Discovering the happiest mode of transportation

Activities and trips detected by the Daynamica smartphone application can be easily be annotated by users, allowing researchers to collect data about the emotions associated with those. The following screenshot shows an example survey for collecting companionship and emotion data associated with a completed activity.

A recent paper published in the journal Transport Findings and co-authored by Dr. Yingling Fan and Dr. Julian Wolfson used Daynamica to study trip-associated emotions for individuals in the Minneapolis-St. Paul metro area.

Here’s the abstract:

Understanding trip happiness—a measurement of people’s emotional well-being during trips—is an essential aspect of people-oriented transportation planning. We use data collected via smartphones from 350 residents in the Minneapolis-St. Paul region to examine trip- and person-level factors associated with trip happiness. Trip mode, purpose, duration, distance, companionship, activities during the trip, and temporal characteristics of the trip are significantly associated with trip happiness. Mode and companionship are the strongest predictors of trip happiness. Among personal factors, age is the strongest predictor, followed by general happiness of the person. Race, gender, and neighborhood have modest effects on trip happiness.

From Understanding Trip Happiness using Smartphone-Based Data: The Effects of Trip- and Person-Level Characteristics

Making sense of the day

“So, what did you do today?”

It’s a simple question, but gathering reliable data on how people spend their time is challenging. Traditional self-report based methods are burdensome to study participants and prone to recall bias. If this were an infomercial, we’d say (or yell): “THERE HAS TO BE A BETTER WAY!”

That’s where Daynamica comes in. We provide cutting-edge tools and infrastructure for collecting, processing, and understanding human activity and travel behavior data, including:

  • Daynamica, a smartphone application that captures detailed daily activity and trip data with minimal user burden.
  • StudyMap, A suite of study management tools to ensure compliance and data quality.
  • Secure cloud-based data storage.
  • Interactive data visualization and analysis tools.

Co-founded by faculty members at the University of Minnesota and based on more than a half-decade of research, Daynamica was developed by researchers, for researchers. Our aim is to provide a platform that research teams and organizations can use to collect high-resolution activity and behavior data on study participants in a transparent, secure, and ethical manner while protecting individual privacy and confidentiality.

Interested in using Daynamica in one of your studies? Here’s how you can get started. And, of course, you’re also welcome to contact us at info@daynamica.com. You’ll also find us on Twitter at @DaynamicaApp.

Daynamica and mobile health

It seems like almost everyone is interested in mobile health (or, to be hipper, mHealth) these days. There are a ton of devices out there that can measure physical activity, heart rate, and a number of other physiological parameters. For the most part, these devices provide only a partial picture of human activity during the day. Daily habits and behavior patterns have a substantial impact on health, but until recently, our ability to uncover links between lifestyle and health outcomes has been limited by the inherent difficulty of accurately measuring individual human activity and behavior patterns. 

For example, a mountain of research has shown that high levels of air pollution are associated with increased mortality. However, these findings are based primarily on pollution levels measured at fixed measuring stations; much less is known about how individual exposures vary over time, and hence how they impact health. Since the Daynamica app captures both movement patterns (i.e., location) and activity types (indoor/outdoor), it could be used either in conjunction with fixed or personal air pollution monitors to obtain much more precise, personalized measures of air pollution exposure. Indeed, Daynamica data could be paired with data from a wide variety of medical devices such as continuous glucose monitors or cardiac monitoring devices.

Another potential use of Daynamica is for developing and optimizing behavioral interventions. There is currently great interest in developing interventions that encourage behavior changes to improve health. But these interventions have mostly had only a modest degree of success. One key barrier to increasing the success of these interventions is that it is difficult to obtain accurate information on compliance, particularly since the behavior changes involved tend to be over-reported due to social desirability bias. Daynamica provides a platform for obtaining objective information about intervention compliance so that the reasons for intervention success or failure can be understood. The Daynamica app can also be used to deliver “just-in-time” interventions that adapt to each user’s past and current locations and activities. For instance, an intervention to decrease sedentary behavior could potentially be much more effective if it delivered reminders to users to increase their activity level at times when, based on past data, they have typically been sedentary.

