family member


LoCEC: Local Community-based Edge Classification in Large Online Social Networks

arXiv.org Machine Learning

Relationships in online social networks often imply social connections in the real world. An accurate understanding of relationship types benefits many applications, e.g. social advertising and recommendation. Some recent attempts have been proposed to classify user relationships into predefined types with the help of pre-labeled relationships or abundant interaction features on relationships. Unfortunately, both relationship feature data and label data are very sparse in real social platforms like WeChat, rendering existing methods inapplicable. In this paper, we present an in-depth analysis of WeChat relationships to identify the major challenges for the relationship classification task. To tackle the challenges, we propose a Local Community-based Edge Classification (LoCEC) framework that classifies user relationships in a social network into real-world social connection types. LoCEC enforces a three-phase processing, namely local community detection, community classification and relationship classification, to address the sparsity issue of relationship features and relationship labels. Moreover, LoCEC is designed to handle large-scale networks by allowing parallel and distributed processing. We conduct extensive experiments on the real-world WeChat network with hundreds of billions of edges to validate the effectiveness and efficiency of LoCEC.


Microsoft's AI-powered assistant app for the visually impaired will support five new languages

Daily Mail - Science & tech

Today Microsoft announced an update to the Seeing AI app that will include new language output options, including Dutch, French, German, Japanese, and Spanish. The iOS exclusive app was first released in 2017 as a free tool to help people with visual impairments navigate day-to-day life. It's built around a series of different channels, which users can select depending on their particular needs or circumstances. For the first time Microsoft's Seeing AI app will speak in languages other than English. Today's update enables audio output in Japanese, German, Spanish, Dutch, and French In one channel, the app will read out the text of any document the iPhone's or iPad's front facing camera is pointed at.


Facebook built a chatbot to help employees deflect criticism over the holidays

#artificialintelligence

Facebook's public image is in such a disastrous state that the company's public relations team built an artificial intelligence-powered chatbot to help its employees deflect criticism from family members over the holidays, reports The New York Times. The tool, called "Liam Bot" for reasons the company has not disclosed, helps walk employees through tough conversations about Facebook's various controversies. The tool was rolled out to employees shortly before the US Thanksgiving holiday, the NYT reports, and it first entered testing back in the spring. The answers are written by the company's public relations team and largely appear to align with executive team's public statements on topics like free speech, election meddling, moderation, and more. When asked about hate speech, for instance, the NYT reports that Liam Bot will respond with a few available prompts like, "It [Facebook] has hired more moderators to police its content," and, "Regulation is important for addressing the issue."


Doctors Using AI for Cancer Diagnoses Is Sought By Millennial Parents

#artificialintelligence

Around the globe, a majority of Millennial parents say they are very likely to seek out a doctor using AI for cancer diagnoses should their child or a family member need such an evaluation. A majority of Millennial parents in China (94%), India (88%) and Brazil (78%) would be very likely to seek out a doctor using AI for cancer diagnoses for their child or a family member, while 59% of U.K. parents and 53% of U.S. parents are very likely to do so.


Artificial Intelligence Identifies Patients with Potentially Fatal Genetic Disease

#artificialintelligence

A Stanford University-led team of scientists has developed a machine learning tool that can analyse electronic healthcare records (EHR) to identify individuals who are likely to have familial hypercholesterolemia (FH), an underdiagnosed genetic cause of elevated low-density lipoprotein (LDL) cholesterol, which puts patients at a 20-fold increased risk of coronary artery disease. In separate test runs the classifier, described today in npj Digital Medicine, correctly identified more than 80% of cases--its positive predictive value (PPV)--and demonstrated 99% specificity. The team says the classifier could help to flag up patients who are most likely to have FH, so that they and their families can undergo further genetic testing. "Theoretically, when someone comes into the clinic with high cholesterol or heart disease, we would run this algorithm," said Nigam Shah, MBBS, PhD, Stanford University associate professor of medicine and biomedical data science. "If they're flagged, it means there's an 80% chance that they have FH. Those few individuals could then get sequenced to confirm the diagnosis and could start an LDL-lowering treatment right away."


