Blind separation of mutually correlated sources using precoders

This paper studies the problem of blind source separation (BSS) from instantaneous mixtures with the assumption that the source signals are mutually correlated.We propose a novel approach to BSS by using precoders in transmitters.We show that if the precoders are properly designed, some cross-correlation coefficients of the coded signals can be forced to be zero at certain time lags. Then, the unique correlation properties of the coded signals can be exploited in receiver to achieve source separation. Based on the proposed precoders, a subspace-based algorithm is derived for the blind separation of mutually correlated sources. The effectiveness of the algorithm is illustrated by simulation examples.

A Bayesian framework for learning shared and individual subspaces from multiple data sources

This paper presents a novel Bayesian formulation to exploit shared structures across multiple data sources, constructing foundations for effective mining and retrieval across disparate domains. We jointly analyze diverse data sources using a unifying piece of metadata (textual tags). We propose a method based on Bayesian Probabilistic Matrix Factorization (BPMF) which is able to explicitly model the partial knowledge common to the datasets using shared subspaces and the knowledge specific to each dataset using individual subspaces. For the proposed model, we derive an efficient algorithm for learning the joint factorization based on Gibbs sampling. The effectiveness of the model is demonstrated by social media retrieval tasks across single and multiple media. The proposed solution is applicable to a wider context, providing a formal framework suitable for exploiting individual as well as mutual knowledge present across heterogeneous data sources of many kinds.

Multimedia authoring : human-computer partnership for harvesting metadata from the right sources

This chapter takes a look at the task of creating multimedia authoring tools for the amateur media creator, and the problems unique to the undertaking. It argues that a deep understanding of both the media creation process, together with insight into the precise nature of the relative strengths of computers and users, given the domain of application, is needed before this gap can be bridged by software technology. These issues are further demonstrated within the context of a novel media collection environment, including a real- world example of an occasion filmed in order to automatically create two movies of distinctly different styles. The authors hope that such tools will enable amateur videographers to produce technically polished and aesthetically effective media, regardless of their level of expertise.

Invertebrate food sources for waterbirds provided by the reconstructed wetland of Nyirkai-Hany, northwestern Hungary

The Nyirkai-Hany wetland reconstruction area in northwestern Hungary is now designated as a Ramsar and a Natura 2000 site. It was created in 2001–2002 by the Fertő-Hanság National Park Directorate to restore a part of the formerly drained large wetland called Hanság and to offer waterbirds a suitable habitat for feeding and breeding. We focused on this aim of the restoration project and studied the temporal and spatial variation in abundance of birds and their invertebrate prey in this newly created wetland. From April 2007 until May 2008, we sampled plankton, nekton and benthos of different habitats monthly and monitored waterbirds weekly on the three different areas of the Nyirkai-Hany. During our investigations, 135 invertebrate and 53 waterbird species were recorded. Benthos and macrophyte decomposition accelerating guilds were the most abundant waterbird guilds—besides the dominant grazing importer material transporter guild, represented primarily by geese—in the Nyirkai-Hany. Zooplankton assemblages primarily consisted of small species not easily used as a food by planktivorous waterbirds. The low density of zoobenthic biomass and the small extent of shallow water mudflats probably accounted for the scarcity of the bioturbing guild group of birds. Nektonic biomass varied greatly among locations having different vegetation types, was greatest in the shallow water areas dominated by Typha, Carex and Phragmites species and lowest at offshore vegetation-free sites. Chironomids, mayflies and odonates were especially abundant and their biomass significantly correlated with several waterbird species, mainly belonging to the macrophyte decomposition accelerating guild (e.g. Anas platyrynchos, Fulica atra). This guild itself, which has increased in abundance in recent years, showed an exceptionally strong correlation with odonate abundance. These results indicate the growing importance of the Nyirkai-Hany wetland area as a foraging site for waterbirds.

A bayesian nonparametric joint factor model for learning shared and individual subspaces from multiple data sources

Joint analysis of multiple data sources is becoming increasingly popular in transfer learning, multi-task learning and cross-domain data mining. One promising approach to model the data jointly is through learning the shared and individual factor subspaces. However, performance of this approach depends on the subspace dimensionalities and the level of sharing needs to be specified a priori. To this end, we propose a nonparametric joint factor analysis framework for modeling multiple related data sources. Our model utilizes the hierarchical beta process as a nonparametric prior to automatically infer the number of shared and individual factors. For posterior inference, we provide a Gibbs sampling scheme using auxiliary variables. The effectiveness of the proposed framework is validated through its application on two real world problems - transfer learning in text and image retrieval.

Journalists, remote Indigenous sources and cultural competence

This is the report of the Australian news media and Indigenous policymaking 1988-2008 Australian Research Council Discovery Project.