Collaborating Authors

The Self-Driving Car's Bicycle Problem

IEEE Spectrum Robotics

Robotic cars are great at monitoring other cars, and they're getting better at noticing pedestrians, squirrels, and birds. The main challenge, though, is posed by the lightest, quietest, swerviest vehicles on the road. "Bicycles are probably the most difficult detection problem that autonomous vehicle systems face," says UC Berkeley research engineer Steven Shladover. Nuno Vasconcelos, a visual computing expert at the University of California, San Diego, says bikes pose a complex detection problem because they are relatively small, fast and heterogenous. "A car is basically a big block of stuff.

How Can Lean Six Sigma Help Machine Learning?


I have been using Lean Six Sigma (LSS) to improve business processes for the past 10 year and am very satisfied with its benefits. Recently, I've been working with a consulting firm and a software vendor to implement a machine learning (ML) model to predict remaining useful life (RUL) of service parts. The result which I feel most frustrated is the low accuracy of the resulting model. As shown below, if people measure the deviation as the absolute difference between the actual part life and the predicted one, the resulting model has 127, 60, and 36 days of average deviation for the selected 3 parts. I could not understand why the deviations are so large with machine learning. After working with the consultants and data scientists, it appears that they can improve the deviation only by 10% through data cleansing.

Buffalo AirStation Extreme WXR-1900DHPD review: Open-source firmware is supposed to be a good thing


Fans of open-source software might initially find Buffalo's WXR-1900DPHD appealing because it uses the open-source DD-WRT firmware. This firmware is famous for unlocking hardware features that router manufacturers choose not to expose to end users for one reason or another. But that's not the case here, because Buffalo chose the underdeveloped DD-WRT NXT build, which is stable but not at all comprehensive when it comes to enabling this router's hardware features. One of the most disconcerting omissions is the absence of support for either of the router's USB ports (there's a USB 2.0 port in back and a USB 3.0 in front). Whether you're looking for Time Machine support to back up your Mac, interested in streaming media from shared hard drive, or intend to share a USB printer or scanner over your network, the WXR-1900DPHD's USB ports are absolutely useless with the currently available firmware.

Best AC1900 Wi-Fi router: Buffalo WXR-1900DHPD vs. Linksys EA7500


For most people, an AC1900 Wi-Fi router hits the sweet spot. It delivers enough speed to support media streaming, and enough features to handle the needs of most homes without blasting a hole in your pocketbook. They're not the most powerful, but they're much less expensive than higher-end routers equipped with all the latest whiz-bang features. This review compares two of the newer contenders: the Buffalo WXR-1900DHPD (notable for its use of open-source DD-WRT NXT firmware), and the somewhat more conventional Linksys EA7500 (one of the lowest-price routers to offer MU-MIMO). I'm not a big fan of the router industry's methodology when it comes to identifying 802.11ac router speeds.

3 key ways the Xperia X Performance is a better phone than the Xperia X


Sony has been a relative no-show in the smartphone scene for the last few years, and the recent release of the mid-range Xperia X hasn't done much to improve the company's fortunes. I gave the Xperia X just 3 out of 5 stars, yet there's an even worse phone--the Xperia XA--in the Xperia line-up. But now Sony is touting the Xperia X Performance, which has all the high-end specs that the company needs to compete with its competitors' flagship phones. Will this "performance"-caliber hardware be enough to pull Sony out of its smartphone rut? You'll have to wait for our full review for the final score later this week.