In addition to ML, the Internet of Things (IoT) and predictive maintenance will come into play as Niagara Bottling will collect data from machine sensors. Sensory data includes humidity within the building and the amount of pressure and speed when factory workers pull the plastic stretch wrap. "Getting into predictive equipment maintenance is going to be an area where we could use data science and ML," Rao said. "We have just started down that path of being able to instrument different manufacturing equipment with the right sensors, and being able to measure and gain insights from the measurements." In addition to water bottle manufacturing plants, IoT data from predictive maintenance is valuable in power plants and oil refineries.

Ordnance survey has unveiled a solar-powered drone that is capable of flying for 90 days at a time without needing to come back to Earth and will be used to provide higher quality images of Earth. It will circle at approximately 67,000 ft (20,400m) above the ground and snap images to sell to organisations and businesses. First tests of the Astigan unmanned aerial vehicle are scheduled to take place before the end of 2019. Ordnance Survey is the majority stakeholder in Astigan, a firm based in Bridgwater, Somerset. The company works in the same factory that was once home to Facebook's Aquila internet drone project.

Scientists know that you can dramatically alter a crystalline material's properties by applying a bit of strain to it, but finding the right strain is another matter when there are virtually limitless possibilities. There may a straightforward solution, though: let AI do the heavy lifting. An international team of researchers has devised a way for machine learning to find strains that will achieve the best results. Their neural network algorithm predicts how the direction and degree of strain will affect a key property governing the efficiency of semiconductors, making them far more efficient without requiring educated guesses from humans. The technology could lead to semiconductor-based inventions that are far more powerful than usual with only minor changes.

The owner of the wrecked Fukushima No. 1 power plant is trying this week to touch melted fuel at the bottom of the plant for the first time since the disaster almost eight years ago, a tiny but key step toward retrieving the radioactive material amid a ¥21.5 trillion ($195 billion) cleanup effort. Tokyo Electric Power Co. Holdings Inc. will on Wednesday insert a robot developed by Toshiba Corp. to make contact with material believed to contain melted fuel inside the containment vessel of the unit 2 reactor, one of three units that melted down after the March 2011 earthquake and tsunami. "We plan to confirm if we can move or lift the debris or if it crumbles," Joji Hara, a spokesman for Tepco said by phone Friday. Tepco doesn't plan to collect samples during the survey. The country is seeking to clean up the Fukushima disaster, the world's worst atomic accident since Chernobyl, which prompted a mass shutdown of its reactors.

At the top of its hype cycle, Artificial intelligence (AI) is transforming the energy landscape, revolutionizing how solar assets are managed, operated and maintained. The ever so expanding global capacity of solar PV combined with the growing disparity of these assets have made the job of an asset owner only more complex. There are substantial financial and efficiency gains to be made in using AI-driven solutions. Moreover, as AI technology advances and becomes more ubiquitous, it is incumbent on every solar asset owner to answer the question of how this technology will disrupt the industry and can benefit their portfolio. The latest white paper, published by Solarplaza, explores the areas, which are enhanced by AI, utilizing case studies to capture the current potential of artificial intelligence to drive efficiency and Return On Investment (ROI) in solar portfolios. Furthermore, the facets of asset management and O&M that can be automated are discussed, to help you navigate through the noise surrounding the topic of AI.

The automated construction of coarse-grained models represents a pivotal component in computer simulation of physical systems and is a key enabler in various analysis and design tasks related to uncertainty quantification. Pertinent methods are severely inhibited by the high-dimension of the parametric input and the limited number of training input/output pairs that can be generated when computationally demanding forward models are considered. Such cases are frequently encountered in the modeling of random heterogeneous media where the scale of the microstructure necessitates the use of high-dimensional random vectors and very fine discretizations of the governing equations. The present paper proposes a probabilistic Machine Learning framework that is capable of operating in the presence of Small Data by exploiting aspects of the physical structure of the problem as well as contextual knowledge. As a result, it can perform comparably well under extrapolative conditions. It unifies the tasks of dimensionality and model-order reduction through an encoder-decoder scheme that simultaneously identifies a sparse set of salient lower-dimensional microstructural features and calibrates an inexpensive, coarse-grained model which is predictive of the output. Information loss is accounted for and quantified in the form of probabilistic predictive estimates. The learning engine is based on Stochastic Variational Inference. We demonstrate how the variational objectives can be used not only to train the coarse-grained model, but also to suggest refinements that lead to improved predictions.

Artificial intelligence (AI) has permeated every aspect of our lives. From major advancements in medicine to transforming the way business is conducted, machine learning shows great potential to improve the quality of our lives in a variety of ways. A behind-the-scenes look into different companies' AI ventures shows that certain aspects of machine learning even aid in making the world a safer place. Manufacturing problems can have serious negative impacts on a business. From cars to home appliances, product safety is of utmost importance when it comes to customer satisfaction.

The rise of voice assistants has put a new customer-facing channel on the map for marketers. The promise is clear: voice-enabled devices operate as a fine blend of digital and physical realities, which makes room for truly contextual interactions with users. But with voice technology so young, it's still unclear if it can add up meaningfully to the marketing toolkit. In 2016, Gartner predicted 75 percent penetration of voice-activated devices in US households by 2020. We're now two years short of this deadline and the penetration rate is a humble 13 percent (though expected to rise to 55 percent by 2022).

In her article in The MIT Technology Review--"Giving Algorithms a Sense of Uncertainty Could Make Them More Ethical" (January 18, 2019)--Karen Hao reached out to Cornell CS Professor Carla Gomes to ask if Peter Eckersley (and his Partnership on AI) is onto something in his approach to considering partial orders of solutions with respect to multiple, often conflicting, objectives, and possibly introducing uncertainty into AI systems, especially those addressing decision making and moral dilemmas. Eckersley says: "We as humans want multiple incompatible things. There are many high-stakes situations where it's actually inappropriate--perhaps dangerous--to program in a single objective function that tries to describe your ethics." Supportively, Gomes remarks: "The overall problem is very complex. It will take a body of research to address all issues, but Peter's approach is making an important step in the right direction."

This paper documents the release of the ELKI data mining framework, version 0.7.5. ELKI is an open source (AGPLv3) data mining software written in Java. The focus of ELKI is research in algorithms, with an emphasis on unsupervised methods in cluster analysis and outlier detection. In order to achieve high performance and scalability, ELKI offers data index structures such as the R*-tree that can provide major performance gains. ELKI is designed to be easy to extend for researchers and students in this domain, and welcomes contributions of additional methods. ELKI aims at providing a large collection of highly parameterizable algorithms, in order to allow easy and fair evaluation and benchmarking of algorithms. We will first outline the motivation for this release, the plans for the future, and then give a brief overview over the new functionality in this version. We also include an appendix presenting an overview on the overall implemented functionality.