Connect with us

AI

Build a cognitive search and a health knowledge graph using AWS AI services

Published

on

Medical data is highly contextual and heavily multi-modal, in which each data silo is treated separately. To bridge different data, a knowledge graph-based approach integrates data across domains and helps represent the complex representation of scientific knowledge more naturally. For example, three components of major electronic health records (EHR) are diagnosis codes, primary notes, and specific medications. Because these are represented in different data silos, secondary use of these documents for accurately identifying patients with a specific observable trait is a crucial challenge. By connecting those different sources, subject matter experts have a richer pool of data to understand how different concepts such as diseases and symptoms interact with one another and help conduct their research. This ultimately helps healthcare and life sciences researchers and practitioners create better insights from the data for a variety of use cases, such as drug discovery and personalized treatments.

In this post, we use Amazon HealthLake to export EHR data in the Fast Healthcare Interoperability Resources (FHIR) data format. We then build a knowledge graph based on key entities extracted and harmonized from the medical data. Amazon HealthLake also extracts and transforms unstructured medical data, such as medical notes, so it can be searched and analyzed. Together with Amazon Kendra and Amazon Neptune, we allow domain experts to ask a natural language question, surface the results and relevant documents, and show connected key entities such as treatments, inferred ICD-10 codes, medications, and more across records and documents. This allows for easy analysis of co-occurrence of key entities, co-morbidities analysis, and patient cohort analysis in an integrated solution. Combining effective search capabilities and data mining through graph networks reduces time and cost for users to find relevant information around patients and improve knowledge serviceability surrounding EHRs. The code base for this post is available on the GitHub repo.

Solution overview

In this post, we use the output from Amazon HealthLake for two purposes.

First, we index EHRs into Amazon Kendra for semantic and accurate document ranking out of patient notes, which help improve physician efficiency identifying patient notes and compare it with other patients sharing similar characteristics. This shifts from using a lexical search to a semantic search that introduces context around the query, which results in better search output (see the following screenshot).

Second, we use Neptune to build knowledge graph applications for users to view metadata associated with patient notes in a more simple and normalized view, which allows us to highlight the important characteristics stemming from a document (see the following screenshot).

The following diagram illustrates our architecture.

The steps to implement the solution are as follows:

  1. Create and export Amazon HealthLake data.
  2. Extract patient visit notes and metadata.
  3. Load patient notes data into Amazon Kendra.
  4. Load the data into Neptune.
  5. Set up the backend and front end to run the web app.

Create and export Amazon HealthLake data

As a first step, create a data store using Amazon HealthLake either via the Amazon HealthLake console or the AWS Command Line Interface (AWS CLI). For this post, we focus on the AWS CLI approach.

  1. We use AWS Cloud9 to create a data store with the following code, replacing <<your data store name >> with a unique name:
aws healthlake create-fhir-datastore --region us-east-1 --datastore-type-version R4 --preload-data-config PreloadDataType="SYNTHEA" --datastore-name "<<your_data_store_name>>"

The preceding code uses a preloaded dataset from Synthea, which is supported in FHIR version R4, to explore how to use Amazon HealthLake output. Running the code produces a response similar to the following code, and this step takes a few minutes to complete (approximately 30 minutes at the time of writing):

{ "DatastoreEndpoint": "https://healthlake.us-east-1.amazonaws.com/datastore/<<your_data_store_id>>/r4/", "DatastoreArn": "arn:aws:healthlake:us-east-1:<<your_AWS_account_number>>:datastore/fhir/<<your_data_store_id>>", "DatastoreStatus": "CREATING", "DatastoreId": "<<your_data_store_id>>"
}

You can check the status of completion either on the Amazon HealthLake console or in the AWS Cloud9 environment.

