{"id":1025,"date":"2011-09-15T10:40:07","date_gmt":"2011-09-15T14:40:07","guid":{"rendered":"https:\/\/engineering.jhu.edu\/magazine-archive\/?p=1025"},"modified":"2017-08-02T10:39:19","modified_gmt":"2017-08-02T14:39:19","slug":"data-driven","status":"publish","type":"post","link":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/","title":{"rendered":"Data Driven"},"content":{"rendered":"

As computing ability jumps by leaps and bounds, researchers wrestle with making the best use\u2014and reuse\u2014of all that data.<\/em><\/p>\n

\"data-driven\"<\/a>On July 16, 1969, Apollo 11 left the Earth bound for the moon with the most sophisticated guidance computer of its time. Built by the finest engineering minds, it held the lives of three Americans and the hopes of the entire planet in its solid-state memory.<\/p>\n

All 32 kilobytes of it.<\/p>\n

These days, one doesn\u2019t have to travel to orbiting satellites to find that kind of computational capacity. Heck, just reach in your front pocket; the average 32 GB iPhone has 1 million times the computing memory that navigated for Neil Armstrong and Co.<\/p>\n

Quantifying this quantum jump in artificial intelligence often comes down to an explanation of the law, in this case Moore\u2019s law. In 1965, Intel\u2019s Gordon Moore noted that the number of transistors that could be placed on a chip was roughly doubling every year. Ever since, Moore\u2019s law has held almost true (the doubling has occurred more on the order of every two years, but still…).<\/p>\n

Moore\u2019s law applied to a computer\u2019s processing speed, but clearly data storage has kept pace. Entire genomes can now be stored on drives that fit in the palm of the hand, while galaxies might call for something a little bigger\u2014like a drive the size of a cigar box.<\/p>\n

That ability to collect and store data has infiltrated nearly every aspect of the human condition while captivating human imagination. From exploring the heavens to researching repetitive motion injuries, if an action can be observed\u2014whether it\u2019s stargazing or typing\u2014it stands a very good chance these days of being quantified and placed in a database.<\/p>\n

Organizing all that data \u2014and making it more easily accessible\u2014is arguably the next great wave in computing, akin to the way the Dewey Decimal System brought order to what had been the chaos of referencing the printed word.<\/p>\n

\u201cI think of computing as having gone through three generations at this point,\u201d says Greg Hager, chair and professor of computer science at the Whiting School. \u201cWe had the hardware generation, which was concerned with constructing the computer, the software generation where we were more concerned with what ran inside the computer, and now the data generation\u2014which is about what computing can do to essentially take data and turn it into usable information.\u201d<\/p>\n

Information that for many Whiting School faculty is changing the way they do business and, in turn, impacting how each of us lives our lives.<\/p>\n

 <\/p>\n

\"Data-Driven\"<\/a>MODEL HEART<\/strong><\/h2>\n

Even before Apollo soared into space, or Gemini, or even Mercury, the human heart was the target of some of the first computational modeling. It is a story Rai Winslow, professor of biomedical engineering and director of the Whiting School\u2019s Institute for Computational Medicine, is fond of telling. How, in November of 1960, a lone wolf researcher named Denis Noble published the first paper showing how heart cells\u2014aka cardiac myocytes\u2014functioned, notably how they could fire off long-lasting bolts of electricity, the first clue into how the heart as an organ contracted and acted as a pump.<\/p>\n

It was glorious work that, Winslow laughs, Noble conducted under less than ideal conditions at the University of Oxford. \u201c[His model] was done on an old computer, very slow, very little memory\u2014something like 16 kilobytes\u2014it was hard to program and took a long time to even simulate one [myocyte electrical] action potential. The computer was hard to get access to; he sneaked into the basement where this computer was, programmed it at night \u2026 but it was a tour de force of modeling at the time.\u201d<\/p>\n

Some 30 years later, that paper and its author changed the course of Winslow\u2019s career path. The two met by happenstance and found their work, though separated by a generation, had a computational link. Winslow was modeling electrical activity in a different part of the body. He was investigating neural information processing\u2014collecting thousands of readings and millions of data points to reconstruct the electrical action of neurons up and down the visual pathway from the retina to the brain. The goal: to better understand how the eye encoded vision in a way that the brain could process.<\/p>\n

