Detecting and reducing redundancy in alarm networks

Butters, T D; Güttel, Stefan; Shapiro, Johanna

doi:10.1109/coase.2015.7294265

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis of triggered alarm patterns can reveal underlying incipient behaviour [6,7], and this information could be used alongside the system presented here to identify the root cause of anomalies.…”

Section: Limitationsmentioning

confidence: 99%

Automatic real-time fault detection for industrial assets using metasensors

Butters¹,

Güttel

Shapiro³

et al. 2015

Asset Management Conference 2015

View full text Add to dashboard Cite

Large-scale industrial plants require physical sensors to continuously measure quantities such as temperatures or pressures. A large number of sensors is required to accurately describe the operating state of the plant, which unfortunately makes it very difficult for them to be effectively monitored by human operators. In this work we present a method to construct so-called metasensors, virtual sensors that compress the information from several sensors in an optimal manner. These metasensors are used as inputs to a novel anomaly detection system that automatically alerts operators to abnormal operation behaviour.

show abstract

Section: Limitationsmentioning

confidence: 99%

Automatic real-time fault detection for industrial assets using metasensors

Butters¹,

Güttel

Shapiro³

et al. 2015

Asset Management Conference 2015

View full text Add to dashboard Cite

show abstract

“…However, deeper CNNs need more memory and computational power. These full-precision CNNs quickly overtax the limited storage [32], battery power, and computing capabilities of a portable embedded device like cell phones. So it is very meaningful to study new vision methods based deep CNNs with low memory and computing power requirement.…”

Section: Introductionmentioning

confidence: 99%

Fast object detection based on binary deep convolution neural networks

Sun

Yin

Wang

et al. 2018

CAAI Transactions on Intelligence Technology

View full text Add to dashboard Cite

In this study, a fast object detection algorithm based on binary deep convolution neural networks (CNNs) is proposed. Convolution kernels of different sizes are used to predict classes and bounding boxes of multi-scale objects directly in the last feature map of a deep CNN. In this way, rapid object detection with acceptable precision loss is achieved. In addition, binary quantisation for weight values and input data of each layer is used to squeeze the networks for faster object detection. Compared to full-precision convolution, the proposed binary deep CNNs for object detection results in 62 times faster convolutional operations and 32 times memory saving in theory, what'sm o r e , the proposed method is easy to be implemented in embedded computing systems because of the binary operation for convolution and low memory requirement. Experimental results on Pascal VOC2007 validate the effectiveness of the authors' proposed method.

show abstract

Detecting and reducing redundancy in alarm networks

Cited by 2 publications

References 15 publications

Automatic real-time fault detection for industrial assets using metasensors

Automatic real-time fault detection for industrial assets using metasensors

Fast object detection based on binary deep convolution neural networks

Contact Info

Product

Resources

About