Searcharxiv⌕ Search

arXiv subjects

Anurag Kumar

Publications and source records attributed to Anurag Kumar.

At least 109 records · Page 6Linked to original sources
arXiv2016

Audio Event Detection using Weakly Labeled Data

Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data. However, the labels available for majority of multimedia data are generally weak and do not provide sufficient detail for such methods to be employed. In this paper we propose a framework for learning acoustic event detectors using only weakly labeled data. We first show that audio event detection using weak labels can be formulated as an Multiple Instance Learning problem. We then suggest two frameworks for solving multiple-instance learning, one based on support vector machines, and the other on neural networks. The proposed methods can help in removing the time consuming and expensive process of manually annotating data to facilitate fully supervised learning. Moreover, it can not only detect events in a recording but can also provide temporal locations of events in the recording. This helps in obtaining a complete description of the recording and is notable since temporal information was never known in the first place in weakly labeled data.

cs.SD↗
arXiv2016

Weakly Supervised Scalable Audio Content Analysis

Audio Event Detection is an important task for content analysis of multimedia data. Most of the current works on detection of audio events is driven through supervised learning approaches. We propose a weakly supervised learning framework which can make use of the tremendous amount of web multimedia data with significantly reduced annotation effort and expense. Specifically, we use several multiple instance learning algorithms to show that audio event detection through weak labels is feasible. We also propose a novel scalable multiple instance learning algorithm and show that its competitive with other multiple instance learning algorithms for audio event detection tasks.

cs.SD↗
arXiv2016

Speech Enhancement In Multiple-Noise Conditions using Deep Neural Networks

In this paper we consider the problem of speech enhancement in real-world like conditions where multiple noises can simultaneously corrupt speech. Most of the current literature on speech enhancement focus primarily on presence of single noise in corrupted speech which is far from real-world environments. Specifically, we deal with improving speech quality in office environment where multiple stationary as well as non-stationary noises can be simultaneously present in speech. We propose several strategies based on Deep Neural Networks (DNN) for speech enhancement in these scenarios. We also investigate a DNN training strategy based on psychoacoustic models from speech coding for enhancement of noisy speech

cs.SD↗
arXiv2015

Competitive Selection of Ephemeral Relays in Wireless Networks

We consider a setting in which two nodes (referred to as forwarders) compete to choose a relay node from a set of relays, as they ephemerally become available (e.g., wake up from a sleep state). Each relay, when it arrives, offers a (possibly different) "reward" to each forwarder. Each forwarder's objective is to minimize a combination of the delay incurred in choosing a relay and the reward offered by the chosen relay. As an example, we develop the reward structure for the specific problem of geographical forwarding over a network of sleep-wake cycling relays. We study two variants of the generic relay selection problem, namely, the completely observable (CO) case where, when a relay arrives, both forwarders get to observe both rewards, and the partially observable (PO) case where each forwarder can only observe its own reward. Formulating the problem as a two person stochastic game, we characterize solution in terms of Nash Equilibrium Policy Pairs (NEPPs). For the CO case we provide a general structure of the NEPPs. For the PO case we prove that there exists an NEPP within the class of threshold policy pairs. We then consider the particular application of geographical forwarding of packets in a shared network of sleep-wake cycling wireless relays. For this problem, for a particular reward structure, using realistic parameter values corresponding to TelosB wireless mote, we numerically compare the performance (in terms of cost to both forwarders) of the various NEPPs and draw the following key insight: even for moderate separation between the two forwarders, the performance of the various NEPPs is close to the performance of a simple strategy where each forwarder behaves as if the other forwarder is not present. We also conduct simulation experiments to study the end-to-end performance of the simple forwarding policy.

cs.NI↗
arXiv2015

An Approximate Inner Bound to the QoS Aware Throughput Region of a Tree Network under IEEE 802.15.4 CSMA/CA and Application to Wireless Sensor Network Design

We consider a tree network spanning a set of source nodes that generate measurement packets, a set of additional relay nodes that only forward packets from the sources, and a data sink. We assume that the paths from the sources to the sink have bounded hop count. We assume that the nodes use the IEEE 802.15.4 CSMA/CA for medium access control, and that there are no hidden terminals. In this setting, starting with a set of simple fixed point equations, we derive sufficient conditions for the tree network to approximately satisfy certain given QoS targets such as end-to-end delivery probability and delay under a given rate of generation of measurement packets at the sources (arrival rates vector). The structures of our sufficient conditions provide insight on the dependence of the network performance on the arrival rate vector, and the topological properties of the network. Furthermore, for the special case of equal arrival rates, default backoff parameters, and for a range of values of target QoS, we show that among all path-length-bounded trees (spanning a given set of sources and BS) that meet the sufficient conditions, a shortest path tree achieves the maximum throughput.