\u201cDenis saw how we were using large-scale parallel computing to simulate neural network models, no one had done that before, and his response was \u2018Gee\u2026you have [the equivalent of] a heart here. You just need to put in different [electrical] currents.\u2019\u201d By looking at Winslow\u2019s leap from the work of a cell to an entire system, \u201cNoble realized that the cell modeling he had been doing could be translated to the level of tissue and the whole heart using these same computer modeling techniques,\u201d says Winslow.<\/p>\n

That\u2019s exactly what Winslow has done, embarking on a fascinating journey that has allowed him to model the heart on both a macro- and micro-level. In the 1990s, collaborating with Noble, Winslow uncovered how the heart\u2019s spark plug\u2014the sinus node\u2014functioned. It seemed so incongruous to scientists: How could a tiny clump of cells located in the northwest corner of the heart essentially run the whole show? \u201cYou\u2019d think that the [heart] is so big that node couldn\u2019t generate enough current to do that,\u201d says Winslow.<\/p>\n

It turns out the elegant node didn\u2019t have to provide the entire electrical wallop, just a wee oscillation of current\u2014enough to activate the microscopic filaments of atrial [heart] tissue that penetrate deep into the node. Like a roar that starts with a single voice, the node\u2019s spark sends its voltage out the filaments, and the atrial tissue does the rest of the work, convincing other, larger cardiac cells to add their juice to the wave that spreads over the heart, causing it to contract in time.<\/p>\n

Winslow had successfully modeled a healthy heart, which led to an obvious question. What happens in a diseased heart marked by notoriously poor electrical timing, such as the common case of congestive heart failure? To model that, Winslow has gone back to where it all started\u2014those cardiac myocytes\u2014but in levels only recently made possible by advanced computer imaging and data processing. Winslow was able to dissect what he says were \u201cterabytes\u201d of information to make a rather startling and somewhat apropos discovery: It turns out that not only is the heart a pump, but each myocyte is also a pump\u2014perhaps many of them\u2014that regulates the flow of calcium, sodium, and potassium throughout the cell. Those internal mechanisms control both the cell\u2019s ability to create energy and the timing by which it fires out of the cell.<\/p>\n

Winslow\u2019s models\u2014and the data upon which they are built\u2014have uncovered a connection between failing cells and a lower release of calcium during heart contractions. Armed with that knowledge, Winslow says at least one drug company is already investigating whether it can target the calcium imbalance and perhaps improve failing hearts.<\/p>\n

\u201cI think that\u2019s the point of these kinds of models,\u201d says Winslow. \u201cIf you find a compound that blocks a particular calcium pump, how does that fit into the big picture of the networks that molecule participates in?<\/p>\n

\u201cIt\u2019s a systems-level problem, and that\u2019s the power of these sophisticated models \u2026 to help point out targets in treating disease.\u201d<\/p>\n

And that, my friends, gets right to the heart of the matter.<\/p>\n

 <\/p>\n

\"data-driven-2\"<\/a>EASY ACCESS: A TOUGH PROBLEM<\/strong><\/h2>\n

It\u2019s one thing to create reams of data but quite another to have anyone else come along and make sense of it. That\u2019s the conundrum facing Sayeed Choudhury, associate dean for Library Digital Programs at Hopkins\u2019 Sheridan Libraries. The Sheridan Libraries are the information nexus for all of Hopkins and for researchers around the world. Choudhury\u2019s job is to make sure the digital end\u2014which is quickly becoming the majority of the various collections\u2014remains accessible as data storage technology constantly changes.<\/p>\n

That old library model of placing a book on a shelf for a decade until some curious researcher decides to retrieve it is quickly changing. Imagine said researcher opening those pages to find them either blank or horribly jumbled, and you get some idea of the challenge facing Choudhury \u201988, MSE \u201990, who is both a librarian and a Whiting School alumnus.<\/p>\n

\u201cOur view is preservation. When you\u2019re talking about digital content, there are plenty of cases of data generated five years ago where I could not go to a researcher today and say, \u2018Could you please give me those data?\u2019\u201d Part of the issue is how and where data has been stored. Think of having a 5 \u00bd-inch floppy disk in your possession. Sure there may still be information on it, but it\u2019s like owning a Betamax tape: Where are you going to find a playback unit?<\/p>\n

