Uma Parthavi Moravapalle

Pulsar: improving throughput estimation in enterprise LTE small cells

With the great success of LTE(-A) outdoor, LTE-based small cell technology has become popular and is penetrating indoor enterprise environment, co-existing with WiFi networks, to provide better user experience or Quality-of-Experience (QoE). However, accurate estimation of LTE links is challenging and critical to continue providing QoE for many enterprise applications (e.g., video/audio) and services (network selection). While prior work on LTE link throughput estimation depends mostly on a single factor (e.g., link rate), we argue that it needs to consider more factors to improve the estimation to meet increasing demands on QoE. In this paper, we propose a new metric, called Pulsar (Per-user LTE ShAre of Resources), that estimates per flow throughput in LTE networks by leveraging both underlying channel information and application traffic characteristics. Our extensive evaluation study through ns-3 shows that Pulsar reduces the estimation error more than 92%, compared to prior work, in various scenarios, while keeping estimation overhead low.

Blood Count on a Smartphone Microscope: Challenges

Low-cost lenses with magnifications of 150-200x are being sold in the market today as accessories for mobile smartphones. Attaching these lenses to a smartphone camera creates low-cost, ultra-portable digital microscopes, with a potential for significant impact on applications in a variety of fields such as healthcare, agriculture, education etc. In this paper, we consider a low-cost do-it-yourself Complete Blood Count (CBC) application using a smartphone microscope. We discuss several unique challenges that come up in implementing this application that include preparing the blood sample, correcting the small field of view and blur of the lens, and automating the cell counting procedure. We present our approach to overcome these challenges and report early promising results on counting red blood cells.

Duet: An adaptive algorithm for the coexistence of LTE-U and WiFi in Unlicensed spectrum

LTE in Unlicensed band (LTE-U) has gained intensive attention recently due to its capability to offload mobile data to unlicensed bands. In order to use unlicensed band, LTE-U has to coexist with WiFi - another wireless technology that operates in unlicensed bands. This coexistence is riddled with several challenges as these technologies use different core networks, backhauls and deployment plans. Within this broad paradigm, we present Duet, a Medium Access Control (MAC) layer solution that enables both LTE-U and WiFi nodes to operate fairly and efficiently, with the following properties: (1) no changes in WiFi framework, (2) high performance of LTE-U and WiFi networks within static and dynamic load scenarios, and (3) robustness to fully and partially connected networks. Using ns-3, we simulate Duet in various scenarios and show that Duet can improve the overall network throughput by up to 74%.

Just Do It : Fast and Easy Mobilization of Spot Tasks in Web-based Enterprise Applications

In this paper, we consider the problem of mobilizing Spot Tasks, a special category of workflows within web-based enterprise applications. Spot tasks are simple workflows that can be finished by interacting with only one page of the application. We present Taskr, a do-it-yourself mobilization solution that users, regardless of their skills, can rely on to mobilize their spot tasks in a robust fashion. Taskr uses remote computing with application refactoring to achieve code-less mobilization and allows for flexible mobile delivery wherein users can execute their spot tasks through Twitter, Email or a native mobile app. We implement a prototype of Taskr and show through user studies that it has the potential to reduce task burden significantly.

DejaVu: A case for assisted email replies on smartphones

More email is opened on mobile devices today than on other platforms [1]. At the same time, enterprises are constantly investing in approaches to improve employee productivity. In this paper, we consider the problem of automated information suggestions to assist in reply construction. The basic premise of the work is that a significant portion of the information content of a reply is likely to be present in prior emails. We first show that the premise is valid by analyzing both public and private email datasets. We then present a simple algorithm that relies on inverse document frequency (IDF) and keyword matching to provide relevant suggestions during reply construction. Through prototype evaluations done using the Email datasets, we show that the proposed algorithm has attractive benefits.

Poster: Observe. Patternize. Mimic. : Leveraging Patterns in Mobile-User Behavior for Enterprise Applications

Application Mobilization, or the ability of an enterprise employee to rely on mobile devices such as smartphones and tablets, to continue to perform business workflows even when mobile, is seen as a game changer to improve productivity. However, the practical adoption of enterprise mobility is very much in its in fancy, and seemingly has barriers. We posit that these barriers include heavy user-burden in accomplishing tasks (e.g. number of actions required to execute a workflow), high cost of mobile access (e.g. latency for content fetching), and irrelevance of available mobile functions (e.g. mobile app defeaturization done inappropriately).The novelty of our research is in a unified observe-patternize-mimic paradigm we explore to address these barriers, based on a simple question: could patterns in user-behavior be learned, and leveraged for reducing user-burden? If patterns are discovered, then we show that intelligent mimicking of these patterns at appropriate junctures can considerably relieve the mobile user burden. We motivate this paradigm through three application scenarios representing read, write, and act usage modalities.

Precog: action-based time-shifted prefetching for web applications on mobile devices

Wireless providers today are highly motivated to improve efficiencies of spectrum usage. One approach to achieve this is to shift the load from expensive cellular networks to cheaper WiFi networks. In this context, we propose Precog, an action-based prefetching solution for time-shifted WiFi offloading. We argue that traditional prefetching solutions, that rely on the URLs visited in the past by a user for predicting future access, are ineffective in todays dynamic, interactive, and personalized web. Precog addresses this issue by remembering, not the exact URL accessed in the past, but the actions performed on a particular website. The actions are remembered as interactions with the content layout, which stays consistent over a long period of time. Unlike prior offloading solutions that require concurrent cellular and WiFi connectivity, Precog offloads cellular content over time-shifted WiFi access. We evaluate Precog over both synthetic and real user datasets to demonstrate its benefits.

Peek: A mobile-to-mobile remote computing protocol for smartphones and tablets

A mobile-to-mobile remote computing protocol for smartphones presents a user with the ability to run an application remotely and to interact with it in a responsive way, where I/O updates can be performed midstream and the results can be viewed in real time. Even though several protocols exist for desktop remote computing, we argue that these cannot be applied as-is for mobile-to-mobile remote computing. In this context, we introduce Peek, a remote computing protocol with i) multi-touch support, ii) context association, and iii) multi-modal frame compression. Through implementation on real devices, we show that Peek reduces the time taken to perform actions on a server by 62% on average, compared to Virtual Network Computing (VNC). We also test Peeks multi-modal frame compression, against VNC, on datasets and show that it has the potential to reduce 30% of the bytes sent on the network.