Using Smartphone Sensors to Measure Metro Traffic in New Delhi

Our next guest post is by Vinayak Naik, Associate Professor and Founding Coordinator of the MTech in CSE with specialization in Mobile Computing at IIIT-Delhi, New Delhi, India.  He writes about his group’s research on using smartphone sensors to measure metro traffic in New Delhi.

Vinayak Naik   In recent years, mobile sensing has been used in myriad of interesting problems that rely on collection of real-time data from various sources. The field of crowd-sourcing or participatory sensing is extensively being used for data collection to find solutions to day-to-day problems. One such problem of growing importance is analytics for smart cities. As per Wikipedia, a smart city is defined as an urban development vision to integrate multiple information and communication technology (ICT) solutions in a secure fashion to manage a city’s assets and notable research is being conducted in this direction. One of the important assets is transportation. With the growing number of people and shrinking land space, it is important to come up with solutions to reduce pollution caused by the vehicles and ease commuting between any two locations within the city.

Today, cities in developed countries, such as New York, London, etc, have millions of bytes of data being logged on a diurnal basis using sensors installed at highway and metro stations. This data is typically leveraged to carry out an extensive analysis to understand usage of roads and metro across the city’s layout and aid in the process of better and uniform city planning in long term. However, a common challenge faced in developing countries is the paucity of such detailed data due to lack of sensors in the infrastructure. In the absence of these statistics, the most credible solution is to collect data via participatory sensing using low-cost sensors like accelerometer, gyroscope, magnetometer, GPS, and WiFi that come packaged with modern day smartphones. These sensors can be used to collect data on behalf of users, which upon analysis can be leveraged in the same way as data made available through infrastructure-based.

IIT Metro
Figure 1: (a) and (b) show the relative rush at a given station which aids us in estimating wait time across metro stations. (c) shows a possible Google Maps Utility where an alternate route or transport mode can be suggested depending on the amount.

In short term, this data can be leveraged to guide commuters about expected rush at the stations. This is important as in some extreme cases wait time at stations could be more than the travel time itself. Aged people, those with disabilities, and children can possibly avoid traveling if there is rush at stations. We show two snapshots of platform at Rajiv Chowk metro station in Delhi, in Figure 1(a) and Figure 1(b). These figures show variation in the amount of rush that can happen in a real life scenario. In the long run information from our solution can also be integrated with route planning tools (e.g., Google Maps, see Figure 1(c)), to give an estimated waiting time at the stations. This will help those who want to minimize or avoid waiting at the stations.

About a decade ago, even cities in developed countries had less infrastructural support to get sensory data. The author was the lead integrator of the Personal Environmental Impact Report (PEIR) project in 2008. The objective of the project was to estimate emission and exposure to pollution for the city of Los Angeles [1] in USA. PEIR used data from smartphones to address the problem of lack of data. Today, the same approach is applicable in developing countries, where reach of smartphones is more than that of infrastructure-based sensors. At IIIT-Delhi, master’s student Megha Vij, co-advised by Prof. Viswanath Gunturi and the author, worked her thesis [2] on the problem to build a model, which can predict the metro station activity in the city of New Delhi, India using accelerometer logs collected from a smartphone app.

Our approach is to detect commuter’s entry into metro station and thereon measure time spent by the commuter till he/she boards the train. Similarly, we measure the time spent from disembarking the train until exiting the metro station. These two time-durations are indicative of the rush at metro stations, i.e., more the rush, more the time spent. We leverage geo-fencing APIs on the smartphones to detect entry into and exit from the metro stations. These APIs efficiently use GPS to detect whether the user has crossed a boundary, in our case perimeter around the metro station. For detecting boarding and disembarking, we use accelerometers on the smartphones to detect whether the commuter is in a train or not. Unlike geo-fencing, the latter is an unsolved problem. We treat this problem as a two class classification, where the goal is to detect whether a person is traveling in a train or is at the metro station. Furthermore, the “in-metro-station” activity is a collection of many micro-activities including walking, climbing stairs, queuing, etc and therefore, needs to be combined into one single category for the classification. We map this problem to machine learning and explore an array of classification algorithms to solve it. We attempt to use discriminating, both probabilistic and non-probabilistic, classification methods to effectively distinguish such patterns into “in-train” and “in-metro-station” classes.

