Wildfires are one of the most catastrophic natural disasters, causing increasingly severe ecological and economic damage. Early response is critically important for wildfire management, but also difficult due to the wide geographical area to monitor, often far from utility infrastructures such as stable power and high-bandwidth network. In this work, we present Xyloni, a very low-cost, low-power neural network accelerator for sensor nodes, which improves the cost-effectiveness and scalability of real-time wildfire detection by drastically reducing wireless data transmission and overall power consumption. Xyloni uses low-power flash and FeRAM memories to store a hardware co-optimized Neural Network model for fire and smoke detection, as well as intermediate activations during inference. It also time-shares a Field-Programmable Gate Array across different model layers for power-efficient computation. The detection model prevents benign images from consuming network traffic, allowing the use of low-bandwidth, low-power network fabrics such as a LoRa mesh network with enough range for the necessary geographical coverage. Compared to a wide range of edge and sensor platforms capable of real-time data collection, Xyloni demonstrated an order of magnitude reduction in power consumption for the network transmission reduction task, leading to a corresponding reduction in battery and deployment cost.

This article presents Eciton, a very low-power recurrent neural network accelerator for time series data within low-power edge sensor nodes, achieving real-time inference with a power consumption of 17 mW under load. Eciton reduces memory and chip resource requirements via 8-bit quantization and hard sigmoid activation, allowing the accelerator as well as the recurrent neural network model parameters to fit in a low-cost, low-power Lattice iCE40 UP5K FPGA. We evaluate Eciton on multiple, established time-series classification applications including predictive maintenance of mechanical systems, sound classification, and intrusion detection for IoT nodes. Binary and multi-class classification edge models are explored, demonstrating that Eciton can adapt to a variety of deployable environments and remote use cases. Eciton demonstrates real-time processing at a very low power consumption with minimal loss of accuracy on multiple inference scenarios with differing characteristics, while achieving competitive power efficiency against the state-of-the-art of similar scale. We show that the addition of this accelerator actually reduces the power budget of the sensor node by reducing power-hungry wireless transmission. The resulting power budget of the sensor node is small enough to be powered by a power harvester, potentially allowing it to run indefinitely without a battery or periodic maintenance.

This paper presents Eciton, a very low-power LSTM neural network accelerator for low-power edge sensor nodes, demonstrating real-time processing on predictive maintenance applications with a power consumption of 17 mW under load. Eciton reduces memory and chip resource requirements via 8-bit quantization and hard sigmoid activation, allowing the accelerator as well as the LSTM model parameters to fit in a lowcost, low-power Lattice iCE40 UP5K FPGA. Eciton demonstrates real-time processing at a very low power consumption with minimal loss of accuracy on two predictive maintenance scenarios with differing characteristics, while achieving competitive power efficiency against the state-of-the-art of similar scale. We also show that the addition of this accelerator actually reduces the power budget of the sensor node by reducing power-hungry wireless transmission.The resulting power budget of the sensor node is small enough to be powered by a power harvester, potentially allowing it to run indefinitely without a battery or periodic maintenance.

We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images. Unlike most existing methods that require voxel-wise densely labeled training data, our weakly-supervised CIVA-Net is the first model that only needs image-level class labels as guidance to learn accurate volumetric segmentation. Our model learns from cross-image co-occurrence for integral region generation, and explores inter-voxel affinity relations to predict segmentation with accurate boundaries. We empirically validate our model on both simulated and real cryo-ET datasets. Our experiments show that CIVA-Net achieves comparable performance to the state-of-the-art models trained with stronger supervision.

Diversity in the exhibited behavior of a given system is a desirable characteristic in a variety of application contexts. Synthesis of conformant implementations often proceeds by discovering witnessing Skolem functions, which are traditionally deterministic. In this paper, we present a novel Skolem extraction algorithm to enable synthesis of witnesses with random behavior and demonstrate its applicability in the context of reactive systems. The synthesized solutions are guaranteed by design to meet the given specification, while exhibiting a high degree of diversity in their responses to external stimuli. Case studies demonstrate how our proposed framework unveils a novel application of synthesis in model-based fuzz testing to generate fuzzers of competitive performance to general-purpose alternatives, as well as the practical utility of synthesized controllers in robot motion planning problems.

