Deepak Vasisht

RF-IDraw: virtual touch screen in the air using RF signals

Prior work in RF-based positioning has mainly focused on discovering the absolute location of an RF source, where state-of-the-art systems can achieve an accuracy on the order of tens of centimeters using a large number of antennas. However, many applications in gaming and gesture based interface see more benefits in knowing the detailed shape of a motion. Such trajectory tracing requires a resolution several fold higher than what existing RF-based positioning systems can offer. This paper shows that one can provide a dramatic increase in trajectory tracing accuracy, even with a small number of antennas. The key enabler for our design is a multi-resolution positioning technique that exploits an intrinsic tradeoff between improving the resolution and resolving ambiguity in the location of the RF source. The unique property of this design is its ability to precisely reconstruct the minute details in the trajectory shape, even when the absolute position might have an offset. We built a prototype of our design with commercial off-the-shelf RFID readers and tags and used it to enable a virtual touch screen, which allows a user to interact with a desired computing device by gesturing or writing her commands in the air, where each letter is only a few centimeters wide.

Active learning for sparse bayesian multilabel classification

We study the problem of active learning for multilabel classification. We focus on the real-world scenario where the average number of positive (relevant) labels per data point is small leading to positive label sparsity. Carrying out mutual information based near-optimal active learning in this setting is a challenging task since the computational complexity involved is exponential in the total number of labels. We propose a novel inference algorithm for the sparse Bayesian multilabel model of [17]. The benefit of this alternate inference scheme is that it enables a natural approximation of the mutual information objective. We prove that the approximation leads to an identical solution to the exact optimization problem but at a fraction of the optimization cost. This allows us to carry out efficient, non-myopic, and near-optimal active learning for sparse multilabel classification. Extensive experiments reveal the effectiveness of the method.

Exploiting sparsity and co-occurrence structure for action unit recognition

We present a novel Bayesian framework for facial action unit recognition. The first key observation behind this work is sparsity: out of possible 45 (and more) facial action units, only very few are active at any moment. The second is the strong statistical co-occurrence structure: most facial expressions are made by common combinations of facial action units, so knowing the presence of one can act as a strong prior for inferring the presence of others. We developed a novel Bayesian graphical model that encodes these two natural aspects of facial action units via compressed sensing and group-wise sparsity inducing priors. One crucial aspect of our approach is the allowance of overlapping group structures, which proves useful in dealing with action units that occur frequently across multiple groups. We derive an efficient inference scheme and show how such sparsity and co-occurrence can be automatically learned from data. Experiments on three standard benchmark datasets show superiority over the state-of-the-art.

Sub-Nanosecond Time of Flight on Commercial Wi-Fi Cards

The time-of-flight of a signal captures the time it takes to propagate from a transmitter to a receiver. Time-of-flight is perhaps the most intuitive method for localization using wireless signals. If one can accurately measure the time-of-flight from a transmitter, one can compute the transmitters distance simply by multiplying the time-of-flight by the speed of light. Today, GPS, the most widely used outdoor localization system, localizes a device using the time-of-flight of radio signals from satellites. However, applying the same concept to indoor localization has proven difficult. Systems for localization in indoor spaces are expected to deliver high accuracy (e.g., a meter or less) using consumer-oriented technologies (e.g., Wi-Fi on ones cellphone). Unfortunately, past work could not measure time-of-flight at such an accuracy on Wi-Fi devices. As a result, over the years, research on accurate indoor positioning has moved towards more complex alternatives such as employing large multi-antenna arrays to compute the angle-of-arrival of the signal. These new techniques have delivered highly accurate indoor localization systems. Despite these advances, time-of-flight based localization has some of the basic desirable features that state-of-the-art indoor localization systems lack. In particular, measuring time-of-flight does not require more than a single antenna on the receiver. In fact, by measuring time-of-flight of a signal to just two antennas, a receiver can intersect the corresponding distances to locate its source. Thus, a receiver can locate a wireless transmitter with no support from the surrounding infrastructure. This is quite unlike current indoor localization systems, which require multiple access points at known locations, to find the distance between a pair of mobile devices. Furthermore, each of these access points need to have many antennas -- far beyond what is supported in commercial Wi-Fi devices. In this demo, we will present Chronos, a system that combines a set of novel algorithms to measure the time-of-flight to sub-nanosecond accuracy on commercial Wi-Fi cards. In particular, we will measure distance/time-of-flight between two devices equipped with commercial Wi-Fi cards, without any support from the infrastructure or environment fingerprinting.

In-body backscatter communication and localization

Backscatter requires zero transmission power, making it a compelling technology for in-body communication and localization. It can significantly reduce the battery requirements (and hence the size) of micro-implants and smart capsules, and enable them to be located on-the-move inside the body. The problem however is that the electrical properties of human tissues are very different from air and vacuum. This creates new challenges for both communication and localization. For example, signals no longer travel along straight lines, which destroys the geometric principles underlying many localization algorithms. Furthermore, the human skin backscatters the signal creating strong interference to the weak in-body backscatter transmission. These challenges make deep-tissue backscatter intrinsically different from backscatter in air or vacuum. This paper introduces ReMix, a new backscatter design that is particularly customized for deep tissue devices. It overcomes interference from the body surface, and localizes the in-body backscatter devices even though the signal travels along crooked paths. We have implemented our design and evaluated it in animal tissues and human phantoms. Our results demonstrate that ReMix delivers efficient communication at an average SNR of 15.2 dB at 1 MHz bandwidth, and has an average localization accuracy of 1.4cm in animal tissues.

Research for practice: toward a network of connected things

Expert-curated guides to the best of CS research.

Eliminating Channel Feedback in Next-Generation Cellular Networks

The high cost of cellular spectrum has motivated network providers to seek advanced MIMO techniques to improve spectral efficiency [2, 1]. Yet, only point-to-point MIMO multiplexing can be performed efficiently in current networks [3]. More advanced MIMO solutions, such as massive MIMO, coordinated multi-point, distributed MIMO, and multi-user MIMO, all require the base station to know the downlink channels prior to transmission. In the absence of this information, the base station cannot beamform its signal to its users

Experiences Deploying an Always-on Farm Network

Data-driven techniques for agriculture can help farmers reduce waste, increase farm output and ensure sustainability for the environment. The key enabler for such techniques is an always-on connected IoT system that can sense the different characteristics of the farm and generate short-term and long-term actionable insights for the farmer. Yet building such a system is very challenging due to sparse Internet connectivity and lack of reliable power sources. This is further exacerbated by weather variability that stresses the system in numerous ways. We discuss how we built and deployed Farmbeats [6] in the face of these challenges. We hope our experiences will aid researchers who are beginning to explore deployments in farming or other weakly connected, power-starved scenarios, such as construction, oil fields, mining, and others.

Toward a Network of Connected Things

While the scale of data presents new avenues for improvement, the key challenges for the everyday adoption of IoT systems revolve around managing this data. First, we need to consider where the data is being processed and stored and what the privacy and systems implications of these policies are. Second, we need to develop systems that generate actionable insights from this diverse, hard-to-interpret data for non-tech users. Solving these challenges will allow IoT systems to deliver maximum value to end users.