Brakes squeal, hard drives crunch, air conditioners rattle, and their owners know it's time for a service call. But some of the most valuable machinery in the world often operates with nobody around to hear the mechanical breakdowns, from the chillers and pumps that drive big-building climate control systems to the massive turbines at hydroelectric power plants. That's why a number of startups are working to train computers to pick up on changes in the sounds, vibrations, heat emissions, and other signals that machines give off as they're working or failing. The hope is that the computers can catch mechanical failures before they happen, saving on repair costs and reducing downtime. "We're developing an expert mechanic's brain that identifies exactly what is happening to a machine by the way that it sounds," says Amnon Shenfeld, founder and CEO of 3DSignals, a startup based in Kfar Saba, Israel, that is using machine learning to train computers to listen to machinery and diagnose problems at facilities like hydroelectric plants and steel mills.

Bike Sharing Systems (BSSs) are widely adopted in major cities of the world due to concerns associated with extensive private vehicle usage, namely, increased carbon emissions, traffic congestion and usage of nonrenewable resources. In a BSS, base stations are strategically placed throughout a city and each station is stocked with a pre-determined number of bikes at the beginning of the day. Customers hire the bikes from one station and return them at another station. Due to unpredictable movements of customers hiring bikes, there is either congestion (more than required) or starvation (fewer than required) of bikes at base stations. Existing data has shown that congestion/starvation is a common phenomenon that leads to a large number of unsatisfied customers resulting in a significant loss in customer demand. In order to tackle this problem, we propose an optimisation formulation to reposition bikes using vehicles while also considering the routes for vehicles and future expected demand. Furthermore, we contribute two approaches that rely on decomposability in the problem (bike repositioning and vehicle routing) and aggregation of base stations to reduce the computation time significantly. Finally, we demonstrate the utility of our approach by comparing against two benchmark approaches on two real-world data sets of bike sharing systems. These approaches are evaluated using a simulation where the movements of customers are generated from real-world data sets.

Applied machine learning

Roughly 163,000 oil jobs were lost nationally from the 2014 peak, or about 30 percent of the total, while oil prices plummeted, at one point by as much as 70 percent. The job losses just in Texas, the most productive oil-producing state, totaled 98,000. Several thousand workers have come back to work in recent months as the price of oil has begun to rise again, but energy experts say that between a third and a half of the workers who lost their jobs are not returning. Many have migrated to construction or even jobs in renewable energy, like wind power. "People have left the industry, and they are not coming back," said Michael Dynan, vice president for portfolio and strategic development at Schramm, a Pennsylvania manufacturer of drilling rigs.

At the edge of a plot of muddy farmland, a few miles down the road from the University of California at Davis, an engineer takes a few quick steps across crop rows and lets go of a three-foot drone. Within seconds, the device – which weighs less than 2lbs and carries a powerful camera – ascends hundreds of feet into the cold, clear, blue sky and begins to snap detailed photos of the ground far below, including a long row of large solar panels mounted on steel poles. This flight is just a test, demonstrated by Kingsley Chen, the drone fleet coordinator for SunPower at the solar company's research and development center, which is under construction and about a two-hour drive northeast of the San Francisco Bay Area. The drone will enable SunPower to survey a wide region and help design a solar power farm that can fit more solar panels on a piece of land, more quickly and for lower costs than it previously could. The test highlights a growing use of the latest computing technologies – drones, robots, software, sensors and networks – by US companies to design, build and operate solar farms.

In this series of exploratory blog posts, we explore the relationship between recurrent neural networks (RNNs) and IoT data. The article is written by Ajit Jaokar, Dr Paul Katsande and Dr Vinay Mehendiratta as part of the Data Science for Internet of Things practitioners course. RNNs are already used for Time series analysis. Because IoT problems can often be modelled as a Time series, RNNs could apply to IoT data. In this multi-part blog, we first discuss Time series applications and then discuss how RNNs could apply to Time series applications.

Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements. The present paper leverages online learning advances to facilitate stochastic resource allocation tasks. By recognizing the central role of Lagrange multipliers, the underlying constrained optimization problem is formulated as a machine learning task involving both training and operational modes, with the goal of learning the sought multipliers in a fast and efficient manner. To this end, an order-optimal offline learning approach is developed first for batch training, and it is then generalized to the online setting with a procedure termed learn-and-adapt. The novel resource allocation protocol permeates benefits of stochastic approximation and statistical learning to obtain low-complexity online updates with learning errors close to the statistical accuracy limits, while still preserving adaptation performance, which in the stochastic network optimization context guarantees queue stability. Analysis and simulated tests demonstrate that the proposed data-driven approach improves the delay and convergence performance of existing resource allocation schemes.

The brain is capable of massively parallel information processing while consuming only 1–100 fJ per synaptic event. Inspired by the efficiency of the brain, CMOS-based neural architectures and memristors are being developed for pattern recognition and machine learning. However, the volatility, design complexity and high supply voltages for CMOS architectures, and the stochastic and energy-costly switching of memristors complicate the path to achieve the interconnectivity, information density, and energy efficiency of the brain using either approach. Here we describe an electrochemical neuromorphic organic device (ENODe) operating with a fundamentally different mechanism from existing memristors. ENODe switches at low voltage and energy ( 10 pJ for 103 μm2 devices), displays 500 distinct, non-volatile conductance states within a 1 V range, and achieves high classification accuracy when implemented in neural network simulations. Plastic ENODes are also fabricated on flexible substrates enabling the integration of neuromorphic functionality in stretchable electronic systems. Mechanical flexibility makes ENODes compatible with three-dimensional architectures, opening a path towards extreme interconnectivity comparable to the human brain.

For decades, industrial control systems have been generating enormous volumes of data, but in many cases that data hasn't been fully employed to help companies reduce operating costs, improve reliability, and increase productivity--three goals that amount to the holy grail of manufacturing. Until recently, the path forward has been blocked by insufficient compute power, storage, and machine learning technologies to allow companies to harness the richness of the data they generate. Today, all of this is changing. Thanks to the rise of the Industrial Internet of Things, dramatic advances in computing systems, and the rapid maturation of machine learning algorithms, manufacturers now have the ability to collect, store, and analyze huge amounts of data in real time to turn it into actionable information. They can use this information to enhance operations, remedy equipment issues proactively, improve plant availability, and meet countless other goals that drive toward better margins for the business.

The latest robot attempting to find the 600 tons of nuclear fuel and debris that melted down six years ago in the wrecked Fukushima No. 1 nuclear power plant met its end in less than a day.