Top TechTop Tech #147: machine learning predict crimes, paralyzed patient types, nano device converts light to current
Important innovations in science and technology
By Paul Worthington
Wednesday’s Top Tech:
• Machine learning predicts crimes
• Paralyzed patient types six words per minute
• Nano device converts light to DC current
Machine learning predicts crimes
Hitachi promises to predict where and when crime is likely to occur by ingesting a panoply of data, Fast Company reports, from historical crime statistics to public transit maps, from weather reports to social media chatter.
Hitachi says that about half a dozen U.S. cities will join a proof of concept test of the technology beginning in October. The company already provides video surveillance and sensor systems to police departments in several dozen cities in the U.S.
Hitachi Visualization Predictive Crime Analytics ingests streams of sensor and Internet data from a wide variety of sources, and applies machine learning to find patterns that humans would miss.
Paralyzed patient types six words per minute
A neural implant enables a paralyzed ALS patient to type six words per minute, IEEE Spectrum reports — a new world record.
The developer, BrainGate, says it is “turning thought into action.”
The company says its system consists of a device implanted in the brain that records signals directly related to imagined limb movement; a set of computers and embedded software that turns the brain signals into a useful command for an external device which could be a standard computer desktop or other communication device, a powered wheelchair, a prosthetic or robotic limb, or, in the future, a functional electrical stimulation device that can move paralyzed limbs directly.
Nano device converts light to DC current
A device combining the functions of an antenna and a rectifier diode converts light directly into DC current, Georgia Institute of Technology reports. It could lead to “a new technology for photodetectors that would operate without the need for cooling, energy harvesters that would convert waste heat to electricity – and ultimately for a new way to efficiently capture solar energy.”
Billed as the first optical “rectenna,” it uses nanometer-scale components — multiwall carbon nanotubes with tiny rectifiers fabricated onto them.
The nanotubes “act as antennas to capture light from the sun or other sources,” Georgia Tech adds. “As the waves of light hit the nanotube antennas, they create an oscillating charge that moves through rectifier devices attached to them. The rectifiers switch on and off at record high petahertz speeds, creating a small direct current.”
Efficiency “so far remains below one percent” but researchers “believe a rectenna with commercial potential may be available within a year.” It could “ultimately make solar cells that are twice as efficient at a cost that is ten times lower, and that is an opportunity to change the world in a very big way.”
The research is supported by the Defense Advanced Research Projects Agency (DARPA), the Space and Naval Warfare (SPAWAR) Systems Center and the Army Research Office (ARO). It was reported September 28 in the journal Nature Nanotechnology.
Here is the full announcement.
Unwind in the Mountains
Now is the best time to get out of your crowded city, enjoy the natural beauty of a private home in the Sierra Nevada, and leisurely explore nearby Yosemite National Park.
You’ll be comfortable in a large and fully-stocked house with a great mountain view from the deck, a sunroom patio with an indoor hot tub, and an outdoor pool — all on 15 acres of mountain forest.
All for less than $200 per night.
