Archive for the ‘Machine Learning’ Category

The roles of machine learning methods in limiting the spread of deadly diseases: A systematic review – DocWire News

This article was originally published here

Heliyon. 2021 Jun;7(6):e07371. doi: 10.1016/j.heliyon.2021.e07371. Epub 2021 Jun 23.

ABSTRACT

Machine learning (ML) methods can be leveraged to prevent the spread of deadly infectious disease outbreak (e.g., COVID-19). This can be done by applying machine learning methods in predicting and detecting the deadly infectious disease. Most reviews did not discuss about the machine learning algorithms, datasets and performance measurements used for various applications in predicting and detecting the deadly infectious disease. In contrast, this paper outlines the literature review based on two major ways (e.g., prediction, detection) to limit the spread of deadly disease outbreaks. Hence, this study aims to investigate the state of the art, challenges and future works of leveraging ML methods to detect and predict deadly disease outbreaks according to two categories mentioned earlier. Specifically, this study provides a review on various approaches (e.g., individual and ensemble models), types of datasets, parameters or variables and performance measures used in the previous works. The literature review included all articles from journals and conference proceedings published from 2010 through 2020 in Scopus indexed databases using the search terms Predicting Disease Outbreaks and/or Detecting Disease using Machine Learning. The findings from this review focus on commonly used machine learning approaches, challenges and future works to limit the spread of deadly disease outbreaks through preventions and detections.

PMID:34179541 | PMC:PMC8219638 | DOI:10.1016/j.heliyon.2021.e07371

Continue reading here:
The roles of machine learning methods in limiting the spread of deadly diseases: A systematic review - DocWire News

Environmental Impact of Oil and Gas Drilling Explored With Novel Machine Learning Method – Technology Networks

Crude oil production and natural gas withdrawals in the United States have lessened the country's dependence on foreign oil and provided financial relief to U.S. consumers, but have also raised longstanding concerns about environmental damage, such as groundwater contamination.

A researcher in Syracuse University's College of Arts and Sciences, and a team of scientists from Penn State, have developed a new machine learning technique to holistically assess water quality data in order to detect groundwater samples likely impacted by recent methane leakage during oil and gas production. Using that model, the team concluded that unconventional drilling methods like hydraulic fracturing - or hydrofracking - do not necessarily incur more environmental problems than conventional oil and gas drilling.

The two common ways to extract oil and gas in the U.S. are through conventional and unconventional methods. Conventional oil and gas are pumped from easily accessed sources using natural pressure. Conversely, unconventional oil and gas are acquired from hard-to-reach sources through a combination of horizontal drilling and hydraulic fracturing. Hydrofracking extracts natural gas, petroleum and brine from bedrock formations by injecting a mixture of sand, chemicals and water. By drilling into the earth and directing the high-pressure mixture into rock, the gas inside releases and flows out to the head of a well.

Tao Wen, assistant professor of earth and environmental sciences (EES) at Syracuse, recently led a study comparing data from different states to see which method might result in greater contamination of groundwater. They specifically tested levels of methane, which is the primary component of natural gas.

The team selected four U.S. states located in important shale zones to target for their study: Pennsylvania, Colorado, Texas and New York. One of those states - New York - banned the practice of hydrofracking in 2015 following a review by the NYS Department of Health which found significant uncertainties about health, including increased water and air pollution.

Wen and his colleagues compiled a large groundwater chemistry dataset from multiple sources including federal agency reports, journal articles, and oil and gas companies. The majority of tested water samples in their study were collected from domestic water wells. Although methane itself is not toxic, Wen says that methane contamination detected in shallow groundwater could be a risk to the relevant homeowner as it could be an explosion hazard, could increase the level of other toxic chemical species like manganese and arsenic, and would contribute to global warming as methane is a greenhouse gas.

Their model used sophisticated algorithms to analyze almost all of the retained geochemistry data in order to predict if a given groundwater sample was negatively impacted by recent oil and gas drilling.

The data comparison showed that methane contamination cases in New York - a state without unconventional drilling but with a high volume of conventional drilling - were similar to that of Pennsylvania - a state with a high volume of unconventional drilling. Wen says this suggests that unconventional drilling methods like fracking do not necessarily lead to more environmental problems than conventional drilling, although this result might be alternatively explained by the different sizes of groundwater chemistry datasets compiled for these two states.