The Daynamica app and data collection platform is already being used in several ongoing projects (and producing some interesting results), but the possibilities extend far beyond our existing partnerships. If you would like to know more about what Daynamica can do for your organization or research group, see our Services page or get in touch.

Understanding and visualizing travel emotions

Background

One of the most challenging tasks for those interested in understanding human activity and behavior is the tracking of individual emotions over time. In several recent projects, we have used our Daynamica smartphone app to ask users to tell us about their emotional state during each of the daily trips and activities that was detected by the app. Following established protocols, we asked users to rate their level of two positive (Happy, Meaningful) and four negative (Sad, Pain, Tired, Stressed) emotions on a scale from 1 (lowest intensity) to 7 (highest intensity). This post gives a quick overview of the resulting data, and shows some ways of visualizing them.

The Data

A sample of the data for one individual is shown below. Note that the reported emotion levels are associated with given trips or activities (e.g., Home, Eat Out, Car, Walk) which are of varying duration. But while we do not have regularly-measured emotion data, we can aggregate across multiple days of data to (or groups of individuals) to gain insight about emotional states over time.

Trip.Activity Start End Happy Meaningful Sad Tired Stressed Pain
Home 2016-10-26 15:48:00 2016-10-27 08:11:00 7 7 1 3 1 1
Home 2016-10-29 07:44:00 2016-10-29 11:22:00 5 3 1 4 5 2
Home 2016-10-29 11:28:00 2016-10-29 15:45:00 5 4 3 1 1 2
Car 2016-10-29 15:45:00 2016-10-29 16:38:00 7 7 1 4 1 3
Eat Out 2016-10-29 16:38:00 2016-10-29 19:00:00 7 6 1 1 1 1
Home 2016-10-29 19:35:00 2016-10-30 08:47:00 7 4 1 1 1 1
In Vehicle 2016-10-30 08:47:00 2016-10-30 08:57:00 7 7 1 1 1 3
Walk 2016-10-30 08:57:00 2016-10-30 08:58:00 7 7 1 1 1 3
Other 2016-10-30 08:58:00 2016-10-30 11:02:00 7 7 1 1 1 5
Walk 2016-10-30 11:02:00 2016-10-30 11:06:00 7 7 1 1 1 1

Individual emotion plots

First, we start by visualizing data for a single individual, aggregated over the time that they were asked to provide data (for this study, approximately two weeks). Since emotions are recorded at irregularly spaced intervals, we start by “filling in” emotional states for every hour. There are many ways one could do this, but we assumed that the emotions associated with a given trip or activity were constant during the time interval covered by that trip or activity.

Next, we aggregate across days by taking the average emotion level at every hour. However, reporting the simple average is somewhat problematic because different people have different “baseline” levels of each emotion. Hence, we scale each emotion to have mean zero and unit standard deviation.

Our data, then, can be shown as follows. More intense colors correspond to higher levels of the corresponding emotion:

emo-rect-1

But we can do more! By switching to polar coordinates, we can depict the same data with concentric circles showing the various emotions and angle displaying hour of the day, similar to a 24-hour analog watch or clock face.

emo-target-1

Yet another circular representation puts each emotion on a wedge of a single circle:

emo-pie-1

Comparisons

One of the benefits of visualizing emotional “trajectories” in this way is the ability to compare different groups of individuals. Below, we compare those who average more than 30 hours at work per week to those averaging less than 10. It is apparent that those working more are more tired, in less pain, and have fewer happy and meaningful moments. Interestingly, and perhaps somewhat counter-intuitively, stress levels are not markedly different between the groups.

emo-compare-1

Conclusions

Smartphone-derived human activity data can provide interesting insights into well-being and decision-making processes. The data are multi-dimensional and complex; this post only scratches the surface of what is possible. There are also a lot of open analysis questions: for instance, how do we statistically compare “emotion-time” patterns visualized in this post, to assess whether two individuals or groups of individuals are significantly different?