  1. To check the status in AWS Cloud9, use the following code to check the status and wait until DatastoreStatus changes from CREATING to ACTIVE:
aws healthlake describe-fhir-datastore --datastore-id "<<your_data_store_id>>" --region us-east-1

  1. When the status changes to ACTIVE, get the role ARN from the HEALTHLAKE-KNOWLEDGE-ANALYZER-IAMROLE stack in AWS CloudFormation, associated with the physical ID AmazonHealthLake-Export-us-east-1-HealthDataAccessRole, and copy the ARN in the linked page.
  2. In AWS Cloud9, use the following code to export the data from Amazon HealthLake to the Amazon Simple Storage Service (Amazon S3) bucket generated from AWS Cloud Development Kit (AWS CDK) and note the job-id output:
aws healthlake start-fhir-export-job --output-data-config S3Uri="s3://hl-synthea-export-<<your_AWS_account_number>>/export-$(date +"%d-%m-%y")" --datastore-id <<your_data_store_id>> --data-access-role-arn arn:aws:iam::<<your_AWS_account_number>>:role/AmazonHealthLake-Export-us-east-1-HealthKnoMaDataAccessRole

  1. Verify that the export job is complete using the following code with the job-id obtained from the last code you ran. (when the export is complete, JobStatus in the output states COMPLETED):
aws healthlake describe-fhir-export-job --datastore-id <<your_data_store_id>> --job-id <<your_job_id>>

Extract patient visit notes and metadata

The next step involves decoding patient visits to obtain the raw texts. We will import the following file DocumentReference-0.ndjson (shown in the following screenshot of S3) from the Amazon HealthLake export step we previously completed into the CDK deployed Amazon SageMaker notebook instance. First, save the notebook provided from the Github repo into the SageMaker instance. Then, run the notebook to automatically locate and import the DocumentReference-0.ndjson files from S3.

For this step, use the resourced SageMaker to quickly run the notebook. The first part of the notebook creates a text file that contains notes from each patient’s visit and is saved to an Amazon S3 location. Because multiple visits could exist for a single patient, a unique identification combines the patient unique ID and the visit ID. These patients’ notes are used to perform semantic search against using Amazon Kendra.

The next step in the notebook involves creating triples based on the automatically extracted metadata. By creating and saving the metadata in an Amazon S3 location, an AWS Lambda function gets triggered to generate the triples surrounding the patient visit notes.

Load patient notes data into Amazon Kendra

The text files that are uploaded in the source path of the S3 bucket need to be crawled and indexed. For this post, a developer edition is created during the AWS CDK deployment, so the index is created to connect the raw patient notes.

  1. On the AWS CloudFormation console under the HEALTHLAKE-KNOWLEDGE-ANALYZER-CORE stack, search for kendra on the Resources tab and take note of the index ID and data source ID (copy the first part of the physical ID before the pipe ( | )).

  1. Back in AWS Cloud9, run the following command to synchronize the patient notes in Amazon S3 to Amazon Kendra:
aws kendra start-data-source-sync-job --id <<data_source_id_2nd_circle>> --index-id <<index_id_1st_ circle>>

  1. You can verify when the sync status is complete by running the following command:
aws kendra describe-data-source --id <<data_source_id_2nd_circle>> --index-id <<index_id_1st_circle>>

Because the ingested data is very small, it should immediately show that Status is ACTIVE upon running the preceding command.

Load the data into Neptune

In this next step, we access the Amazon Elastic Compute Cloud (Amazon EC2) instance that was spun up and load the triples from Amazon S3 into Neptune using the following code:

curl -X POST -H 'Content-Type: application/json' https://healthlake-knowledge-analyzer-vpc-and-neptune-neptunedbcluster.cluster-<<your_unique_id>>.us-east-1.neptune.amazonaws.com:8182/loader -d '
{ "source": "s3://<<your_Amazon_S3_bucket>>/stdized-data/neptune_triples/nquads/", "format": "nquads", "iamRoleArn": "arn:aws:iam::<<your_AWS_account_number>>:role/KNOWLEDGE-ANALYZER-IAMROLE-ServiceRole", "region": "us-east-1", "failOnError": "TRUE"
}'

Set up the backend and front end to run the web app

The preceding step should take a few seconds to complete. In the meantime, configure the EC2 instance to access the web app. Make sure to have both Python and Node installed in the instance.

