensor value interpretations and video analysis applications, few have realized the importance of incorporating common-sense capabilities to support the recognition process. Unfortunately, human action recognition cannot be successfully accomplished by only analyzing body postures. On the contrary, this task should be supported by profound knowledge of human agency nature and its tight connection to the reasons and motivations that explain it. The combination of this knowledge and the knowledge about how the world works is essential for recognizing and understanding human actions without committing common-senseless mistakes. This work demonstrates the impact that episodic reasoning has in improving the accuracy of a computer vision system for human action recognition. This work also presents formalization, implementation, and evaluation details of the knowledge model that supports the episodic reasoning.

Non-contact under-mattress sleep monitoring

Sleep quality and duration are increasingly recognised as being important prognostic parameters in the assessment of an individual's health. However, reliable non-invasive long-term monitoring of sleep in a non-clinical setting remains a challenging problem. This paper describes the validation of a novel under mattress pressure sensing sleep monitoring modality that can be seamlessly integrated into existing home environments and provides a pervasive and distributed solution for monitoring long-term changes in sleep patterns and sleep disorders in adults. 410 minutes of concomitant Under Mattress Bed Sensor (UMBS) and strain gauge data were analysed from eight healthy adults lying passively. In this analysis, customised respirations rate detection algorithms yielded a mean difference of −0.12 breaths per five minutes and a mean percentage error (MPE) of 0.16% when the sensor was placed beneath the mattress. 1,491 minutes of UMBS and video data were recorded simultaneously from four participants in order to assess the movement detection efficacy of customised UMBS algorithms. These algorithms yielded accuracies, sensitivities and specificities of over 90% when compared to a video-based movement detection gold standard. A reduced data set (267 minutes) of wrist actigraphy, the gold standard ambulatory sleep monitor, was recorded. The UMBS was shown to outperform the movement detection ability of wrist actigraphy and has the added advantage of not requiring active subject participation.

Seasonal variations in nitrate reductase activity and internal N pools in intertidal brown algae are correlated with ambient nitrate concentrations.

Nitrogen metabolism was examined in the intertidal seaweeds Fucus vesiculosus, Fucus serratus, Fucus spiralis and Laminaria digitata in a temperate Irish sea lough. Internal NO3- storage, total N content and nitrate reductase activity (NRA) were most affected by ambient NO3-, with highest values in winter, when ambient NO3- was maximum, and declined with NO3- during summer. In all species, NRA was six times higher in winter than in summer, and was markedly higher in Fucus species (e.g. 256 ± 33 nmol NO3- min1 g1 in F. vesiculosus versus 55 ± 17 nmol NO3- min1 g1 in L. digitata). Temperature and light were less important factors for N metabolism, but influenced in situ photosynthesis and respiration rates. NO3- assimilating capacity (calculated from NRA) exceeded N demand (calculated from net photosynthesis rates and C : N ratios) by a factor of 0.7–50.0, yet seaweeds stored significant NO3- (up to 40–86 µmol g1). C : N ratio also increased with height in the intertidal zone (lowest in L. digitata and highest in F. spiralis), indicating that tidal emersion also significantly constrained N metabolism. These results suggest that, in contrast to the tight relationship between N and C metabolism in many microalgae, N and C metabolism could be uncoupled in marine macroalgae, which might be an important adaptation to the intertidal environment.

Artificial Intelligence and Cognitive Science

Editorial for 17th AICS Conference