System Bits: April 15

Making game play more engaging
Engineers at Stanford University have developed what could be the next big thing in interactive gaming: handheld game controllers that measure the player’s physiology and alter the game play to make it more engaging. The prototype controller was born from research conducted in the lab of Gregory Kovacs, a professor of electrical engineering at Stanford, in collaboration with Texas Instruments. The main area of research by grad students in Kovacs’ lab involves developing practical ways of measuring physiological signals to determine how a person’s bodily systems are functioning.

One such system of interest to Corey McCall, a doctoral candidate in Kovacs’ lab, is the autonomic nervous system, the emotional part of the brain – the part that changes when you get excited or bored, happy or sad. This activity, in turn, influences your heart rate, respiration rate, temperature, perspiration and other key bodily processes. Measuring these outward signs offers a way of reverse engineering what’s occurring in the brain.

The expression of a person’s autonomic nervous system can be seen in their heart rate and skin temperature and respiration rate. By measuring those outputs, it is possible to understand what’s happening in the brain almost instantaneously. This method of sensing autonomic activity is particularly intriguing, McCall said, because it can be conducted through non-invasive means. In fact, another of his projects involves monitoring the skin temperature of epilepsy patients at Stanford Hospital in an effort to sense the early indicators of a seizure.

As the researchers worked out other ways to measure autonomic activity, they realized they could easily monitor people in various mental states as they played video games and the data needed to do that could come straight from test subjects’ hands – in the form of a modified Xbox 360 controller that contains 3D printed plastic module with a number of sensors. Small metal pads on the controller’s surface measure the user’s heart rate, blood flow, and both the rate of breath and how deeply the user is breathing. Another light-operated sensor gives a second heart rate measurement, and accelerometers measure how frantically the person is shaking the controller. Then, custom-built software gauges the intensity of the game – a simple but fast-paced racing game in which the player must drive over colored tiles in a particular sequence. The data can be analyzed to generate an overall picture of the player’s level of mental engagement.

The next phase of the research is to use the controller to provide feedback to the gaming console, which can then alter the pace of game play to better suit the player.

“If a player wants maximum engagement and excitement, we can measure when they are getting bored and, for example, introduce more zombies into the level,” McCall said. “We can also control the game for children. If parents are concerned that their children are getting too wrapped up in the game, we can tone it down or remind them that it’s time for a healthy break.”

Making mobile devices more secure with touch signature
Passwords, gestures and fingerprint scans are all helpful ways to keep a thief from unlocking and using a cell phone or tablet and cybersecurity researchers from the Georgia Institute of Technology have gone a step further. They’ve developed a new security system that continuously monitors how a user taps and swipes a mobile device. If the movements don’t match the owner’s tendencies, the system recognizes the differences and can be programmed to lock the device.

‘LatentGesture’ was used during a Georgia Tech lab study using Android devices. The system was nearly 98 percent accurate on a smartphone and 97 percent correct on tablets.

The system learns a person’s ‘touch signature,’ then constantly compares it to how the current user is interacting with the device, according to the professor who led the study.

To test the system, the researchers set up an electronic form with a list of tasks for 20 participants. They were asked to tap buttons, check boxes and swipe slider bars on a phone and tablet to fill out the form. The system tracked their tendencies and created a profile for each person. After profiles were stored, the researchers designated one person’s signature as the “owner” of the device and repeated the tests. LatentGesture successfully matched the owner and flagged everyone else as unauthorized users.

Just like a fingerprint, everyone is unique when they use a touchscreen. Some people slide the bar with one quick swipe. Others gradually move it across the screen. Everyone taps the screen with different pressures while checking boxes. The research team also programmed the system to store five touch signatures on the same device – one “owner” and four authorized users. When someone other than the owner used the tablet, the system identified each with 98 percent accuracy.

This feature could be used when a child uses a parent’s tablet, for instance. The system would recognize the touch signature and allow for use the device. But if the child tried to buy an app, the system could prevent it.

The researchers say LatentGesture’s biggest advantage is that the system is constantly running in the background. The user doesn’t have to do anything different for added security and authentication.