Google and Amazon Web Services (AWS) have highlighted their respective work on machine-learning (ML) models that may help nations deal with environmental crises happening with increasing regularity across the world.

The companies flagged up their efforts to tackle climate change effects such as floods and wildfires as the UN Climate Change Conference UK 2021 (COP26) wraps up this week.

Google has published a non-peer-reviewed paper about its flood forecasting system with machine-learning models that it claims provide "accurate real-time flood warnings to agencies and the public, with a focus on riverine floods in large, gauged rivers". The paper was written by researchers at Google Research and the Hebrew University of Jerusalem in Israel.

SEE: Report finds startling disinterest in ethical, responsible use of AI among business leaders

Google's flood-forecasting initiative, launched in 2018, sends alerts to smartphones of people in flood-affected areas. It's part of Google's Crisis Response program, which works with front-line and emergency workers to develop technology.

Since 2018, the program has expanded to cover much of India and Bangladesh, encompassing an area populated by some 220 million people. As of the 2021 monsoon season, this has further expanded to cover an area where 360 million people live.

"Thanks to better flood prediction technology, we sent out over 115 million alerts -- that's about triple the amount we previously sent out," says Yossi Matias, Google's VP engineering and crisis response lead,in a blogpost.

Google's alerts don't just indicate how many centimetres a river will rise. Thanks to its new machine-learning models that use Long Short-Term Memory (LTSM) deep neural networks, it can now provide "inundation maps" that show the extent and depth of flooding as a layer on Google Maps.

The researchers contend that "LSTM models performed better than conceptual models that were calibrated to long data records in every basin".

"While previous studies provided encouraging results, it is rare to find actual operational systems with ML models as their core components that are capable of computing timely and accurate flood warnings," Google's researchers said.

AWS, meanwhile, has been working with AusNet, an energy company based in Melbourne, Australia, to help mitigate bushfires in the region.

AusNet has 54,000 kilometres of power lines that distribute energy to about 1.5 million homes and businesses in Victoria. It's estimated that 62% of the network is in high bushfire risk areas.

AusNet has been using cars equipped with Google Maps-style LiDAR cameras and Amazon SageMaker machine learning to map out the state's vegetation areas that need to be trimmed to stem bushfire threats. Its previous system relied on a GIS (Geographic Information System) and used custom tools to label LiDAR points.

AusNet worked with AWS to automate the classification of LiDAR points by using AWS's managed deep-learning models, GPU instances and S3 storage.

AusNet and AWS built a semantic segmentation model that accurately classified 3D point cloud data for conductors, buildings, poles, vegetation, and other categories, AWS notes in a blogpost.

SEE:What is digital transformation? Everything you need to know about how technology is reshaping business

"The team was able to train a model at a rate of 10.8 minutes per epoch on 17.2 GiB of uncompressed data across 1,571 files totaling approximately 616 million points. For inference, the team was able to process 33.6 GiB of uncompressed data across 15 files totaling 1.2 billion points in 22.1 hours. This translates to inferencing an average of 15,760 points per second including amortized startup time," AWS states.

"Being able to quickly and accurately label our aerial survey data is a critical part of minimizing the risk of bushfires," says Daniel Pendlebury, a product manager at AusNet.

"Working with the Amazon Machine Learning Solutions Lab, we were able to create a model that achieved 80.53% mean accuracy in data labeling. We expect to be able to reduce our manual labeling efforts by up to 80% with the new solution."

The rest is here:
Google and AWS harness the power of machine learning to predict floods and fires - ZDNet

This article was originally published here

J Clin Monit Comput. 2021 Nov 13. doi: 10.1007/s10877-021-00778-x. Online ahead of print.

