Games of skill are an excellent source of recreation, entertainment and relaxation. However when these games are played with real money, the important facet of responsible game play must be addressed rigorously and efficiently by game providers. Ensuring game prudence, whereby users play real-money skill games only for entertainment purposes, and do so well within their resourceful means, necessary for the wellness of players, and also for the sustained engagement and retention of players in the system. To this end, in this work we present a deep learning model that helps identify players who are on the verge of displaying irresponsible or addictive game play in a fully unsupervised manner. We use a combination of long short-term memory and adversarial auto-encoder networks to analyze game play along three tell-tale dimensions of immoderation, namely, money, time and despair. Our model provides a state of the art solution for identifying a precise set of problem gamers in skill-based cash games well ahead of time, effectively addressing the challenges of (i) extreme class imbalance, (ii) sparse and incomplete ground truth, (iii) overlapping behavioral patterns between risky and non-risky but highly engaged players.

We present a deep learning framework for game action modeling, which enables fine-grained analyses of player behavior. We develop CNN-based supervised models that effectively learn the critical game play decisions from skilled players, and use these models to assess player characteristics in the system, such as their retention, engagement, deposit buckets, etc. We show that with a carefully constructed input format, that efficiently represents the game state and history as a multi-dimensional image, along with a custom architecture the model learns the strategies of the game accurately. It is further enhanced with look-ahead achieved by self-play simulation to better estimate the game state, and this information is used in a new loss function. Next, we show that analyzing the players with these models as reference has immense benefit in understanding player potential in terms of engagement and revenue. We also use the model to understand the various contexts under which players tend to make mistakes, and use these insights to up-skill players.

Making design choices for big data systems is not trivial. If not planned out efficiently, keeping in mind the practical requirements, there's a possibility that the deployed system can lack important features to match up the application or it may contain over-sophisticated methods that incurs a large cost, but little increase in the efficiency, output. To equip the end user towards wise design choices, we have proposed a decision support framework for big data systems that can evaluate the suitability over numerous design combinations and outputs the one most efficient for the end-user requirement.

Mining and profiling intent of players is an important facet in today's online games for the gaming companies to take targeted actions and provide personalized services. While analyzing and predicting player behavior have been studied in the online gaming domain, investigating intent behind those behaviors from the data has not been studied. We introduce the problem of player intent mining. With the example of online Rummy, a popular card game in India, we show how specific behavior aspects of player over time plays a key role in identifying their intent. Through both supervised and unsupervised techniques we achieve reasonable accuracy in identifying the intent.

We investigate the possibility of using a combination of a smartphone and a smartwatch, carried by a shopper, to get insights into the shopper's behavior inside a retail store. The proposed IRIS framework uses standard locomotive and gestural micro-activities as building blocks to define novel composite features that help classify different facets of a shopper's interaction/experience with individual items, as well as attributes of the overall shopping episode or the store. Besides defining such novel features, IRIS builds a novel segmentation algorithm, which partitions the duration of an entire shopping episode into atomic item-level interactions, by using a combination of feature-based landmarking, change point detection and variable-order HMM-based sequence prediction. Experiments with 50 real-life grocery shopping episodes, collected from 25 shoppers, we show that IRIS can demarcate item-level interactions with an accuracy of approx. 91%, and subsequently characterize item-and-episode level shopper behavior with accuracies of over 90%.

In-network Processing, involving operations such as filtering, compression, and fusion is a technique widely used in wireless sensor and ad hoc networks for reducing the communication overhead. In many tactical stream-oriented applications, especially in military scenarios, both link bandwidth and node energy are critically constrained resources. For such applications, in-network processing itself imposes nonnegligible computing cost. In this work, we have developed a unified, utility-based closed-loop control framework that permits distributed convergence to both 1) the optimal level of compression performed by a forwarding node on streams, and 2) the best set of nodes where the operators of the stream processing graph should be deployed. We also show how the generalized model can be adapted to more realistic cases, where the in-network operator may be varied only in discrete steps, and where a fusion operation cannot be fractionally distributed across multiple nodes. Finally, we provide a real-time implementation of the protocol on an 802.11b network with a video application and show that the performance of the network is improved significantly in terms of the packet loss, node lifetime, and quality of video received.

Both bandwidth and energy become important resource constraints when multihop wireless networks are used to transport high-data-rate traffic for a moderately long duration. In such networks, it is important to control the traffic rates to not only conform to the link capacity bounds, but also to ensure that the energy of battery-powered forwarding nodes is utilized judiciously to avoid premature exhaustion (i.e., the network lasts as long as the applications require data from the sources) without being unnecessarily conservative (i.e., ensuring that the applications derive the maximum utility possible). Unlike prior work that focuses on the instantaneous distributed optimization of such networks, we consider the more challenging question of how such optimal usage of both link capacity and node energy may be achieved over a time horizon. Our key contributions are twofold. We first show how the formalism of optimal control may be used to derive optimal resource usage strategies over a time horizon, under a variety of both deterministic and statistically uncertain variations in various parameters, such as the duration for which individual applications are active or the time-varying recharge characteristics of renewable energy sources (e.g., solar cell batteries). In parallel, we also demonstrate that these optimal adaptations can be embedded, with acceptably low signaling overhead, into a distributed, utility-based rate adaptation protocol. Simulation studies, based on a combination of synthetic and real data traces, validate the close-to-optimal performance characteristics of these practically realizable protocols.

