Saving lives or economy is a dilemma for epidemic control in most cities while smart-tracing technology raises people's privacy concerns. In this paper, we propose a solution for the life-or-economy dilemma that does not require private data. We bypass the private-data requirement by suppressing epidemic transmission through a dynamic control on inter-regional mobility that only relies on Origin-Designation (OD) data. We develop DUal-objective Reinforcement-Learning Epidemic Control Agent (DURLECA) to search mobility-control policies that can simultaneously minimize infection spread and maximally retain mobility. DURLECA hires a novel graph neural network, namely Flow-GNN, to estimate the virus-transmission risk induced by urban mobility. The estimated risk is used to support a reinforcement learning agent to generate mobility-control actions. The training of DURLECA is guided with a well-constructed reward function, which captures the natural trade-off relation between epidemic control and mobility retaining. Besides, we design two exploration strategies to improve the agent's searching efficiency and help it get rid of local optimums. Extensive experimental results on a real-world OD dataset show that DURLECA is able to suppress infections at an extremely low level while retaining 76\% of the mobility in the city. Our implementation is available at https://github.com/anyleopeace/DURLECA/.

Current strategies employed for maritime target search and tracking are primarily based on the use of agents following a predetermined path to perform a systematic sweep of a search area. Recently, dynamic Particle Swarm Optimization (PSO) algorithms have been used together with swarming multi-robot systems (MRS), giving search and tracking solutions the added properties of robustness, scalability, and flexibility. Swarming MRS also give the end-user the opportunity to incrementally upgrade the robotic system, inevitably leading to the use of heterogeneous swarming MRS. However, such systems have not been well studied and incorporating upgraded agents into a swarm may result in degraded mission performances. In this paper, we propose a PSO-based strategy using a topological k-nearest neighbor graph with tunable exploration and exploitation dynamics with an adaptive repulsion parameter. This strategy is implemented within a simulated swarm of 50 agents with varying proportions of fast agents tracking a target represented by a fictitious binary function. Through these simulations, we are able to demonstrate an increase in the swarm's collective response level and target tracking performance by substituting in a proportion of fast buoys.

The paper describes an ongoing effort in developing a declarative system for supporting operators in the Nuclear Power Plant (NPP) control room. The focus is on two modules: diagnosis and explanation of events that happened in NPPs. We describe an Answer Set Programming (ASP) representation of an NPP, which consists of declarations of state variables, components, their connections, and rules encoding the plant behavior. We then show how the ASP program can be used to explain the series of events that occurred in the Three Mile Island, Unit 2 (TMI-2) NPP accident, the most severe accident in the USA nuclear power plant operating history. We also describe an explanation module aimed at addressing answers to questions such as ``why an event occurs?'' or ``what should be done?'' given the collected data. This paper is *under consideration* for acceptance in TPLP Journal.

This paper presents an approach for constructing multifidelity surrogate models to simultaneously represent, and learn representations of, multiple information sources. The approach formulates a network of surrogate models whose relationships are defined via localized scalings and shifts. The network can have general structure, and can represent a significantly greater variety of modeling relationships than the hierarchical/recursive networks used in the current state of the art. We show empirically that this flexibility achieves greatest gains in the low-data regime, where the network structure must more efficiently leverage the connections between data sources to yield accurate predictions. We demonstrate our approach on four examples ranging from synthetic to physics-based simulation models. For the numerical test cases adopted here, we obtained an order-of-magnitude reduction in errors compared to multifidelity hierarchical and single-fidelity approaches.

The notion of graph filters can be used to define generative models for graph data. In fact, the data obtained from many examples of network dynamics may be viewed as the output of a graph filter. With this interpretation, classical signal processing tools such as frequency analysis have been successfully applied with analogous interpretation to graph data, generating new insights for data science. What follows is a user guide on a specific class of graph data, where the generating graph filters are low-pass, i.e., the filter attenuates contents in the higher graph frequencies while retaining contents in the lower frequencies. Our choice is motivated by the prevalence of low-pass models in application domains such as social networks, financial markets, and power systems. We illustrate how to leverage properties of low-pass graph filters to learn the graph topology or identify its community structure; efficiently represent graph data through sampling, recover missing measurements, and de-noise graph data; the low-pass property is also used as the baseline to detect anomalies.

