Artificial Neural Networks (ANNs) are currently being used as function approximators in many state-of-the-art Reinforcement Learning (RL) algorithms. Spiking Neural Networks (SNNs) have been shown to drastically reduce the energy consumption of ANNs by encoding information in sparse temporal binary spike streams, hence emulating the communication mechanism of biological neurons. In this work, the use of SNNs as stochastic policies is explored under an energy-efficient first-to-spike action rule, whereby the action taken by the RL agent is determined by the occurrence of the first spike among the output neurons. A policy gradient-based algorithm is derived and implemented on a windy grid-world problem. Experimental results demonstrate the capability of SNNs as stochastic policies to gracefully trade energy consumption, as measured by the number of spikes, and control performance.

Multi-Criteria Decision Analysis (MCDA) methods are widely used in various fields and disciplines. While most of the research has been focused on the development and improvement of new MCDA methods, relatively limited attention has been paid to their appropriate selection for the given decision problem. Their improper application decreases the quality of recommendations, as different MCDA methods deliver inconsistent results. The current paper presents a methodological and practical framework for selecting suitable MCDA methods for a particular decision situation. A set of 56 available MCDA methods was analyzed and, based on that, a hierarchical set of methods characteristics and the rule base were obtained. This analysis, rules and modelling of the uncertainty in the decision problem description allowed to build a framework supporting the selection of a MCDA method for a given decision-making situation. The practical studies indicate consistency between the methods recommended with the proposed approach and those used by the experts in reference cases. The results of the research also showed that the proposed approach can be used as a general framework for selecting an appropriate MCDA method for a given area of decision support, even in cases of data gaps in the decision-making problem description. The proposed framework was implemented within a web platform available for public use at www.mcda.it.

The application of Artificial Intelligence (AI) requires that data be processed at the speed of operations in order to analyze the performance of any given process system. In this way, important decisions can be made quickly to improve the performance of the operation. But for those decisions to be made in real-time, data must be of the highest quality, and that presents a challenge to the industry. IoT has driven a tremendous explosion in the quantity of data. Today, there are many sensors measuring and providing data on temperature, flow, vibration, product viscosity and energy consumption, just to name a few. Add, for example, video and images to that mix and you start to get a feel for the vast amount of data that has to be processed.

Docked in Lewes, Delaware, is a 166-foot ship called the DELRIVER that is rarely called out of port. Nonetheless, it's staffed 24/7 by a four-person crew and stands ready for action at a moment's notice. The DELRIVER is an oil-spill response vessel, funded by the local oil industry to clean up spills in the Delaware Bay as soon as they happen. The last major spill in the area was in 2004, when the tanker Athos spewed 265,000 gallons of heavy crude from Venezuela into the Delaware River. The last spill of any kind that it responded to was a small diesel spill in 2014.

This paper presents a new meta-modeling framework to employ deep reinforcement learning (DRL) to generate mechanical constitutive models for interfaces. The constitutive models are conceptualized as information flow in directed graphs. The process of writing constitutive models are simplified as a sequence of forming graph edges with the goal of maximizing the model score (a function of accuracy, robustness and forward prediction quality). Thus meta-modeling can be formulated as a Markov decision process with well-defined states, actions, rules, objective functions, and rewards. By using neural networks to estimate policies and state values, the computer agent is able to efficiently self-improve the constitutive model it generated through self-playing, in the same way AlphaGo Zero (the algorithm that outplayed the world champion in the game of Go)improves its gameplay. Our numerical examples show that this automated meta-modeling framework not only produces models which outperform existing cohesive models on benchmark traction-separation data but is also capable of detecting hidden mechanisms among micro-structural features and incorporating them in constitutive models to improve the forward prediction accuracy, which are difficult tasks to do manually.

The extraction of clusters from a dataset which includes multiple clusters and another significant portion of "background" samples is a task of practical importance. The traditional spectral clustering algorithm, relying on the leading $K$ eigenvectors to detect the $K$ clusters, fails in such cases. This paper proposes the spectral embedding norm which sums the squared values of the first $I$ (normalized) eigenvectors, where $I$ can be larger than $K$. We prove that the quantity can be used to separate clusters from the background under generic conditions motivated by applications such as anomaly detection. The performance of the algorithm is not sensitive to the choice of $I$, and we present experiments on synthetic and real-world datasets.

A generalized gamification framework is introduced as a form of smart infrastructure with potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. The proposed framework enables a Human-Centric Cyber-Physical System using an interface to allow building managers to interact with occupants. The interface is designed for occupant engagement-integration supporting learning of their preferences over resources in addition to understanding how preferences change as a function of external stimuli such as physical control, time or incentives. Towards intelligent and autonomous incentive design, a noble statistical learning algorithm performing occupants energy usage behavior segmentation is proposed. We apply the proposed algorithm, Graphical Lasso, on energy resource usage data by the occupants to obtain feature correlations--dependencies. Segmentation analysis results in characteristic clusters demonstrating different energy usage behaviors. The features--factors characterizing human decision-making are made explainable.

This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed of vehicles on the intersecting road and use a policy that adapts its speed along its pre-defined trajectory to pass the crossing efficiently. Deep Q-learning is used on simulated traffic with different predefined driver behaviors and intentions. The results show a policy that is able to cross the intersection avoiding collision with other vehicles 98% of the time, while at the same time not being too passive. Moreover, inferring information over time is important to distinguish between different intentions and is shown by comparing the collision rate between a Deep Recurrent Q-Network at 0.85% and a Deep Q-learning at 1.75%.

Nowadays, the contemporary manufactured and small unmanned aerial vehicles (UAVs) known as drones are mostly electric-based, using electric engines for their flight power. The application of such propulsion systems need proper elaboration of efficient and light electric energy sources. The paper tends to shift our approach to drones towards one that will see efficient energy storage through the use of hydrogen – which is outlined in the following sections of this article. Speaking of, there are primarily two methods of on-board energy storing in today's drone system: The second method is one on which we are focusing in this article – mostly because of the complexity of the fuel cells and their constant need for the supply of hydrogen. Currently, hydrogen can be stored in compressed state in pressure bottles or in its liquid state (in cryogenic tanks).

SURE, COMPUTER ALGORITHMS ARE TAKING over tech and science and medicine … but the creatives are still safe, right? A new program from software developer Autodesk called Dreamcatcher (rendering above) can use A.I. techniques to assist human designers as they go about their creative tasks. Already in use by companies including Airbus, Under Armour, and Stanley Black & Decker, the software is an example of the burgeoning field of generative design. The software then produces hundreds or even thousands of options. As the human designer winnows the choices, the software susses out preferences and helps iterate even better options.