Classification as applied to streaming data implies that only a small number of new training instances appear at each generation and are never explicitly reintroduced by the stream. Pareto competitive coevolution provides a potential framework for archiving useful training instances between generations under an archive of finite size. Such a coevolutionary framework is defined for the online evolution of classifiers under genetic programming. Benchmarking is performed under multi-class data sets with class imbalance and training partitions with between 1,000's to 100,000's of instances. The impact of enforcing different constraints for accessing the stream are investigated. The role of online adaptation is explicitly documented and tests made on the relative impact of label error on the quality of streaming classifier results.

No abstract

A framework for coevolving genetic programming teams with Pareto archiving is benchmarked under two representative tasks for non-stationary streaming environments. The specific interest lies in determining the relative contribution of diversity and aging heuristics to the maintenance of the Pareto archive. Pareto archiving, in turn, is responsible for targeting data (and therefore champion individuals) as appropriate for retention beyond the limiting scope of the sliding window interface to the data stream. Fitness sharing alone is considered most effective under a non-stationary stream characterized by continuous (incremental) changes. Fitness sharing with an aging heuristic acts as the preferred heuristic when the stream is characterized by non-stationary stepwise changes.

A framework is introduced for applying GP to streaming data classification tasks under label budgets. This is a fundamental requirement if GP is going to adapt to the challenge of streaming data environments. The framework proposes three elements: a sampling policy, a data subset and a data archiving policy. The sampling policy establishes on what basis data is sampled from the stream, and therefore when label information is requested. The data subset is used to define what GP individuals evolve against. The composition of such a subset is a mixture of data forwarded under the sampling policy and historical data identified through the data archiving policy. The combination of sampling policy and the data subset achieve a decoupling between the rate at which the stream passes and the rate at which evolution commences. Benchmarking is performed on two artificial data sets with specific forms of sudden shift and gradual drift as well as a well known real-world data set.

Security and usability issues with pass-locks on mobile devices have prompted researchers to develop implicit authentication (IA) schemes, which continuously and transparently authenticate users using behavioural biometrics. Contemporary IA schemes proposed by the research community are challenging to deploy, and there is a need for a framework that supports: different behavioural classifiers, given that different apps have different requirements; app developers using IA without becoming domain experts; and real-time classification on resource-constrained mobile devices. We present Itus, an IA framework for Android that allows the research community to improve IA schemes incrementally, while allowing app developers to adopt these improvements at their own pace.We describe the Itus framework and how it provides: ease of use: Itus allows app developers to use IA by changing as few as two lines of their existing code-on the other hand, Itus provides an oracle capable of making advanced recommendations should developers wish to fine-tune the classifiers; flexibility: developers can deploy Itus in an application-specific manner, adapting to their unique needs; extensibility: researchers can contribute new behavioural features and classifiers without worrying about deployment particulars; low performance overhead: Itus operates with minimal performance overhead, allowing app developers to deploy it without compromising end-user experience. These goals are accomplished with an API allowing individual stakeholders to incrementally improve Itus without reengineering new systems. We implement Itus in two demo apps and measure its performance impact. To our knowledge, Itus is the first open-source extensible IA framework for Android that can be deployed off-the-shelf.