  1. Run the following code in the terminal of the instance:
sudo iptables -t nat -I PREROUTING -p tcp --dport 80 -j REDIRECT --to-ports 3000

This routes the public address to the deployed app.

  1. Copy the two folders titled ka-webapp and ka-server-webapp and upload them to a folder named dev in the EC2 instance.
  2. For the front end, create a screen by running the following command:
screen -S back 

  1. In this screen, change the folder to ka-webapp and run npm install.
  2. After installation, go into the file .env.development and place the Amazon EC2 public IPv4 address and save the file.
  3. Run npm start and then detach the screen.
  4. For the backend, create another screen by entering:
screen -S back

  1. Change the folder to ka-server-webapp and run pip install -r requirements.txt.
  2. When the libraries are installed, enter the following code:
  1. Detach from the current screen, and using any browser, go the Amazon EC2 Public IPv4 address to access the web app.

Try searching for a patient diagnosis and choose a document link to visualize the knowledge graph of that document.

Next steps

In this post, we integrate data output from Amazon HealthLake into both a search and graph engine to semantically search relevant information and highlight important entities linked to documents. You can further expand this knowledge graph and link it to other ontologies such as MeSH and MedDRA.

Furthermore, this provides a foundation to further integrate other clinical datasets and expand this knowledge graph to build a data fabric. You can make queries on historical population data, chaining structured and language-based searches for cohort selection to correlate disease with patient outcome.

Clean up

To clean up your resources, complete the following steps:

  1. To delete the stacks created, enter the following commands in the order given to properly remove all resources:
$ cdk destroy HEALTHLAKE-KNOWLEDGE-ANALYZER-UPDATE-CORE
$ cdk destroy HEALTHLAKE-KNOWLEDGE-ANALYZER-WEBAPP
$ cdk destroy HEALTHLAKE-KNOWLEDGE-ANALYZER-CORE

  1. While the preceding commands are in progress, delete the Amazon Kendra data source that was created:
$ cdk destroy HEALTHLAKE-KNOWLEDGE-ANALYZER-VPC-AND-NEPTUNE
$ cdk destroy HEALTHLAKE-KNOWLEDGE-ANALYZER-IAMROLE
$ aws healthlake delete-fhir-datastore --datastore-id <<your_data_store_id>> 

  1. To verify it’s been deleted, check the status by running the following command:
$ aws healthlake describe-fhir-datastore --datastore-id "<<your_data_store_id>>" --region us-east-1

  1. Check the AWS CloudFormation console to ensure that all associated stacks starting with HEALTHLAKE-KNOWLEDGE-ANALYZER have all been deleted successfully.

Conclusion

Amazon HealthLake provides a managed service based on the FHIR standard to allow you to build health and clinical solutions. Connecting the output of Amazon HealthLake to Amazon Kendra and Neptune gives you the ability to build a cognitive search and a health knowledge graph to power your intelligent application.

Building on top of this approach can enable researchers and front-line physicians to easily search across clinical notes and research articles by simply typing their question into a web browser. Every clinical evidence is tagged, indexed, and structured using machine learning to provide evidence-based topics on things like transmission, risk factors, therapeutics, and incubation. This particular functionality is tremendously valuable for clinicians or scientists because it allows them to quickly ask a question to validate and advance their clinical decision support or research.

Try this out on your own! Deploy this solution using Amazon HealthLake in your AWS account by deploying the example on GitHub.


About the Authors

Prithiviraj Jothikumar, PhD, is a Data Scientist with AWS Professional Services, where he helps customers build solutions using machine learning. He enjoys watching movies and sports and spending time to meditate.