We describe Service Fabric (SF), Microsoft's distributed platform for building, running, and maintaining microservice applications in the cloud. SF has been running in production for 10+ years, powering many critical services at Microsoft. This paper outlines key design philosophies in SF. We then adopt a bottom-up approach to describe low-level components in its architecture, focusing on modular use and support for strong semantics like fault-tolerance and consistency within each component of SF. We discuss lessons learned, and present experimental results from production data.

OpenVX is an open standard for cross platform acceleration of computer vision applications. It was created to address the challenge of implementing efficient, portable and easy to use vision processing algorithms by separating application specification and implantation. It offers a set of basic, widely used vision kernels that accelerator vendors are supposed to provide. This work presents a framework for turning a high-level OpenVX graph specification into an efficient FPGA implementation.

Recent high-profile fire incidents in cities around the world have highlighted gaps in fire risk reduction efforts, as cities grapple with fewer resources and more properties to safeguard. To address this resource gap, prior work has developed machine learning frameworks to predict fire risk and prioritize fire inspections. However, existing approaches were limited by not including time-varying data, never deploying in real-time, and only predicting risk for a small subset of commercial properties in their city. Here, we have developed a predictive risk framework for all 20,636 commercial properties in Pittsburgh, based on time-varying data from a variety of municipal agencies. We have deployed our fire risk model on Pittsburgh Bureau of Fire's (PBF), and we have developed preliminary risk models for residential property fire risk prediction. Our commercial risk model outperforms the prior state of the art with a kappa of 0.33 compared to their 0.17, and is able to be applied to nearly 4 times as many properties as the prior model. In the 5 weeks since our model was first deployed, 58% of our predicted high-risk properties had a fire incident of any kind, while 23% of the building fire incidents that occurred took place in our predicted high or medium risk properties. The risk scores from our commercial model are visualized on an interactive dashboard and map to assist the PBF with planning their fire risk reduction initiatives. This work is already helping to improve fire risk reduction in Pittsburgh and is beginning to be adopted by other cities.

The AID / APOBEC genes are a family of cytidine deaminases that have evolved in vertebrates, and particularly mammals, to mutate RNA and DNA at distinct preferred nucleotide contexts (or "hotspots") on foreign genomes such as viruses and retrotransposons. These enzymes play a pivotal role in intrinsic immunity defense mechanisms, often deleteriously mutating invading retroviruses or retrotransposons and, in the case of AID, changing antibody sequences to drive affinity maturation. We investigate the strength of various hotspots on their known biological targets by evaluating the potential impact of mutations on the DNA coding sequences of these targets, and compare these results to hypothetical hotspots that did not evolve. We find that the existing AID / APOBEC hotspots have a large impact on retrotransposons and non-mammalian viruses while having a much smaller effect on vital mammalian genes, suggesting co-evolution with AID / APOBECs may have had an impact on the genomes of the viruses we analyzed. We determine that GC content appears to be a significant, but not sole, factor in resistance to deaminase activity. We discuss possible mechanisms AID and APOBEC viral targets have adopted to escape the impacts of deamination activity, including changing the GC content of the genome.

A tremendous amount of Earth and Climate related data and information are available from the U.S. Federal government. Among the proposed actions of the President's Climate Action Plan are several efforts to foster the use of existing data to encourage development of additional data products and tools that can be used to improve community resilience and prepare for the impacts of climate change. Building on previous efforts to organize the presentation of this material from Federal web pages and data centers, the Climate Data Initiative is working together with other related efforts to link Earth observation systems through to data resulting from them and on to related web pages, case studies, decision making tools, and other relevant content. Often such information is not located in a single web site, data center, or even a single agency, but distributed across the Federal Government. Linking such information across the breadth of interagency holdings can increase understanding of the complexity of those holdings and their inter-relationships and allow a more cohesive presentation of all of the material.