We propose a data fusion method based on multi-fidelity Gaussian process regression (GPR) framework. This method combines available data of the quantity of interest (QoI) and its gradients with different fidelity levels, namely, it is a Gradient-enhanced Cokriging method (GE-Cokriging). It provides the approximations of both the QoI and its gradients simultaneously with uncertainty estimates. We compare this method with the conventional multi-fidelity Cokriging method that does not use gradients information, and the result suggests that GE-Cokriging has a better performance in predicting both QoI and its gradients. Moreover, GE-Cokriging even shows better generalization result in some cases where Cokriging performs poorly due to the singularity of the covariance matrix. We demonstrate the application of GE-Cokriging in several practical cases including reconstructing the trajectories and velocity of an underdamped oscillator with respect to time simultaneously, and investigating the sensitivity of power factor of a load bus with respect to varying power inputs of a generator bus in a large scale power system. We also show that though GE-Cokriging method requires a little bit higher computational cost than Cokriging method, the result of accuracy comparison shows that this cost is usually worth it.

With countless laptops, gaming devices, eBikes, and more, 2020 has been on a roll. As we speak, there are preparations going on for Samsung Unpacked, the Google Pixel 4a release, and also a whole bunch of new Sony audio gear. So, it wouldn't be wrong to say that technology hasn't slowed down this year. This week, we went ahead and listed the best cool tech gadgets and the most trending technologies of the year. Be it Artificial Intelligence (AI), Internet of Things (IoT), or even Wi-Fi 6E, this weekly blog gives you a quick glimpse of every technology you should be aware of. As Elon Musk stated recently, "We're headed toward a situation where AI is vastly smarter than humans and I think that time frame is less than five years from now. But that doesn't mean that everything goes to hell in five years. It just means that things get unstable or weird." This statement does add value to the fact that more AI gadgets can actually make our lives easier. The below examples will show you how. If you need some friendly help around the house, look to the Nabot AI Trainable Robot.

A growing number of old economy companies are using technologies such as internet-of-things (IoT) and artificial intelligence (AI) to expand their digital presence, taking on IT majors and global diversified conglomerates which are also aggressively muscling into this space. Leading domestic industrial and engineering companies such as Larsen & Toubro, Reliance Industries and the Tata group, as well as multinational firms including General Electric, Siemens and ABB, are all trying to capture a share of the pie and the timing seems just right. Most companies are not making huge investments in expanding capacity, although they see merit in putting money into digital platforms, which help improve efficiency and render more profitable the extant capacity. Industrial firms traditionally entered the services business to offer operations and maintenance support, which gave them additional revenue streams and helped build customer loyalty. Now, they are taking it a notch higher -- by adding sensors to products to provide steady data, and analytics, which predict breakdowns and improve efficiency. "This is a hardware-plus-service business; the value-added services have high margins that will reflect on the bottomline," JD Patil, senior executive vice-president (defence business) and member of the board at Larsen & Toubro, told ET. "Companies like us have an edge because analytics can be done only when you understand the domain very well."

Technological innovation plays a decisive role in the evolution of changes towards a new model that involves improving development, without leaving anyone behind, and with the focus on avoiding inequality and injustice, ensuring better protection of the environment. These are broadly the foundations of the 17 Sustainable Development Goals (SDGs) of the United Nations 2030 Agenda. Technology with its multiplier effect can accelerate the achievement of objectives and goals. There are four technologies (based on AI) that allow addressing the five basic elements on which the 2030 Agenda is structured: people, prosperity, planet, peace and alliances. The interconnection of the five pillars of the 2030 Agenda and with four technological blocks that pivot on the Internet of Things (IoT), Automation, the Analysis of large volumes of data (Big Data) and Advanced Robotics is essential so that the developed world that we know is in balance and the current imbalances are corrected.

Enabling high energy efficiency is crucial for embedded implementations of deep learning. Several studies have shown that the DRAM-based off-chip memory accesses are one of the most energy-consuming operations in deep neural network (DNN) accelerators, and thereby limit the designs from achieving efficiency gains at the full potential. DRAM access energy varies depending upon the number of accesses required as well as the energy consumed per-access. Therefore, searching for a solution towards the minimum DRAM access energy is an important optimization problem. Towards this, we propose the ROMANet methodology that aims at reducing the number of memory accesses, by searching for the appropriate data partitioning and scheduling for each layer of a network using a design space exploration, based on the knowledge of the available on-chip memory and the data reuse factors. Moreover, ROMANet also targets decreasing the number of DRAM row buffer conflicts and misses, by exploiting the DRAM multi-bank burst feature to improve the energy-per-access. Besides providing the energy benefits, our proposed DRAM data mapping also results in an increased effective DRAM throughput, which is useful for latency-constraint scenarios. Our experimental results show that the ROMANet saves DRAM access energy by 12% for the AlexNet, by 36% for the VGG-16, and by 46% for the MobileNet, while also improving the DRAM throughput by 10%, as compared to the state-of-the-art.