ABSTRACT

The Hypotension Prediction Index (HPI) is a commercially available machine-learning algorithm that provides warnings for impending hypotension, based on real-time arterial waveform analysis. The HPI was developed with arterial waveform data of surgical and intensive care unit (ICU) patients, but has never been externally validated in the latter group. In this study, we evaluated diagnostic ability of the HPI with invasively collected arterial blood pressure data in 41 patients with COVID-19 admitted to the ICU for mechanical ventilation. Predictive ability was evaluated at HPI thresholds from 0 to 100, at incremental intervals of 5. After exceeding the studied threshold, the next 20 min were screened for positive (mean arterial pressure (MAP) < 65 mmHg for at least 1 min) or negative (absence of MAP < 65 mmHg for at least 1 min) events. Subsequently, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and time to event were determined for every threshold. Almost all patients (93%) experienced at least one hypotensive event. Median number of events was 21 [7-54] and time spent in hypotension was 114 min [20-303]. The optimal threshold was 90, with a sensitivity of 0.91 (95% confidence interval 0.81-0.98), specificity of 0.87 (0.81-0.92), PPV of 0.69 (0.61-0.77), NPV of 0.99 (0.97-1.00), and median time to event of 3.93 min (3.72-4.15). Discrimination ability of the HPI was excellent, with an area under the curve of 0.95 (0.93-0.97). This validation study shows that the HPI correctly predicts hypotension in mechanically ventilated COVID-19 patients in the ICU, and provides a basis for future studies to assess whether hypotension can be reduced in ICU patients using this algorithm.

PMID:34775533 | DOI:10.1007/s10877-021-00778-x

Follow this link:
Performance of a machine-learning algorithm to predict hypotension in mechanically ventilated patients with COVID-19 admitted to the intensive care...

Global Machine Learning in Healthcare Market Analytical reportis intended to function as a supportive means to assess the Machine Learning in Healthcare market along with the complete analysis and clear-cut statistics related to this market. The Machine Learning in Healthcare market report has analyzed the market using various marketing tools such asPorters Five Forces Analysis, player positioning analysis, SWOT analysis, market share analysis, and value chain analysis. In Porters Five Forces analysis, the market dynamics and factors such as the threat of substitute for Machine Learning in Healthcare, threat of new entrants in the Machine Learning in Healthcare market, bargaining power of buyers, bargaining power of suppliers to Machine Learning in Healthcare providing companies, and internal rivalry among the Machine Learning in Healthcare providers are analyzed to provide the readers of the report with a detailed view of the market current dynamics. In other words, the report would provide an up-to-date study of the market in terms of its latest trends, present scenario, and the overall market situation.

Further, it will also help the clients in decision-making by presenting knowledgeable data about the global Machine Learning in Healthcare market to them. In addition, the report will take account of the top players [Oracle, Intel Corporation, IBM Corporation, Amazon Web Services Inc., Philips, CareSkore, Google Inc., Siemens Healthcare, Hewlett Packard Enterprise Development, Zephyr Health, Sap, Microsoft Corporation, Dell] of the Machine Learning in Healthcare market. In this section, the report will provide insights such as product pictures & specifications, market share, contact details, sales, and company profiles.The report includes the precise forecasts and calculations for the growth of each segment and sub-segment of the global Machine Learning in Healthcare market. This scrutiny can assist the clients to grow their business by steering at competent niche markets.

Get Free PDF Sample Copy of the Report (Including Covid-19 Impact Analysis)

Note In order to provide a more accurate market forecast, all our reports will be updated before delivery by considering the impact of COVID-19.

(*If you have any special requirements, please let us know and we will offer you the report as you want.)

By types and Application the Machine Learning in Healthcare Business Competition Split as:

By Types:Cloud, On-premises

By Applications:Disease Identification and Diagnosis, Image Analytics, Drug Discovery/Manufacturing, Personalized Treatment, Others (clinical trial research and epidemic outbreak prediction)

Impact of COVID-19:Last but not the least, we all are aware of the ongoing coronavirus pandemic and it still carries on impacting the expansion of numerous markets across the world. However, the direct effect of the pandemic varies based on market demand. Though some markets might observe a decrease in demand, several others will carry on to stay unscathed and present potential expansion opportunities.

Thus, our Machine Learning in Healthcare market report will be presenting a detailed study of the market along with theimpact of COVID-19on the global Machine Learning in Healthcare market.

