The clustering ensemble technique aims to combine multiple clusterings into a probably better and more robust clustering and has been receiving an increasing attention in recent years. There are mainly two aspects of limitations in the existing clustering ensemble approaches. Firstly, many approaches lack the ability to weight the base clusterings without access to the original data and can be affected significantly by the low-quality, or even ill clusterings. Secondly, they generally focus on the instance level or cluster level in the ensemble system and fail to integrate multi-granularity cues into a unified model. To address these two limitations, this paper proposes to solve the clustering ensemble problem via crowd agreement estimation and multigranularity link analysis. We present the normalized crowd agreement index (NCAI) to evaluate the quality of base clusterings in an unsupervised manner and thus weight the base clusterings in accordance with their clustering validity. To explore the relationship between clusters, the source aware connected triple (SACT) similarity is introduced with regard to their common neighbors and the source reliability. Present address: School of Information Science and Technology, Sun Yat-sen University, Guangzhou Higher Education Mega Center, Panyu District, Guangzhou, Guangdong, 510006, P. R. China. The experiments are conducted on eight real-world datasets. The experimental results demonstrate the effectiveness and robustness of the proposed methods. Keywords: Clustering ensemble, Clustering aggregation, Weighted evidence accumulation clustering, Graph partitioning with multi-granularity link analysis 1. Introduction Data clustering is a fundamental and very challenging problem in data mining and machine learning.

Driving styles have a great influence on vehicle fuel economy, active safety, and drivability. To recognize driving styles of path-tracking behaviors for different divers, a statistical pattern-recognition method is developed to deal with the uncertainty of driving styles or characteristics based on probability density estimation. First, to describe driver path-tracking styles, vehicle speed and throttle opening are selected as the discriminative parameters, and a conditional kernel density function of vehicle speed and throttle opening is built, respectively, to describe the uncertainty and probability of two representative driving styles, e.g., aggressive and normal. Meanwhile, a posterior probability of each element in feature vector is obtained using full Bayesian theory. Second, a Euclidean distance method is involved to decide to which class the driver should be subject instead of calculating the complex covariance between every two elements of feature vectors. By comparing the Euclidean distance between every elements in feature vector, driving styles are classified into seven levels ranging from low normal to high aggressive. Subsequently, to show benefits of the proposed pattern-recognition method, a cross-validated method is used, compared with a fuzzy logic-based pattern-recognition method. The experiment results show that the proposed statistical pattern-recognition method for driving styles based on kernel density estimation is more efficient and stable than the fuzzy logic-based method.

If you still think Minecraft is a PC game--well, you're flat wrong. According to new numbers released by Mojang and Microsoft, the original version for the PC is the least popular platform, in almost every region worldwide. Microsoft said Thursday that Minecraft has sold more than 106,859,714 copies to date across all platforms--which would represent the twelfth most populous nation in the world, right behind Japan. Four copies have even been sold into Antarctica. But if you dig into Microsoft's numbers, they reveal that far, far more users are buying Minecraft on platforms other than the PC.

Robots play football in a demonstration of artificial intelligence at the stand of the German Research Center for Artificial Intelligence (Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH) at the CeBIT Technology Fair on March 2, 2010 in Hannover, Germany. China's National Development and Reform Commission (NDRC) has announced a three-year guidance program in which the country plans to increase the advancement of the nation's artificial intelligence (AI) sector. According to the NDRC, the plan - which was devised together with China's Ministry of Science and Technology, the Ministry of Industry and Information Technology, and the Cyberspace Administration of China - is expected to create new AI industries and economic growth which will result in a market value of over 15.26 million (100 billion Yuan) in the next three years. The three-year program for "Internet Plus" AI indicated that the move will eventually see China developing "platforms for fundamental AI resources and innovation" by the year 2018. In the same year the country is expected to be at about the same level of the world's AI industry and technology, according to the NDRC website.

The fact that most insects (except for the really freaky ones) are very small doesn't stop them from getting everywhere they want to, especially all of those places that you try to keep them out of. Roboticists have been experimenting with bug-sized robots, but they're still pretty large, about the size of giant beetles or moths. Most insects are far smaller than that, which means that they experience the world much differently, and that can be a hard thing to study effectively. At ICRA last month, Ryan St. Pierre and Professor Sarah Bergbreiter from the University of Maryland presented a paper on the gait characteristics of magnetically actuated legged robots weighing less than 2 grams, which was very cool to see. It's only the beginning, though: robots like these are about to get way, way smaller.

Social media and interplanetary mission -- what do they have in common? Well, they have in common the Mars Orbiter Mission, also known as'Mangalyaan'. It was launched on 5th November by the Indian Space Research Organization (ISRO). It generated a lot of interest across the globe among millions of people on Social Media networks. In this blog, we analyze how Twitterati reacted to this news. Asia was by far the most interested in the subject, covering 74% of all the tweets on'Mangalyaan'.

Hollywood can take almost anything and adapt it into gold. It's common knowledge these days that a movie based on a Marvel comic book can grow into a billion-dollar franchise, and producers have found lucrative source material in everything from theme park rides to toys. But movies based on video games have yet to hit the same stride, despite the fact that the global gaming industry is expected to generate close to 100 billion this year, more than Hollywood itself. The history of failed movie adaptations serves as a cautionary backdrop for "Warcraft," based on the popular Activision Blizzard game series, which will be released in North America June 10. At a time when all things geek are considered mainstream, there's still much uncertainty about whether "Warcraft" will be the one to end the cycle of bad video game movies.

Much of that success can be attributed to the game's open structure and limitless potential. Players can build anything they imagine, provided its outward-facing geometry is made up of simple, colorful blocks. The focus on creativity is why so many players, young and old, have been drawn to the game and continue to play years after its release. Mojang has supported the game with a steady stream of updates that have added new mechanics, creatures and materials. The game's flexibility has also made it a smash-hit in the classroom, teaching art, geology, coding and other subjects.

Uber is facing challenges in acquiring drivers, paying drivers and managing the liability of drivers, but these issues will vanish, along with a good chunk of its costs, if Uber can establish a massive fleet of self-driving cars,

BOSTON, MA – June 2, 2016 – Neurala, Inc., a creator of artificial intelligence, deep learning software for robots, drones, self-driving cars, toys, consumer electronics, and smart devices (ioT), today announced that it has completed a 1.2-million round of financing lead by the fund run by well-known venture capitalist Tim Draper, Draper Associates Investments, LLC, and by Haiyin Capital, a Beijing-based venture capital firm. This second round of financing brings the total external investment in Neurala to 2 million. Haiyin Capital is a new investor in Neurala. The firm actively invests worldwide in technology teams whose innovations are, in their opinion, poised for global impact. In addition to their financial investment in Neurala, Haiyin will provide access to its network of OEM and technology companies in China.