This work studies the entity-wise topical behavior from massive network logs. Both the temporal and the spatial relationships of the behavior are explored with the learning architectures combing the recurrent neural network (RNN) and the convolutional neural network (CNN). To make the behavioral data appropriate for the spatial learning in CNN, several reduction steps are taken to form the topical metrics and place them homogeneously like pixels in the images. The experimental result shows both the temporal- and the spatial- gains when compared to a multilayer perceptron (MLP) network. A new learning framework called spatially connected convolutional networks (SCCN) is introduced to more efficiently predict the behavior.

The Galaxy S8 is shipping all over the world, people are raving about it, and it's breaking all sorts of sales records. Samsung's AI assistant Bixby wasn't quite ready to launch when the Galaxy S8 did, so Samsung held back its biggest feature, voice commands, with a vague promise that it will launch "later this spring." But we could be getting to know Bixby sooner than we think. Samsung has launched the voice component of Bixby in its home country of South Korea, a clear signal that the company is hard at work at perfecting its voice recognition engine. The plan has always been for Korean language support to launch first followed by English.

Recently, a co-worker said AI was so extreme that if put in charge of human happiness, it would strap us to a chair on a heroin drip à la "The Matrix." He's watched too many movies. Mostly, AI simply finds "which of these things is not like the other" in a large set--or handles the opposite task of grouping similar objects. It's not something to be afraid of anytime soon, really. But his fantasy made me wonder what other things people think is or isn't coming in the next five years or so.

We investigate the 3-architecture Connected Facility Location Problem arising in the design of urban telecommunication access networks. We propose an original optimization model for the problem that includes additional variables and constraints to take into account wireless signal coverage. Since the problem can prove challenging even for modern state-of-the art optimization solvers, we propose to solve it by an original primal heuristic which combines a probabilistic fixing procedure, guided by peculiar Linear Programming relaxations, with an exact MIP heuristic, based on a very large neighborhood search. Computational experiments on a set of realistic instances show that our heuristic can find solutions associated with much lower optimality gaps than a state-of-the-art solver.

Internet companies are readying for a showdown with telecoms and a Republican-controlled government over a policy near and dear to their hearts: net neutrality. Net neutrality basically prevents broadband providers from playing favourites or steering users toward (or away from) particular internet sites. Under rules enacted during the Obama administration, the likes of Comcast and Verizon -- which offer their own video services they'd very much like subscribers to use -- can't slow down Netflix, can't block YouTube, and can't charge Spotify extra to stream faster than Pandora. Broadband companies hate the net neutrality rules, and they have an ally in new Federal Communications Commission (FCC) chairman Ajit Pai, who has repeatedly called the regulations a mistake. Pai could launch the process of unwinding the rules as early as Wednesday, according to reports.

If there wasn't already a mountain of pressure on Apple to deliver something spectacular with this year's iPhone update, there surely is now. If you haven't noticed, Samsung has released the Galaxy S8 and S8, and they're pretty remarkable. As a former iPhone 7 Plus user, the S8 might very well be the best phone I've ever used, with a stunning screen, speedy processor, and, yes, a gorgeous design. But what makes the S8 so amazing is how unique it is. I got to spend a week with it while writing my review, and I came away stunned.

The densification of small-cell base stations in a 5G architecture is a promising approach to enhance the coverage area and facilitate the ever increasing capacity demand of end users. However, the bottleneck is an intelligent management of a backhaul/fronthaul network for these small-cell base stations. This involves efficient association and placement of the backhaul hubs that connects these small-cells with the core network. Terrestrial hubs suffer from an inefficient non line of sight link limitations and unavailability of a proper infrastructure in an urban area. Seeing the popularity of flying platforms, we employ here an idea of using networked flying platform (NFP) such as unmanned aerial vehicles (UAVs), drones, unmanned balloons flying at different altitudes, as aerial backhaul hubs. The association problem of these NFP-hubs and small-cell base stations is formulated considering backhaul link and NFP related limitations such as maximum number of supported links and bandwidth. Then, this paper presents an efficient and distributed solution of the designed problem, which performs a greedy search in order to maximize the sum rate of the overall network. A favorable performance is observed via a numerical comparison of our proposed method with optimal exhaustive search algorithm in terms of sum rate and run-time speed.

How many virtual assistants can you fit in one smartphone? European network operator Orange is hoping there's room to squeeze in one more. With the right apps, you can already talk to Alexa, Cortana and Google through your smartphone -- and maybe also to Siri or Bixby if you went with one of the big brands. Djingo will be able to answer questions, send text messages, place calls, play music and video from Orange's set-top box, and control smart home devices. It draws on the company's research into linguistics and artificial intelligence, and will even offer financial advice in conjunction with a new banking service Orange is launching, the company said.

The European Telecommunications Standards Institute (ETSI), which wrote the original specification for network functions virtualisation (NFV), has set up its experiential network intelligence industry specification group to handle the task. He sees many parallels between the evolution of cars and where networks can get to. "Years ago, cars were painfully manual, but we've made it much more convenient and 14 years ago we started looking at self-driving cars, which is an absolute disruptive change." In order for self-driving networks to become a reality, vendors and providers must fully collaborate, he says. Interestingly, ETSI's AI initiative, which has an initial two-year work programme, is coming from vendors, ETSI director general Luis Jorge Romero told GTB at Mobile World Congress.