Rijurekha Sen

Zee: zero-effort crowdsourcing for indoor localization

Radio Frequency (RF) fingerprinting, based onWiFi or cellular signals, has been a popular approach to indoor localization. However, its adoption in the real world has been stymied by the need for sitespecific calibration, i.e., the creation of a training data set comprising WiFi measurements at known locations in the space of interest. While efforts have been made to reduce this calibration effort using modeling, the need for measurements from known locations still remains a bottleneck. In this paper, we present Zee -- a system that makes the calibration zero-effort, by enabling training data to be crowdsourced without any explicit effort on the part of users. Zee leverages the inertial sensors (e.g., accelerometer, compass, gyroscope) present in the mobile devices such as smartphones carried by users, to track them as they traverse an indoor environment, while simultaneously performing WiFi scans. Zee is designed to run in the background on a device without requiring any explicit user participation. The only site-specific input that Zee depends on is a map showing the pathways (e.g., hallways) and barriers (e.g., walls). A significant challenge that Zee surmounts is to track users without any a priori, user-specific knowledge such as the users initial location, stride-length, or phone placement. Zee employs a suite of novel techniques to infer location over time: (a) placement-independent step counting and orientation estimation, (b) augmented particle filtering to simultaneously estimate location and user-specific walk characteristics such as the stride length,(c) back propagation to go back and improve the accuracy of ocalization in the past, and (d) WiFi-based particle initialization to enable faster convergence. We present an evaluation of Zee in a large office building.

GruMon: fast and accurate group monitoring for heterogeneous urban spaces

Real-time monitoring of groups and their rich contexts will be a key building block for futuristic, group-aware mobile services. In this paper, we propose GruMon, a fast and accurate group monitoring system for dense and complex urban spaces. GruMon meets the performance criteria of precise group detection at low latencies by overcoming two critical challenges of practical urban spaces, namely (a) the high density of crowds, and (b) the imprecise location information available indoors. Using a host of novel features extracted from commodity smartphone sensors, GruMon can detect over 80% of the groups, with 97% precision, using 10 minutes latency windows, even in venues with limited or no location information. Moreover, in venues where location information is available, GruMon improves the detection latency by up to 20% using semantic information and additional sensors to complement traditional spatio-temporal clustering approaches. We evaluated GruMon on data collected from 258 shopping episodes from 154 real participants, in two large shopping complexes in Korea and Singapore. We also tested GruMon on a large-scale dataset from an international airport (containing ≈37K+ unlabelled location traces per day) and a live deployment at our university, and showed both GruMons potential performance at scale and various scalability challenges for real-world dense environment deployments.

Horn-ok-please

Road congestion is a common problem worldwide. Existing Intelligent Transport Systems (ITS) are mostly inapplicable in developing regions due to high cost and assumptions of orderly traffic. In this work, we develop a low-cost technique to estimate vehicular speed, based on vehicular honks. Honks are a characteristic feature of the chaotic road conditions common in many developing regions like India and South-East Asia. We envision a system where dynamic road-traffic information is learnt using inexpensive, wireless-enabled on-road sensors. Subsequent analyzed information can then be sent to mobile road users; this would fit well with the burgeoning mobile market in developing regions. The core of our technique comprises a pair of road side acoustic sensors, separated by a distance. If a moving vehicle honks between the two sensors, its speed can be estimated from the Doppler shift of the honk frequency. In this context, we have developed algorithms for honk detection, honk matching across sensors, and speed estimation. Based on the speed estimates, we subsequently detect road congestion. We have done extensive experiments in semi-controlled settings as well as real road scenarios under different traffic conditions. Using over 18 hours of road-side recordings, we show that our speed estimation technique is effective in real conditions. Further, we use our data to characterize traffic state as free-flowing versus congested using a variety of metrics: the vehicle speed distribution, the number and duration of honks. Our results show clear statistical divergence of congested versus free flowing traffic states, and a threshold-based classification accuracy of 70-100% in most situations.