cs.NI↗
arXiv2015

Unsupervised Fusion Weight Learning in Multiple Classifier Systems

In this paper we present an unsupervised method to learn the weights with which the scores of multiple classifiers must be combined in classifier fusion settings. We also introduce a novel metric for ranking instances based on an index which depends upon the rank of weighted scores of test points among the weighted scores of training points. We show that the optimized index can be used for computing measures such as average precision. Unlike most classifier fusion methods where a single weight is learned to weigh all examples our method learns instance-specific weights. The problem is formulated as learning the weight which maximizes a clarity index; subsequently the index itself and the learned weights both are used separately to rank all the test points. Our method gives an unsupervised method of optimizing performance on actual test data, unlike the well known stacking-based methods where optimization is done over a labeled training set. Moreover, we show that our method is tolerant to noisy classifiers and can be used for selecting N-best classifiers.

cs.LG↗
arXiv2014

SmartConnect: A System for the Design and Deployment of Wireless Sensor Networks

We have developed SmartConnect, a tool that addresses the growing need for the design and deployment of multihop wireless relay networks for connecting sensors to a control center. Given the locations of the sensors, the traffic that each sensor generates, the quality of service (QoS) requirements, and the potential locations at which relays can be placed, SmartConnect helps design and deploy a low- cost wireless multihop relay network. SmartConnect adopts a field interactive, iterative approach, with model based network design, field evaluation and relay augmentation per- formed iteratively until the desired QoS is met. The design process is based on approximate combinatorial optimization algorithms. In the paper, we provide the design choices made in SmartConnect and describe the experimental work that led to these choices. We provide results from some experimental deployments. Finally, we conduct an experimental study of the robustness of the network design over long time periods (as channel conditions slowly change), in terms of the relay augmentation and route adaptation required.

cs.NI↗
arXiv2014

Impromptu Deployment of Wireless Relay Networks: Experiences Along a Forest Trail

We are motivated by the problem of impromptu or as- you-go deployment of wireless sensor networks. As an application example, a person, starting from a sink node, walks along a forest trail, makes link quality measurements (with the previously placed nodes) at equally spaced locations, and deploys relays at some of these locations, so as to connect a sensor placed at some a priori unknown point on the trail with the sink node. In this paper, we report our experimental experiences with some as-you-go deployment algorithms. Two algorithms are based on Markov decision process (MDP) formulations; these require a radio propagation model. We also study purely measurement based strategies: one heuristic that is motivated by our MDP formulations, one asymptotically optimal learning algorithm, and one inspired by a popular heuristic. We extract a statistical model of the propagation along a forest trail from raw measurement data, implement the algorithms experimentally in the forest, and compare them. The results provide useful insights regarding the choice of the deployment algorithm and its parameters, and also demonstrate the necessity of a proper theoretical formulation.

cs.NI↗
arXiv2014

A Fast and Accurate Performance Analysis of Beaconless IEEE 802.15.4 Multi-Hop Networks

We develop an approximate analytical technique for evaluating the performance of multi-hop networks based on beaconless IEEE 802.15.4, a popular standard for wireless sensor networks. The network comprises sensor nodes, which generate measurement packets, relay nodes which only forward packets, and a data sink (base station). We consider a detailed stochastic process at each node, and analyse this process taking into account the interaction with neighboring nodes via certain time averaged unknown variables (e.g., channel sensing rates, collision probabilities, etc.). By coupling the analyses at various nodes, we obtain fixed point equations that can be solved numerically to obtain the unknown variables, thereby yielding approximations of time average performance measures, such as packet discard probabilities and average queueing delays. The model incorporates packet generation at the sensor nodes and queues at the sensor nodes and relay nodes. We demonstrate the accuracy of our model by an extensive comparison with simulations. As an additional assessment of the accuracy of the model, we utilize it in an algorithm for sensor network design with quality-of-service (QoS) objectives, and show that designs obtained using our model actually satisfy the QoS constraints (as validated by simulating the networks), and the predictions are accurate to well within 10% as compared to the simulation results.

cs.NI↗
arXiv2014

Influence Spread in Social Networks: A Study via a Fluid Limit of the Linear Threshold Model

