Self Assessment-Based Decision Making for Multiagent Cooperative Search

This paper addresses a search problem with multiple limited capability search agents in a partially connected dynamical networked environment under different information structures. A self assessment-based decision-making scheme for multiple agents is proposed that uses a modified negotiation scheme with low communication overheads. The scheme has attractive features of fast decision-making and scalability to large number of agents without increasing the complexity of the algorithm. Two models of the self assessment schemes are developed to study the effect of increase in information exchange during decision-making. Some analytical results on the maximum number of self assessment cycles, effect of increasing communication range, completeness of the algorithm, lower bound and upper bound on the search time are also obtained. The performance of the various self assessment schemes in terms of total uncertainty reduction in the search region, using different information structures is studied. It is shown that the communication requirement for self assessment scheme is almost half of the negotiation schemes and its performance is close to the optimal solution. Comparisons with different sequential search schemes are also carried out. Note to Practitioners-In the futuristic military and civilian applications such as search and rescue, surveillance, patrol, oil spill, etc., a swarm of UAVs can be deployed to carry out the mission for information collection. These UAVs have limited sensor and communication ranges. In order to enhance the performance of the mission and to complete the mission quickly, cooperation between UAVs is important. Designing cooperative search strategies for multiple UAVs with these constraints is a difficult task. Apart from this, another requirement in the hostile territory is to minimize communication while making decisions. This adds further complexity to the decision-making algorithms. In this paper, a self-assessment-based decision-making scheme, for multiple UAVs performing a search mission, is proposed. The agents make their decisions based on the information acquired through their sensors and by cooperation with neighbors. The complexity of the decision-making scheme is very low. It can arrive at decisions fast with low communication overheads, while accommodating various information structures used for increasing the fidelity of the uncertainty maps. Theoretical results proving completeness of the algorithm and the lower and upper bounds on the search time are also provided.

Experiments on three-dimensional wire-frame object recognition

Some experimental results on the recognition of three-dimensional wire-frame objects are presented. In order to overcome the limitations of a recent model, which employs radial basis functions-based neural networks, we have proposed a hybrid learning system for object recognition, featuring: an optimization strategy (simulated annealing) in order to avoid local minima of an energy functional; and an appropriate choice of centers of the units. Further, in an attempt to achieve improved generalization ability, and to reduce the time for training, we invoke the principle of self-organization which utilises an unsupervised learning algorithm.

Learning polyhedral classifiers using logistic function

In this paper we propose a new algorithm for learning polyhedral classifiers. In contrast to existing methods for learning polyhedral classifier which solve a constrained optimization problem, our method solves an unconstrained optimization problem. Our method is based on a logistic function based model for the posterior probability function. We propose an alternating optimization algorithm, namely, SPLA1 (Single Polyhedral Learning Algorithm1) which maximizes the loglikelihood of the training data to learn the parameters. We also extend our method to make it independent of any user specified parameter (e.g., number of hyperplanes required to form a polyhedral set) in SPLA2. We show the effectiveness of our approach with experiments on various synthetic and real world datasets and compare our approach with a standard decision tree method (OC1) and a constrained optimization based method for learning polyhedral sets.

An Online Actor-Critic Algorithm with Function Approximation for Constrained Markov Decision Processes

We develop an online actor-critic reinforcement learning algorithm with function approximation for a problem of control under inequality constraints. We consider the long-run average cost Markov decision process (MDP) framework in which both the objective and the constraint functions are suitable policy-dependent long-run averages of certain sample path functions. The Lagrange multiplier method is used to handle the inequality constraints. We prove the asymptotic almost sure convergence of our algorithm to a locally optimal solution. We also provide the results of numerical experiments on a problem of routing in a multi-stage queueing network with constraints on long-run average queue lengths. We observe that our algorithm exhibits good performance on this setting and converges to a feasible point.

Reducing convergence times of self-propelled swarms via modified nearest neighbor rules

Vicsek et al. proposed a biologically inspired model of self-propelled particles, which is now commonly referred to as the Vicsek model. Recently, attention has been directed at modifying the Vicsek model so as to improve convergence properties. In this paper, we propose two modification of the Vicsek model which leads to significant improvements in convergence times. The modifications involve an additional term in the heading update rule which depends only on the current or the past states of the particle's neighbors. The variation in convergence properties as the parameters of these modified versions are changed are closely investigated. It is found that in both cases, there exists an optimal value of the parameter which reduces convergence times significantly and the system undergoes a phase transition as the value of the parameter is increased beyond this optimal value. (C) 2012 Elsevier B.V. All rights reserved.

