EEG Transient Event Detection and Classification Using Association Rules

2006 ◽  
Vol 10 (3) ◽  
pp. 451-457 ◽  
Author(s):  
T.P. Exarchos ◽  
A.T. Tzallas ◽  
D.I. Fotiadis ◽  
S. Konitsiotis ◽  
S. Giannopoulos
Keyword(s):  
Association Rules ◽  
Event Detection ◽  
Transient Event

scholarly journals Optimization of Survey Strategies for Detecting Slow Radio Transients

2014 ◽  
Vol 31 ◽  
Author(s):  
Jean-Pierre Macquart
Keyword(s):  
Event Detection ◽  
Detection Rate ◽  
Field Of View ◽  
Integration Time ◽  
Transient Event ◽  
Optimal Value ◽  
Drift Scan ◽  
Transient Events ◽  
Radio Transients ◽  
Special Circumstances

AbstractWe investigate the optimal tradeoff between sensitivity and field of view in surveys for slow radio transients using the event detection rate as the survey metric. This tradeoff bears implications for the design of surveys conducted with upcoming widefield radio interferometers, such as the ASKAP VAST survey and the MeerKAT TRAPUM survey. We investigate (i) a survey in which the events are distributed homogeneously throughout a volume centred on the Earth, (ii) a survey in which the events are homogeneously distributed, but are only detectable beyond a certain minimum distance, and (iii) a survey in which all the events occur at an identical distance, as is appropriate for a targetted survey of a particular field which subtends Npoint telescope pointings. For a survey of fixed duration, Tobs, we determine the optimal tradeoff between number of telescope pointings, N, and integration time per field. We consider a population in which the event luminosity distribution follows a power law with index − α, and tslew is the slewing time between fields or, for a drift scan, the time taken for the telescope drift by one beamwidth. Several orders of magnitude improvement in detection rate is possible by optimization of the survey parameters. The optimal value of N for case (i) is Nmax ~ Tobs/4tslew, while for case (iii) we find Nmax = (Lmax/L0)2[(3 − α)/2]2/(α − 1), where Lmax is the maximum luminosity of a transient event and L0 is the minimum luminosity event detectable in an integration of duration Tobs. (The instance Nmax > Npoint in (iii) implies re-observation of fields over the survey area, except when the duration of transient events exceeds that between re-observations of the same field, where Nmax = Npoint applies instead.) We consider the balance in survey optimization between telescope field of view, Ω, and sensitivity, characterised by the minimum detectable flux density, S0. For homogeneously distributed events (i), the detection rate scales as NΩS−3/20, while for targetted events (iii) it scales as NΩS1 − α0. However, if the targetted survey is optimised for N the event detection rate scales instead as ΩS−20. This analysis bears implications for the assessment of telescope designs: the quantity ΩS−20 is often used as the metric of telescope performance in the SKA transients literature, but only under special circumstances is it the metric that optimises the event detection rate.

A multiprocessor for transient event detection

1997 ◽  
Vol 12 (1) ◽  
pp. 51-60 ◽  
Author(s):  
U.A. Khan ◽  
S.B. Leeb ◽  
M.C. Lee
Keyword(s):  
Event Detection ◽  
Transient Event

A Multiprocessor for Transient Event Detection

1997 ◽  
Vol 17 (1) ◽  
pp. 39-39
Author(s):  
U.A. Khan ◽  
S.B. Lee
Keyword(s):  
Event Detection ◽  
Transient Event

scholarly journals A Patch-Based Method for Repetitive and Transient Event Detection in Fluorescence Imaging

PLoS ONE ◽  
2010 ◽  
Vol 5 (10) ◽  
pp. e13190 ◽  
Author(s):  
Jérôme Boulanger ◽  
Alexandre Gidon ◽  
Charles Kervran ◽  
Jean Salamero
Keyword(s):  
Fluorescence Imaging ◽  
Event Detection ◽  
Transient Event

scholarly journals A Machine-Learning Based Nonintrusive Smart Home Appliance Status Recognition

2020 ◽  
Vol 2020 ◽  
pp. 1-21
Author(s):  
Liston Matindife ◽  
Yanxia Sun ◽  
Zenghui Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recurrent Neural Network ◽  
Event Detection ◽  
Smart Home ◽  
High Performance ◽  
Recognition Performance ◽  
Parallel Structure ◽  
Transient Event ◽  
Signal Parameters

In a smart home, the nonintrusive load monitoring recognition scheme normally achieves high appliance recognition performance in the case where the appliance signals have widely varying power levels and signature characteristics. However, it becomes more difficult to recognize appliances with equal or very close power specifications, often with almost identical signature characteristics. In literature, complex methods based on transient event detection and multiple classifiers that operate on different hand crafted features of the signal have been proposed to tackle this issue. In this paper, we propose a deep learning approach that dispenses with the complex transient event detection and hand crafting of signal features to provide high performance recognition of close tolerance appliances. The appliance classification is premised on the deep multilayer perceptron having three appliance signal parameters as input to increase the number of trainable samples and hence accuracy. In the case where we have limited data, we implement a transfer learning-based appliance classification strategy. With the view of obtaining an appropriate high performing disaggregation deep learning network for the said problem, we explore individually three deep learning disaggregation algorithms based on the multiple parallel structure convolutional neural networks, the recurrent neural network with parallel dense layers for a shared input, and the hybrid convolutional recurrent neural network. We disaggregate a total of three signal parameters per appliance in each case. To evaluate the performance of the proposed method, some simulations and comparisons have been carried out, and the results show that the proposed method can achieve promising performance.

Sign in / Sign up

Export Citation Format

Share Document