This paper proposes a simple and effective method for classification of fundamental ferroresonance, single phase-to-ground and wire breakage over-voltages. In isolated neutral networks, power frequency over-voltages due to ferroresonance, single phase-to-ground and wire breakage may exist for a long time, and have very highly similar voltage features. If the improper suppression operation is ap...

wireless sensor networks are the new generation of networks that typically are formed great numbers of nodes and the communications of these nodes are done as wireless. the main goal of these networks is collecting data from neighboring environment of network sensors. since the sensor nodes are battery operated and there is no possibility of charging or replacing the batteries, the lifetime of ...

In this letter, we introduce deep active learning (AL) for multi-label classification (MLC) problems in remote sensing (RS). particular, investigate the effectiveness of several AL query functions MLC RS images. Unlike existing (which are defined single-label or semantic segmentation problems), each function paper is based on evaluation two criteria: i) uncertainty; and ii) diversity. The uncer...

The multiple-agent scheduling problems have received increasing attention recently. However, most of the research focuses on studying the computational complexity of the intractable cases or examining problems with a single criterion. Often a decision maker has to decide the schedule based on multiple criteria. In this paper, we consider a single machine problem where the objective is to minimi...

IfN is a queueing network and cs is the mean service time at server s of N , de ne NC,FCFS (respectively, NE,FCFS) to be the queueing network N where the service time at server s is a constant cs (respectively, an independent exponentially distributed random variable with mean cs) and the packets are served in a rst-comerst-served order. Recently, Harchol-Balter and Wolfe introduced the problem...

For the congestion problems in high-speed networks, a Metropolis criterion based Q-learning flow controller is proposed. Because of the uncertainties and highly time-varying, it is not easy to accurately obtain the complete information for high-speed networks. The Q-learning algorithm, which is independent of mathematic model, shows the particular superiority in high-speed networks. It obtains ...

The analysis of complex networks permeates all sciences, from biology to sociology. A fundamental, unsolved problem is how to characterize the community structure of a network. Here, using both standard and novel benchmarks, we show that maximization of a simple global parameter, which we call Surprise (S), leads to a very efficient characterization of the community structure of complex synthet...

In the training of neural networks using the error-backpropagation(BP) algorithm, overlearning phenomenon has been observed. In the previous works we showed how over-learning can be viewed as being the result of using the BP criterion as a substitute for some true criterion. There, the concept of admissibility was introduced and discussed conditions for a true criterion admits a substitute crit...

Graphical structures such as Bayesian networks or Markov networks are very useful tools for representing irrelevance or independency relationships, and they may be used to e ciently perform reasoning tasks. Singly connected networks are important speci ® c cases where there is no more than one undirected path connecting each pair of variables. The aim of this paper is to investigate the kind o...