Damage-tolerant design optimization of laminated composite structures using dispersion of ply angles by genetic algorithm

This article aims to obtain damage-tolerant designs with minimum weight for a laminated composite structure using genetic algorithm. Damage tolerance due to impacts in a laminated composite structure is enhanced by dispersing the plies such that too many adjacent plies do not have the same angle. Weight of the structure is minimized and the Tsai-Wu failure criterion is considered for the safe design. Design variables considered are the number of plies and ply orientation. The influence of dispersed ply angles on the weight of the structure for a given loading conditions is studied by varying the angles in the range of 0 degrees-45 degrees, 0 degrees-60 degrees and 0 degrees-90 degrees at intervals of 5 degrees and by using specific ply angles tailored to loading conditions. A comparison study is carried out between the conventional stacking sequence and the stacking sequence with dispersed ply angles for damage-tolerant weight minimization and some useful designs are obtained. Unconventional stacking sequence is more damage tolerant than the conventional stacking sequence is demonstrated by performing a finite element analysis under both tensile as well as compressive loading conditions. Moreover, a new mathematical function called the dispersion function is proposed to measure the dispersion of ply angles in a laminate. The approach for dispersing ply angles to achieve damage tolerance is especially suited for composite material design space which has multiple local minima.

Infinite push: a new support vector ranking algorithm that directly optimizes accuracy at the absolute top of the list

Ranking problems have become increasingly important in machine learning and data mining in recent years, with applications ranging from information retrieval and recommender systems to computational biology and drug discovery. In this paper, we describe a new ranking algorithm that directly maximizes the number of relevant objects retrieved at the absolute top of the list. The algorithm is a support vector style algorithm, but due to the different objective, it no longer leads to a quadratic programming problem. Instead, the dual optimization problem involves l1, ∞ constraints; we solve this dual problem using the recent l1, ∞ projection method of Quattoni et al (2009). Our algorithm can be viewed as an l∞-norm extreme of the lp-norm based algorithm of Rudin (2009) (albeit in a support vector setting rather than a boosting setting); thus we refer to the algorithm as the ‘Infinite Push’. Experiments on real-world data sets confirm the algorithm’s focus on accuracy at the absolute top of the list.

Adaptive power optimization of on-chip SNUCA cache on tiled chip multicore architecture using remap policy

Advances in technology have increased the number of cores and size of caches present on chip multicore platforms(CMPs). As a result, leakage power consumption of on-chip caches has already become a major power consuming component of the memory subsystem. We propose to reduce leakage power consumption in static nonuniform cache architecture(SNUCA) on a tiled CMP by dynamically varying the number of cache slices used and switching off unused cache slices. A cache slice in a tile includes all cache banks present in that tile. Switched-off cache slices are remapped considering the communication costs to reduce cache usage with minimal impact on execution time. This saves leakage power consumption in switched-off L2 cache slices. On an average, there map policy achieves 41% and 49% higher EDP savings compared to static and dynamic NUCA (DNUCA) cache policies on a scalable tiled CMP, respectively.

Polyceptron a polyhedral learning algorithm

In this paper we propose a new algorithm for learning polyhedral classifiers which we call as Polyceptron. It is a Perception like algorithm which updates the parameters only when the current classifier misclassifies any training data. We give both batch and online version of Polyceptron algorithm. Finally we give experimental results to show the effectiveness of our approach.

A h-Adaptive Algorithm Using Residual Error Estimates for Fluid Flows

Algorithms for adaptive mesh refinement using a residual error estimator are proposed for fluid flow problems in a finite volume framework. The residual error estimator, referred to as the R-parameter is used to derive refinement and coarsening criteria for the adaptive algorithms. An adaptive strategy based on the R-parameter is proposed for continuous flows, while a hybrid adaptive algorithm employing a combination of error indicators and the R-parameter is developed for discontinuous flows. Numerical experiments for inviscid and viscous flows on different grid topologies demonstrate the effectiveness of the proposed algorithms on arbitrary polygonal grids.