Classification of behavior using unsupervised temporal neural networks

Adair, Kristin Lynn; Argo, P.E.

doi:10.1109/icsmc.1997.635324

Cited by 9 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It would be interesting to compare his hierarchical STCN model with other hierarchical ones (Kangas, 1990) to discover what kind of representational and computational advantage they have over nonhierarchical ones. With the same goals, comparison among recurrent unsupervised STCNs, such as the CSOM (Voegtlin, 2000) and the temporal Fuzzy ART (Adair & Argo, 1997), could be similarly performed.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

“…The TAD memories have been applied to landmark discrimination for robot navigation (Euliano, Kulzer, & Principe, 1997) and recognition of phoneme sequences (Dobrzewski, Ruwisch, & Bode, 1997). Adair and Argo (1997) proposed the temporal fuzzy ART (TFA) network, a recurrent variant of the fuzzy ART network . The state vector of the TFA network is defined as the 1 0.5…”

Section: Fed Memory In Temporal Activity Diffusion Modelsmentioning

confidence: 99%

See 1 more Smart Citation

A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case

2003

View full text Add to dashboard Cite

Spatiotemporal connectionist networks (STCNs) comprise an important class of neural models that can deal with patterns distributed in both time and space. In this article, we widen the application domain of the taxonomy for supervised STCNs recently proposed by Kremer (2001) to the unsupervised case. This is possible through a reinterpretation of the state vector as a vector of latent (hidden) variables, as proposed by Meinicke (2000). The goal of this generalized taxonomy is then to provide a nonlinear generative framework for describing unsupervised spatiotemporal networks, making it easier to compare and contrast their representational and operational characteristics. Computational properties, representational issues, and learning are also discussed, and a number of references to the relevant source publications are provided. It is argued that the proposed approach is simple and more powerful than the previous attempts from a descriptive and predictive viewpoint. We also discuss the relation of this taxonomy with automata theory and state-space modeling and suggest directions for further work.

show abstract

Section: Conclusion and Further Workmentioning

confidence: 99%

Section: Fed Memory In Temporal Activity Diffusion Modelsmentioning

confidence: 99%

A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case

2003

View full text Add to dashboard Cite

show abstract

“…One of the most important is the work of Mozer who applied such techniques to the control of heating and lighting in a smart home referred to as the Neural Network House [14]. Other work [1] has used unsupervised temporal neural networks for security systems in order to learn from activities and detect abnormal behaviours inside a nuclear power plant.…”

Section: Human Behaviour Recognition Systemsmentioning

confidence: 99%

“…Despite the fact that elder people prefer to "age in place", in order for people to live independently they must be capable to perform certain activities and maintain some independence. One of the metrics used [1], [13], [16], [20] is the ability to perform basic Activities of Daily Living or ADLs, and the capacity to carry out Instrumental Activities of Daily Living or IADLs. ADLs focus on assessing the person's ability to perform basic self care activities such as eating, dressing, bathing, going to the toilet and transferring in and out of bed/chair and walking.…”

Section: Introductionmentioning

confidence: 99%

“…ADLs focus on assessing the person's ability to perform basic self care activities such as eating, dressing, bathing, going to the toilet and transferring in and out of bed/chair and walking. IADLs measure activities related to independent living and include preparing meals, shopping for personal items, medication management, managing money, using the telephone, doing laundry, and transportation 1 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A neural network agent based approach to activity detection in AmI environments

Rivera-Illingworth

Callaghan

Hagras

2005

IEE Seminar on Intelligent Building Environments

View full text Add to dashboard Cite

Many countries are facing the problem of caring economically for their ageing population. One approach to this is the development of environments which possess ambient intelligence that will provide care for older people while assisting them with their everyday life activities. One function that is required in care provision is spotting abnormal behaviours as this might be an indicator of a problem requiring attention from a carer. Agent technology can be employed to detect abnormalities by first learning a normal set of personal behaviours and then detecting deviations from these. This paper presents a novel connectionist embedded agent architecture that combines the use of unobtrusive and relatively simple sensors and employs a constructive algorithm with temporal capabilities which is able to recognize different high level activities (such as "sleeping", "working at computer", "eating"), and identify abnormal behaviours. The network is trained in an online mode, and is able to adapt and expand itself as new data are made available over time or it can add new output nodes to represent new classes or accommodate the abnormal instances. The developed connectionist approach is not computationally demanding and hence it can be integrated into the limited processor-power embedded computing platforms used in intelligent domestic environments.

show abstract