Results 1  10
of
49
MULTIARMED BANDIT PROBLEMS
"... Multiarmed bandit (MAB) problems are a class of sequential resource allocation problems concerned with allocating one or more resources among several alternative (competing) projects. Such problems are paradigms of a fundamental conflict between making decisions (allocating resources) that yield ..."
Abstract

Cited by 16 (0 self)
 Add to MetaCart
Multiarmed bandit (MAB) problems are a class of sequential resource allocation problems concerned with allocating one or more resources among several alternative (competing) projects. Such problems are paradigms of a fundamental conflict between making decisions (allocating resources) that yield
USING DIRECTED INFORMATION TO BUILD BIOLOGICALLY RELEVANT INFLUENCE NETWORKS
"... The systematic inference of biologically relevant influence networks remains a challenging problem in computational biology. Even though the availability of highthroughput data has enabled the use of probabilistic models to infer the plausible structure of such networks, their true interpretation o ..."
Abstract

Cited by 13 (0 self)
 Add to MetaCart
The systematic inference of biologically relevant influence networks remains a challenging problem in computational biology. Even though the availability of highthroughput data has enabled the use of probabilistic models to infer the plausible structure of such networks, their true interpretation of the biology of the process is questionable. In this work, we propose a network inference methodology, based on the directed information (DTI) criterion, which incorporates the biology of transcription within the framework, so as to enable experimentally verifiable inference. We use publicly available embryonic kidney and Tcell microarray datasets to demonstrate our results. We present two variants of network inference via DTI (supervised and unsupervised) and the inferred networks relevant to mammalian nephrogenesis as well as Tcell activation. Conformity of the obtained interactions with literature as well as comparison with the coefficient of determination (CoD) method is demonstrated. Apart from network inference, the proposed framework enables the exploration of specific interactions, not just those revealed by data. To illustrate the latter point, a DTI based framework to resolve interactions between transcription factor modules and target coregulated genes is proposed. Additionally, we show that DTI can be used in conjunction with mutual information to infer higherorder influence networks involving cooperative gene interactions.
MonteCarloBased Partially Observable Markov Decision Process Approximations for Adaptive Sensing
"... Abstract — Adaptive sensing involves actively managing sensor resources to achieve a sensing task, such as object detection, classification, and tracking, and represents a promising direction for new applications of discrete event system methods. We describe an approach to adaptive sensing based on ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
Abstract — Adaptive sensing involves actively managing sensor resources to achieve a sensing task, such as object detection, classification, and tracking, and represents a promising direction for new applications of discrete event system methods. We describe an approach to adaptive sensing based on approximately solving a partially observable Markov decision process (POMDP) formulation of the problem. Such approximations are necessary because of the very large state space involved in practical adaptive sensing problems, precluding exact computation of optimal solutions. We review the theory of POMDPs and show how the theory applies to adaptive sensing problems. We then describe MonteCarlobased approximation methods, with an example to illustrate their application in adaptive sensing. The example also demonstrates the gains that are possible from nonmyopic methods relative to myopic methods. I.
A Geometric Optimization Approach to Tracking Maneuvering Targets Using a Heterogeneous Mobile Sensor Network
"... Abstract—A methodology is developed to deploy a mobile sensor network for the purpose of detecting and capturing mobile targets in the plane. The mobile sensor network consists of a set of heterogeneous robotic sensors modeled as hybrid systems with individual processing capabilities. The targets ar ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
Abstract—A methodology is developed to deploy a mobile sensor network for the purpose of detecting and capturing mobile targets in the plane. The mobile sensor network consists of a set of heterogeneous robotic sensors modeled as hybrid systems with individual processing capabilities. The targets are modeled by a Markov motion process that is commonly used in target tracking applications. Since the sensors are installed on mobile robots and have limited range, the geometry of their platforms and fieldsofview play a critical role in motion planning and obstacle avoidance. The methodology presented in this paper uses line transversals and cell decomposition in order to compute sensing and pursuit strategies that maximize the probability of detection, while minimizing energy consumption. The approach is demonstrated through progressive simulation scenarios involving multiple sensors installed on UGVs and UAVs, that are characterized by different sensing and motion capabilities, but are deployed to cooperatively detect, track, and pursue the same set of maneuvering targets. I.
A Novel TCP with Dynamic BurstContention Loss Notification over OBS
 Networks”, Elservier Journal of Computer Networks
, 2008
"... Abstract — In this paper, a novel congestioncontrol scheme with dynamic BurstContention Loss notifications in Optical Burst Switching (OBS) networks is proposed. The proposed scheme, called TCPBCL, aims to handle various OBS bursty conditions that negatively affect TCP throughput performance and ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
(Show Context)
Abstract — In this paper, a novel congestioncontrol scheme with dynamic BurstContention Loss notifications in Optical Burst Switching (OBS) networks is proposed. The proposed scheme, called TCPBCL, aims to handle various OBS bursty conditions that negatively affect TCP throughput performance and fairness. The basic design principle of the scheme is to tune the congestioncontrol parameters α and β such that the congestion window sizes in the corresponding TCP senders can be adjusted with an explicit notification from the OBS edge node. The performance impact on TCP in terms of burst dropping due to random contention, which is also known as false congestion detection is considered and investigated. An analytical model is developed and further verified through extensive simulation.
