Software launches focus on AI, analytics, 5G for operators - RCR Wireless News


Nokia launched a new offering that utilizes artificial intelligence and machine learning to support customer care as well as analytics for crowd behavior and operational improvements. Rich Crowe, head of OSS marketing at Nokia, said that the new addition to Nokia's customer care suit relies on those algorithms to predict and assist customers in resolving common issues before they disrupt a customer's service. Crowe said that in one case with a fixed network operator delivering residential services, he machine learning capabilities were able to predict and resolve up to 70% of residential issues that would lead to service disruptions, such as issues with the home router or television and internet service, and resolve them before a subscriber was aware of disruption. Nokia's new Cognitive Analytics for Crowd Insight application relies on real-time network data and machine learning to track and analyze aggregated, anonymized user movement.

Google's next smart speaker may double as a WiFi router


If you're Google and you want the next Home speaker to clearly one-up the Amazon Echo, what do you do? A source speaking to the Information claims that an upcoming Home model will include a built-in WiFi router with mesh networking. You wouldn't need to buy a separate router (like, say, Google WiFi) just to connect devices around your household. And even if you already have a router, this would improve Home's performance by giving it a stronger connection in weak coverage areas. The tipster also maintains that the original version of Google WiFi had a microphone and speaker for Home-style interactions, but that Google axed it to avoid confusion.

These boring wifi routers are actually some of the best tech to come out of CES

Popular Science

In October 2016, an attack on Dyn DNS shut down the internet. It soon became clear that the attack was possible because of an overwhelming number of new, unsecured, internet-connected devices--the Internet of Things (IoT). This year's Consumer Electronic's Show has introduced us to plenty of new IoT devices, including cute robots, new capabilities for Amazon's Alexa (despite the fact that she keeps buying things for people that they didn't order), and even a smart hairbrush and pillow, which both sound very necessary. Symantec, the company behind Norton AntiVirus, has come up with a unique answer to the growing IoT problem. Rather than protecting each of your devices individually, Symantec's new wifi router (the Norton Core) will use the company's expertise and software to protect up to 20 laptops, computers, tablets, or smartphones--and an unlimited number of IoT devices--in one fell swoop.

Hey, Poker Face -- This Wi-Fi Router Can Read Your Emotions


A team of researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a device that can measure human inner emotional states using wireless signals. Using EQ-Radio, which emits and captures reflected radio frequency (RF) waves, the team bounced waves off a person's body to measure subtle changes in breathing patterns and heart rates. "The whole thing started by trying to understand how we can extract information about people's emotions and health in general using something that's completely passive--does not require people to wear anything on their body or have to express things themselves actively," says Prof. Dina Katabi, who conducted the research along with graduate students Mingmin Zhao and Fadel Adib. In its test, the team says if their device is trained on each subject separately, it measures emotions with 87 percent accuracy and 72.3 percent accuracy when using a single classifier for all subjects.

Google planning to release WiFi router at October event, Home to cost 129: Report


Google plans to release its own, self-branded wireless router dubbed "Google Wi-Fi" that will retail for 129, according to Android Police. The Google Wi-Fi router is expected to be released at Google's October 4 event, according to the blog, which has correctly pegged past Google releases. Android Police further reports that Google's take on Amazon Echo called Google Home, which was announced at Google I/O in May, will cost 129. Google's plan to release a wireless router could suggest a bigger home push from the search giant, as competitors like Amazon and Apple have gone further into the home.

Google might introduce another WiFi router on October 4th


We're less than two weeks away from Google's big fall event in San Francisco, and we already have a good idea of what to expect -- Pixel-branded smartphones, maybe Google Home, maybe a 4K-capable Chromecast. The OnHub line launched late last summer as a router that's simple to control with your smartphone and good looks that'll make you want to place it prominently in your home. This new Google WiFi router would be presumably built in-house, like the rest of the hardware that Google is set to introduced in October. Additionally, Android Police says that buying multiple routers (they are rumored to cost 129 a pop) would link together to create a mesh network, a nice feature for larger dwelling that are hard to blanket with WiFi signals.

Blindspotter Uses Machine Learning to Find Suspicious Network Activity


NEWS ANALYSIS: The use of machine learning to identify suspicious online activity is a new and important capability in securing the network, but privileged users were the weak point until now.

Sentiment Analysis on Social Network Data (Twitter, Facebook, etc.)


Sentiment analysis is a useful service for just about any business. It is always valuable to know whether your customers are saying positive or negative things about you. This gives you more flexibility to start with their sample and then tweak it to your needs. Then you would deploy it yourself and call it yourself.

A Combinatorial Optimisation Approach to Designing Dual-Parented Long-Reach Passive Optical Networks Artificial Intelligence

We present an application focused on the design of resilient long-reach passive optical networks. We specifically consider dual-parented networks whereby each customer must be connected to two metro sites via local exchange sites. An important property of such a placement is resilience to single metro node failure. The objective of the application is to determine the optimal position of a set of metro nodes such that the total optical fibre length is minimized. We prove that this problem is NP-Complete. We present two alternative combinatorial optimisation approaches to finding an optimal metro node placement using: a mixed integer linear programming (MIP) formulation of the problem; and, a hybrid approach that uses clustering as a preprocessing step. We consider a detailed case-study based on a network for Ireland. The hybrid approach scales well and finds solutions that are close to optimal, with a runtime that is two orders-of-magnitude better than the MIP model.

Sonet Network Design Problems Artificial Intelligence

This paper presents a new method and a constraint-based objective function to solve two problems related to the design of optical telecommunication networks, namely the Synchronous Optical Network Ring Assignment Problem (SRAP) and the Intra-ring Synchronous Optical Network Design Problem (IDP). These network topology problems can be represented as a graph partitioning with capacity constraints as shown in previous works. We present here a new objective function and a new local search algorithm to solve these problems. Experiments conducted in Comet allow us to compare our method to previous ones and show that we obtain better results.