• No results found

Integration of discriminative and generative models for activity recognition in smart homes

N/A
N/A
Protected

Academic year: 2019

Share "Integration of discriminative and generative models for activity recognition in smart homes"

Copied!
15
0
0

Loading.... (view fulltext now)

Full text

Loading

Figure

Figure 1: Block diagram of the proposed activity recognition approach. Switch s = 1 is training.
Figure 2: Examples of distributions of obtained distances of instances from the mean of their activity class
Table 1: The summary of five smart home datasets used in the evaluation of proposed approach
Table 2: Performance evaluation metrics on five smart home datasets for proposed approach and the existing approaches: DM, PE, ET-KNN [7, 45]and PNN [8, 46] using leave one day out cross validation
+5

References

Related documents

obstarávacej ceny a náklady za prípadné nadštandardné služby. V prípade, že pacient si na zákrok nepriniesol výsledky predopera č ného vyšetrenia, urobí sa za úhradu

olism of carbon-i4 labeled pyruvate by the newborn rat. : Anaerobic lipogenesis in fetal liver slices. : Ef-. fects of oxygen deprivation on the me- tabolism of fetal and adult

This framework incorporates macro (structural & symbolic institutions), meso (group), and micro (individual) levels of analysis, the idea of time and life course analysis, and

The tonnage of the vessel (200 grt) will be the average commercial fishing vessel size in the locality of the training facility. The

To do this, we defined an optimization problem to find a partitioning of the individuals based on their protected attributes that exhibits the highest unfairness by a given

• Pauli exclusion principle prevents multiple occupancy, and electron distribution of atoms with closed shells can overlap only if accompanies by the partial.. promotion of

Dry magnetic particles can typically be purchased in red, black, gray, yellow and several  other  colors  so  that  a  high  level  of  contrast  between  the  particles