Searching for small objects in large images is currently challenging for deep learning systems, but is a task with numerous applications including remote sensing and medical imaging. Thorough scanning of very large images is computationally expensive, particularly at resolutions sufficient to capture small objects. The smaller an object of interest, the more likely it is to be obscured by clutter or otherwise deemed insignificant. We examine these issues in the context of two complementary problems: closed-set object detection and open-set target search. First, we present a method for predicting pixel-level objectness from a low resolution gist image, which we then use to select regions for subsequent evaluation at high resolution. This approach has the benefit of not being fixed to a predetermined grid, allowing fewer costly high-resolution glimpses than existing methods. Second, we propose a novel strategy for open-set visual search that seeks to find all objects in an image of the same class as a given target reference image. We interpret both detection problems through a probabilistic, Bayesian lens, whereby the objectness maps produced by our method serve as priors in a maximum-a-posteriori approach to the detection step. We evaluate the end-to-end performance of both the combination of our patch selection strategy with this target search approach and the combination of our patch selection strategy with standard object detection methods. Both our patch selection and target search approaches are seen to significantly outperform baseline strategies.

Machine learning models have been successfully used in many scientific and engineering fields. However, it remains difficult for a model to simultaneously utilize domain knowledge and experimental observation data. The application of knowledge-based symbolic AI represented by an expert system is limited by the expressive ability of the model, and data-driven connectionism AI represented by neural networks is prone to produce predictions that violate physical mechanisms. In order to fully integrate domain knowledge with observations, and make full use of the prior information and the strong fitting ability of neural networks, this study proposes theory-guided hard constraint projection (HCP). This model converts physical constraints, such as governing equations, into a form that is easy to handle through discretization, and then implements hard constraint optimization through projection. Based on rigorous mathematical proofs, theory-guided HCP can ensure that model predictions strictly conform to physical mechanisms in the constraint patch. The performance of the theory-guided HCP is verified by experiments based on the heterogeneous subsurface flow problem. Due to the application of hard constraints, compared with fully connected neural networks and soft constraint models, such as theory-guided neural networks and physics-informed neural networks, theory-guided HCP requires fewer data, and achieves higher prediction accuracy and stronger robustness to noisy observations.

Researchers at Oregon State University are making key advances with a new type of optical sensor that more closely mimics the human eye's ability to perceive changes in its visual field. The sensor is a major breakthrough for fields such as image recognition, robotics and artificial intelligence. Findings by OSU College of Engineering researcher John Labram and graduate student Cinthya Trujillo Herrera were published today in Applied Physics Letters. Previous attempts to build a human-eye type of device, called a retinomorphic sensor, have relied on software or complex hardware, said Labram, assistant professor of electrical engineering and computer science. But the new sensor's operation is part of its fundamental design, using ultrathin layers of perovskite semiconductors--widely studied in recent years for their solar energy potential--that change from strong electrical insulators to strong conductors when placed in light.

Here are the Wyze Outdoor Cam's specs: The Wyze Outdoor Starter Bundle includes one Outdoor Cam and one base station required for use. Running on two 2,600 mAh integrated rechargeable batteries, Wyze's Outdoor Cam is completely wire-free and claims a battery life of three to six months for normal use (about 10-20 events per day). A base station is required to use the camera, but it's included in the Wyze Outdoor Cam Starter Bundle, so there are no additional products to buy. Up to four total cameras can be added to the base station, allowing you to outfit the exterior of your home with multiple cameras for less than the cost of one Arlo Pro 4, our No. 1 pick for outdoor security cameras. Wyze's outdoor camera delivers 1080p video and night vision that are easy on the eyes, as well as two-way talk functionality that's clear and easy to understand.

