SaveRF: Towards efficient relevance feedback search

In multimedia retrieval, a query is typically interactively refined towards the ‘optimal’ answers by exploiting user feedback. However, in existing work, in each iteration, the refined query is re-evaluated. This is not only inefficient but fails to exploit the answers that may be common between iterations. In this paper, we introduce a new approach called SaveRF (Save random accesses in Relevance Feedback) for iterative relevance feedback search. SaveRF predicts the potential candidates for the next iteration and maintains this small set for efficient sequential scan. By doing so, repeated candidate accesses can be saved, hence reducing the number of random accesses. In addition, efficient scan on the overlap before the search starts also tightens the search space with smaller pruning radius. We implemented SaveRF and our experimental study on real life data sets show that it can reduce the I/O cost significantly.

Population-based continuous optimization, probabilistic modelling and mean shift

Evolutionary algorithms perform optimization using a population of sample solution points. An interesting development has been to view population-based optimization as the process of evolving an explicit, probabilistic model of the search space. This paper investigates a formal basis for continuous, population-based optimization in terms of a stochastic gradient descent on the Kullback-Leibler divergence between the model probability density and the objective function, represented as an unknown density of assumed form. This leads to an update rule that is related and compared with previous theoretical work, a continuous version of the population-based incremental learning algorithm, and the generalized mean shift clustering framework. Experimental results are presented that demonstrate the dynamics of the new algorithm on a set of simple test problems.

Toward efficient multifeature query processing

In many advanced applications, data are described by multiple high-dimensional features. Moreover, different queries may weight these features differently; some may not even specify all the features. In this paper, we propose our solution to support efficient query processing in these applications. We devise a novel representation that compactly captures f features into two components: The first component is a 2D vector that reflects a distance range ( minimum and maximum values) of the f features with respect to a reference point ( the center of the space) in a metric space and the second component is a bit signature, with two bits per dimension, obtained by analyzing each feature's descending energy histogram. This representation enables two levels of filtering: The first component prunes away points that do not share similar distance ranges, while the bit signature filters away points based on the dimensions of the relevant features. Moreover, the representation facilitates the use of a single index structure to further speed up processing. We employ the classical B+-tree for this purpose. We also propose a KNN search algorithm that exploits the access orders of critical dimensions of highly selective features and partial distances to prune the search space more effectively. Our extensive experiments on both real-life and synthetic data sets show that the proposed solution offers significant performance advantages over sequential scan and retrieval methods using single and multiple VA-files.

Flexible proof reuse for software verification

Proof reuse, or analogical reasoning, involves reusing the proof of a source theorem in the proof of a target conjecture. We have developed a method for proof reuse that is based on the generalisation replay paradigm described in the literature, in which a generalisation of the source proof is replayed to construct the target proof. In this paper, we describe the novel aspects of our method, which include a technique for producing more accurate source proof generalisations (using knowledge of the target goal), as well as a flexible replay strategy that allows the user to set various parameters to control the size and the shape of the search space. Finally, we report on the results of applying this method to a case study from the realm of software verification.

Teleonomic entropy: measuring the phase-space of end-directed systems

We introduce a novel way of measuring the entropy of a set of values undergoing changes. Such a measure becomes useful when analyzing the temporal development of an algorithm designed to numerically update a collection of values such as artificial neural network weights undergoing adjustments during learning. We measure the entropy as a function of the phase-space of the values, i.e. their magnitude and velocity of change, using a method based on the abstract measure of entropy introduced by the philosopher Rudolf Carnap. By constructing a time-dynamic two-dimensional Voronoi diagram using Voronoi cell generators with coordinates of value- and value-velocity (change of magnitude), the entropy becomes a function of the cell areas. We term this measure teleonomic entropy since it can be used to describe changes in any end-directed (teleonomic) system. The usefulness of the method is illustrated when comparing the different approaches of two search algorithms, a learning artificial neural network and a population of discovering agents. (C) 2004 Elsevier Inc. All rights reserved.