Accelerometer Plot
Figure 2: Sample accelerometer data annotated with the two mobility patterns, “in-train” and “in-station”

Figure 2 illustrates “in-train” and “in-metro-station” classes on sample accelerometer data that we collected. One may observe a stark difference in accelerometer values across the two classes. The values for the”in-train” class have less variance, whereas for the “in-metro-station” class, we observe heavy fluctuations (and thus much greater variance). This was expected since a train typically moves at a uniform speed, whereas in a station we would witness several small activities such as walking, waiting, climbing, sprinting, etc.

It is important to note that this problem is not limited to only analytics for smart cities, e.g., our work is applicable for personal health. Smart bands and watches are used these days to detect users’ activities, such as sitting, walking, and running. At IIIT-Delhi, we are working on these problems. A standardized data collection and sharing app for smartphones would leapfrog our research. fills this need aptly.

[1] PEIR (Personal Environmental Impact Report)

[2] Using smartphone-based accelerometer to detect travel by metro train


Connect with Vinayak: Facebook   Twitter   LinkedIn

Backer Profile: Takeshi Okadome, Professor at Kwansei Gakuin University

Takeshi OkadomeTakeshi Okadome is a Professor in the Department of Informatics at Kwansei Gakuin University. His group works on environmental media design, using various sensors to design a new media that represents a physical or “mind” state of a physical object in an environment, and using the media, they create various contents, in particular, web contents together with each person’s favorite objects.

They use sensor network, physical computing, and machine learning technologies to attempt to: (1) to establish a method for interpreting sensor data and verbalizing or visualizing them, (2) to interpolate human actions or real-world events that cannot be directly inferred from sensor data by mining the information on the web, (3) to design “environment media” that represent the verbalized or visualized data, and (4) to create web contents using the environment media. The group also works on recognition of daily living activities from sensor data using machine learning techniques.

Kwansei Gakuin University


Prof. Okadome will use the data to construct better recognition methods for daily living activities using Data and also test the methods using them.

Backer Profile: Michael Noll-Hussong, Associate Professor of Psychosomatic Medicine and Psychotherapy at University of Ulm

Michael Noll-HussongMichael is an Associate Professor of Psychosomatic Medicine and Psychotherapy in the Department of Psychosomatic Medicine, Psychotherapy and Medical Psychology at the University of Ulm, Germany. As senior physician and head of the psychosomatic outpatient clinic he works especially with patients and their “significant others” that suffer from mental disorders like somatic symptom disorders, chronic pain disorder, personality disorders, and eating disorders. Michael Noll-Hussong is medical specialist, certified psychotherapist, certified physiologist and neuroscientist. His research focuses on – amongst others – the link between psychological stress and bodily symptoms, affective meaning construction, empathy and social neuroscience. Methods include clinical, phenomenological, psychometric, cognitive psychology, psychophysiology, and neuroimaging (fMRI).

University of Ulm

He will use the data to begin a study of how personal device data may be used to study mental disorders like pain, depressive and eating disorders in more detail and in combination with other methods, especially of social neuroscience.

Backer Profile: Jonathan Rubin, Research Scientist at PARC

Jonathan Rubin Jonathan is a Research Scientist at PARC, where his research focuses on the use of machine learning and deep learning in biomedical and physiological data. He is interested in the analysis of data from mobile and wearable devices for pervasive and ubiquitous health management purposes. He has investigated how mobile and wearable technology can be used within health condition management systems for disorders such as panic disorder, post-traumatic stress disorder and depressive disorder. He is particularly interested in the analysis of physiological data in order to infer information about psychological state. His research interests include affective computing, ubiquitous computing, artificial intelligence, machine learning, deep learning, and physiological data analysis. Jonathan holds a Ph.D. from the University of Auckland where his research focused on the use of artificial intelligence for strategy generation in computer games.

