Big Data Customer Engagement Solution Unveiled

Editor's note: This article is by Anshul Sheopuri, research staff member and manager of Consumer Modeling at IBM Research.

Skillsoft, a company that develops learning programs for business and government, recently partnered with us to develop new enterprise learning capabilities. These capabilities, based on advanced algorithms, predict optimal times that a business should engage or interact with customers, and also recommend content the business should provide.

“We're building a powerful new big data engine that will let us optimize learning experiences and uncover new learning patterns that can be applied immediately so that the system is continually improving.

“This is the perfect application of big data: harness it and apply it to improve individual and organizational performance,” John Ambrose, Senior Vice President, Strategy, Corporate Development and Emerging Business, Skillsoft, wrote on his blog.

This "Customer Engagement Solution" we developed addresses a fundamental question in Customer Experience: "How can we transform user engagement?"

Now we can mine the usage patterns of Skillsoft's 20 million user base by using advanced machine learning algorithms and stochastic modeling techniques. This means that a business gets customized content recommendations for different engagement points – the “where” and “how” to talk to customers. The customer’s experience improves, too. They receive personalized visuals that explain why they received those customized recommendations. 


New Physical Phenomenon on Nanowires Seen for the First Time

False-colour scanning electron micrograph of a nanowire strain device.
Very tiny wires made of semiconducting materials – more than one thousand times thinner than a human hair – promise to be an essential component for the semiconductor industry. Thanks to these tiny nanostructures, scientists envision not only a more powerful new generation of transistors, but also to integrate optical communication systems within the very same piece of silicon. This would make possible data transfer between chips at the speed of light.

But for optical communication to happen, it is essential to convert the electrical information used in the microprocessor into light, by using light emitters. On the other end of the optical link, one needs to translate the information contained in the stream of light into electrical signals by using light detectors. Current technologies use different materials to realize these two distinct functions – silicon or germanium for light detection and materials combining elements from the III-V columns of the periodic table for light emission. However, this might be going to change soon thanks to a new discovery.

In a paper appearing today in the journal Nature Communications, scientists at IBM Research – Zurich and the Norwegian University of Science and Technology have demonstrated for the first time that both, efficient light emission and detection functionalities can be achieved in the very same nanowire material by applying mechanical strain.

Using this new physical phenomenon, scientists might be able to integrate the light emitter and the detector functions in the very same material. This would drastically reduce the complexity of future silicon nanophotonic chips.

IBM scientist Giorgio Signorello explains, "When you pull the nanowire along its length, the nanowire is in a state that we call “direct bandgap” and it can emit light very efficiently; when instead you compress the length of the wire, its electronic properties change and the material stops emitting light. We call this state “pseudo-direct”: the III-V material behaves similarly to silicon or germanium and becomes a good light detector."

IBM Fellow Heike Riel comments, “These are unique and surprising properties and they all come from the fact that the atoms are located at very special positions within the nanowire. We call this crystal structure “Wurtzite”. This structure is possible only because the nanowire dimensions are so small. You cannot achieve the same properties at dimensions visible to the eye. This is a great example of the power of nanotechnology.”

This remarkable properties might find interesting applications also outside the field of optical communication.

For the scientific background read the Nature Communications paper titled "Inducing a Direct-to-Pseudodirect Bandgap Transition in Wurtzite GaAs Nanowires with Uniaxial Stress”, doi:10.1038/ncomms4655


Powering communities with discarded laptop batteries

By Vikas Chandan, Research Staff Member with IBM’s Smarter Energy Group

Located right across Bangalore’s Ramaiah College is Chill and Grill, a fast-food joint that is an easy jaunt for students as well as young working professionals who work in the area. The piping hot evening snacks such as wraps and samosas attracts large crowds. And business has been growing for Lalit, 39, who has been running the eatery for more than five years. While business is good, he’s had a persistent worry – the frequent power outages in the neighborhood. He cannot afford inverters or diesel generators to provide back up power, and sans an alternate, business stops until the lights come back on.