Kyun queue: a sensor network system to monitor road traffic queues

Unprecedented rate of growth in the number of vehicles has resulted in acute road congestion problems worldwide. Better traffic flow management, based on enhanced traffic monitoring, is being tried by city authorities. In many developing countries, the situation is worse because of greater skew in growth of traffic vs the road infrastructure. Further, the existing traffic monitoring techniques perform poorly in the chaotic non-lane based traffic here. In this paper, we present Kyun Queue, a sensor network system for real time traffic queue monitoring. Compared to existing systems, it has several advantages: it (a) works in chaotic traffic, (b) does not interrupt traffic flow during its installation and maintenance and (c) incurs low cost. Our contributions in this paper are four-fold. (1) We propose a new mechanism to sense road occupancy based on variation in RF link characteristics, when line of sight between a transmitter-receiver pair is obstructed. (2) We design algorithms to classify traffic states into congested or free-flowing at time scales of 20 seconds with above 90% accuracy. (3) We design and implement the embedded platforms needed to do the sensing, computation and communication to form a network of sensors. This network can correlate the traffic state classification decisions of individual sensors, to detect multiple levels of traffic congestion or traffic queue length on a given stretch of road, in real time. (4) Deployment of our system on a Mumbai road, after careful consideration of issues like localization and interference, gives correct estimates of traffic queue lengths, validated against 9 hours of image-based ground truth. Our system can provide input to several traffic management applications like traffic light control, incident detection, and congestion monitoring.

RoadSoundSense: Acoustic sensing based road congestion monitoring in developing regions

Road congestion is a common problem all over the world. In many developed countries, automated congestion detection techniques have been deployed, that are used in road travel assisting applications. But these techniques are mostly inapplicable in many developing regions due to high cost and their assumptions of orderly traffic. Efforts in developing regions have been few. In this paper, we present RoadSoundSense, an acoustic sensing based technique, for near real time congestion monitoring on chaotic roads, at a moderate cost. We present the detailed design of an acoustic sensing hardware prototype, which has to be deployed by the side of the road to be monitored. This unit samples and processes road noise to compute various metrics like amount of vehicular honks and vehicle speed distribution, with speeds calculated from honks using differential Doppler shift. The metrics are sent to a remote server over GPRS every alternate minute. Based on the metric values, the server can decide the traffic condition on the road. Data from deployment of this prototype in six different Mumbai roads, validated against manually observed ground truth, shows feasibility of per minute congestion monitoring from a remote server. K-means clustering gives on average 90% accuracy to group unlabeled data on a new road into two clusters of congested and free-flow. Deployment data from one road for six days shows the temporal variation in traffic state for that road. Though we test our technique in Mumbai, we believe that most of our claims and experimental results can be extended to city roads of other developing regions as well.

Wireless across road: RF based road traffic congestion detection

Road congestion is a common problem worldwide. Intelligent Transport Systems (ITS) seek to alleviate this problem using technology. But most ITS techniques, currently used in developed countries, are inapplicable in developing regions due to high cost and assumptions of orderly traffic. Efforts in developing regions have been few. In this paper, we seek to develop a low-cost ITS technique to detect congestion in disorderly road conditions. We take Indian traffic conditions as an example for our analysis. But we believe that most of our claims and experimental results can be extended to other developing countries too. Our technique is based on exploiting the variation in wireless link characteristics when line of sight conditions between a wireless sender and receiver vary. Our system comprises of a wireless sender-receiver pair across a road. The sender continuously sends packets. The receiver measures metrics like signal strength, link quality and packet reception. These metrics show a marked change in values depending on whether the road in between has free-flowing or congested traffic. We have experimented with off-theshelf IEEE 802.15.4 compliant CROSSBOW Telosb motes. From about 15 hours of experimental data on two different roads in Mumbai, we show that we can classify traffic states as free-flowing and congested using a decision tree based classifier with 97% accuracy.