The Machine Learning in Healthcare market report will be fragmented into the different section to make it more comprehensible. After the initial brief synopsis of the Machine Learning in Healthcare market, the report will present the assessed market dynamics for the forecast period (2021-2027). Further, the report will depict the key factors driving or restraining the expansion of the Machine Learning in Healthcare market. In addition, it also entails the most significant trends that are capable of shaping the growth of the global Machine Learning in Healthcare market during the projected period. Furthermore, it states the opportunities and risks that market players or companies need to mull over while taking any business-related long-term decisions. The report also broadly presents the previous and prevailing market development trends like partnerships, mergers & acquisitions, collaborations, and so on.

Key highlights of the Machine Learning in Healthcare market report:

In the succeeding section, the report aims to describe the global Machine Learning in Healthcare market size (in terms of value and volume) and also assess its distinct segments by Types [Cloud, On-premises] and by Application [Disease Identification and Diagnosis, Image Analytics, Drug Discovery/Manufacturing, Personalized Treatment, Others (clinical trial research and epidemic outbreak prediction)] along with their sub-segments. The report also segregates the global market based on region and its overview in the past years and estimates for the forecast period. In addition, it also entails the quantitative as well as qualitative aspects of the Machine Learning in Healthcare market in relation to each region and country encompassed within the assessment.

Regions Covered in the Global Machine Learning in Healthcare Market:

The report gives answers to the following:

Browse Detailed Report with TOC, Visit Here:https://www.marketresearchstore.com/market-insights/machine-learning-in-healthcare-market-805871

Read our other Exclusive Reports Here:-

Global Bread Improver Market

Global Smooth Hinge Caps Market

Global Polyimide Foam Market

Contact Us:

Market Research Store

244 Fifth Avenue, Suite N202

New York, 10001, United States

Tel: +1 (844) 845-5245

USA/Canada Toll Free No.+1 (855) 465-4651

Mail Us:[emailprotected](Dont Hesitate to contact us)

Read the original:
Global Machine Learning in Healthcare Market Potential growth, attractive valuation make it is a long-term investment 2027 Energy Siren - Energy...

Regular newsletter readers know that I am beyond excited about machine learning (ML) at the edge. Running algorithms on gateways or even on sensors instead of sending data to the cloud to be analyzed can save time, bandwidth costs, and energy, and can protect peoples privacy.

So far, ML at the edge has only involved inference, the process of running incoming data against an existing model to see if it matches. Training the algorithm still takes place in the cloud. But Qualcomm has been researching ways to make the training of ML algorithms at the edge less energy-intensive, which means it could happen at the edge.

Bringing ML to edge devices means user data stays on the device, which boosts privacy; italso reduces the energy and costs associated with moving data around. It can also lead to highly personalized services. These are all good things. So what has Qualcomm discovered?

In an interview with me, Qualcomms Joseph Soriaga, senior director of technology, broke down the companys research into four different categories. But first, lets talk about what it takes to train an ML model.

Training usually happens in the cloud because it requires a computer to analyze a lot of data and hold much of that data in memory while performing probabilities to assess if the data matches whatever goal the algorithm is trying to meet.So to train a model to identify cats, you have to give it a lot of pictures of cats; the computer then tries to figure out what makes a cat. As it refines its understanding, it will produce calculations that a data scientist can assess and refine further by weighting different elements of the assessment more heavily in favor of elements that make something look like a cat.

It requires a lot of computational heft, memory, and bandwidth to build a good model. The edge doesnt historically have a lot of computing power or memory available, which is why edge devices perform inference and dont learn while in operation. Soriaga and his team have come up with methods that can enable personalization and adaptation of existing models at the edge, which is a step in the right direction.

One method is called few-shot learning, which is designed for situations where a researcher wants to tweak an algorithm to better meet the needs of outliers. Soriaga offered up an example involving wake word detection. For customers who have an accent or a hard time saying a wake word, using this method to improve accuracy can boost detection rates by 30%. Because there is a limited and clear data set, and labels, its possible to train existing models without consuming much power or computing resources.

Another method for training at the edge is continuous learning with unlabeled data. Here, an existing model gets updated with new data coming into the edge device over time. But because the data is unlabeled and the edge data may be over-personalized a data scientist has to be aware of those limits when trying to adapt the model.