Even I go to Chill and Grill with my team, Harshad Khadilkar, Zainul Charbiwala and Deva Seetharam, and Rajesh Kunnath and Deepak Ramakumar, and colleagues from our hardware partner, RadioStudio. We had an idea for Lalit.
Lalit, on right, with one of his employees at the Chill and Grill.
By using discarded laptop batteries, we created a device that could power lights, fans and mobile phone chargers. The specific prototype we built was able to provide around 20 Watt-hours of energy. In other words, it can power a 5W DC light bulb for about four hours before running out of charge.

The device, targeted at the Bottom of the Pyramid market (a country’s poorest socio-economic group) made famous by the late management guru, C.K.Prahlad, would be particularly useful for rural or semi-urban populations of developing countries like India – and for those like Lalit, who cannot afford to buy high-end power backup options such as inverters or diesel generators. For example, in villages which only get a few hours of power every day, the device could be charged when power is available through a community charging center. It can then be used to run devices during nights when power might not be available, such as lights for children to study. Road-side vendors, who might not have access to power from the grid, could also charge needed devices before leaving home in the morning, and use them at their shops at night.

The prototype of the device was built with help from RadioStudio. It took four steps:
  • Source laptop battery packs through organized electronic waste (e-waste) collectors
  • Disassemble the packs to extract individual cells that could still deliver power
  • Connect re-usable cells together to build a refurbished battery pack
  • Build a box that contains a charging circuit for the pack of refurbished batteries, converters, and other electronics to power the external devices such as lights and fans.

Battery Pack
Battery Pack

We estimate the bill of material for the device to be about Rs1000 (about $US16.50) each, when compared to conventional backup solutions such as inverters and diesel generators which usually cost upwards of Rs 10,000 (about $US165). The pricing includes the enclosure, electronics, DC fan and an LED light.

Having installed the device at Chill and Grill, we found that it was able to provide about four hours of backup power when the batteries were fully charged. 

Our team also believes that several variants of the device are possible depending on economic and technical feasibility, such as inclusion of a mechanical battery rack instead of a small battery pack; a low battery cut-off indicator; dead battery cell indicators; and the use of other types of battery packs such as cellphone batteries. And we’re also exploring solar energy charging.

The device attempts to mitigate the environmental and economic issues associated with e-waste by providing a means to re-use discarded batteries. In particular, if this technology is adopted commercially at a large scale, it can incentivize organized collection of e-waste. A large chunk of e-waste collection in India is still handled by the informal sector consisting of local garbage dealers or kabariwallas, which is currently unregulated and poses safety and environmental problems.

The device offers potential business opportunity for companies engaged in rural and semi-urban electrification missions. It doesn’t require much capital investment and is easy to build. It also provides a cleaner and potentially cheaper alternative than burning kerosene lamps, and is also compact, light weight, and portable. Most importantly, the device can power homes and communities at the “bottom of the pyramid” for whom access to reliable power is still a challenge.

Back at Chill and Grill, Lalit has been happy with the amount of light he can get from his device. My team is confident that the device will be made commercially available and widely adopted.

KwaZulu-Natal Research Institute and IBM Research Fight Tuberculosis in South Africa

Eamon Duffy, K-RITH Research
Intern reading TB culture plates
On World Tuberculosis Day, IBM and the KwaZulu-Natal Research Institute for Tuberculosis and HIV (K-RITH) have announced plans to research new treatment approaches to fight tuberculosis (TB) in South Africa. IBM’s Big Data analytics technologies will be put to work on bacterial genetics and drug susceptibility tests to better understand the genomic mechanisms that cause resistance to antibiotics. The ultimate goal is to find new treatments and diagnostic approaches to fight TB. 

The scale of the TB problem in Southern Africa is largely a result of HIV infection, lack of integration between HIV and TB treatments and historic challenges in healthcare delivery. Currently South Africa has the world's third highest burden of TB, with the province of KwaZulu-Natal being the most affected by both drug-susceptible and drug-resistant tuberculosis. Over 100,000 cases of TB are reported every year from this province alone and over 60% are also infected with HIV. 