The model also detected a higher rate of methane contamination cases in Pennsylvania than in Colorado and Texas. Wen says this difference could be attributed to different practices when drillers build/drill the oil and gas wells in different states. According to previous research, most of the methane released into the environment from gas wells in the U.S. occurs because the cement that seals the well is not completed along the full lengths of the production casing. However, no data exists to conclude if drillers in those three states use different technology. Wen says this requires further study and review of the drilling data if they become available.

According to Wen, their machine learning model proved to be effective in detecting groundwater contamination, and by applying it to other states/counties with ongoing or planned oil and gas production it will be an important resource for determining the safest methods of gas and oil drilling.

Reference:Wen T, Liu M, Woda J, Zheng G, Brantley SL. Detecting anomalous methane in groundwater within hydrocarbon production areas across the United States.Water Res. 2021;200:117236. doi:10.1016/j.watres.2021.117236

This article has been republished from the following materials. Note: material may have been edited for length and content. For further information, please contact the cited source.

Read the original post:
Environmental Impact of Oil and Gas Drilling Explored With Novel Machine Learning Method - Technology Networks

British AI solution for breast cancer screening arrives in the UAE – Mobihealth News

A UK-based applied science company, focused on supporting cancer diagnostics with machine learning, is bringing its award-winning solution to the United Arab Emirates (UAE).

Kheiron Medical Technologies has partnered with the UAEs Atlas Medical to launch Mia, its breast cancer screening solution that supports radiologists in reducing errors in cancer detection, in the region.

Launched in 2019, Mia which stands for mammography intelligent assessment uses artificial intelligence (AI) to work as a second reader in workflow. Should the radiologist (first human reader) and Mia disagree on a result, then a second radiologist is brought in for a third opinion.

Our mission at Kheiron is to support breast screening professionals in the fight against breast cancer with proven and effective AI-enabled tools, said Alex Hamlow, Kheirons Chief Commercial Officer. Were excited that Mia is the first AI independent reader solution available for use within the breast screening community in the UAE. Based on its performance in the UK and Europe, Mia represents a major breakthrough in helping radiologists dramatically improve breast cancer detection and patient outcomes.

He continued: According to the WHOs International Agency for Research on Cancer, breast cancer was the most prevalent of all cancers detected in the UAE in 2020, accounting for 38.8% of all new cancer cases detected in women. Im excited that Mia can help both radiologists and the women they care for.

WHY IT MATTERS

There are several advantages to using AI technology in cancer screening, says the company.

Using AI technology for the second screening frees up clinicians to spend time with patients, reduces the pressure to find more radiologists, and has the potential to screen greater numbers of women more quickly.

It also prevents unnecessary biopsies.

According to a statement by Kheiron, Mia has learnt to read mammograms to the same level of detail as a consulting radiologist.

ON THE RECORD

I am delighted that Kheiron Medical Technologies is bringing their breakthrough AI platform for breast screening, Mia, to the Gulf region, and that the UKs Department for International Trade played a role in making this happen, said Simon Penney, Her Majestys Trade Commissioner for the Middle East. Kheirons technology brings pioneering AI to the frontline, freeing up clinicians time and helping to save lives.

V. Kalyanasundaram, General Manager for Atlas Medical in Dubai and the Northern Emirates, added: We are looking forward to bringing the Mia solution to the breast screening community throughout the UAE. It has tremendous potential to transform breast screening for radiologists and for women.

By improving radiologist productivity and empowering breast screening professionals to detect potential malignancies more accurately and quickly, Mia ultimately will help save more lives in the fight against breast cancer.

In addition to the UAE, Mia is reportedly set to launch soon in Qatar and Oman, pending local requirements.

More:
British AI solution for breast cancer screening arrives in the UAE - Mobihealth News

New Open Source Project Uses Machine Learning to Inform …

Linux Foundation with support from IBM and Call for Code hosts Intelligent Supervision Assistant for Construction project from Build Change to help builders identify structural issues in masonry walls or concrete columns, especially in areas affected by disasters

SAN FRANCISCO, June 10, 2021 The Linux Foundation, the nonprofit organization enabling mass innovation through open source, today announced it will host the Intelligent Supervision Assistant for Construction (ISAC-SIMO) project, which was created by Build Change with a grant from IBM as part of the Call for Code initiative. The Autodesk Foundation, a Build Change funder, also contributed pro-bono expertise to advise the projects development.

Build Change helps save lives in earthquakes and windstorms. Its mission is to prevent housing loss caused by disasters by transforming the systems that regulate, finance, build and improve houses around the world.