A total electron content space weather study of the Nighttime Weddell Sea Anomaly of 1996/97 southern summer with TOPEX/Poseidon radar altimetry

This paper reports on a total electron content space weather study of the nighttime Weddell Sea Anomaly, overlooked by previously published TOPEX/Poseidon climate studies, and of the nighttime ionosphere during the 1996/1997 southern summer. To ascertain the morphology of spatial TEC distribution over the oceans in terms of hourly, geomagnetic, longitudinal and summer-winter variations, the TOPEX TEC, magnetic, and published neutral wind velocity data are utilized. To understand the underlying physical processes, the TEC results are combined with inclination and declination data plus global magnetic field-line maps. To investigate spatial and temporal TEC variations, geographic/magnetic latitudes and local times are computed. As results show, the nighttime Weddell Sea Anomaly is a large (∼1,600(°)2; ∼22 million km2 estimated for a steady ionosphere) space weather feature. Extending between 200°E and 300°E (geographic), it is an ionization enhancement peaking at 50°S–60°S/250°E–270°E and continuing beyond 66°S. It develops where the spacing between the magnetic field lines is wide/medium, easterly declination is large-medium (20°–50°), and inclination is optimum (∼55°S). Its development and hourly variations are closely correlated with wind speed variations. There is a noticeable (∼43%) reduction in its average area during the high magnetic activity period investigated. Southern summer nighttime TECs follow closely the variations of declination and field-line configuration and therefore introduce a longitudinal division of four (Indian, western/eastern Pacific, Atlantic). Northern winter nighttime TECs measured over a limited area are rather uniform longitudinally because of the small declination variation. TOPEX maps depict the expected strong asymmetry in TEC distribution about the magnetic dip equator.

Optimising profitability and environmental trade-offs in managing cropping systems using differential evolution

Whilst traditional optimisation techniques based on mathematical programming techniques are in common use, they suffer from their inability to explore the complexity of decision problems addressed using agricultural system models. In these models, the full decision space is usually very large while the solution space is characterized by many local optima. Methods to search such large decision spaces rely on effective sampling of the problem domain. Nevertheless, problem reduction based on insight into agronomic relations and farming practice is necessary to safeguard computational feasibility. Here, we present a global search approach based on an Evolutionary Algorithm (EA). We introduce a multi-objective evaluation technique within this EA framework, linking the optimisation procedure to the APSIM cropping systems model. The approach addresses the issue of system management when faced with a trade-off between economic and ecological consequences.

Novel array geometries for free-space optical interconnects with improved signal-to-noise ratio

We investigate the effect of transmitter and receiver array configurations on the stray-light and diffraction-caused crosstalk in free-space optical interconnects. The optical system simulation software (Code V) is used to simulate both the stray-light and diffraction-caused crosstalk. Experimentally measured, spectrally-resolved, near-field images of VCSEL higher order modes were used as extended sources in our simulation model. Our results show that by changing the square lattice geometry to a hexagonal configuration, we obtain the reduction in the stray-light crosstalk of up to 9 dB and an overall signal-to-noise ratio improvement of 3 dB.

Genetic algorithm based distance spectrum technique for performance union bound of space-time trellis coded OFDM

This paper derives the performance union bound of space-time trellis codes in orthogonal frequency division multiplexing system (STTC-OFDM) over quasi-static frequency selective fading channels based on the distance spectrum technique. The distance spectrum is the enumeration of the codeword difference measures and their multiplicities by exhausted searching through all the possible error event paths. Exhaustive search approach can be used for low memory order STTC with small frame size. However with moderate memory order STTC and moderate frame size the computational cost of exhaustive search increases exponentially, and may become impractical for high memory order STTCs. This requires advanced computational techniques such as Genetic Algorithms (GAS). In this paper, a GA with sharing function method is used to locate the multiple solutions of the distance spectrum for high memory order STTCs. Simulation evaluates the performance union bound and the complexity comparison of non-GA aided and GA aided distance spectrum techniques. It shows that the union bound give a close performance measure at high signal-to-noise ratio (SNR). It also shows that GA sharing function method based distance spectrum technique requires much less computational time as compared with exhaustive search approach but with satisfactory accuracy.