Constraint Reasoning with Uncertain Data Using CDFIntervals
 Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems
, 2010
"... Abstract. Interval coefficients have been introduced in OR and CP to specify uncertain data in order to provide reliable solutions to convex models. The output is generally a solution set, guaranteed to contain all solutions possible under any realization of the data. This set can be too large to be ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
Abstract. Interval coefficients have been introduced in OR and CP to specify uncertain data in order to provide reliable solutions to convex models. The output is generally a solution set, guaranteed to contain all solutions possible under any realization of the data. This set can be too large to be meaningful. Furthermore, each solution has equal uncertainty weight, thus does not reflect any possible degree of knowledge about the data. To overcome these problems we propose to extend the notion of interval coefficient by introducing a second dimension to each interval bound. Each bound is now specified by its data value and its degree of knowledge. This is formalized using the cumulative distribution function of the data set. We define the formal framework of constraint reasoning over this cdfintervals. The main contribution of this paper concerns the formal definition of a new interval arithmetic and its implementation. Promising results on problem instances demonstrate the approach. 1
Estimation Error Guarantees for Poisson Denoising with Sparse and Structured Dictionary Models
"... Abstract—Poisson processes are commonly used models for describing discrete arrival phenomena arising, for example, in photonlimited scenarios in lowlight and infrared imaging, astronomy, and nuclear medicine applications. In this context, several recent efforts have evaluated Poisson denoising me ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
Abstract—Poisson processes are commonly used models for describing discrete arrival phenomena arising, for example, in photonlimited scenarios in lowlight and infrared imaging, astronomy, and nuclear medicine applications. In this context, several recent efforts have evaluated Poisson denoising methods that utilize contemporary sparse modeling and dictionary learning techniques designed to exploit and leverage (local) shared structure in the images being estimated. This paper establishes a theoretical foundation for such procedures. Specifically, we formulate sparse and structured dictionarybased Poisson denoising methods as constrained maximum likelihood estimation strategies, and establish performance bounds for their meansquare estimation error using the framework of complexity penalized maximum likelihood analyses. I.
EMACs: Towards More Secure and More Efficient Constructions of Secure Channels
, 2010
"... In cryptography, secure channels enable the confidential and authenticated message exchange between authorized users. A generic approach of constructing such channels is by combining an encryption primitive with an authentication primitive (MAC). In this work, we introduce the design of a new crypt ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
In cryptography, secure channels enable the confidential and authenticated message exchange between authorized users. A generic approach of constructing such channels is by combining an encryption primitive with an authentication primitive (MAC). In this work, we introduce the design of a new cryptographic primitive to be used in the construction of secure channels. Instead of using general purpose MACs, we propose the deployment of special purpose MACs, named EMACs. The main motive behind this work is the observation that, since the message must be both encrypted and authenticated, there might be some redundancy in the computations performed by the two primitives. Therefore, removing such redundancy can improve the efficiency of the overall composition. Moreover, computations performed by the encryption algorithm can be further utilized to improve the security of the authentication algorithm. In particular, we will show how EMACs can be designed to reduce the amount of computation required by standard MACs based on universal hash functions, and show how EMACs can be secured against keyrecovery attacks.
Polarimetric MIMO Radar With Distributed Antennas for Target Detection
"... Abstract—Multipleinput–multipleoutput (MIMO) radar systems with widely separated antennas enable viewing the target from different angles, thereby providing spatial diversity gain. Polarimetric design of the transmit waveforms based on the properties of the target scattering matrix provides bett ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
Abstract—Multipleinput–multipleoutput (MIMO) radar systems with widely separated antennas enable viewing the target from different angles, thereby providing spatial diversity gain. Polarimetric design of the transmit waveforms based on the properties of the target scattering matrix provides better performance than transmitting waveforms with only fixed horizontal or vertical polarizations. We propose a radar system that combines the advantages of both systems by transmitting polarized waveforms from multiple distributed antennas, in order to detect a pointlike stationary target. The proposed system employs 2D vector sensors at the receivers, each of which measures the horizontal and vertical components of the received electric field separately. We design the Neyman–Pearson detector for such systems. We derive approximate expressions for the probability of false alarm and the probability of detection . Using numerical simulations, we demonstrate that optimal design of the antenna polarizations provides improved performance over MIMO systems that transmit waveforms of fixed polarizations over all the antennas. We also demonstrate that having multiple widely separated antennas gives improved performance over singleinput–singleoutput (SISO) polarimetric radar. We also demonstrate that processing the vector measurements at each receiver separately gives improved performance over systems that linearly combine both the received signals to give scalar measurements. Index Terms—Distributed, multipleinput–multipleoutput (MIMO), polarimetric, radar.