The KwaZulu-Natal Research Institute for Tuberculosis and HIV (K-RITH), which is based at the University of Kwazulu-Natal’s Nelson R. Mandela School of Medicine, is an independent research institute established in 2009 to conduct basic science research into TB and HIV, and translate the scientific findings into new tools to control these deadly diseases. The Institute's work has boosted the TB and HIV research capabilities of scientists in South Africa. The work with IBM involving its Big Data and deep data analytics technology-- will enable K-RITH to understand bacteria genomes from drug-resistant strains of M. tuberculosis-- the bacteria that causes TB. 

According to Associate Investigator at K-RITH, Dr. Alex Pym, the agreement with IBM is “a significant collaboration” that gives South African scientists access to IBM’s computational expertise in bioinformatics and machine learning. “This will allow us to analyze data in new and imaginative ways and it holds the promise of giving us better insight into the mechanisms of drug resistance, leading to better diagnostic tests,” said Dr. Pym.

The science has benefitted from IBM’s global network of research labs and world leading expertise in computational biology. Researchers from the Haifa, Melbourne, and Africa labs are working together to analyze over 200 TB genomes, each with 4.4 million base pairs, to better understand the complex clinical picture of African tuberculosis infections.

The classic mycobacterial stain is an acid fast
stain, in which TB appears red with a blue counterstain.
Michal Rosen-Zvi, senior manager of analytics at IBM’s Research Lab in Haifa, Israel said, "TB drug resistance is a far more complex genome by comparison to something like the HIV virus. The bioinformatics or computational tools needed to extract information on the disease are very new, yet cracking the code of this genomic information will help define which treatment combinations work best for different patients and how they work on different strains of TB."

“For HIV, technology can look at the difference in viral load before and after treatment, and use that to understand whether the treatment was a success. But in TB, there is no single measure that defines the status of the disease. We will need to develop multiple ways to label the treatment outcomes and new methods to indicate whether a treatment was effective,” said Rosen-Zvi.

IBM's work on other solutions, including the well known EuResist programme, developed to help physicians select the optimal treatments for HIV patients, have paved the way for the use of bioinformatics in disease treatment. EuResist combines large databases and new prediction engines to provide predictive modeling of how HIV would react in a particular person treated with specific combination of drugs. This system, available since 2008, is the world’s largest database containing clinical and genomic information on HIV. 

Dr. Pym said, “What we believe is that through the partnership between K-RITH and IBM we can combine and enable TB analytics from IBM to map which antibiotic treatments are successful for which TB strains. And then, by finding the associations between the genetic markers and the correct antibiotic treatment, we can improve treatment protocols. This can make a significant difference to many lives across the globe, let alone Africa.”

Sequencing of the KRITH strains was performed by the Broad Institute, a world leader in genomics, with funding from the National Institute of Allergy and Infectious Diseases of the U.S. National Institutes of Health. Analysis of sequencing data from the K-RITH strains and other organizations in South Africa was given first priority due to the magnitude of TB drug resistance in that country.  

The research work at IBM and K-RITH can interact with global initiatives like TBresist, and with leadership and collaboration from organizations such as the CDC Foundation. The intent is to add data from different parts of the world, from different strains of TB, to culture a global database that researchers and physicians can use to determine the best treatment to combat a particular strain of tuberculosis. The impact of this would be more effective treatments for patients and a reduction of the cost of treating tuberculosis in Africa and potentially around the world.

In similar news, last week the New York Genome Center and IBM announced that they will test a unique IBM Watson prototype designed specifically for genomic research as a tool to help oncologists deliver more personalized care to cancer patients. 

IBM is making a long term, strategic investment in the future of Africa and the company’s new Africa research lab is at the heart of its operations. IBM has been present in Africa for over 70 years and today has a presence in over 20 African countries, including Tanzania, Senegal, South Africa, Morocco, Egypt, Tunisia, Algeria, Ghana, Nigeria, Kenya, and Mauritius


Advancing brain cancer treatment through genomics

IBM and the New York Genome Center testing Watson prototype on glioblastoma

By Dr. Ajay Royyuru, Director of IBM Research’s Computational Biology Center

We have put Watson to work in any number of different ways and in any number of different industries. Healthcare, though, was its first real job. It’s gone to medical school, and even studied health insurance. And now Watson is working with the New York Genome Center to launch a pilot that tackles a new medical challenge – glioblastoma.
Dr. Robert Darnell, MD, PhD, President, CEO and Scientific Director of the New York Genome Center
(left) and Dr. Ajay Royyuru, PhD, Director of the Computational Biology Center, IBM Research (right)

The most common kind of brain cancer, glioblastoma annually kills 13,000 people in the US alone. As a cancer of the brain, it’s difficult to take tissue samples, for one, so it can’t be examined like most other kinds of cancers. And it moves quickly. Diagnosis to death is on average only 12 months.