Phi Nguyen is a solutions architect at AWS helping customers with their cloud journey with a special focus on data lake, analytics, semantics technologies and machine learning. In his spare time, you can find him biking to work, coaching his son’s soccer team or enjoying nature walk with his fami

Parminder Bhatia is a science leader in the AWS Health AI, currently building deep learning algorithms for clinical domain at scale. His expertise is in machine learning and large scale text analysis techniques in low resource settings, especially in biomedical, life sciences and healthcare technologies. He enjoys playing soccer, water sports and traveling with his family.

Garin Kessler is a Senior Data Science Manager at Amazon Web Services, where he leads teams of data scientists and application architects to deliver bespoke machine learning applications for customers. Outside of AWS, he lectures on machine learning and neural language models at Georgetown. When not working, he enjoys listening to (and making) music of questionable quality with friends and family.

Dr. Taha Kass-Hout is Director of Machine Learning and Chief Medical Officer at Amazon Web Services, and leads our Health AI strategy and efforts, including Amazon Comprehend Medical and Amazon HealthLake. Taha is also working with teams at Amazon responsible for developing the science, technology, and scale for COVID-19 lab testing. A physician and bioinformatician, Taha served two terms under President Obama, including the first Chief Health Informatics officer at the FDA. During this time as a public servant, he pioneered the use of emerging technologies and cloud (CDC’s electronic disease surveillance), and established widely accessible global data sharing platforms, the openFDA, that enabled researchers and the public to search and analyze adverse event data, and precisionFDA (part of the Presidential Precision Medicine initiative).

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://aws.amazon.com/blogs/machine-learning/build-a-cognitive-search-and-a-health-knowledge-graph-using-amazon-healthlake-amazon-kendra-and-amazon-neptune/

Artificial Intelligence

Extra Crunch roundup: influencer marketing 101, spotting future unicorns, Apple AirTags teardown

Published

on

With the right message, even a small startup can connect with established and emerging stars on TikTok, Instagram and YouTube who will promote your products and services — as long as your marketing team understands the influencer marketplace.

Creators have a wide variety of brands and revenue channels to choose from, but marketers who understand how to court these influencers can make inroads no matter the size of their budget. Although brand partnerships are still the top source of revenue for creators, many are starting to diversify.

If you’re in charge of marketing at an early-stage startup, this post explains how to connect with an influencer who authentically resonates with your brand and covers the basics of setting up a revenue-share structure that works for everyone.


Full Extra Crunch articles are only available to members
Use discount code ECFriday to save 20% off a one- or two-year subscription


Our upcoming TC Early Stage event is devoted to marketing and fundraising, so expect to see more articles than usual about growth marketing in the near future.

We also ran a post this week with tips for making the first marketing hire, and Managing Editor Eric Eldon spoke to growth leader Susan Su to get her thoughts about building remote marketing teams.

We’re off today to celebrate the Juneteenth holiday in the United States. I hope you have a safe and relaxing weekend.

Walter Thompson
Senior Editor, TechCrunch
@yourprotagonist

As the economy reopens, startups are uniquely positioned to recruit talent

Little Fish in Form of Big Fish meeting a fish.

Image Credits: ballyscanlon (opens in a new window) / Getty Images

The pandemic forced a reckoning about the way we work — and whether we want to keep working in the same way, with the same people, for the same company — and many are looking for something different on the other side.

Art Zeile, the CEO of DHI Group, notes this means it’s a great time for startups to recruit talent.

“While all startups are certainly not focused on being disruptive, they often rely on cutting-edge technology and processes to give their customers something truly new,” Zeile writes. “Many are trying to change the pattern in their particular industry. So, by definition, they generally have a really interesting mission or purpose that may be more appealing to tech professionals.”

Here are four considerations for high-growth company founders building their post-pandemic team.

