Most online fraud (诈骗) involves identity theft passwords help. But many can be guessed. Newer phones, tablets, laptops and desktop computers often have strengthened security with fingerprint and facial recognition. But these can be imitated (模仿). That is why a new approach, behavioral biometrics (行为生物识别) is gaining ground.

It relies on the wealth of measurements made by today’s devices (设备). These include data from sensors that reveal how people hold their phones when using them, how they carry them and even the way they walk. Touchscreens, keyboards and mice can be monitored to show the distinctive ways in which someone’s fingers and hands move. These features can then be used to determine whether someone attempting to make a deal is likely to be the device’s habitual user.

“Behavioral biometrics make it possible to identify an individual’s unique motion fingerprint”, says John Whaley, head of Unifyid, a firm in Silicon Valley that is involved in the field. When coupled with information about a user’s finger pressure and speed on the touchscreen, as well as a device’s regular places of use—as revealed by its GPS unit—that user’s identity can be pretty well determined.

Used wisely, behavioral biometrics could be a great benefit. In fact, Unifyid and an unnamed car company are even developing a system that unlocks the doors of a vehicle once the pace of the driver, as measured by his phone, is recognized. Used unwisely, however, the system would become yet another electronic spy on people’s privacy, permitting complete strangers to monitor your every action, from the moment you reach for your phone in the morning, to when you throw it on the floor at night.

An era in which an Alzheimer’s diagnosis can begin in a doctor’s office is now arriving. Advances in technologies to detect early signs of disease from a blood sample are helping doctors to identify the memory-robbing disorder more accurately and to screen participants more quickly for trials of potential treatments for the more than five million people in the U.S. afflicted with Alzheimer’s. Estimates predict that, by 2030, there will be 76 million people worldwide who will receive a diagnosis of Alzheimer’s or other dementias.

Last fall, a blood test developed by C2N Diagnostics in St. Louis, Mo., became available to most of the U.S. as a routine lab test—regulated under the CMS Clinical Laboratory Improvement Amendments (CLIA) program. It has also received a CE mark as a diagnostic medical device in the European Union—indicating it has met safety, health and environmental protection standards for the region.

“The development of a blood-based test for Alzheimer’s disease is just amazing,” says Michelle Mielke, a neuroscientist and epidemiologist at the Mayo Clinic. “The field has been thinking about this for a very long time. It’s really been in the last couple of years that the possibility has come to fruition.”

The C2N test, called PrecivityAD, uses an analytic technique known as mass spectrometry to detect specific types of beta-amyloid(ß-淀粉样蛋白), a protein fragment that is a pathological-hallmark of disease. Beta-amyloid proteins accumulate and form plaques visible on brain scans two decades before a patient notices memory problems. As plaques build up in the brain, levels of beta-amyloid decline in the surrounding fluid.

Such changes can be measured in spinal fluid samples—and now in blood, where beta-amyloid concentrations are significantly lower. PrecivityAD is the first blood test for Alzheimer’s to be cleared for widespread use and one of a new generation of such assays that could enable early detection of the leading neurodegenerative disease—perhaps decades before the onset of the first symptoms.

Zoologists studied the nervous systems of insects to investigate principles of biological brain computation and possible effects on machine learning and artificial intelligence. Specifically, they analysed how insects learn to associate sensory information in their environment with a food reward, and how they can recall this information later in order to solve complex tasks such as the search for food.

Living organisms show remarkable abilities in coping with problems posed by complex and dynamic environments. They are able to generalize their experiences in order to rapidly adapt their behaviour when the environment changes. The zoologists investigated how the nervous system of the fruit fly controls its behaviour when searching for food.

Using a computer model, they simulated and analysed the computations in the fruit fly’s nervous system in response to scents (气味) coming from the food source. They initially trained their model of the fly brain in exactly the same way as insects are trained in experiments. They presented a specific scent in the simulation together with a reward and a second scent without a reward.

“The model rapidly learns a strong representation of the rewarded scent after just a few scent presentations and is then able to find the source of this scent in a complex environment,” said computer scientist Dr Hannes Rapp, who created the model.

The model created is thus capable to generalize from its memory and to apply what it has learned previously in a completely new and complex environment, while learning required only a very small database of training samples.

The results suggest that the transformation of sensory information into memories in the brain can inspire future machine learning and artificial intelligence applications to solving complex tasks.