ISAC-SIMO packages important construction quality assurance checks into a convenient mobile app. The tool harnesses the power of machine learning and image processing to provide feedback on specific construction elements such as masonry walls and reinforced concrete columns. Users can choose a building element check and upload a photo from the site to receive a quick assessment.

ISAC-SIMO has amazing potential to radically improve construction quality and ensure that homes are built or strengthened to a resilient standard, especially in areas affected by earthquakes, windstorms, and climate change, said Dr. Elizabeth Hausler, Founder & CEO of Build Change. Weve created a foundation from which the open source community can develop and contribute different models to enable this tool to reach its full potential. The Linux Foundation, building on the support of IBM over these past three years, will help us build this community.

ISAC-SIMO was imagined as a solution to gaps in technical knowledge that were apparent in the field. The app ensures that workmanship issues can be more easily identified by anyone with a phone, instead of solely relying on technical staff. It does this by comparing user-uploaded images against trained models to assess whether the work done is broadly acceptable (go) or not (no go) along with a specific score. The project is itself built on open source software, including Python through Django, Jupyter Notebooks, and React Native.

Due to the pandemic, the project deliverables and target audience have evolved. Rather than sharing information and workflows between separate users within the app, the app has pivoted to provide tools for each user to perform their own checks based on their role and location. This has led to a general framework that is well-suited for plugging in models from the open source community, beyond Build Changes original use case, said Daniel Krook, IBM Chief Technology Officer for the Call for Code Global Initiative.

IBM and The Linux Foundation have a rich history of deploying projects that fundamentally make change and progress in society through innovation and remain committed during COVID-19. The winner of the 2018 Call for Code Global Challenge, Project OWL, contributed its IoT device firmware in March 2020 as the ClusterDuck Protocol, and since then, twelve more Call for Code deployment projects like ISAC-SIMO that address disasters, climate change, and racial justice, have been open sourced for communities that need them most.

The project encourages new users to contribute and to deploy the software in new environments around the world. Priorities for short term updates include improvements in user interface, contributions to the image dataset for different construction elements, and support to automatically detect if the perspective of an image is flawed. For more information, please visit: https://www.isac-simo.net/docs/contribute/.

For more information on IBMs role in this work, please visit: https://developer.ibm.com/callforcode/blogs/call-for-code-app-uses-ai-to-make-homes-safer-and-more-resilient/.

About The Linux Foundation

Founded in 2000, The Linux Foundation is supported by more than 1,000 members and is the worlds leading home for collaboration on open source software, open standards, open data, and open hardware. The Linux Foundations projects are critical to the worlds infrastructure including Linux, Kubernetes, Node.js, and more. The Linux Foundations methodology focuses on leveraging best practices and addressing the needs of contributors, users and solution providers to create sustainable models for open collaboration. For more information, please visit us at linuxfoundation.org.

###

The Linux Foundation has registered trademarks and uses trademarks. For a list of trademarks of The Linux Foundation, please see our trademark usage page: https://www.linuxfoundation.org/trademark-usage. Linux is a registered trademark of Linus Torvalds.

Media Contact

Jennifer Cloerfor the Linux Foundation503-867-2304jennifer@storychangesculture.com

More here:
New Open Source Project Uses Machine Learning to Inform ...

Using large-scale experiments and machine learning to discover theories of human decision-making – Science Magazine

Discovering better theories

Theories of human decision-making have proliferated in recent years. However, these theories are often difficult to distinguish from each other and offer limited improvement in accounting for patterns in decision-making over earlier theories. Peterson et al. leverage machine learning to evaluate classical decision theories, increase their predictive power, and generate new theories of decision-making (see the Perspective by Bhatia and He). This method has implications for theory generation in other domains.

Science, abe2629, this issue p. 1209; see also abi7668, p. 1150

Predicting and understanding how people make decisions has been a long-standing goal in many fields, with quantitative models of human decision-making informing research in both the social sciences and engineering. We show how progress toward this goal can be accelerated by using large datasets to power machine-learning algorithms that are constrained to produce interpretable psychological theories. Conducting the largest experiment on risky choice to date and analyzing the results using gradient-based optimization of differentiable decision theories implemented through artificial neural networks, we were able to recapitulate historical discoveries, establish that there is room to improve on existing theories, and discover a new, more accurate model of human decision-making in a form that preserves the insights from centuries of research.

Original post:
Using large-scale experiments and machine learning to discover theories of human decision-making - Science Magazine