Monaural sound source separation using covariance profile of partials

This paper addresses the problem of separation of pitched sounds in monaural recordings. We present a novel feature for the estimation of parameters of overlapping harmonics which considers the covariance of partials of pitched sounds. Sound templates are formed from the monophonic parts of the mixture recording. A match for every note is found among these templates on the basis of covariance profile of their harmonics. The matching template for the note provides the second order characteristics for the overlapped harmonics of the note. The algorithm is tested on the RWC music database instrument sounds. The results clearly show that the covariance characteristics can be used to reconstruct overlapping harmonics effectively.

Covariance profiles: a signature representation for object sets

We consider the problem of extracting a signature representation of similar entities employing covariance descriptors. Covariance descriptors can efficiently represent objects and are robust to scale and pose changes. We posit that covariance descriptors corresponding to similar objects share a common geometrical structure which can be extracted through joint diagonalization. We term this diagonalizing matrix as the Covariance Profile (CP). CP can be used to measure the distance of a novel object to an object set through the diagonality measure. We demonstrate how CP can be employed on images as well as for videos, for applications such as face recognition and object-track clustering.

Wind speed prediction using spatio-temporal covariance

High wind poses a number of hazards in different areas such as structural safety, aviation, and wind energy-where low wind speed is also a concern, pollutant transport, to name a few. Therefore, usage of a good prediction tool for wind speed is necessary in these areas. Like many other natural processes, behavior of wind is also associated with considerable uncertainties stemming from different sources. Therefore, to develop a reliable prediction tool for wind speed, these uncertainties should be taken into account. In this work, we propose a probabilistic framework for prediction of wind speed from measured spatio-temporal data. The framework is based on decompositions of spatio-temporal covariance and simulation using these decompositions. A novel simulation method based on a tensor decomposition is used here in this context. The proposed framework is composed of a set of four modules, and the modules have flexibility to accommodate further modifications. This framework is applied on measured data on wind speed in Ireland. Both short-and long-term predictions are addressed.

Simulating dynamic covariance structures for testing the adaptive behavior of variable selection algorithms (Invited Paper)

Variable selection for regression is a classical statistical problem, motivated by concerns that too large a number of covariates may bring about overfitting and unnecessarily high measurement costs. Novel difficulties arise in streaming contexts, where the correlation structure of the process may be drifting, in which case it must be constantly tracked so that selections may be revised accordingly. A particularly interesting phenomenon is that non-selected covariates become missing variables, inducing bias on subsequent decisions. This raises an intricate exploration-exploitation tradeoff, whose dependence on the covariance tracking algorithm and the choice of variable selection scheme is too complex to be dealt with analytically. We hence capitalise on the strength of simulations to explore this problem, taking the opportunity to tackle the difficult task of simulating dynamic correlation structures. © 2008 IEEE.

Streaming covariance selection with applications to adaptive querying in sensor networks

Sensor networks can be naturally represented as graphical models, where the edge set encodes the presence of sparsity in the correlation structure between sensors. Such graphical representations can be valuable for information mining purposes as well as for optimizing bandwidth and battery usage with minimal loss of estimation accuracy. We use a computationally efficient technique for estimating sparse graphical models which fits a sparse linear regression locally at each node of the graph via the Lasso estimator. Using a recently suggested online, temporally adaptive implementation of the Lasso, we propose an algorithm for streaming graphical model selection over sensor networks. With battery consumption minimization applications in mind, we use this algorithm as the basis of an adaptive querying scheme. We discuss implementation issues in the context of environmental monitoring using sensor networks, where the objective is short-term forecasting of local wind direction. The algorithm is tested against real UK weather data and conclusions are drawn about certain tradeoffs inherent in decentralized sensor networks data analysis. © 2010 The Author. Published by Oxford University Press on behalf of The British Computer Society. All rights reserved.

A new method to analyse the Peierls-Nabarro model of an edge dislocation in a rectangular plate

A new method is presented here to analyse the Peierls-Nabarro model of an edge dislocation in a rectangular plate. The analysis is based on the superposition scheme and series expansions of complex potentials. The stress field and dislocation density field on the slip plane can be expressed as the first and the second Chebyshev polynomial series respectively. Two sets of governing equations are obtained on the slip plane and outer boundary of the rectangular plate respectively. Three numerical methods are used to solve the governing equations.