All cancers are a disease of the genome. It’s the genome itself that’s progressively changing from normal to abnormal when someone has cancer. When we can determine which genes start to “go bad,” we can better-determine what specific treatment would work to stop it. Therein lies the challenge: How can we better understand what is happening at a genetic level?

The key to glioblastoma’s genetic code is in the human genome. So while we know our cells’ biochemical pathways, it’s also an overwhelming amount of data – billions of DNA base sequences, plus millions of studies, medical documents and clinical records.

Different kinds of brain cancers manifest in different ways and progression rates, so finding these details about glioblastoma is a molecule-sized needle in the genome haystack.

That’s why my team – with decades of research experience in biology as a data science – and NYGC, with the expertise and resources of a dozen top hospitals and medical schools, are collaborating on a project with Watson in genomics. Our goals with this prototype and ensuing studies are to assist physicians with discovering personalized treatment for patients with glioblastoma.

Watson can read millions of pages of medical literature in seconds. By applying its natural language processing and analytics to the genome, it could find connections between what’s buried in journals about the interaction of certain genes, and where those genes are in the genome. And so, in the same way Watson evaluates and hypothesizes on other medical diagnosis based on electronic health records and a doctor’s evaluation (see a demo), it could evaluate and hypothesize about mutations in a cancer cell’s genome that caused the disease, not based on a wide demographic swath of those with similar characteristics, but for an individual based on their personal genome.

Connecting medical literature to the genome


Today, we know and have detailed medical literature on the biochemical pathways our genes take. But we don’t know where in the genome these cancerous perturbations happen in that molecular network of interactions. So, we’re loading Watson with genome data from NYGC, along with medical literature to map out where these deviations happen. Watson will be able to see that, in the context of given cancer mutations in the genome, which pathways matter. And in the context of those interactions, suggest evidence of potential treatments.

This journey takes clinicians from trials, to validating what genomic knowledge improves treatment, to routine analysis that helps patients. Ultimately, we want to see our partners at NYGC and physicians upload genomic data into the Watson Genome on the cloud, where the system could quickly synthesize a personalized report of available evidence of treatment options.


Help Set a Guinness World Records Title

IBM scientists are partnering with National Geographic Kids to set a Guinness World Records title for the world's smallest magazine cover.

You can participate by voting for your favorite
National Geographic Kids cover here.

How will we create the world's smallest magazine cover? 

The SwissLitho NanoFrazor Probe
IBM scientists have invented a tiny chisel with a nano-size tip 100,000 times smaller than a sharpened pencil point. Using this tip the scientists will etch the magazine cover onto sliver of polymer (plastic) called polyphthalaldehyde. If they are successful, the cover will be so small that 2,000 of them could fit on a grain of salt.

The tip, similar to the kind used in atomic force microscopes, is attached to a bendable cantilever that controllably scans the surface of the substrate material with the accuracy of one nanometer—a millionth of a millimeter. By applying heat and force, the nano-sized tip can remove substrate material based on predefined patterns, thus operating like a “nanomilling” machine or 3D printer with ultra-high precision.

Similar to using 3D printer, more material can be removed to create complex 3D structures with nanometer precision by modulating the force or by readdressing individual spots.

Sound familiar? It should, IBM scientists announced this breakthrough innovation in 2010 in a series of papers published in the journals Science and Advanced Materials where they demonstrated the technique to create a map of the world. Check out the video below to see how they did it.

This new capability may impact the prototyping of new transistor devices, including tunneling field effect transistors, for more energy efficient and faster electronics for anything from cloud data center to smartphones.