Researchers from CSIRO, Charles Darwin University and The University of Western Australia have developed a machine-learning approach that reliably detects invasive gamba grass from high-resolution satellite imagery. Gamba grass is listed as a Weed of National Significance, and is one of five introduced grass species that pose extensive and significant threats to Australia's biodiversity. The perennial grass can grow to four metres in height and forms dense tussocks which can burn as large, hot fires late in the dry season. Mapping where gamba grass occurs is essential to managing it effectively, but northern Australia is so vast and remote that on-the-ground mapping and even airborne detection of the weed is too labour-intensive. So, the researchers turned to high-quality satellite imagery and developed a technique that could help detect and prioritise gamba grass for management.

The Living Planet Index produced by WWF estimates that wildlife population sizes have dropped by 68 per cent since 1970. The charity advocates the use of artificial intelligence (AI) as a tool of conservation technology to monitor and curb this alarming rate of decline. One of the most useful applications is in acoustic monitoring, recording the sounds of wildlife ecosystems on weatherproof sensors. Many animals, from birds and bats to mammals and even invertebrates, use sound for communication, navigation and territorial defence, providing reams of rich data on how a species population is doing. AI provides a fast and cost-effective way to analyse hours of recordings for patterns of behaviour.

A unifying mathematical formulation is needed to move from one-off digital twins built through custom implementations to robust digital twin implementations at scale. This work proposes a probabilistic graphical model as a formal mathematical representation of a digital twin and its associated physical asset. We create an abstraction of the asset-twin system as a set of coupled dynamical systems, evolving over time through their respective state-spaces and interacting via observed data and control inputs. The formal definition of this coupled system as a probabilistic graphical model enables us to draw upon well-established theory and methods from Bayesian statistics, dynamical systems, and control theory. The declarative and general nature of the proposed digital twin model make it rigorous yet flexible, enabling its application at scale in a diverse range of application areas. We demonstrate how the model is instantiated as a Bayesian network to create a structural digital twin of an unmanned aerial vehicle. The graphical model foundation ensures that the digital twin creation and updating process is principled, repeatable, and able to scale to the calibration of an entire fleet of digital twins.

Human population are striving against energy-related issues that not only affects society and the development of the world, but also causes global warming. A variety of broad approaches have been developed by both industry and the research community. However, there is an ever increasing need for comprehensive, end-to-end solutions aimed at transforming human behavior rather than device metrics and benchmarks. In this paper, a micro-moment-based smart plug system is proposed as part of a larger multi-appliance energy efficiency program. The smart plug, which includes two sub-units: the power consumption unit and environmental monitoring unit collect energy consumption of appliances along with contextual information, such as temperature, humidity, luminosity and room occupancy respectively. The plug also allows home automation capability. With the accompanying mobile application, end-users can visualize energy consumption data along with ambient environmental information. Current implementation results show that the proposed system delivers cost-effective deployment while maintaining adequate computation and wireless performance.

While cosmological dark matter-only simulations relying solely on gravitational effects are comparably fast to compute, baryonic properties in simulated galaxies require complex hydrodynamic simulations that are computationally costly to run. We explore the merging of an extended version of the equilibrium model, an analytic formalism describing the evolution of the stellar, gas, and metal content of galaxies, into a machine learning framework. In doing so, we are able to recover more properties than the analytic formalism alone can provide, creating a high-speed hydrodynamic simulation emulator that populates galactic dark matter haloes in N-body simulations with baryonic properties. While there exists a trade-off between the reached accuracy and the speed advantage this approach offers, our results outperform an approach using only machine learning for a subset of baryonic properties. We demonstrate that this novel hybrid system enables the fast completion of dark matter-only information by mimicking the properties of a full hydrodynamic suite to a reasonable degree, and discuss the advantages and disadvantages of hybrid versus machine learning-only frameworks. In doing so, we offer an acceleration of commonly deployed simulations in cosmology.

The objective of model selection is to find the network architecture with the best generalization properties. That is, we want to improve the final selection error obtained before (0.263 NSE). The best selection error is achieved by using a model with the most appropiate complexity to produce an adequate fit of the data. Order selection algorithms are responsible for find the optimal number of perceptrons in the neural network. The following chart shows the results of the incremental order algorithm.