Analyse der Beifangreduktion durch Gitternetze in der kommerziellen Garnelenfischerei

Trials for the determination of the magnitude of bycatch reduction by sorting grids used in the commercial brown shrimp fishery were carried out from September to December 1997. Trawls with 9 m beam length were used on different fishing grounds in the estuary of the Elbe River near Cuxhaven. The sorting grids tested were made of stainless steel bars spaced at 18, 20, 22, 26 and 30 mm, built into a cylindrical stainless steel frame with a diameter of 65 cm at an angle of attack of 45 degrees. This frame was positioned between the forenet and codend. Simultaneous hauls were made with a trawl of equal construction but without a sorting grid, and the weighed catch components (fish, discard shrimps and commercial size shrimps) separated by means of a riddle were compared. The composition of the sorted out part of the catch of the sorting grid net could be calculated by comparise the corresponding catch components in both the standard trawl and the sorting grid trawl. According to this the total catch of the beam trawl with the sorting grid is reduced by 18 to 38 % depending on the space between the bars. 7 to 31 % of the sorted out part of the catch consists of fish. The use of the sorting grid, however, also leads to losses of 4 to 12 % in Oktober. Per hour of towing this means a loss of 10,3 % commerical size shrimps with a sorting grid of 18 mm space between the bars and of 12,4 % for a 26 mm grid.

Analyse der Beifangreduktion durch Trichternetze in der kommerziellen Garnelenfischerei

Trials for the determination of the magnitude of bycatch reduction by the sievenets used in the commercial brown shrimp fishery were carried out from September to December 1997. Trawls with 9 m beam length were the subjected to the investigation. They were used on different fishing grounds in the estuary of the Elbe near Cuxhaven. Sievenets with 50, 60 and 80 mm mesh opening were tested in 29 hauls and 31.6 h total duration. A trawl of equal construction without sievenets fished synchronously was used for comparison. The proportional catch composition in the codend was determined by weighing the catch components (fish, discard shrimps and commercial size shrimps) as separated by means of a riddle. The composition of the sorted out part of the catch could be calculated by comparison of the corresponding catch components both in standard trawl and sievenettrawl. According to this the total catch of a beam trawl with sievenet is diminished by 9 to 34 % depending on the mesh opening of the sievenet. 32 to 58 % of the sorted out part of the catch consists of fish. Use of a sievenet, however, also leads to a loss of 6 to 15 % of commercial size shrimps. Per hour of towing this means a loss of 8.7 kg commercial size shrimps with a sievenet of 60 mm mesh opening and of 1.8 kg for a mesh size of 80 mm.

Differenzierung roher und geräucherter Aale durch Protein- und DNA-Analyse

Raw or smoked eel was analysed by isoelectric focusing of sarcoplasmic proteins. For raw fish specific protein patterns were obtained for A. anguilla/A. rostrata, A. japonica and A. australis, but in case of smoked fish differentiation was only possible between Atlantic and Pacific species. Differentiation of raw or smoked eel was possible by PCR-SSCP, but patterns of ssDNA showed some intra-specific variability depending on the type of amplicon.

Fischartbestimmung von Caviar durch Protein- und DNA-Analyse

Deutscher Caviar, made from roe of lumpfish or capelin, gives species specific patterns in protein electrophoresis. The same techniques can be used to differentiate caviar from salmon and trout. The differentiation of sturgeon caviar (beluga, osietra, sevruga) is possible by isoelectric focusing, but not by SDS-PAGE. PCR-based methods of DNA-analysis for identification of the origin of sturgeon caviar are under development.

Analyse des Fluchtverhaltens von Fischen auf Schiffsgeräusche mit hydroakustischen Methoden

Investigations on the avoidance reactions of pelagic schooling fish (herring and sprat) released by an approaching fishery vessel were carried out during the 378th cruise of FRC "Solea" from 25 September to 3 October 1995 in the Arkona Sea, southern Baltic. An echosounder system EK 500/BI500 with a 38 kHz transducer mounted on a towed body as weIl as a 120 kHz hull mounted transducer were used. Fish densities were measured synchronously as well as under the ship as at a laterally distances from the ship by the transducer of the towed body. By these means the variation of fish densities up to a certain distance from the ship is possible. The advantage of using an echo integrating system for these measurements is, that it works also for not schooling fish and under conditions where schooling fish disperse (e.g. at night).