IBM scientists envision other applications as well in the emerging field of quantum systems. One way to address and connect such quantum systems is via electromagnetic radiation or light. The new technique may be used to create high quality patterns to control and manipulate light for this purpose at unprecedented precision. 

The technology has been licensed by IBM to the Swiss start-up SwissLitho who brought the desktop-sized tool to market under the name NanoFrazor.

Click and Vote

Voting is now open.
Check back on the NG KIDS website on April 11 to find out which cover will be turned into the world's smallest magazine cover. 

After it's miniaturized, the tiny cover will be unveiled on April 25 at the 2014 USA Science and Engineering Festival in Washington DC. If you plan to attend the event stop by the IBM and National Geographic Kids booth to meet the scientist who created the cover and to see it for yourself.

Cognitive Cooking: Applying Computational Creativity to Recipe Generation

Editor's note: This article is by Pavankumar Murali, an IBM Research staff member in Business Solutions and Mathematical Sciences.

Pulse is IBM’s Cloud Computing conference. Public clouds. Private cloud. Clouds as a service. Even a new developers’ cloud called BlueMix. At this year’s conference, I was there to demonstrate something that runs on the cloud – our Cognitive Cooking technology.

I’m part of an IBM Research team exploring whether a computer can be creative. And we chose the culinary arts in our effort to design a system that generates surprising yet flavorful recipes not found in any cookbook. So, there I was, a computer scientist standing in front of the IBM Food Truck, showing conference goers how a cognitive system can generate unique recipes – all the while, they picked up machine-generated, Institute of Culinary Education (ICE) chef-prepared dishes like Austrian chocolate burritos (as voted on Twitter by the public).

This cognitive cloud-based system can reason about flavor the same way we use our palate. It combines databases of recipes, ingredients, flavor compounds, food-pairing theories, as well as psychological data about human perception of taste to come up with a novel, yet pleasant, recipe. 

The system starts the recipe genesis process by combing through tens of thousands of existing recipes to learn about ingredient pairing, ingredient-cuisine pairing, and dish composition. It then designs recipes by cross-referencing data on the chemistry of the ingredients, and the psychology of people’s likes and dislikes (hedonic perception theory) to model how our palate might respond to different combinations of flavors. This results in quintillions of possible recipes, which are narrowed down to around 5,000 options by employing sampling techniques. 

At Pulse, the ICE chefs then chose what dish to prepare from the samples, including this Creole shrimp-lamb dumpling (find other recipes, here).

The capabilities of such a cognitive computing system will be truly realized when it can scale and meet performance guarantees. For this purpose, we are currently developing novel optimization algorithms that can generate recipes that, while adhering to knowledge of food chemistry, and human perception, are guaranteed to deliver one or more of our evaluation metrics, such as surprise, pleasantness and flavor pairing. Due to the nonlinear and non-convex nature of the search space (the quintillion ways in which ingredients can be combined), and the constraints on the algorithm's run-time, developing such search algorithms can be quite complex.

The cognitive cooking system runs on the bare metal servers of IBM’s SoftLayer cloud. Bare metal machines in the cloud allow us to get every ounce of performance possible, and also eliminate sharing system resources typically found in other cloud arrangements. 

Surmounting this “creative” challenge also helps us then examine how the technology could make a bigger societal impact. For example, the system could be adjusted to take into account food allergies, dietary restrictions, or other nutritional needs. This could mean school cafeteria lunches that students like, and meet diet nutritional requirements.

Beyond food, what we learn from this research will also lay the groundwork for how the system could apply to the design and discovery of things in other domains. “Taste” could refer to how we experience retail or a good. What if computational creativity helped develop new clothing fashion or scent of cologne? These are the kinds of ideas where we’re applying this technology.

In the meantime, we’re still working on perfecting creative recipes. You can try some of what we cook up with ICE Chef Michael Laiskonis at the South by Southwest Interactive Conference, March 7-11. You will also meet my colleagues Florian Pinel, who not only wrote many of this system’s algorithms, but is a trained chef; and Rob High, an IBM Fellow and the Chief Technology Officer for IBM’s Watson Group. So, vote for a dish you want to try by tweeting it, here).

About the IBM Food Truck