\u201cI\u2019ve said that in five years, a 1-terabyte hard drive [the current standard] is going to be like a 5 \u00bd-inch floppy disk,\u201d notes Choudhury, adding that there\u2019s more than technological obsolescence facing data collection. There\u2019s often a false sense of security, what Choudhury calls \u201ca na\u00efve approach that \u2018I\u2019ve got copies of [the data] so what\u2019s the problem?<\/p>\n

\u201cThe problem is that copies get corrupted\u2014you ought to check those copies regularly. And even if you do everything right from the viewpoint of the bits and the media, on a deeper fundamental level, there\u2019s context associated with data. [Researchers] tell you an amazing story of their data and what they\u2019re doing with it, but I can assure you they have often not documented all of that in a way that someone without any knowledge of the work could come along and say, \u2018OK, I get it, I can take your data and run my own analysis against it.\u2019\u201d<\/p>\n

Given his unique background, Choudhury sees himself as the human interface between researchers who create the data, librarians who want users to make data easily searchable, and software engineers who can design the appropriate algorithms and metadata context to make it so. On a pragmatic level that means he has lots of conversations with everyone from storage manufacturers to scientists anticipating future use of their data.<\/p>\n

Working with National Science Foundation grants, Choudhury has reached out to large data collection projects such as the Hopkins-led Sloan Digital Sky Survey, which bills itself as \u201cthe most ambitious astronomical survey ever undertaken.\u201d Its goal is to map literally a quarter of the heavens, and that\u2019s a lot of data \u2026 on the order of 140 terabytes. \u201cSloan can keep its data on disks, back it up, and have IT experts who can fine-tune the databases, it\u2019s part of their budget,\u201d says Choudhury. \u201cWe interfaced with this group as their project was winding down about preservation. They concluded it\u2019s preferable for us to provide long-term curation. We have definitely learned a great deal [from them] that we\u2019re applying to other domains or projects.\u201d<\/p>\n

Pretty soon it may be the scientists who are first approaching Choudhury. There\u2019s nothing like money to motivate, and Choudhury notes that the National Science Foundation now requires all primary investigators to include a two-page data management plan in their proposals, a guarantee that their results won\u2019t end up in the data desert.<\/p>\n

Choudhury says his team is helping researchers formulate data retention strategies\u2014\u201cWe\u2019ve heard from people saying, \u2018Yeah, I understand I have to do this, but honestly, it\u2019s useful, because I can\u2019t even get back to the data I produced five years ago,\u2019\u201d he says\u2014and also sparking curiosity. As word spreads, Choudhury has found some researchers thrilled that their colleagues\u2019 data may be coming online. \u201c[They say], \u2018That will help with collaboration more than anything, because the best insight I get into somebody\u2019s research is the kind of data they produce and the kind of questions they ask about those data.\u2019\u201d<\/p>\n

Now that\u2019s what we call recycling.<\/p>\n

<\/p>\n

\"data-driven_story3\"<\/a>PARTS OF SPEECH<\/strong><\/h2>\n

You may never have heard of Sanjeev Khudanpur, but if you own a phone, you\u2019ve definitely met some of the women in his line of work. They\u2019re universally perky and helpful (or at least they promise to be), and go by a series of All-American Anglo names: Mary, Linda, and perhaps this region\u2019s best known example, Julie … as in \u201cHi, I\u2019m Julie from Amtrak. Where would you like to go?\u201d<\/p>\n

This is the data-intensive world of speech and text recognition software that Khudanpur plies, and \u201cJulie\u201d is just the latest example. \u201cActually, the earliest was a toy, Radio Rex, from the 1960s. It was a plastic dog, it sat in its little dog house, and if you said \u2018REX!\u2019 loudly enough, it jumped out of the house,\u201d laughs Khudanpur, an associate professor of electrical and computer engineering at the Whiting School. Rex was, in his own electronic way, a little hard of hearing. \u201cIt wasn\u2019t really recognizing \u2018Rex.\u2019 You could say \u2018hex\u2019 or \u2018sex\u2019\u2014anything that had the \u2018eh\u2019 sound in it\u2014and it would respond. If you said \u2018baby\u2019 or \u2018dog\u2019 it wouldn\u2019t do anything.\u201d<\/p>\n

