Venkat Padmanabhan

RadioJockey: mining program execution to optimize cellular radio usage

Many networked applications that run in the background on a mobile device incur significant energy drains when using the cellular radio interface for communication. This is mainly due to the radio-tail, where the cellular radio remaining in a high energy state for up to 20s after each communication spurt. In order to cut down energy consumption, many recent devices employ fast dormancy, a feature that forces the client radio to quickly go into a low energy state after a fixed short idle period. However, aggressive idle timer values for fast dormancy can increase signaling overhead due to frequent state transitions, which negatively impacts the network. In this work, we have designed and implemented RadioJockey, a system that uses program execution traces to predict the end of communication spurts, thereby accurately invoking fast dormancy without increasing network signaling load. We evaluate RadioJockey on a broad range of background applications and show that it achieves 20-40\% energy savings with negligible increase in signaling overhead compared to fixed idle timer-based approaches.

Deja vu: fingerprinting network problems

We ask the question: can network problems experienced by applications be identified based on symptoms contained in a network packet trace? An answer in the affirmative would open the doors to many opportunities, including non-intrusive monitoring of such problems on the network and matching a problem with past instances of the same problem. To this end, we present Deja vu, a tool to condense the manifestation of a network problem into a compact signature, which could then be used to match multiple instances of the same problem. Deja vu uses as input a network-level packet trace of an applications communication and extracts from it a set of features. During the training phase, each application run is manually labeled as GOOD or BAD, depending on whether the run was successful or not. Deja vu then employs a novel learning technique to build a signature tree not only to distinguish between GOOD and BAD runs but to also sub-classify the BAD runs, revealing the different classes of failures. The novelty lies in performing the sub-classification without requiring any failure class-specific labels. We evaluate Deja vu in the context of the multiple web browsers in a corporate environment and an email application in a university environment, with promising results. The signature generated by Deja vu based on the limited GOOD/BAD labels is as effective as one generated using full-blown classification with knowledge of the actual problem types.

CamMirror: Single-Camera-based Distance Estimation for Physical Analytics Applications

Distance estimation is key to many physical analytics applications in settings such as driving, shopping, and more. The goal is to tell where an object or person is. While specialized sensors such LIDAR and stereoscopic cameras can solve the problem, these tend to be expensive. In this paper, we present CamMirror, which performs distance estimation with a single camera. The key idea is to use a pair of carefully-positioned mirrors to provide a second view of the scene akin to what a second camera would have provided, which then enables disparity-based ranging. We present the design of CamMirror and two applications, one on vehicle ranging and the other on smart shelf.

Poster: Improving Road Safety Through Smart-Sensing

Road accidents cause an estimated 1.3 million fatalities each year worldwide. We believe that mobile devices can play a positive role by detecting various driving related events like red light cutting, rash driving and many more. We focus on a specific problem that is responsible for many accidents in India: the stopping behaviour of buses especially in the vicinity of bus stops. We propose a smartphone-based system that specifically seeks to detect and report the following scenarios. 1. Has the bus come to a complete stop(instead of a rolling stop)? 2. Has the bus stopped in the left lane? 3. Has the bus stopped exactly at the bus stop? thus prevent from derailment of trains