Threshold based models have been widely used in characterizing collective behavior on social networks. An individual's threshold indicates the minimum level of influence that must be exerted, by other members of the population engaged in some activity, before the individual will join the activity. In this work, we begin with a homogeneous version of the Linear Threshold model proposed by Kempe et al. in the context of viral marketing, and generalize this model to arbitrary threshold distributions. We show that the evolution can be modeled as a discrete time Markov chain, and, by using a certain scaling, we obtain a fluid limit that provides an ordinary differential equation model (o.d.e.). We find that the threshold distribution appears in the o.d.e. via its hazard rate function. We demonstrate the accuracy of the o.d.e. approximation and derive explicit expressions for the trajectory of influence under the uniform threshold distribution. Also, for an exponentially distributed threshold, we show that the fluid dynamics are equivalent to the well-known SIR model in epidemiology. We also numerically study how other hazard functions (obtained from the Weibull and loglogistic distributions) provide qualitative different characteristics of the influence evolution, compared to traditional epidemic models, even in a homogeneous setting. We finally show how the model can be extended to a setting with multiple communities and conclude with possible future directions.

cs.SI↗
arXiv2014

QoS Aware and Survivable Network Design for Planned Wireless Sensor Networks

We study the problem of wireless sensor network design by deploying a minimum number of additional relay nodes (to minimize network cost) at a subset of given potential relay locations, in order to convey the data from already existing sensor nodes (hereafter called source nodes) to a Base Station, while meeting a certain specified hop count bound (the hop count bound is chosen to ensure a pre-determined probability of the data being delivered to the BS within a given maximum delay). We study two variations of the problem. First we sudy the problem of guaranteed QoS connected network design, where the objective is to have at least one path from each source to the BS with the specified hop count bound. We show that the problem is NP-Hard. For a problem in which the number of existing sensor nodes and potential relay locations is n, we propose an O(n) approximation algorithm of polynomial time complexity. Results show that the algorithm performs efficiently (in over 90% of the tested scenarios, it gave solutions that were either optimal or were worse than optimal by just one relay) in various randomly generated network scenarios. Next, we study the problem of survivable network design with guaranteed QoS, i.e, the requirement is to have at least k > 1 node disjoint hop constrained paths from each source to the BS. We show that the problem is NP-Hard. We also show that the problem of finding a feasible solution to this optimization problem is NP-Complete. We propose two polynomial time heuristics for this problem, and compare their performance on various randomly generated network scenarios.

cs.NI↗
arXiv2014

QoS Constrained Optimal Sink and Relay Placement in Planned Wireless Sensor Networks

We are given a set of sensors at given locations, a set of potential locations for placing base stations (BSs, or sinks), and another set of potential locations for placing wireless relay nodes. There is a cost for placing a BS and a cost for placing a relay. The problem we consider is to select a set of BS locations, a set of relay locations, and an association of sensor nodes with the selected BS locations, so that number of hops in the path from each sensor to its BS is bounded by hmax, and among all such feasible networks, the cost of the selected network is the minimum. The hop count bound suffices to ensure a certain probability of the data being delivered to the BS within a given maximum delay under a light traffic model. We observe that the problem is NP-Hard, and is hard to even approximate within a constant factor. For this problem, we propose a polynomial time approximation algorithm (SmartSelect) based on a relay placement algorithm proposed in our earlier work, along with a modification of the greedy algorithm for weighted set cover. We have analyzed the worst case approximation guarantee for this algorithm. We have also proposed a polynomial time heuristic to improve upon the solution provided by SmartSelect. Our numerical results demonstrate that the algorithms provide good quality solutions using very little computation time in various randomly generated network scenarios.

cs.NI↗
arXiv2013

Relay Selection with Channel Probing in Sleep-Wake Cycling Wireless Sensor Networks

In geographical forwarding of packets in a large wireless sensor network (WSN) with sleep-wake cycling nodes, we are interested in the local decision problem faced by a node that has custody of a packet and has to choose one among a set of next-hop relay nodes to forward the packet towards the sink. Each relay is associated with a reward that summarizes the benefit of forwarding the packet through that relay. We seek a solution to this local problem, the idea being that such a solution, if adopted by every node, could provide a reasonable heuristic for the end-to-end forwarding problem. Towards this end, we propose a relay selection problem comprising a forwarding node and a collection of relay nodes, with the relays waking up sequentially at random times. At each relay wake-up instant the forwarder can choose to probe a relay to learn its reward value, based on which the forwarder can then decide whether to stop (and forward its packet to the chosen relay) or to continue to wait for further relays to wake-up. The forwarder's objective is to select a relay so as to minimize a combination of waiting-delay, reward and probing cost. Our problem can be considered as a variant of the asset selling problem studied in the operations research literature. We formulate our relay selection problem as a Markov decision process (MDP) and obtain some interesting structural results on the optimal policy (namely, the threshold and the stage-independence properties). We also conduct simulation experiments and gain valuable insights into the performance of our local forwarding-solution.

cs.NI↗
arXiv2013

As-You-Go Deployment of a Wireless Network with On-Line Measurements and Backtracking

