Maybe Australians haven't noticed, but the little blue marker showing where you are in Google Maps, or even Apple Maps, isn't as accurate as it could be. It's why Australia is spending over A$260 million (US$193 million) to invest in satellite infrastructure and technology to improve GPS accuracy, as part of the Federal Government's budget announcement. As it stands, Australians get uncorrected GPS signals that are accurate to five metres (5.4 yards). To improve that, the majority of the funds will be invested in a Satellite Based Augmentation System (SBAS), which aims to correct GPS accuracy to around a metre (1.09 yards), across Australia and its maritime zone. On top of $41M for a Space Agency, there's also $260M for satellite imaging & GPS infrastructure through @GeoscienceAus -this will improve GPS location accuracy from 5 metre to 10cm in Australia, and to 3-5cm in urban areas #budget18 @SenatorCash #auspol pic.twitter.com/ZwG7Jmiigh
New technology could soon notify you whether your partner had a good day or if you will be walking into the eye of the storm when you get home. A group of scientists have trained an algorithm to identify past conflict episodes among couples in order to determine when a lover's quarrel may arise in the future. Using physiological data and physiological signals from couples, the technology could automatically send notifications advising individuals to do a short meditation module to restore their mental state before interacting with their significant other. A group of scientists have trained an algorithm to identify past conflict episodes among couples in order to determine when a lover's quarrel may arise. The algorithm gathered physiological data from various sources including wearables, mobile phones, and physiological signals (or bio-signals) to assess couples' emotional states.
Imagine playing a video game like Call of Duty or Battlefield and having the ability to lead your virtual army unit while moving freely throughout your house. Gaming could become this realistic, thanks to new technology developed by Dina Katabi's research group at the MIT Computer Science and Artificial Intelligence Lab (CSAIL) that allows for highly accurate, 3-D motion tracking. The new system, dubbed "WiTrack", uses radio signals to track a person through walls and obstructions, pinpointing her 3-D location to within 10 to 20 centimeters -- about the width of an adult hand. The researchers will present their findings during the Usenix Symposium on Networked Systems Design and Implementation in April 2014. "Today, if you are playing a game with the Xbox Kinect or Nintendo Wii, you have to stand right in front of your gaming console, which limits the types of games you can play," says Katabi, a professor of computer science and engineering and co-director of the MIT Center for Wireless Networks and Mobile Computing.
A field of study that gives computers the ability to learn without being explicitly programmed. Despite this common claim, anyone who has worked in the field knows that designing effective machine learning systems is a tedious endeavor, and typically requires considerable experience with machine learning algorithms, expert knowledge of the problem domain, and brute force search to accomplish. Thus, contrary to what machine learning enthusiasts would have us believe, machine learning still requires a considerable amount of explicit programming. In this article, we're going to go over three aspects of machine learning pipeline design that tend to be tedious but nonetheless important. After that, we're going to step through a demo for a tool that intelligently automates the process of machine learning pipeline design, so we can spend our time working on the more interesting aspects of data science.
The P300 Brain-Computer Interface (BCI) is a well-established communication channel for severely disabled people. The P300 event-related potential is mostly characterized by its amplitude or its area, which correlate with the spelling accuracy of the P300 speller. Here, we introduce a novel approach for estimating the efficiency of this BCI by considering the P300 signal-to-noise ratio (SNR), a parameter that estimates the spatial and temporal noise levels and has a significantly stronger correlation with spelling accuracy. Furthermore, we suggest a Gaussian noise model, which utilizes the P300 event-related potential SNR to predict spelling accuracy under various conditions for LDA-based classification. We demonstrate the utility of this analysis using real data and discuss its potential applications, such as speeding up the process of electrode selection.