For massive and heterogeneous modern data sets, it is of fundamental interest to provide guarantees on the accuracy of estimation when computational resources are limited. In the application of learning to rank, we provide a hierarchy of rank-breaking mechanisms ordered by the complexity in thus generated sketch of the data. This allows the number of data points collected to be gracefully traded off against computational resources available, while guaranteeing the desired level of accuracy. Theoretical guarantees on the proposed generalized rank-breaking implicitly provide such trade-offs, which can be explicitly characterized under certain canonical scenarios on the structure of the data.

The buzzwords "Industry 4.0" and "digital business" represent the start of a complex transformational process that will deeply affect industry and society during the next decade. This transformation is based on the convergence of the real (analog) world and the virtual (digital) world by means of machineto- machine (M2M) communication, autonomous systems (for example, robotics) and the Internet of Things (IoT). The German government uses the term "Industry 4.0" as the title of a government project promoting the computerization of traditional industries and the creation of intelligent factories (smart factories) that will be supported by cyberphysical systems and the IoT. The digits "4.0" in Industry 4.0 stand for the fourth industrial revolution: the transition of production from digital processing to fully interconnected processes, products and services. It follows the evolution of production processes for tradable goods from manufacturing to industry production (the first revolution), the move from steam-driven machine production to electricity-driven production (the second revolution) and the shift from analog processing to digital processing and microelectronics (the third revolution). One of the major features of Industry 4.0 is the ability of machines and devices to communicate with each other without a human interface.

Distributed constraint optimization problems enable the representation of many combinatorial problems that are distributed by nature. An important motivation for such problems is to preserve the privacy of the participating agents during the solving process. The present paper introduces a novel privacy-preserving branch and bound algorithm for this purpose. The proposed algorithm, P-SyncBB, preserves constraint, topology and decision privacy. The algorithm requires secure solutions to several multi-party computation problems. Consequently, appropriate novel secure protocols are devised and analyzed. An extensive experimental evaluation on different benchmarks, problem sizes, and constraint densities shows that P-SyncBB exhibits superior performance to other privacy-preserving complete DCOP algorithms.

International travelers could soon be greeted by lie-detecting robot kiosks before crossing the border. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists. The robot uses eye-detection software along with an array of sensors to pick up on the physiological signs that indicate a person is lying, and once it becomes suspicious, it can flag the passenger for further inspection. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists Once a traveler steps up to the kiosk, they will be asked a series of questions, such as: 'Do you have fruits or vegetables in your luggage?' or'Are you carrying any weapons with you?' While this is happening, AVATAR uses eye-detection software and motion and pressure sensors to track any signs of lying or discomfort. To separate the liars from those who are just nervous about flying, it will also ask a number of innocuous baseline questions.

International travelers could soon be greeted by lie-detecting robot kiosks before crossing the border. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists. The robot uses eye-detection software along with an array of sensors to pick up on the physiological signs that indicate a person is lying, and once it becomes suspicious, it can flag the passenger for further inspection. The system, known as the Automated Virtual Agent for Truth Assessment in Real Time, has already begun tests with the Canadian Border Services Agency, and it's hoped this can soon help agents screen for criminals and even potential terrorists Once a traveler steps up to the kiosk, they will be asked a series of questions, such as: 'Do you have fruits or vegetables in your luggage?' or'Are you carrying any weapons with you?' While this is happening, AVATAR uses eye-detection software and motion and pressure sensors to track any signs of lying or discomfort. To separate the liars from those who are just nervous about flying, it will also ask a number of innocuous baseline questions.

When you engage in international travel, you may one day find yourself face-to-face with border security that is polite, bilingual and responsive--and robotic. The Automated Virtual Agent for Truth Assessments in Real Time (AVATAR) is currently being tested in conjunction with the Canadian Border Services Agency (CBSA) to help border security agents determine whether travelers coming into Canada may have undisclosed motives for entering the country. "AVATAR is a kiosk, much like an airport check-in or grocery store self-checkout kiosk," said San Diego State University management information systems professor Aaron Elkins. "However, this kiosk has a face on the screen that asks questions of travelers and can detect changes in physiology and behavior during the interview. The system can detect changes in the eyes, voice, gestures and posture to determine potential risk. It can even tell when you're curling your toes."

Hierarchy Of Multi-label classifiers (HOMER) is a multi-label learning algorithm that breaks the initial learning task to several, easier sub-tasks by first constructing a hierarchy of labels from a given label set and secondly employing a given base multi-label classifier (MLC) to the resulting sub-problems. The primary goal is to effectively address class imbalance and scalability issues that often arise in real-world multi-label classification problems. In this work, we present the general setup for a HOMER model and a simple extension of the algorithm that is suited for MLCs that output rankings. Furthermore, we provide a detailed analysis of the properties of the algorithm, both from an aspect of effectiveness and computational complexity. A secondary contribution involves the presentation of a balanced variant of the k means algorithm, which serves in the first step of the label hierarchy construction. We conduct extensive experiments on six real-world datasets, studying empirically HOMER's parameters and providing examples of instantiations of the algorithm with different clustering approaches and MLCs, The empirical results demonstrate a significant improvement over the given base MLC.

Machines are crucial with how consumers interact with businesses, not just through purchases but also through enquiries. It's thought that machine learning will not only radically alter the customer service industry, but all industries. Thinking about it in terms of pervious technology revolutions, the age of steam created the industrial revolution by replacing man with coal, the age of robotics also moved the manufacturing industry's dependency on mankind and in the future, artificial intelligence and machine learning holds the potential to replace cognitive functions of the human mind. But what does this really mean and how will it change the way that businesses interact with their customers? Customers today demand access to immediate information and want issues to be solved instantly at the click of a button. As a result, more businesses are now tracking a customer's engagement history with a brand through a range of data sources such as social media, purchase history and customer support tickets, to provide a personalised experience in a shorter timeframe.

As packages continue to arrive from this year's record-breaking Black Friday weekend, it's no doubt you're seeing Amazon packages complete with front-and-center ads for Amazon's Echo and Dot devices. You may even be one of the reported millions that ordered one that weekend. These are more than just devices -- they are Alexa-enabled and are helping Alexa further integrate into consumers' lives. And Alexa isn't alone: from Alexa to Google Now to Microsoft's Cortana to Apple's Siri, we have a budding class of intelligent agents (IAs) on the rise. In 2015, 45% of US online adults used at least one.

Coalition formation typically involves the coming together of multiple, heterogeneous, agents to achieve both their individual and collective goals. In this paper, we focus on a special case of coalition formation known as Graph-Constrained Coalition Formation (GCCF) whereby a network connecting the agents constrains the formation of coalitions. We focus on this type of problem given that in many real-world applications, agents may be connected by a communication network or only trust certain peers in their social network. We propose a novel representation of this problem based on the concept of edge contraction, which allows us to model the search space induced by the GCCF problem as a rooted tree. Then, we propose an anytime solution algorithm (CFSS), which is particularly efficient when applied to a general class of characteristic functions called $m+a$ functions. Moreover, we show how CFSS can be efficiently parallelised to solve GCCF using a non-redundant partition of the search space. We benchmark CFSS on both synthetic and realistic scenarios, using a real-world dataset consisting of the energy consumption of a large number of households in the UK. Our results show that, in the best case, the serial version of CFSS is 4 orders of magnitude faster than the state of the art, while the parallel version is 9.44 times faster than the serial version on a 12-core machine. Moreover, CFSS is the first approach to provide anytime approximate solutions with quality guarantees for very large systems of agents (i.e., with more than 2700 agents).