The Industry 4.0 paradigm promises shorter development times, increased ergonomy, higher flexibility, and resource efficiency in manufacturing environments. Collaborative robots are an important tangible technology for implementing such a paradigm. A major bottleneck to effectively deploy collaborative robots to manufacturing industries is developing task planning algorithms that enable them to recognize and naturally adapt to varying and even unpredictable human actions while simultaneously ensuring an overall efficiency in terms of production cycle time. In this context, an architecture encompassing task representation, task planning, sensing, and robot control has been designed, developed and evaluated in a real industrial environment. A pick-and-place palletization task, which requires the collaboration between humans and robots, is investigated. The architecture uses AND/OR graphs for representing and reasoning upon human-robot collaboration models online. Furthermore, objective measures of the overall computational performance and subjective measures of naturalness in human-robot collaboration have been evaluated by performing experiments with production-line operators. The results of this user study demonstrate how human-robot collaboration models like the one we propose can leverage the flexibility and the comfort of operators in the workplace. In this regard, an extensive comparison study among recent models has been carried out.

With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" - manipulating a model such that the features used in reality are hidden and more innocuous features are shown to be important instead. In our work we present an effective defence against such adversarial attacks on neural networks. By a simple aggregation of multiple explanation methods, the network becomes robust against manipulation. This holds even when the attacker has exact knowledge of the model weights and the explanation methods used.

A significant progress has been made in deep-learning based Automatic Essay Scoring (AES) systems in the past two decades. The performance commonly measured by the standard performance metrics like Quadratic Weighted Kappa (QWK), and accuracy points to the same. However, testing on common-sense adversarial examples of these AES systems reveal their lack of natural language understanding capability. Inspired by common student behaviour during examinations, we propose a task agnostic adversarial evaluation scheme for AES systems to test their natural language understanding capabilities and overall robustness.

Artificial intelligence (AI) algorithms have emerged in the educational domain as a tool to make learning more efficient. Different applications for mastering particular skills, learning new languages, and tracking their progress are used by children. What is the impact on children from using this smart technology? We conducted a systematic review to understand the state of the art. We explored the literature in several sub-disciplines: wearables, child psychology, AI and education, school surveillance, and accountability. Our review identified the need for more research for each established topic. We managed to find both positive and negative effects of using wearables, but cannot conclude if smart technology use leads to lowering the young children's performance. Based on our insights we propose a framework to effectively identify accountability for smart technology in education.

A central question in many fields of scientific research is to determine how an outcome would be affected by an action, or to measure the effect of an action (a.k.a treatment effect). In recent years, a need for estimating the heterogeneous treatment effects conditioning on the different characteristics of individuals has emerged from research fields such as personalized healthcare, social science, and online marketing. To meet the need, researchers and practitioners from different communities have developed algorithms by taking the treatment effect heterogeneity modeling approach and the uplift modeling approach, respectively. In this paper, we provide a unified survey of these two seemingly disconnected yet closely related approaches under the potential outcome framework. We then provide a structured survey of existing methods by emphasizing on their inherent connections with a set of unified notations to make comparisons of the different methods easy. We then review the main applications of the surveyed methods in personalized marketing, personalized medicine, and social studies. Finally, we summarize the existing software packages and present discussions based on the use of methods on synthetic, semi-synthetic and real world data sets and provide some general guidelines for choosing methods.

