scholarly journals Load Disaggregation via Pattern Recognition: A Feasibility Study of a Novel Method in Residential Building

Energies ◽  
2018 ◽  
Vol 11 (4) ◽  
pp. 1008 ◽  
Author(s):  
Younghoon Kwak ◽  
Jihyun Hwang ◽  
Taewon Lee
2010 ◽  
Vol 132 (4) ◽  
Author(s):  
Goran Pavić ◽  
Andrew S. Elliott

A novel method has been outlined in the first part of this paper aimed at characterization of structure-borne sound transmission from a vibration source coupled via resilient mounts to a receiver. It can deliver the source mobility and its free velocity, together with the mobility of the receiver to which the source is connected, without decoupling the two structures. The only condition which has to be fulfilled is the conservation of coupling forces and moments across the mounts. In this part of the paper the method is examined from the feasibility point of view. A benchmark test is used as a validation reference for the method, where the properties of the resilient mounts are required and are assumed as known but not completely certain. The feasibility of the principal method is tested by virtual experiment involving two built-up plates resiliently connected at several points. The comparison of the benchmark and the principal method is used to illustrate the benefits of the latter given a small error in the supposedly known mount properties.


Author(s):  
Etse-Oghena Campbell ◽  
Christopher G. Rylander ◽  
Lauren Thaxton ◽  
Marian Yvette Williams-Brown

Abstract The immediate post-partum period offers a convenient time to have an intrauterine device placed because of the co-location of a non-pregnant woman and her clinician; however, this practice is associated with increased expulsion rates of up to 30%, compared with a 3% expulsion rate for interval insertions. This paper presents a device and method to improve intrauterine device delivery and retention in the immediate postpartum period. This initial feasibility study illustrates that it is possible to temporarily tether a commercially available intrauterine device within the uterus of an immediately postpartum baboon. The results indicate this device and method are technically feasible, but further studies will be needed to evaluate safety and efficacy in reducing expulsion rates.


2015 ◽  
Vol 129 (8) ◽  
pp. 773-778 ◽  
Author(s):  
C Yvon ◽  
A Najuko-Mafemera ◽  
R Kanegaonkar

AbstractBackground:Postural sway can be assessed clinically using the Romberg test, or quantified using dynamic posturography. We assessed the potential use of a novel iPhone application as a method of quantifying sway.Methods:Fifty healthy volunteers performed the Romberg and tandem Romberg tests on a hard floor and on foam in soundproofed and normal clinic rooms. Postural sway was recorded using the D+R Balance application and data were compared using pairedt-tests.Results:Significantly more postural sway was noted in participants when standing with their eyes closed and feet in the ‘tandem’ positionvsfeet together; standing with their eyes closed on foamvson the floor; and standing with their eyes closed on foam with feet in the tandem positionvson the floor with feet together.Conclusion:This feasibility study suggests that the iPhone D+R Balance application deserves further investigation as a means of assessing postural sway and may provide an alternative to current dynamic posturography systems.


Author(s):  
Ke Chen ◽  
Lan Wang ◽  
Huisheng Chi

In practical applications of pattern recognition, there are often different features extracted from raw data which needs recognizing. Methods of combining multiple classifiers with different features are viewed as a general problem in various application areas of pattern recognition. In this paper, a systematic investigation has been made and possible solutions are classified into three frameworks, i.e. linear opinion pools, winner-take-all and evidential reasoning. For combining multiple classifiers with different features, a novel method is presented in the framework of linear opinion pools and a modified training algorithm for associative switch is also proposed in the framework of winner-take-all. In the framework of evidential reasoning, several typical methods are briefly reviewed for use. All aforementioned methods have already been applied to text-independent speaker identification. The simulations show that results yielded by the methods described in this paper are better than not only the individual classifiers' but also ones obtained by combining multiple classifiers with the same feature. It indicates that the use of combining multiple classifiers with different features is an effective way to attack the problem of text-independent speaker identification.


Sign in / Sign up

Export Citation Format

Share Document