Refraction AI’s Matthew Johnson-Roberson on finding the middle path to robotic delivery

Matthew Johnson-roberson

Image Credits: Bryce Durbin

“Refraction AI calls itself the Goldilocks of robotic delivery,” Rebecca Bellan writes. “The Ann Arbor-based company … was founded by two University of Michigan professors who think delivery via full-size autonomous vehicles (AV) is not nearly as close as many promise, and sidewalk delivery comes with too many hassles and not enough payoff.

“Their ‘just right’ solution? Find a middle path, or rather, a bike path.”

Rebecca sat down with the company’s CEO to discuss his motivation to make “something that is useful to the general public.”

How to identify unicorn founders when they’re still early-stage

Image Credits: RichVintage (opens in a new window)/ Getty Images

What are investors looking for?

Founders often tie themselves in knots as they try to project qualities they hope investors are seeking. In reality, few entrepreneurs have the acting skills required to convince someone that they’re patient, dedicated or hard working.

Johan Brenner, general partner at Creandum, was an early backer of Klarna, Spotify and several other European startups. Over the last two decades, he’s identified five key traits shared by people who create billion-dollar companies.

“A true unicorn founder doesn’t need to have all of those capabilities on day one,” Brenner, writes “but they should already be thinking big while executing small and demonstrating that they understand how to scale a company.”

Founders Ben Schippers and Evette Ellis are riding the EV sales wave

disrupt mobility roundup

Image Credits: TechCrunch

EV sales are driving demand for services and startups that fulfill the new needs of drivers, charging station operators and others.
Evette Ellis and Ben Schippers took to the main stage at TC Sessions: Mobility 2021 to share how their companies capitalized on the new opportunities presented by the electric transportation revolution.

Scale AI CEO Alex Wang weighs in on software bugs and what will make AV tech good enough

Image Credits: Alexandr Wang

Scale co-founder and CEO Alex Wang joined us at TechCrunch Sessions: Mobility 2021 to discuss his company’s role in the autonomous driving industry and how it’s changed in the five years since its founding.

Scale helps large and small AV players establish reliable “ground truth” through data annotation and management, and along the way, the standards for what that means have shifted as the industry matures.

Even if two algorithms in autonomous driving might be created more or less equal, their real-world performance could vary dramatically based on what they’re consuming in terms of input data. That’s where Scale’s value prop to the industry starts, and Wang explains why.

Edtech investors are flocking to SaaS guidance counselors

Image Credits: Getty Images / Vertigo3d

The prevailing post-pandemic edtech narrative, which predicted higher ed would be DOA as soon as everyone got their vaccine and took off for a gap year, might not be quite true.

Natasha Mascarenhas explores a new crop of edtech SaaS startups that function like guidance counselors, helping students with everything from study-abroad opportunities to swiping right on a captivating college (really!).

“Startups that help students navigate institutional bureaucracy so they can get more value out of their educational experience may become a growing focus for investors as consumer demand for virtual personalized learning increases,” she writes.

Dear Sophie: Is it possible to expand our startup in the US?

lone figure at entrance to maze hedge that has an American flag at the center

Image Credits: Bryce Durbin/TechCrunch

Dear Sophie,

My co-founders and I launched a software startup in Iran a few years ago, and I’m happy to say it’s now thriving. We’d like to expand our company in California.

Now that President Joe Biden has eliminated the Muslim ban, is it possible to do that? Is the pandemic still standing in the way? Do you have any suggestions?

— Talented in Tehran

Companies should utilize real-time compensation data to ensure equal pay

Two women observing data to represent collecting data to ensure pay equity.

Image Credits: Rudzhan Nagiev (opens in a new window) / Getty Images

Chris Jackson, the vice president of client development at CompTrak, writes in a guest column that having a conversation about diversity, equity and inclusion initiatives and “agreeing on the need for equality doesn’t mean it will be achieved on an organizational scale.”