By comparison to Rex\u2019s crude Texas Instruments chip, Julie may seem a veritable chatterbox, but to Khudanpur\u2019s mind, there\u2019s plenty of room for technological improvement in that she works in \u201ca limited domain. If you start asking Julie whether she likes Phantom of the Opera, she has no opinion on it, she just wants to figure out where it is and whether you want to go there.\u201d<\/p>\n

Khudanpur\u2019s work at the Whiting School\u2019s Center for Language and Speech Processing takes him in the opposite direction, expanding the boundaries of speech and text recognition to create programs that more accurately translate languages. That involves delving into how people really speak to each other\u2014so-called \u201cconversational speech\u201d\u2014versus the way most of us interact with Julie. \u201cWe talk to each other very differently than we talk to a computer,\u201d says Khudanpur, who has researched the nuances. \u201cPeople tend to be more cooperative when they\u2019re talking to a computer, more measured in their speech.\u201d<\/p>\n

By contrast, Khudanpur\u2019s current speech recognition investigation \u201cis focused on [quantifying] conversational speech, pronunciation variations, dialectical variability, accents, and so on.\u201d He notes that people have the ability to discern sloppy pronunciations of words during conversation, to realize that, in a chat about their beloved pet, they may say something that sounds a lot like \u201cdiskette\u201d but it\u2019s understood by all in the room to mean \u201cthis cat.\u201d But how do you get a computer to make the right call?<\/p>\n

The answer, says Khudanpur, is twofold; one aspect involves sampling thousands of sounds used in speech, looking for the common patterns that can be programmed into a model (think of a computer that could quickly recognize a thick Boston or Baltimore accent, and adjust its translations accordingly). The other side involves creating mathematical formulas that look at millions of complete sentences from which a computer could deduce the likely translation of a given word. In the example above, Khudanpur says the computer would know \u201cdiskette\u201d really means \u201cthis cat\u201d if it recognized the context of the adjacent words, as in \u201cThe black fur on (\u2018diskette\u2019) really makes her green eyes stand out.\u201d<\/p>\n

Khudanpur says the applications of such work are numerous. On a national security front, software can tap international calls in a way far beyond human manpower, looking for certain words and phrases that could be tip-offs of planned attacks. On a far more benign front, Khudanpur imagines a chip that could search TV not by programming but by spoken content, referring viewers to news and talk shows that offer the most references to a given subject.<\/p>\n

For all his accomplishments, Khudanpur says his most interesting work still lies ahead of him\u2014the world of text-to-text translation. As anyone familiar with the phrase \u201clost in translation\u201d has learned, using a computer to move from one language to another is problematic at best. Khudanpur may be on the way to solving that contextual gap. By pouring thousands of parallel sentences in multiple languages into a database (think of numerous UN translators simultaneously translating the same speech), Khudanpur is creating language matrices where a mathematical process of elimination narrows down a word in one language to its counterpart in another.<\/p>\n

\u201cIt\u2019s like having millions of necklaces, all with many different colored beads, and I asked you to pick out a subset of necklaces that had one bead of your favorite color,\u201d he says. \u201cIf you gave me that subpile, I\u2019d look for the color they all had in common \u2026 and that would be your favorite.\u201d<\/p>\n

In any language.<\/p>\n

<\/p>\n

\"data-driven_story4\"<\/a>ENERGY SMART<\/strong><\/h2>\n

From the production of power to its delivery, Whiting School professors Charles Meneveau and Ben Hobbs are crunching serious numbers to understand alternative sources of energy and the most efficient ways to keep the power flowing to our communities.<\/p>\n

Let\u2019s take the latter first. The current system of energy delivery is an arcane and often wasteful one. Hobbs notes that, especially among the 200 utility control areas on the East Coast that include thousands of power plants, there\u2019s almost no storage capacity for electricity. This means producers have to constantly guess at how much electricity their customers need. What\u2019s worse, those guesses have traditionally been made several days out, to account for the lag time it takes to get big, lumbering power plants up and running. Overproduce and energy is wasted; underproduce and the risk of brownouts and blackouts soars. \u201cIt\u2019s the ultimate \u2018just-in-time\u2019 system,\u201d says Hobbs, the Theodore M. and Kay Schad Professor in Environmental Management and director of the Environment, Energy, Sustainability and Health Institute.<\/p>\n