Jonathan will use the data that provides to improve and broaden the types of activity recognition that currently exist. In addition, he will use physiological data from wearable devices for affective computing purposes.

Learn More
On GitHub:

Featured Sponsor: Smart Data Innovation Lab at Karlsruhe Institute of Technology

SDIL   The Smart Data Innovation Lab (SDIL) offers big data researchers a unique access to a large variety of Big Data and In-Memory predictive analytics technologies (e.g. SAP HANA, IBM WATSON, Software AG Terracotta). Industry and science collaborate closely in order to find hidden value in big data and generate smart data. Projects are focused on the strategic research areas of Industrie 4.0, Smart Energy, Smart Cities and Personalized Medicine. In order to close today’s gap between academic research and industry problems through a data driven innovation cycle the SDIL provides extensive support to all collaborative research projects free of charge (applications are accepted via the web site).

SDIL Diagram-1SDIL provides access to experts and domain-specific skills within Data Innovation Communities fostering the exchange of project results. They further provide the possibility for open-innovation and bilateral matchmaking between industrial partners and academic institutions. Template agreements and processes ensure fast project initiation at maximum legal security fit to the common technological platform. A standardized process allows anyone to set up a new collaborative project at SDIL within 2 weeks. Furthermore, it actively lists data sources such as and lists relevant code artifacts to augment the unique industrial grade solutions provided within the platform.

SDIL is a community effort from both industry and academia in Germany coordinated by Prof. Michael Beigl’s team at TECO. The Karlsruhe Institute of Technology runs the platform.

SDIL Activities

One use case for data that will be investigated by KIT TECO in personalized medicine is investigating correlations between interruptibility of a user and their context for field research and surveying. They expect to be able to infer interruptibility rules to implement a smart notification management system. It shall handle notifications with respect to the user’s interruptibility with the objective to improve user experience.

Learn More

Backer Profile: Adam Joinson, Professor of Information Systems at University of Bath

Adam JoinsonAdam has a first degree in Psychology from the University of London (Goldsmiths College), and a PhD in social psychology from the University of Hertfordshire (on self-esteem and motivation). Immediately after my PhD, he worked at the University of Glamorgan as a lecturer in social psychology (from 1995 until 1999). He then joined the Institute of Educational Technology at the Open University as a lecturer (and then senior lecturer) in ICT and Social Science (from 1999 until 2007). Adam joined the University of Bath, School of Management in June 2007, first as a senior lecturer, then as a Reader in ‘Information Systems’. In September 2012 he joined UWE Bristol as Professor of Behavioural Change, and returned to the University of Bath in January 2016 to become Professor of Information Systems. Adam works at the intersection between human sciences and technology – on topics such as communication, social media, wearable technology and behaviour, and privacy / surveillance / cyber-security.

Adam is particularly interested in issues of public-private space and activity, mood and use, and patterns of behaviour. He also hopes to use the data sets in a new Masters course at Bath to help train future data scientists.

Learn more
University of Bath Homepage
Connect with Adam on LinkedIn

Featured Sponsor: SenseGrow + InstaMsg Free Trial – Build and Launch IoT Apps 10x Faster!

InstaMsgFounded in 2014, SenseGrow is a technology startup committed to providing the best possible Internet of Things (IoT) technology to its customers. SenseGrow creates easy to use IoT software that enables developers to build IoT solutions faster and businesses to get more value from their connected devices.

