Optimized mobility through smartphones

If the data of all smartphones were networked worldwide, quasi phone users could access a "supercomputer in their pocket". The networked, ever-increasing computing capacity not only optimizes data collection in real time, but also simplifies the analysis of any data. For example, data on the climate, noise, navigation aids or orientation could be retrieved at any time using Big Data technology.

However, technical hurdles and data protection concerns still need to be overcome.

Scientists working on the Swiss SenseSynergy project, which is funded by the Swiss National Science Foundation (SNSF), have tackled these problems and found new ways of collecting and using such data.

crowd sensing
The project essentially uses "crowd sensing", where information about a specific location area can be gathered by accessing smart phone sensors. A typical example of this is mapping apps that can use the acceleration

" Sensor data is used that penetrates walls and concrete."

The smartphone's tilt sensors can detect traffic jams. As networked devices collect information about many aspects of our environment (e.g. movements, sounds, people and air quality), they could help us decide where to eat, what clothes to wear and generally how to travel.

"This information can be used for a wide variety of applications: for marketing or to predict the behavior of groups of people," explains the project's coordi nator, Torsten Braun from the University of Bern. However, there are still some hurdles to overcome for such crowd-sensing apps. There are conflicts between data collection, data protection and the effects on the user-friendliness of the smartphone.

In addition, hardware resources are impaired by the massive data transfer, and inadequate security measures can encourage identity theft. Four teams have developed new concepts for improving crowd sensing technology and practical recommendations for its application. Their work focuses on four key areas: more accurate location data, improved data protection, industrial applications, and more efficient data collection.

Location function outperforms GPS
Scientists from the Universities of Bern and Geneva have jointly developed a mobile app that combines crowd sensing with indoor positioning and smart spaces. This mobile app integrates sophisticated positioning algorithms and sensor measurements with location information, which are then stored in a cloud. There, the data is available for the Internet of Things and can be used in personalized and location-based automation applications for numerous "smart" objects or products.

Torsten Braun's team in Bern improved the location accuracy in buildings and below ground level to 1.1 meters in 90 percent of cases. This is roughly equivalent to the performance of GPS systems.

Only the sensor data of the devices and radio signals are used, which, unlike GPS, also penetrate walls and concrete. The researchers collect the data transmitted by the smartphone sensors and information on the WiFi signal strength. This in formation is then processed by several machine learning algorithms. "The next step is then to determine the location that users are heading to," says Braun. "This could be interesting for shopping malls or train stations, for example."

A team from the University of Applied Sciences of the Italian-speaking part of Switzerland (SUPSI) in Lugano has developed models that use predictive location data for data transmission in social media. The experiments have shown that fast data transmission is not only useful in socia

"It's a balancing act between data use and privacy."

The messages could react to local behavior, evaluate feedback in real time, and circulate more quickly among selected users. The messages could react to local behavior, evaluate feedback in real time, and circulate more quickly among selected users.

Artificial noise as data protection
"One of the biggest difficulties for researchers is the balancing act between data use and privacy," says Torsten Braun. "The accuracy of the data can come at the expense of privacy." If user data is also collected during data collection, willingness to participate decreases. To ensure data security, the team at Chalmers University of Technology in Sweden has developed machine learning techniques for data analysis and automated decision making that enable "differential data protection.

Personal data is protected by carefully tuned noise (random data) introduced into the data collected by the devices.

Researchers at the University of Geneva have addressed another conflict: the desire to collect as much data as possible while keeping the hardware load of crowd sensing as low as possible. If users fear a burden on their smartphones, they may reject apps that access otherwise unused sensors. This project investigates game-theoretic models to find out how the load can be distributed across multiple phones and users.

As part of a field experiment in San Francisco, free-will participants downloaded an app to map noise levels in the city. While collecting useful data for the city government, they also tested different methods of measuring noise levels.
The load can be distributed over several devices.