Hobbs\u2019 recent work has looked at creating a smarter energy grid for both producer and consumers. By analyzing usage patterns and making that data easily accessible, he\u2019s hoping to improve communication between neighboring utilities. \u201cRight now, they don\u2019t communicate as well as they should. And one consequence is waste. There\u2019s some generator that\u2019s sitting idle that\u2019s cheap to run while another generator that\u2019s expensive to run is operating.<\/p>\n

\u201cThere\u2019s also a reliability aspect,\u201d he adds. \u201cThere\u2019s a Department of Energy report that lays the blame for the 2003 East Coast blackout on lack of data on how much power was flowing; a utility in Ohio wasn\u2019t aware it was overloading a line, [it] overheated, sagged, and short-circuited, and led to a chain reaction that blacked out New York City. And then there\u2019s coordination; the utilities in Ohio and elsewhere weren\u2019t communicating terribly well. If they had quickly switched out certain transmission lines, they could have confined the blackout.\u201d<\/p>\n

Hobbs\u2019 work is addressing these issues, right down to incorporating weather forecasting. For example, by looking at wind patterns, he says it\u2019s possible to help utilities predict bad-air-quality days and, in turn, encourage customers to use less electricity on those days to lower ozone levels.<\/p>\n

That forecasting may well be aided by Meneveau\u2019s research. Meneveau, the Louis M. Sardella Professor of Mechanical Engineering and deputy director of the Johns Hopkins Institute for Data Intensive Engineering and Science, is a turbulence specialist, using sophisticated modeling to predict how air currents interact with their environment. It sounds esoteric but has numerous practical implications. He notes that a better understanding of turbulence influences car, train, and ship designs to reduce losses due to drag. \u201cEven if you reduce the drag forces by just half a percent, that translates into billions of dollars a year to the economy.\u201d<\/p>\n

From an energy production viewpoint, Meneveau is researching wind farms, everything from the turbulence they create (and the localized small but definitely recognizable effect on the environment), to the best arrangement of wind turbines for maximum power generation. But from a data storage and sharing perspective, his recent work with the Turbulence Database Group may be the most interesting. It involves simulating and analyzing so-called isotropic turbulence, answering statistical questions like: Given a wind vortex at a given location, what\u2019s the probability that another vortex will be spawned or intersected with later? Such violent but fortunately rare events are associated with how kinetic energy turns into heat generation, a phenomenon that needs to be understood to better model both turbulence and the land and sea effects of wind farms.<\/p>\n

It is a question to which 27 terabytes of information have been devoted; that\u2019s the total amount of data in the Turbulence Database Cluster, a public, easily accessible database of detailed wind information that has already informed several papers from researchers scattered around the world.<\/p>\n

\u201cIt\u2019s nice, because these are the kinds of scientists who would not have been able [because of resources or technical background] to do these simulations themselves. So they were able to access [our database] and now there\u2019s a new kind of science because people who didn\u2019t do very large kinds of simulations before now have this user-friendly way of accessing the data. We think new things may come out of that.\u201d<\/p>\n

May the wind be always at their backs.<\/p>\n

<\/p>\n

\"data-driven_story5\"<\/a>TO YOUR HEALTH<\/strong><\/h2>\n

\u201dPersonalized\u201d medicine has become a buzzword among physicians, the idea that the key to the best care possible is refining established treatment silos\u2014age, gender, and the like\u2014to get at the underlying unique pathophysiology that causes illness. What\u2019s sustaining that buzz\u2014indeed, what\u2019s likely to make personalized medicine a reality sooner rather than later\u2014is the huge quantity of data being amassed on anyone encountering our health care system.<\/p>\n

That data stream is only going to increase as hospitals move to electronic record keeping for patients and more computerized testing comes online. And while it all may seem invasive and raise confidentiality concerns, there\u2019s a growing recognition among researchers that well-managed data can reduce both morbidity and mortality.<\/p>\n

Greg Hager, chair of the Department of Computer Science at the Whiting School, points to robotic surgery as just one area where improved data collection offers an opportunity for medicine to advance. The robot can be programmed to replicate a surgeon\u2019s hand movements inside the body, but that\u2019s merely the beginning; it can also be told to record data that reveals a surgeon\u2019s skill and whether that skill is improving, slipping, or staying status quo. \u201cThere are more than 7 million surgeries a year, including more than a quarter million done by robotic surgery,\u201d says Hager. \u201cCertainly there\u2019s collective wisdom there that you\u2019d like to bring to bear\u201d on surgical practice, he notes.<\/p>\n