There were 25.6 million attendances at Emergency Departments (EDs) in England in 2019 corresponding to an increase of 12 million attendances over the past ten years. The steadily rising demand at EDs creates a constant challenge to provide adequate quality of care while maintaining standards and productivity. Managing hospital demand effectively requires an adequate knowledge of the future rate of admission. Using 8 years of electronic admissions data from two major acute care hospitals in London, we develop a novel ensemble methodology that combines the outcomes of the best performing time series and machine learning approaches in order to make highly accurate forecasts of demand, 1, 3 and 7 days in the future. Both hospitals face an average daily demand of 208 and 106 attendances respectively and experience considerable volatility around this mean. However, our approach is able to predict attendances at these emergency departments one day in advance up to a mean absolute error of +/- 14 and +/- 10 patients corresponding to a mean absolute percentage error of 6.8% and 8.6% respectively. Our analysis compares machine learning algorithms to more traditional linear models. We find that linear models often outperform machine learning methods and that the quality of our predictions for any of the forecasting horizons of 1, 3 or 7 days are comparable as measured in MAE. In addition to comparing and combining state-of-the-art forecasting methods to predict hospital demand, we consider two different hyperparameter tuning methods, enabling a faster deployment of our models without compromising performance. We believe our framework can readily be used to forecast a wide range of policy relevant indicators.

Commercial buildings account for approximately 36% of US electricity consumption, of which nearly two-thirds is met by fossil fuels [1] resulting in an adverse impact on the environment. Reducing this impact requires improving energy efficiency and lowering energy consumption. Most existing studies focus on designing methods to regulate and reduce HVAC and lighting energy consumption. However, few studies have focused on the control of occupant plugload energy consumption. In this study, we conducted multiple experiments to analyze changes in occupant plugload energy consumption due to monetary incentives and/or feedback. The experiments were performed in government office and university buildings at NASA Research Park located in Moffett Field, CA. Analysis of the data reveal significant plugload energy reduction can be achieved via feedback and/or incentive mechanisms. Autoregressive models are used to predict expected plugload savings in the presence of exogenous variables. The results of this study suggest that occupant-in-the-loop control architectures have the potential to reduce energy consumption and hence lower the carbon footprint of commercial buildings.

As a long-time proponent of AI regulation that is designed to protect public health and safety while also promoting innovation, I believe Congress must not delay in enacting, on a bipartisan basis, Section 102(b) of The Artificial Intelligence Data Protection Act -- my proposed legislation and now a House of Representatives Discussion Draft Bill. Guardrails in the form of Section 102(b)'s ethical AI legislation are necessary to maintain the dignity of the individual. What does Section 102(b) of The AI Data Protection Act provide and why the urgent need for the federal government to enact it now? To answer these questions, it is first necessary to understand how artificial intelligence (AI) is being used during this historic moment when our democratic society is confronting two simultaneous existential threats. Only then can the risks that AI poses to our individual dignity be recognized, and Section 102(b) be understood as one of the most important remedies to protect the liberties that Americans hold dear and that serve as the bedrock of our society.

At the American Association of Physicists in Medicine (AAPM) 2019 meeting, new artificial intelligence (AI) software to assist with radiotherapy treatment planning systems was highlighted. The goal of the AI-based systems is to save staff time, while still allowing clinicians to do the final patient review. RaySearch demonstrated a new U.S. Food and Drug Administration (FDA)-cleared machine learning treatment planning system. The RaySearch RayStation machine learning algorithm is being used clinically by University Health Network, Princess Margaret Cancer Center, Toronto, Canada, where it was rolled out over several months in late-2019. Medical physicist Leigh Conroy, Ph.D., was involved in this rollout and helped conduct a study, showing the automated plans and traditionally made plans to radiation oncologists to get valuable feedback.

Robotic vehicles including unmanned ground, air, and sea vehicles, robotics and automation, intelligent control systems, intelligent manufacturing, intelligent transportation systems, weapon systems are some of the wonder deployments of robotics that have caught the attention of businesses. Robotic products under development include collaborating with intelligent systems to control complex systems of systems that serve as decision tools for human decision-makers, and autonomous intelligent robots and vehicles for military and civil applications. Robots are helpful to make repetitive activities much easier, for instance, assembly lines in a factory or collecting large amounts of mundane data, can be boring. Multiple pieces of research have connected mundane tasks associated with negative behaviours and lethargy, thus impacting production capabilities. This holds especially true for rule-based duties that require continuous attention, leaving the manual workforce tired and agitated.