Ancestry Debuts the World's Largest Digital Archive of Searchable Online Obituaries and Death Announcements, Powered by Cutting-Edge Artificial Intelligence

#artificialintelligence

LEHI, Utah & SAN FRANCISCO--(BUSINESS WIRE)--Today, Ancestry, the global leader in family history and consumer genomics, is releasing the new Newspapers.com Obituary Collection and announcing an upgrade to its U.S. Obituary Collection, adding to what is now the world's largest, searchable digital archive of over 262 million worldwide obituaries and death announcements, containing almost 1 billion searchable family members. Obituaries are one of the most comprehensive records available about an ancestor. An obituary can act like a'starter kit' for family history -- it can include places of birth, marriage, occupation, residence, and family members, and may even suggest burial site location. One-third of Americans are unable to name all four of their grandparents,* but obituaries offer one of the easiest ways to understand recent family history and launch a journey of personal discovery.


Sony's $2,900 robotic dog AIBO will soon be able to turn on microwaves, vacuum cleaners and more

Daily Mail - Science & tech

If you've ever thought turning on your microwave or vacuum cleaner was too hard, the solution may be as easy as spending $2,900 on a robotic dog that will do it for you. That's the operating theory behind Aibo, a robotic pet canine created by Sony, which was released last year. Sony has been continually adding features to Aibo and the latest features will allow the small robotic dog to communicate with a range of household smart appliances to help make life easier for its owners. According to a report from Gizmodo, Sony hosted a demonstration of the new features at the CEATEC show in Tokyo, Japan's largest IT and electronics trade show. One example showed Aibo communicating wirelessly with a smart microwave, telling it to start cooking a snack as soon as its owners come home from a long day.


Laundroid: A home robot that folds and sorts clothes ZDNet

#artificialintelligence

Engineers at Tokyo-based company Seven Dreamers started developing a laundry-folding robot called Laundroid in 2005, and now, there is finally a robot to show off at CES 2018. We haven't seen it in person yet, but we spoke with Seven Dreamers CEO Shin Sakane for a preview. The idea is: You drop clean, dry clothes into a box in a pretty home appliance, and then several hours later you can collect the folded, sorted items. "Soft material like clothing is one of the hardest problems for AI even now," Sakane says. "Laundry folding seems like an easy task but it's actually very hard, so that's why no one has ever done it before."


Trifo Adds a Little Brother, Max, to Its A.I.-Powered Line of Robot Vacuums Digital Trends

#artificialintelligence

One of Silicon Valley's million robot companies brought another cool toy to the IFA conference in Berlin this month, and it sees, hears, and speaks as it cleans. The company is Trifo: They've been around for a few years, and they're tapping into a seriously lucrative market. According to the company, Statista estimates that shipments of home robots will grow to nearly 30 billion units by 2025 and The International Federation of Robotics says the personal household service robots market will reach over $10 billion by 2020. The new gizmo, announced at the IFA event in Berlin last week, is Max, a delightfully simple brand for a pretty curious, aware, and able robot. Trifo also launched Ironpie at CES in Las Vegas early this year, a smart robot vacuum that reportedly "cleans faster, protects furniture better, is controllable from anywhere, and with a host of features that improve on the original home vacuum concept."


How a doctor and a linguist are using AI to better talk to dying patients

#artificialintelligence

One afternoon in the summer of 2018, Bob Gramling dropped by the small suite that serves as his lab in the basement of the University of Vermont's medical school. There, in a grey lounge chair, an undergrad research assistant named Brigitte Durieux was doing her summer job, earphones plugged into a laptop. Then he saw her tears. Bob doesn't balk at tears. As a palliative care doctor, he has been at thousands of bedsides and had thousands of conversations, often wrenchingly difficult ones, about dying. But in 2007, when his father was dying of Alzheimer's, Bob was struck by his own sensitivity to every word choice of the doctors and nurses, even though he was medically trained. "If we [doctors] are feeling that vulnerable, and we theoretically have access to all the information we would want, it was a reminder to me of how vulnerable people without those types of resources are," he says. He began to do research into how dying patients, family members, and doctors talk in these moments about end of treatment, pain management, and imminent death. Six years later, he received over $1 million from the American Cancer Society to undertake what became the most extensive study of palliative care conversations in the US.