The Defense Department has decided to make a game out of the problem of spectrum crowding. The Spectrum Collaboration Challenge (SC2), the Defense Advanced Projects Research Agency's newest Grand Challenge, will reward teams that develop systems that collaboratively (as opposed to competitively) adapt in real time to changes in congested electromagnetic spectrum, DARPA said in a release. SC2's primary goal is to imbue radios with advanced machine-learning capabilities to collectively develop strategies for optimizing use of the wireless spectrum that aren't possible today due to the intrinsically inefficient approach of pre-allocating exclusive access to designated frequencies. Making more efficient use of the finite spectrum environment has become a DOD priority as the spectrum becomes ever more crowded, and DOD has to comply with a presidential order to free up 500 MHz of its spectrum for commercial use by 2020. "I think today we're in a good spot…We did well with the last auction and the money is there to change where DOD can move and share spectrum," DOD CIO Terry Halvorsen said on March 22.
The two biggest opportunities for spectrum management leading up to 5G and the Internet of Things (IoT) are spectrum sharing and the current review being undertaken by the government, according to Christopher Hose, executive manager of the Australian Communications and Media Authority (ACMA) Spectrum Planning Branch. "There are two very big and important opportunities: The first is technology and what it might mean for sharing into the future," Hose said, speaking at the ACMA's Spectrum Tune-Up event on Monday morning. "Sharing is very much at the heart of what we do in spectrum management, but it has been limited in the past by practical limitations in the technology. For a long time now, the idea of dynamic spectrum access and the use of geolocation and databases and so forth have promised a world where sharing becomes almost automatic and very simple." He added that spectrum sharing is already present in the United States, but that there needs to be more cooperation between industry and the ACMA to achieve this goal -- which is fortunately another opportunity present within Australia.
Nowadays, hyperspectral image classification widely copes with spatial information to improve accuracy. One of the most popular way to integrate such information is to extract hierarchical features from a multiscale segmentation. In the classification context, the extracted features are commonly concatenated into a long vector (also called stacked vector), on which is applied a conventional vector-based machine learning technique (e.g. SVM with Gaussian kernel). In this paper, we rather propose to use a sequence structured kernel: the spectrum kernel. We show that the conventional stacked vector-based kernel is actually a special case of this kernel. Experiments conducted on various publicly available hyperspectral datasets illustrate the improvement of the proposed kernel w.r.t. conventional ones using the same hierarchical spatial features.
EE's 4G coverage now exceeds that of any 3G network in the UK, the carrier has announced, after it switched on 800MHz spectrum capacity at 700 cell sites across the country. This filled in 5,000 square kilometers of 4G'not spots' and improved indoor coverage in half a million homes overnight, according to the provider (the low-frequency signals penetrate trees, walls and such better, you see). EE hopes to add 800MHz capacity to a further 3,000 sites before the end of next year, too. Thanks to the new spectrum rollout, parts of Shropshire, Somerset, Snowdonia, Oban, Glasgow, Berkshire and Derbyshire have been graced with 4G coverage for the first time. There is a bit of fine print attached to this, though.