Activity recognition using temporal evidence theory

McKeever, Susan; Ye, Juan; Coyle, Lorcan; Bleakley, Chris J.; Dobson, Simon

doi:10.3233/ais-2010-0071

Cited by 68 publications

(33 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to other uncertainty reasoning frameworks such as fuzzy logic [58], DST has the advantage of preserving uncertainty levels from each evidence channel and providing a boundary for the certainty levels of the final belief [59]. Due to DST's wide applicability, it has been used for decision fusion in visual tracking [60], human activity recognition [61] and robot localization [62], to mention a few examples.…”

Section: Early Predictionmentioning

confidence: 99%

Early prediction for physical human robot collaboration in the operating room

Zhou

Wachs

2017

Auton Robot

View full text Add to dashboard Cite

To enable a natural and fluent human robot collaboration flow, it is critical for a robot to comprehend their human peers' on-going actions, predict their behaviors in the near future, and plan its actions correspondingly. Specifically, the capability of making early predictions is important, so that the robot can foresee the precise timing of a turn-taking event and start motion planning and execution early enough to smooth the turn-taking transition. Such proactive behavior would reduce human's waiting time, increase efficiency and enhance naturalness in collaborative task. To that end, this paper presents the design and implementation of an early turn-taking prediction algorithm, catered for physical human robot collaboration scenarios. Specifically, a Robotic Scrub Nurse (RSN) system which can comprehend surgeon's multimodal communication cues and perform turn-taking prediction is presented. The developed algorithm was tested on a collected data set of simulated surgical procedures in a surgeon-nurse tandem. The proposed turn-taking prediction algorithm is found to be significantly superior to its algorithmic counterparts, and is more accurate than human baseline when little partial input is given (less than 30% of full action). After observing more information, the algorithm can achieve comparable performances as humans with a F1 score of 0.90.

show abstract

Section: Early Predictionmentioning

confidence: 99%

Early prediction for physical human robot collaboration in the operating room

Zhou

Wachs

2017

Auton Robot

View full text Add to dashboard Cite

show abstract

“…In contrast, dynamic sliding window methods enable varying sizes of sliding windows at runtime based on di erent features, such as the duration of activities [29,33,41], change of sensor states [24], or change of location context of consecutive sensor data [16]. Krishnan et al [23] explore both static and dynamic sliding window approaches, with the incorporation of the time decay and mutual information of sensor events within a window; e.g., the occurrence ratio of two sensors occurring consecutively in the entire sensor stream.…”

Section: Segmentationmentioning

confidence: 99%

KCAR: A knowledge-driven approach for concurrent activity recognition

Stevenson

Dobson

2015

Pervasive and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Recognising human activities from sensors embedded in an environment or worn on bodies is an important and challenging research topic in pervasive computing. Existing work on activity recognition is mainly concerned with identifying single user sequential activities from well-scripted or pre-segmented sequences of sensor events. However a real-world environment often contains multiple users, with each performing activities simultaneously, in their own way and with no explicit instructions to follow. Recognising multiuser concurrent activities is challenging, but essential for designing applications for real environments. This paper presents a novel Knowledge-driven approach for Concurrent Activity Recognition (KCAR). Within KCAR, we explore the semantics underlying each sensor event and use semantic dissimilarity to segment a continuous sensor sequence into fragments, each of which corresponds to one ongoing activity. We exploit the Pyramid Match Kernel, with a strength in approximate matching on hierarchical concepts, to recognise activities of varying grained constraints from a potentially noisy sensor sequence. We conduct an empirical evaluation on a large-scale real-world data set that is collected over one year and consists of 2.8 millions of sensor events. Our results demonstrate that KCAR achieves an average recognition accuracy of 91%.

show abstract

“…Hybrid (Riboni and Bettini, 2011a;Roy et al, 2011;Augusto et al, 2008) Markov Logic Networks (Helaoui et al, 2011;Skarlatidis et al, 2011) Evidence Theory (McKeever et al, 2010;Sebbak et al, 2012;Hong et al, 2009) Constraint-based reasoning (Pecora et al, 2012;Cirillo et al, 2009) Can handle quantitative and qualitative uncertainty…”

Section: Yes Very Limited Yesmentioning

confidence: 99%

Resolving conflicts in knowledge for ambient intelligence

Homola

Patkos

Flouris

et al. 2015

The Knowledge Engineering Review

View full text Add to dashboard Cite

Ambient intelligence (AmI) proposes pervasive information systems composed of autonomous agents embedded within the environment who, in orchestration, complement human activity in an intelligent manner. As such, it is an interesting and challenging application area for many computer science fields and approaches. A critical issue in such application scenarios is that the agents must be able to acquire, exchange, and evaluate knowledge about the environment, its users, and their activities. Knowledge populated between the agents in such systems may be contextually dependent, ambiguous, and incomplete. Conflicts may thus naturally arise, that need to be dealt with by the agents in an autonomous way. In this survey, we relate AmI to the area of knowledge representation and reasoning (KR), where conflict resolution has been studied for a long time. We take a look at a number of KR approaches that may be applied: context modelling, multi-context systems, belief revision, ontology evolution and debugging, argumentation, preferences, and paraconsistent reasoning. Our main goal is to describe the state of the art in these fields, and to draw attention of researchers to important theoretical issues and practical challenges that still need to be resolved, in order to reuse the results from KR in AmI systems or similar complex and demanding applications.

show abstract

Activity recognition using temporal evidence theory

Cited by 68 publications

References 38 publications

Early prediction for physical human robot collaboration in the operating room

Early prediction for physical human robot collaboration in the operating room

KCAR: A knowledge-driven approach for concurrent activity recognition

Resolving conflicts in knowledge for ambient intelligence

Contact Info

Product

Resources

About