My favorite research topic is federated device learning, where you might use the prior two methods to tweak algorithms locally and then send the tweaked models back to the cloud or share them with other edge devices. Qualcomm, for example, has explored how to identify people based on biometrics. Recognizing someone based on their face, fingerprint, or voice could involve sending all of those data points to the cloud, but it would be far more secure to have an algorithm that can be trained locally for each user.

So the trained algorithm built in the cloud might recognize how to differentiate a face, but locally, it would have to match with an individual face. That individual face data would stay private but the features that make it a face would get sent back to help adjust the initial algorithm. Then that tweaked version of the algorithm would get sent back to the edge devices where some noise would get added to the face data to ensure privacy, but also to ensure that over time the cloud-based algorithm gets better without sharing that persons data.

This approach provides large sets of face or voice data without having to scrape it from social media or photo sites without permission. Federating the learning over many devices also means data scientists can get a lot of inputs but that the raw data doesnt ever leave the device.

Finally, we also need ways to reduce the computational complexity associated with building algorithms from scratch. Im not going to get too into depth here, because theres a lot of math, butheres where you can find more information. Broadly speaking, the solution to traditional training in the cloud is to make training on less compute-heavy devices easier.

Qualcomm researchers have decided that one way to do that is to avoid using backpropagationto figure out how to weigh certain elements when building a model. Instead, data scientists can use quantized training to reduce the complexity associated with backpropagationand use more efficient models. Qualcomms researchers came up with something called in-hindsight range estimation, to efficiently adapt models for edge devices. If you are keen on understanding this, then click through to the research paper. But the money statement is that using this method was as accurate as traditional training methods and resulted in a 79% reduction in memory transfer. That reduction computes to needing less memory and compute power.

This research is very exciting because training at the edge has long been the dream, but a dream that has been so hard to turn into reality. As regulations promote more privacy and security for the IoT, all while demanding reduced energy consumption, edge-based training is moving from a wish-we-had-it option to a need-to-have it option. Im hoping R&D keeps up.

Related

Read the rest here:
Qualcomm is researching machine learning at the edge - Stacey on IoT

Now that you've got mid-level tech skills, it's time to direct them into one of the tech industry's most in-demand fields.

Image: Chinnawat Ngamsom, Getty Images/iStockphoto

If your tech skills have reached the intermediate level and you're ready to turbocharge your career, then check out the Pay What You Want: The Comprehensive Machine Learning Bundle and learn the latest commercial machine learning methods.

The bundle consists of six books and four courses, and you get to choose what you want to pay. Here's the way it works.

Four of the books focus on Python. "Machine Learning for the Web" explores how to use Python to make better predictions, while "Python Machine Learning" will teach you how to generate the most useful data insights by using Python to build extremely powerful machine learning algorithms.

In "Advanced Machine Learning with Python" you can learn how to master Python's latest machine learning techniques and use them to solve problems in data science. Then you can find out how to quickly build potent machine learning models and implement predictive applications on a large scale in "Large Scale Machine Learning with Python."

In the two remaining books, you can learn how to use test-driven development to control machine learning algorithms in "Test Driven Machine Learning" and how to use Apache Spark to create a range of machine learning projects in "Apache Spark Machine Learning Blueprints."

The "Step-by-Step Machine Learning with Python" course covers the most effective tools and techniques for machine learning. And you'll find out how to perform real-world machine learning tasks in the "Python Machine Learning Solutions" course. The "Machine Learning with Open CV and Python" class can teach you how to use Python to analyze and understand data.

The final course is "Machine Learning with TensorFlow." It explains how to use Google's TensorFlow library to solve machine learning issues.

These books and courses are offered by Packt Publishing, which has created more than 3,000 books and videos full of actionable information for IT professionals, from optimizing skills in existing tools to emerging technology. Thousands of these bundles have already been sold.

Don't miss this chance to get a great machine learning bargain. Get the Pay What You Want: The Comprehensive Machine Learning Bundle today(normally $843.92).

Prices subject to change.

Read the original here:
Turn your tech skills into machine learning expertise with this book and class bundle - TechRepublic