This article develops a utility-based optimization framework for resource sharing by multiple competing missions in a mission-oriented wireless sensor network (WSN) environment. Prior work on network utility maximization (NUM) based optimization has focused on unicast flows with sender-based utilities in either wireline or wireless networks. In this work, we develop a generalized NUM model to consider three key new features observed in mission-centric WSN environments: i) the definition of the utility of an individual mission (receiver) as a joint function of data from multiple sensor sources; ii) the consumption of each sender's (sensor) data by multiple missions; and iii) the multicast-tree-based dissemination of each sensor's data flow, using link-layer broadcasts to exploit the “wireless broadcast advantage” in data forwarding. We show how a price-based, distributed protocol (WSN-NUM) can ensure optimal and proportionally fair rate allocation across multiple missions, without requiring any coordination among missions or sensors. We also discuss techniques to improve the speed of convergence of the protocol, which is essential in an environment as dynamic as the WSN. Further, we analyze the impact of various network and protocol parameters on the bandwidth utilization of the network, using a discrete-event simulation of a stationary wireless network. Finally, we corroborate our simulation-based performance results of the WSN-NUM protocol with an implementation of an 802.11b network.

In this paper we propose an end-to-end algorithm, called NUM-RS, for jointly selecting link transmission rates and source rates in a multi-hop multi-rate wireless network. Prior works on rate selection, including those that explicitly account for opportunistic reception, perform rate selection on a hop-by-hop basis, attempting to maximize the throughput on each link. Our algorithm leverages the Network Utility Maximization (NUM) framework, thus providing end-to-end semantics for rate selection and proportional fairness with low overhead. By using end-to-end semantics NUM-RS considers both source rates and congestion in the vicinity of links used by a flow when selecting link rates. Our results show that NUM-RS increasingly outperforms contemporary hop-by-hop rate selection schemes as the number of hops in the flows increase. For example, 20% and 50% of 8-hop flows exhibit performance gains of at least 36% and 15%, respectively, in terms of end-to-end throughput. In some cases, gains of up to 80% can be achieved.

In recent years, utility-oriented resource allocation for wired and wireless networks has been extensively studied. A key goal of utility based analysis is to provide evaluation criteria for efficient network operation based on subjective user assessments such as usefulness and value of data. Yet the vast majority of the prior work has focused on topics like mathematical functions (concave or otherwise) of network metrics such as bandwidth, delay, packet loss, etc., or information entropy, or user-perceived quality (e.g., MOS) for interpreting utility. In this work1, we propose an alternative mission-oriented definition and metric for utility that is based on the accuracy and speed at which tasks are completed, which we believe is closer to the intent of utility-based analysis. Like previous work, our definition supports the design and engineering of networks by mapping utility metrics to the typical network design metrics (bandwidth, delay, loss, etc). Unlike previous work, it also permits simple solutions to important questions such as the joint utility or usefulness of different data streams, the impact on the utility of one data stream by another, and cross-sensory utility (e.g., the impact of a side audio channel on an image processing task, or a side video channel on an audio processing task). We present a novel experimental approach to the design of such experiments, and provide measurement results. The results quantify the effects of information encoding and the impairments incurred during transmission through imperfect networks on the information's usefulness to end-users in terms of being able to complete tasks correctly and on time.

Both bandwidth and energy become important resource constraints when multi-hop wireless networks are used to transport relatively high data rate sensor flows. A particularly challenging problem involves the selection of flow data rates that maximize application (or mission) utilities over a time horizon, especially when different missions are active over different time intervals. Prior works on utility driven adaptation of flow data rates typically focus only on instantaneous utility maximization and are unable to address this temporal variation in mission durations. In this work, we derive an optimal control-based Network Utility Maximization (NUM) framework that is able to maximize the system utility over a lifetime that is known either deterministically or statistically. We first consider a static setup in which all the missions are continuously active for a deterministic duration, and show how the rates can be optimally adapted, via a distributed protocol, to maximize the total utility. Next, we develop adaptive protocols for the dynamic cases when we have (i) complete knowledge about the mission utilities and their arrivals and departures, and (ii) a varying amount of statistical information about the missions. Our simulation results indicate that our protocols are robust, efficient and close to the optimal.

This paper extends the distributed network utility maximization (NUM) framework to consider the case of resource sharing by multiple competing missions in a military-centric wireless sensor network (WSN) environment. Prior work on NUM-based optimization has considered unicast flows with sender-based utilities in either wireline or wireless networks. We extend the NUM framework to consider three key new features observed in mission-centric WSN environments: i) the definition of an individual mission's utility as a joint function of data from multiple sensor sources ii) the consumption of each senders (sensor) data by multiple receivers (missions) and iii) the multicast-tree based dissemination of each sensors data flow, using link-layer broadcasts to exploit the "wireless broadcast advantage" in data forwarding. We show how a receiver-centric, pricing-based, decentralized algorithm can ensure optimal and proportionally-fair rate allocation across the multiple missions, without requiring any coordination among independent missions (or sensors). We also discuss techniques to improve the speed of convergence of the protocol, which is essential in an environment as dynamic as the WSN.

Numerous Grid workflow engines exist, each generally specialized for a single application domain such as protein folding. Although the underlying purpose and functionality of the Grid workflow engines are similar, and they make use of a common set of Grid protocols, the implementations vary vastly, making interoperation among them nearly impossible. On the other hand, the concept of workflows of Web services is very popular in the enterprise domain and many engines exist for business workflows. These mostly revolve around the Business Process Execution Language (BPEL), an emerging standard for Web services workflow description. We study three different business workflow engines - Microsoft's BizTalk Server, Microsoft's Windows Workflow Foundation and Oracle's Business Process Manager and analyze how each of these engines can be adapted to e-science and the Grid environment. We have implemented widely-used grid workflows on each of these engines and show quantitatively and qualitatively that each business engine has positive and negative aspects for large-scale e-science.