Nautilus: The Future Predictor
Can a computer foretell future, Minority Report-style?
Remember the famous 2002 Steven Spielberg film starring Tom Cruise, where criminals were apprehended based on premonitions provided by three psychics called "precogs" who pre-visualize crimes by receiving visions of the future !?
A strikingly similar development in artificial intelligence has been contributed by Kalev Leetaru from The University of Tennessee through an SGI Altix, Xeon-based, 1024-core supercomputer called Nautilus which can predict the future. Back in 2011, it was able to prophesise several cultural and political trends, including a populist, revolutionary uprising in Egypt and the overall stability of Saudi Arabia. Even more, it correctly pinpointed Osama Bin Laden's location in Pakistan with a startling accuracy of 200 km at a time when experts thought he was in an entirely different country!!!
Technical Aspects :
Nautilus is an SGI Altix UV system consisting of one UV1000 (Nautilus), 4 UV10s (Harpoon nodes), and 3 login nodes (Arronax, Conseil, and Nedland). The UV1000 has 1024 cores (128 8-core Intel Nehalem EX processors), 4 terabytes of global shared memory, and 8 GPUs in a single system image. In addition, each UV10 provides 32 cores, 128 GB, and 2 GPUs. Nautilus currently has a CPU speed of 2.0 GHz and a peak performance of 8.2 Teraflops. The Lustre file system Medusa, with 1.3 PB capacity, is mounted on Nautilus.
The primary purpose of Nautilus is to enable data analysis and visualization of data from simulations, sensors, or experiments. Nautilus is intended for serial and parallel visualization and analysis applications that take advantage of large memories, multiple computing cores, and multiple graphics processors. Nautilus allows for both utilization of a large number of processors for distributed processing and the execution of legacy serial analysis algorithms for very large data processing by large numbers of users simultaneously.
Working :
Nautilus gathered its data from over 100 million news articles worldwide dating back to 1945 via a range of sources including the Open Source Center, BBC Monitoring, News outlets and New York Times' archive.
Reports were analysed for two main types of information: mood - whether the article represented good news or bad news, and location - where events were happening and the location of other participants in the story. Mood detection, or "automated sentiment mining" searched for words such as "terrible", "horrific" or "nice". Location, or "geo-coding" took mentions of specific places, such as "Cairo" and converted them in to coordinates that could be plotted on a map. The data set included 10 billion people, places, things, and activities - totaling 100 trillion plus relationships.
The supercomputer was able to piece these facts and figures together and generate graphs that predict human behavior, charted mood with an insane level of perfection. The machine's 1024 Intel Nehalem cores have a total processing power of 8.2 teraflops (trillion floating point operations per second).
Based on specific queries, Nautilus generated graphs for different countries which experienced the "Arab Spring". In each case, the aggregated results of thousands of news stories showed a notable dip in sentiment ahead of time - both inside the country, and as reported from outside. Based on specific queries, the Egypt graph mapped deteriorating national sentiment ahead of the recent revolutions over there and suggested that something unprecedented was happening this time. For Egypt, the tone of media coverage in the month before President Hosni Mubarak's resignation had fallen to a low only seen twice before in the preceding 30 years.
Previous dips coincided with the 1991 US aerial bombardment of Iraqi troops in Kuwait and the 2003 US invasion of Iraq. Similar drops were seen ahead of the revolution in Libya and the Balkans conflicts of the 1990s. Saudi Arabia, which has thus far resisted a popular uprising, had experienced fluctuations, but not to the same extent as some other states where leaders were eventually overthrown.
The geo-analysis of global media reports about Osama Bin Laden yielded important clues about his location and consistently identified him in Northern Pakistan eventually narrowing him down to within 200km. While many believed the al-Qaeda leader to be hiding in Afghanistan, geographic information extracted from media reports consistently identified him with Northern Pakistan. Only one report mentioned the town of Abbottabad prior to Bin Laden's discovery by US forces in April 2011.
Though Nautilus was decommissioned on May 1, 2015 due to lack of funding, it can be said that data mining could be crucial in our intelligence activities in future as researchers and scientists are now looking at making the current statistics work in real time and anticipate upcoming conflict. The computer event analysis model appears to give forewarning of major events, based on deteriorating sentiment. However its analysis is applied to things that have already happened. According to Kalev Leetaru, such a system could easily be adapted to work in real time, giving an element of foresight.
Sources: www.bbc.com and www.outerplaces.com
