Learn More
We consider ensemble classification when there is no common labeled data for designing the function which aggregates classifier decisions. In recent work, we dubbed this problem distributed ensemble classification, addressing e.g. when local classifiers are trained on different (e.g. proprietary, legacy) databases or operate on different sensing modalities.(More)
—The use of synchrophasor data for observation and control is expected to enhance the operation and efficiency of the next generation of power transmission systems. The synchropha-sor measurement data is usually transferred over public domain networks such as the Internet, thereby making it susceptible to a number of attacks. This paper focuses on packet(More)
—The importance of phasor measurement unit (PMU) or synchrophasor data towards the functioning of real-time monitoring and control of power generation and distribution systems makes them an attractive target for cyber-attacks. An attack with potential for significant damage is the packet drop attack, where the adversary arbitrarily drops packets with(More)
Improved iterative scaling (IIS) is a simple, powerful algorithm for learning maximum entropy (ME) conditional probability models that has found great utility in natural language processing and related applications. In nearly all prior work on IIS, one considers discrete-valued feature functions, depending on the data observations and class label, and(More)
We consider ensemble classification for the case when there is no common labeled training data for designing the function which aggregates individual classifier decisions. We dub this problem distributed ensemble classification, addressing e.g. when individual classifiers are trained on different (e.g. proprietary, legacy) databases or operate (perhaps(More)
  • 1