SenseGrow Founders   Build your IoT products and solutions 10x faster with zero upfront cost and no risk. SenseGrow’s secure middleware platform enables you to focus on your business case or product without worrying about the underlying IoT infrastructure. Use SenseGrow APIs to securely connect with Devices, People, Apps or Things and let them worry about the embedded coding involved. Run remote diagnostics, reports and update firmwares on your Things with no hassle. SenseGrow is currently offering a free trial of InstaMsg for real-time IoT connectivity and messaging!

SenseGrow Partners
Learn more about SenseGrow:
– Follow SenseGrow on Facebook
– Follow SenseGrow on Twitter
– Connect with SenseGrow on LinkedIn

Backer Profile: Christian Poellabauer, Associate Professor at Notre Dame

Christian PoellabauerChristian is an Associate Professor at the University of Notre Dame Department of Computer Science and Engineering where he directs the Mobile Computing Lab (M-Lab). His team studies systems and methods that combine various types and sources of information to develop new or improved context-aware applications and services. Examples of such research challenges include: how can we reduce localization and tracking errors using opportunistic sharing of data between mobile devices; how can we detect and assess health problems using information collected from mobile device and wearables; and what can we learn about the relationships between behaviors, health and wellbeing, social ties, etc., using data collected from smartphones?

The key to building context-aware services is access to large-scale and longitudinal data sets, which are difficult to collect. The data will provide contextual information that can help Christian’s team to answer various questions about human behavior and correlations between various forms of activities, traits, and preferences.

Learn more
Homepage at Notre Dame:
M-Lab site:

Wireless Sensor Research at Bogazici University, Istanbul

Our second in a series of expert guest posts comes from Bilgin Kosucu, a doctoral student in the WiSe group at Bogazici University Computer Engineering Department.  He provides a brief history of their unique and diverse group and writes about their work with wireless sensors and wearables in Turkey.
— Evan

WiSe,Bilgin the Wireless Sensor Research group of Bogazici University Computer Engineering Department, is one of the largest research groups in its area in Turkey. Currently the group consists of 4 full time faculty members, a medical doctor, 12 PhD candidates and 10 MS students.

WiSe was established by a computer networks researcher who then extended the work to wireless sensors. Eventually, the research on wireless sensor networks expanded to include wearable/ambient sensors and mobile phones. Currently, we are involved with the analysis of daily activities, ambient assisted living and elderly healthcare including but not limited to the UBI-HEALTH Project, supported by the EC Marie Curie IRSES Program.

As a group we are experienced of designing and developing mobile data collection platforms (e.g. on Android phones and Samsung Galaxy Gear S smartwatches), but we believe that will build a unique database, having dedicated data annotators and considering the immense difficulty of gathering the ground truth data. This database will serve as common platform, owing its popularity to being a crowd funded collaboration, for researchers to test and compare their algorithms.

WiSe Research

In addition to the opportunity of applying our previous research of activity recognition to a well defined and standardized dataset, we hope to reach out to the wearable computing community and build the pavement for finer research through advanced collaboration.

How to reach us:
WiSe group:
Computer Engineering Department:

Featured Sponsor: Lumme – Personalized Quit Programs for Smokers Using Wearable Sensors

Lumme IncLumme Inc is developing a personalized quit program for smokers by combining wearable sensors, data analytics, and behavioral psychology. They are developing the technology to automate and scale personalized care. With data from a phone and wristband, the Lumme platform can automatically detect when the user is smoking and identify triggers associated with smoking behavior. This information is then used to predict high risk situations and prevent a relapse by offering just-in-time intervention, specifically designed to induce lasting behavioral change. This technology pushes the envelope of traditional therapy to make this the last quit attempt of every smoker.

Abhinav and Akshaya
Abhinav Parate, Head of R&D and Akshaya Shanmugam, Project Manager

With data from, Lumme will test their smoking-detection algorithms and expand the technology to include detection of eating behavior as a possible trigger for smoking behavior. This can further enable our technology to detect and treat eating disorders such as binge-eating disorder, anorexia nervosa, bulimia nervosa, and obesity.