Accurate speed and density measurement for road traffic in India

Monitoring traffic density and speed helps to better manage traffic flows and plan transportation infrastructure and policy. In this paper, we present techniques to measure traffic density and speed in unlaned traffic, prevalent in developing countries, and apply those techniques to better understand traffic patterns in Bengaluru, India. Our techniques, based on video processing of traffic, result in about 11% average error for density and speed compared to manually-observed ground truth values. Though we started with intuitive and straight-forward image processing tools, due to a myriad of non-trivial issues posed by the heterogeneous and chaotic traffic in Bengaluru, our techniques have grown to be non-obvious. We describe the techniques and their evaluation, with details of why simpler methods failed under various circumstances. We also apply our techniques to quantify the congestion during peak hours and to estimate the gains achievable by shifting a fraction of traffic to other time periods. Finally, we measure the fundamental curves of transportation engineering, relating speed vs. density and flow vs. speed, which are integral tools for policy makers.

RasteyRishtey: A social incentive system to crowdsource road traffic information in developing regions

Intelligent Transport Systems (ITS), used for efficient road traffic management, largely benefits from probe sensing data like GPS traces. But gathering large scale GPS traces is a bottleneck, especially in developing regions, limiting researchers and government organizations from fully exploiting this potentially rich information base. In this paper; we present RasteyRishtey1, a social networking system, to incentivize smartphone users to gather and share their GPS traces. Our social networking application in the simplest case, aids relatives like parents and spouses to track people, given the latters consent. In the more complex case, groups of users can organize meet-ups collaboratively, starting from choice of venue to track everyone else until they reach the venue, using the application. Both versions produce crowd-sourced GPS traces, that can potentially be a rich source of traffic information. We present the design and implementation of the applications, along with a deployment based user study of the same. We also present some preliminary analysis of the collected GPS traces, that shows certain interesting and intuitive characteristics of road traffic, in the Indian city of Bengaluru.

A Middleware Based Approach to Dynamically Deploy Location Based Services onto Heterogeneous Mobile Devices Using Bluetooth in Indoor Environment

Several methods for providing location based service (LBS) to mobile devices in indoor environment using wireless technologies like WLAN, RFID and Bluetooth have been proposed, implemented and evaluated. However, most of them do not focus on heterogeneity of mobile platforms, memory constraint of mobile devices, the adaptability of client or device to the new services it discovers whenever it reaches a new location. In this paper, we have proposed a Middleware based approach of LBS provision in the indoor environment, where a Bluetooth enabled Base Station (BS) detects Bluetooth enabled mobile devices and pushes a proper client application only to those devices that belong to some registered subscriber of LBS. This dynamic deployment enables the mobile clients to access any new service without having preinstalled interface to that service beforehand and thus the client′s memory consumption is reduced. Our proposed work also addresses the other issues like authenticating the clients before providing them LBSs and introducing paid services. We have evaluated its performance in term of file transfer time with respect to file size and throughput with respect to distance. Experimental results on service consumption time by the mobile client for different services are also presented.

Leveraging Facebook's Free Basics Engine for Web Service Deployment in Developing Regions

In this paper we analyze Facebooks Free Basics program, which provides free Internet access to a restricted set of web services. As the program grows to 60+ developing countries, an independent and data-driven audit of its scope and outreach is highly relevant to the ICTD community. We provide the first large scale empirical observations on how content providers are using the Free Basics platform and what kind of user traffic is expected once a Free Basics service goes live. Implementing an Android app for data collection and recruiting participants from 15 countries, we analyze the current set of Free Basics services and their growth over time. We also deploy our own Free Basics services to gather first hand experience about Facebooks gate-keeping procedure in the program. One of our services Bugle News, an RSS news feed aggregator offered in English, Spanish and French, attracted 95.6K unique visitors from 55+ countries since Sep 2016. This enables us to characterize the nationality, demographics and interests of this Free Basics user population. We specifically deploy an ICTD related Free Basics service called Awaaz: My Voice. Awaaz is a web-service, where citizens can report local issues with location and images. This citizen journalism portal has attracted several hundred users during its short two months deployment in ten cities across South Africa. Visitors have reported concrete issues in categories of road, electricity, water, health and sanitation, school and education, crime and others. Overall our experimental observations allow the ICTD community to understand how Free Basics works and our deployment experiences pave the way for other applications to be launched in future, geared towards important use cases the ICTD community cares about.