We are motivated by the need, in some applications, for impromptu or as-you-go deployment of wireless sensor networks. A person walks along a line, making link quality measurements with the previous relay at equally spaced locations, and deploys relays at some of these locations, so as to connect a sensor placed on the line with a sink at the start of the line. In this paper, we extend our earlier work on the problem (see [1]) to incorporate two new aspects: (i) inclusion of path outage in the deployment objective, and (ii) permitting the deployment agent to make measurements over several consecutive steps before selecting a placement location among them (which we call backtracking). We consider a light traffic regime, and formulate the problem as a Markov decision process. Placement algorithms are obtained for two cases: (i) the distance to the source is geometrically distributed with known mean, and (ii) the average cost per step case. We motivate the per-step cost function in terms of several known forwarding protocols for sleep-wake cycling wireless sensor networks. We obtain the structures of the optimal policies for the various formulations, and provide some sensitivity results about the policies and the optimal values. We then provide a numerical study of the algorithms, thus providing insights into the advantage of backtracking, and a comparison with simple heuristic placement policies.

cs.NI↗
arXiv2013

Cell-Level Modeling of IEEE 802.11 WLANs

We develop a scalable \textit{cell-level} analytical model for multi-cell infrastructure IEEE 802.11 WLANs under a so-called Pairwise Binary Dependence (PBD) condition. The PBD condition is a geometric property under which the relative locations of the nodes inside a cell do not matter and the network is free of \textit{hidden nodes}. For the cases of saturated nodes and TCP-controlled long-file downloads, we provide accurate predictions of cell throughputs. Similar to Bonald et al (Sigmetrics, 2008), we model a multi-cell WLAN under short-file downloads as "a network of processor-sharing queues with state-dependent service rates." Whereas the state-dependent service rates proposed by Bonald et al are based only on the \textit{number} of contending neighbors, we employ state-dependent service rates that incorporate the the impact of the overall \textit{topology} of the network. We propose an \textit{effective service rate approximation} technique and obtain good approximations for the \textit{mean flow transfer delay} in each cell. For TCP-controlled downloads where the APs transmit a large fraction of time, we show that the throughputs predicted under the PBD condition are very good approximations in two important scenarios where hidden nodes are indeed present and the PBD condition does not strictly hold.

cs.NI↗
arXiv2013

Optimal Capacity Relay Node Placement in a Multi-hop Wireless Network on a Line

We use information theoretic achievable rate formulas for the multi-relay channel to study the problem of optimal placement of relay nodes along the straight line joining a source node and a sink node. The achievable rate formulas that we use are for full-duplex radios at the relays and decode- and-forward relaying. For the single relay case, and individual power constraints at the source node and the relay node, we provide explicit formulas for the optimal relay location and the optimal power allocation to the source-relay channel, for the exponential and the power-law path-loss channel models. For the multiple relay case, we consider exponential path-loss and a total power constraint over the source and the relays, and derive an optimization problem, the solution of which provides the optimal relay locations. Numerical results suggest that at low attenuation the relays are mostly clustered close to the source in order to be able to cooperate among themselves, whereas at high attenuation they are uniformly placed and work as repeaters. The structure of the optimal power allocation for a given placement of the nodes, then motivates us to formulate the problem of impromptu ("as-you-go") placement of relays along a line of exponentially distributed length, with exponential path- loss, so as to minimize a cost function that is additive over hops. The hop cost trades off a capacity limiting term, motivated from the optimal power allocation solution, against the cost of adding a relay node. We formulate the problem as a total cost Markov decision process, for which we prove results for the value function, and provide insights into the placement policy via numerical exploration.

cs.NI↗
arXiv2013

Measurement Based Impromptu Deployment of a Multi-Hop Wireless Relay Network

We study the problem of optimal sequential ("as-you-go") deployment of wireless relay nodes as a person walks along a line of random length (with a known distribution). The objective is to create an impromptu multihop wireless network for connecting a packet source to be placed at the end of the line with a sink node located at the starting point, to operate in the light traffic regime. As the deployment person walks along the line from the sink towards the source, at every step, he measures the channel quality to one (or more) previously placed relays, and places the relay nodes based on these measurements, so as to minimize either the sum power or the maximum power from the source to the sink node in the resultant network, subject to a constraint on the expected number of relays placed. For each of these two objectives, two different relay selection strategies are considered: (i) each relay communicates with the sink via its immediate previous relay, (ii) the communication path can skip some of the deployed relays. With appropriate modeling assumptions, we formulate each of these problems as a Markov decision process (MDP). We provide the optimal policy structures for all these cases, and provide illustrations, via numerical results, for some typical parameters.

cs.NI↗