Code and Data

The analyses and plots presented in this post were done using R, with a heavy reliance on the dplyr, tidyr, lubridate and ggplot2 packages. While the data are not publicly available, we are currently in the process of compiling our code into an online repository that we plan to make publicly available at a later date.

Humphrey School Expert Launches Startup to Sell Smartphone App That Collects Travel Data

Daynamica was featured in a recent story from the University of Minnesota Humphrey School of Public Affairs:

March 19, 2018—Transportation agencies need travel behavior data to plan changes to their networks, systems, and policies. They’ll soon be able to purchase a new smartphone application called Daynamica, developed and patented by a University of Minnesota research team, to collect that important information more easily and for less cost than traditional methods.

The researchers, led by Humphrey School Associate Professor Yingling Fan, are in the final stages of creating a startup company and a licensing agreement with the University to sell Daynamica and its services.

This is the first patent and first startup company based on research completed at the Humphrey School, according to Associate Dean Carissa Slotterback.

“The work of Dr. Fan and her colleagues is a perfect example of the opportunities to use research to create products and outcomes that support practitioners in building healthy communities,” Slotterback says. “Her work has also connected to classes, creating opportunities for students to work at the forefront of transportation data and technology.”

Fan says Daynamica is a more efficient way to collect and process detailed data on how people get from place to place—driving or walking, biking or taking transit. It combines smartphone GPS sensing with advanced statistical and machine-learning techniques to automatically detect, identify, and summarize attributes of daily activity and travel periods. The app also allows users to view and add notes to the information at their convenience.

The Daynamica app display, with calendar and map formats.Fan says traditional travel survey methods like paper diaries are impractical, and GPS sensing tools can’t collect key information such as the purpose of a given trip, the traveler’s experience, and whether people are traveling alone or with companions.

“All of these factors are critical for understanding people’s travel choices,” Fan says. “Daynamica gives us the best of both worlds: It captures many more dimensions of travel behavior data than either GPS sensing or travel surveys can do alone.”

Daynamica places a much lower burden on users to recall and record their activities compared with traditional surveys, which means the data is more accurate and detailed. That ease of use could also allow agencies to study longer periods of time.

“Many traditional surveys track only a single day,” Fan says. “It would be better to collect a whole week of data to see how travel varies between weekdays and weekends. We could also look at seasonal variations and other factors. The more data, the better.”

Unlike other apps, Daynamica hosts both the data obtained from sensors and the data entered by users in a single device, and the two data sources interact with each other in real time. This in turn allows for data calibration and processing refinements over time.

“The algorithm learns from past mistakes,” Fan explains. “As it gets smarter, users need to make fewer corrections. After about a week of use, most data collection is automated. It learns what your location is—home, job, day care, or grocery store, for example—and remembers it.”

Daynamica offers several other advantages, Fan says. It’s easier to distribute and manage than other technologies because it doesn’t require an additional device; respondents can simply download the app and run it on their smartphones. In addition, Daynamica collects data in a way that reduces the need for processing, she says, which saves time and expense for the agencies using it.

Fan, who is the CEO of the new Daynamica, Inc., says the app will be marketed to businesses and government agencies interested in understanding and shaping transportation patterns, and to individuals interested in understanding and changing their own behavior for better economic, environmental, and health outcomes.

Daynamica was developed by a multidisciplinary team including Fan, Assistant Professor Julian Wolfson of the School of Public Health, Professor Gediminas Adomavicius of the Carlson School of Management, and computer science students Yash Khandelwal and Jie Kang.

Daynamica expands on the previous SmarTrAC app developed by the team under contract with the Volpe Center at the U.S. Department of Transportation in support of the Intelligent Transportation Systems Joint Program Office. Funding was also provided by the Center for Transportation Studies.