Here’s another selection of items from the Association of Computing Machinery’s ACM Tech News. A lot of modern computing relies on wireless technology, i.e. radio. If you’re thinking of getting involved in any of these wireless technologies, it would be an advantage for you to get an amateur radio license.
The first article below discussses how cars could wirelessly network with one another to avoid crashes. The second discusses how implanted medical can use Bluetooth to connect to external systems.
The third article isn’t really amateur radio related, but I found it to be very interesting. China’s Baidu is making its artificial intelligence (AI) software, PArallel Distributed Deep LEarning (PaddlePaddle), publicly available on GitHub. According to the company, the software can be used by a wide range of coders, even those who are not expert in AI. As far as I know, AI isn’t widely used in amateur radio so far, but perhaps this release will spur this use.
Saving Lives by Letting Cars Talk to Each Other, The Conversation (09/11/16) Huei Peng
Wireless connectivity enabling communication between vehicles, the surrounding infrastructure, and others who share the road offers to improve safety as semi-autonomous and fully autonomous cars mature and proliferate, according to University of Michigan professor Huei Peng. “Connectivity enables smart decisions by individual drivers, by self-driving vehicles, and at every level of automation in between,” he says. Peng says connected vehicles securely communicate to each other and the surrounding infrastructure via Dedicated Short Range Communications, exchanging data 10 times each second via messages that can be securely relayed at least 1,000 feet in any direction, and through inclement weather. The U.S. federal government calculates vehicle-to-vehicle connectivity could prevent or mitigate the severity of approximately 80 percent of crashes that do not involve drug- or alcohol-impaired motorists. “Perhaps the greatest benefit of connectivity is that it can transform a group of independent vehicles sharing a road into a cohesive traffic system that can exchange critical information about road and traffic conditions in real time,” Peng says. He notes the University of Michigan Mobility Transformation Center seeks to advance connected/automated vehicle development. Peng also cites the need “to more fully understand how to fuse information from connectivity and onboard sensors effectively.” View Full Article
Interscatter Communication Enables First-Ever Implanted Devices, Smart Contact Lenses, Credit Cards That ‘Talk’ Wi-Fi, UW Today (08/17/16) Jennifer Langston
University of Washington (UW) researchers’ interscatter communication method enables brain implants, contact lenses, credit cards, and smaller wearables to exchange data with smartphones, watches, and other everyday gadgets. The technique, to be detailed next week at the ACM Special Interest Group on Data Communication (SIGCOMM 2016) conference in Brazil, uses reflections to convert Bluetooth signals from nearby mobile devices into Wi-Fi transmissions over the air. The system relies only on common mobile devices to produce Wi-Fi signals that consume 10,000 times less energy than conventional techniques. “Bluetooth devices randomize data transmissions using a process called scrambling,” says UW professor Shyam Gollakota. “We figured out a way to reverse-engineer this scrambling process to send out a single tone signal from Bluetooth-enabled devices such as smartphones and watches using a software app.” To remove the unwanted, bandwidth-hungry mirror image copy of signals created by the backscattering process, the researchers employed “single sideband backscatter,” says UW doctoral student Bryce Kellogg. “That means that we can use just as much bandwidth as a Wi-Fi network and you can still have other Wi-Fi networks operate without interference,” he notes. Among the proof-of-concept demos the team built were a smart contact lens and an implantable neural recording device. View Full Article
China’s Baidu to Open Source Its Deep Learning AI Platform, SiliconANGLE (08/31/16) Robert Hof
China’s Baidu on Thursday announced it will make its artificial intelligence (AI) software, PArallel Distributed Deep LEarning (PaddlePaddle), publicly available on GitHub. PaddlePaddle lead developer Xu Wei says the software is designed to be used by a wide range of coders, even those who are not expert in deep learning. “You don’t need to be an expert to quickly apply this to your project,” Xu notes. “You don’t worry about writing math formulas or how to handle data tasks.” Xu also says PaddlePaddle needs considerably less code than certain alternatives. For example, he says a machine-translation model based on PaddlePaddle requires only a fraction of the written code other AI platforms need, while existing models can be applied to new problems without demanding complex equations. Xu says the advantage of open sourcing AI algorithms is the potential to attract more deep-learning engineers. More important as a competitive differentiator than the algorithms themselves is the data they collect, with 451 Research’s Peter Christy noting, “the breakthroughs are much more in how you gather and use training datasets.” View Full Article