Hager\u2019s \u201cLanguage of Surgery\u201d project is attempting to do just that. His computer science colleague Rajesh Kumar is recording surgeons\u2019 training on the da Vinci operating robot at several sites around the country, including Hopkins. The project uses computer modeling to turn each surgical gesture, each movement of a surgeon\u2019s hand, into quantifiable data, \u201ca system that doesn\u2019t just replicate motion and provide visualization but models what the surgeon is actually trying to accomplish and can gauge what\u2019s going on relative to those objectives.\u201d<\/p>\n

So far Hager and Co. have looked at general tasks common to many surgeries, collecting data to answer important questions: \u201cWhat does it mean to do suturing well? What does it mean to do dissection well?\u201d<\/p>\n

Eventually, Hager\u2019s surgical work may intersect with that of Natalia Trayanova, a biomedical engineering professor at the Whiting School. Trayanova has been looking at hearts damaged by infarctions, or heart attacks.<\/p>\n

It\u2019s long been known that infarctions kill off heart muscle, but they also create electrical disruptions known as arrhythmias that form around the infarct scars. These impact the proper overall beating of the heart. While certain kinds of arrhythmias in well-charted portions of the heart can be treated with catheter ablation (essentially a burning off of the affected tissue that sustains the arrhythmia), the random location of infarction damage has made ablation an arduous, often ineffective technique\u2014a point-by-point physical poking and burning of the area \u201c[Right now] the procedure lasts four to eight hours, it\u2019s very inaccurate with a high level of complications,\u201d including perforations of the heart, says Trayanova. She and her students may have created an elegant solution.<\/p>\n

By taking an MRI of a patient\u2019s chest, Trayanova is able to create a computer model of the patient\u2019s heart that simulates the heart\u2019s behavior from the molecular level to that of the entire organ, including representation of the processes in cells that have remodeled themselves around the infarcted area. The model produces reams of data that help show how portions of the heart will function over a given period of time. The model accurately predicts the arrhythmic activity that arises from the infarct, allowing electrophysiologists to test for exactly the right places to ablate on the model as opposed to the patient. \u201cWe\u2019ve done animal work and it worked very well. We\u2019re now doing human retrospective studies,\u201d says Trayanova.<\/p>\n

But perhaps the most immediate clinical use of big data may come in the field of disease prevention. The price tag associated with genome collection and analysis has dropped greatly. \u201cWe spent $300 million to sequence the first human genome; now we can do [an individual\u2019s specific genome] for between $2,000 and $10,000,\u201d says Scott Zeger, a professor of biostatistics at the School of Public Health and vice provost for research at Hopkins. This falling cost means that each individual\u2019s personal heredity map may soon be easily accessible to health care providers.<\/p>\n

Zeger says that increasing access to genomic information offers much promise. For example, women with breast cancer related to a growth factor produced by the HER-2 gene can now be tested for the gene and, if positive, receive a drug that blocks the gene\u2019s growth-inducing properties. Similarly, since drug action and effectiveness are often determined by which proteins our bodies can\u2014or can\u2019t\u2014produce, being able to eventually catalog each individual\u2019s proteins (a massive sequencing field called proteomics) could ensure that patients receive only those medications their bodies can process.<\/p>\n

Uncovering our unique genes and proteins could also predict predisposition to a host of disease states ranging from diabetes to autoimmune conditions. Offering early intervention is becoming more precise thanks to heavy data crunching; as our understanding of cellular function improves, so does detection of subclinical markers that accompany the precursors of disease states such as inflammation with cardiovascular disease. To Zeger, this confluence of math and medicine has its own grace, relying on both man and machine to move individualized health forward.<\/p>\n

\u201cWhat\u2019s happening is we\u2019re getting much closer to the real biology that\u2019s going on [in disease-creating states],\u201d says Zeger. \u201cThis is a marriage of the information technologists cutting algorithms while letting deep medical pathobiological knowledge guide us.\u201d<\/p>\n

Here\u2019s to the happy couple.<\/p>\n","protected":false},"excerpt":{"rendered":"

As computing ability jumps by leaps and bounds, researchers wrestle with making the best use\u2014and reuse\u2014of all that data.<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[28],"tags":[],"class_list":["post-1025","post","type-post","status-publish","format-standard","hentry","category-features","issue-fall-2011"],"acf":[],"yoast_head":"\nData Driven - JHU Engineering Magazine<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/\" \/>\n<link rel=\"next\" href=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Data Driven - JHU Engineering Magazine\" \/>\n<meta property=\"og:description\" content=\"As computing ability jumps by leaps and bounds, researchers wrestle with making the best use\u2014and reuse\u2014of all that data.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/\" \/>\n<meta property=\"og:site_name\" content=\"JHU Engineering Magazine\" \/>\n<meta property=\"article:published_time\" content=\"2011-09-15T14:40:07+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2017-08-02T14:39:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large-231x300.jpg\" \/>\n<meta name=\"author\" content=\"Abby Lattes\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Abby Lattes\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"23 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/\"},\"author\":{\"name\":\"Abby Lattes\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"headline\":\"Data Driven\",\"datePublished\":\"2011-09-15T14:40:07+00:00\",\"dateModified\":\"2017-08-02T14:39:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/\"},\"wordCount\":4504,\"commentCount\":0,\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2014\\\/06\\\/data-driven_large-231x300.jpg\",\"articleSection\":[\"Features\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/\",\"name\":\"Data Driven - JHU Engineering Magazine\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2014\\\/06\\\/data-driven_large-231x300.jpg\",\"datePublished\":\"2011-09-15T14:40:07+00:00\",\"dateModified\":\"2017-08-02T14:39:19+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/2011\\\/09\\\/data-driven\\\/#primaryimage\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2014\\\/06\\\/data-driven_large.jpg\",\"contentUrl\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/wp-content\\\/uploads\\\/2014\\\/06\\\/data-driven_large.jpg\",\"width\":612,\"height\":792,\"caption\":\"data-driven\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#website\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/\",\"name\":\"JHU Engineering Magazine\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/magazine-archive\\\/#\\\/schema\\\/person\\\/0244393be370fbc3ead8ec26062e9742\",\"name\":\"Abby Lattes\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g\",\"caption\":\"Abby Lattes\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Data Driven - JHU Engineering Magazine","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/","next":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/2\/","og_locale":"en_US","og_type":"article","og_title":"Data Driven - JHU Engineering Magazine","og_description":"As computing ability jumps by leaps and bounds, researchers wrestle with making the best use\u2014and reuse\u2014of all that data.","og_url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/","og_site_name":"JHU Engineering Magazine","article_published_time":"2011-09-15T14:40:07+00:00","article_modified_time":"2017-08-02T14:39:19+00:00","og_image":[{"url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large-231x300.jpg","type":"","width":"","height":""}],"author":"Abby Lattes","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Abby Lattes","Est. reading time":"23 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#article","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/"},"author":{"name":"Abby Lattes","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"headline":"Data Driven","datePublished":"2011-09-15T14:40:07+00:00","dateModified":"2017-08-02T14:39:19+00:00","mainEntityOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/"},"wordCount":4504,"commentCount":0,"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large-231x300.jpg","articleSection":["Features"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/","name":"Data Driven - JHU Engineering Magazine","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website"},"primaryImageOfPage":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#primaryimage"},"image":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#primaryimage"},"thumbnailUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large-231x300.jpg","datePublished":"2011-09-15T14:40:07+00:00","dateModified":"2017-08-02T14:39:19+00:00","author":{"@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/2011\/09\/data-driven\/#primaryimage","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large.jpg","contentUrl":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-content\/uploads\/2014\/06\/data-driven_large.jpg","width":612,"height":792,"caption":"data-driven"},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#website","url":"https:\/\/engineering.jhu.edu\/magazine-archive\/","name":"JHU Engineering Magazine","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/magazine-archive\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/engineering.jhu.edu\/magazine-archive\/#\/schema\/person\/0244393be370fbc3ead8ec26062e9742","name":"Abby Lattes","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/c56cb7af5427f847aa288542444ba9ff3d2107bf85dc6c6d44a4d1315608258d?s=96&r=g","caption":"Abby Lattes"}}]}},"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/1025","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/comments?post=1025"}],"version-history":[{"count":10,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/1025\/revisions"}],"predecessor-version":[{"id":10103,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/posts\/1025\/revisions\/10103"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/media?parent=1025"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/categories?post=1025"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/magazine-archive\/wp-json\/wp\/v2\/tags?post=1025"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}