He lays out a data-driven proposal that brings in everyone from directors to HR to the talent acquisition team to get companies closer to actual equity — not just talking about it.

Investors Clara Brenner, Quin Garcia and Rachel Holt on SPACs, micromobility and how COVID-19 shaped VC

tc sessions mobility speaker_investorpanel-1

Image Credits: TechCrunch

Few people are more closely tapped into the innovations in the transportation space than investors.

They’re paying close attention to what startups and tech companies are doing to develop and commercialize autonomous vehicle technology, electrification, micromobility, robotics and so much more.

For TC Sessions: Mobility 2021, we talked to three VCs about everything from the pandemic to the most overlooked opportunities within the transportation space.

Experts from Ford, Toyota and Hyundai outline why automakers are pouring money into robotics

disrupt mobility roundup

Image Credits: TechCrunch

Automakers’ interest in robotics is not a new phenomenon, of course: Robots and automation have long played a role in manufacturing and are both clearly central to their push into AVs.

But recently, many companies are going even deeper into the field, with plans to be involved in the wide spectrum of categories that robotics touch.

At TC Sessions: Mobility 2021, we spoke to a trio of experts at three major automakers about their companies’ unique approaches to robotics.

Apple AirTags UX teardown: The trade-off between privacy and user experience

Image Credits: James D. Morgan/Getty Images

Apple’s location devices — called AirTags — have been out for more than a month now. The initial impressions were good, but as we concluded back in April: “It will be interesting to see these play out once AirTags are out getting lost in the wild.”

That’s exactly what our resident UX analyst, Peter Ramsey, has been doing for the last month — intentionally losing AirTags to test their user experience at the limits.

This Extra Crunch exclusive helps bridge the gap between Apple’s mistakes and how you can make meaningful changes to your product’s UX.

How to launch a successful RPA initiative

3D illustration of robot humanoid reading book in concept of future artificial intelligence and 4th fourth industrial revolution . (3D illustration of robot humanoid reading book in concept of future artificial intelligence and 4th fourth industrial r

Image Credits: NanoStockk (opens in a new window) / Getty Images

Robotic process automation (RPA) is no longer in the early-adopter phase.

Though it requires buy-in from across the organization, contributor Kevin Buckley writes, it’s time to gather everyone around and get to work.

“Automating just basic workflow processes has resulted in such tremendous efficiency improvements and cost savings that businesses are adapting automation at scale and across the enterprise,” he writes.

Long story short: “Adapting business automation for the enterprise should be approached as a business solution that happens to require some technical support.”

Mobility startups can be equitable, accessible and profitable

tc sessions

Image Credits: TechCrunch

Mobility should be a right, but too often it’s a privilege. Can startups provide the technology and the systems necessary to help correct this injustice?

At  our TC Sessions: Mobility 2021 event, we sat down with Revel CEO and co-founder Frank Reig, Remix CEO and co-founder Tiffany Chu, and community organizer, transportation consultant and lawyer Tamika L. Butler to discuss how mobility companies should think about equity, why incorporating it from the get-go will save money in the long run, and how they can partner with cities to expand accessible and sustainable mobility.

CEO Shishir Mehrotra and investor S. Somasegar reveal what sings in Coda’s pitch doc

Image Credits: Carlin Ma / Madrona Venture Group/Brian Smale

Coda CEO Shishir Mehrotra and Madrona partner S. Somasegar joined Extra Crunch Live to go through Coda’s pitch doc (not deck. Doc) and stuck around for the ECL Pitch-off, where founders in the audience come “onstage” to pitch their products to our guests.

Extra Crunch Live takes place every Wednesday at 3 p.m. EDT/noon PDT. Anyone can hang out during the episode (which includes networking with other attendees), but access to past episodes is reserved exclusively for Extra Crunch members. Join here.

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://techcrunch.com/2021/06/18/extra-crunch-roundup-influencer-marketing-101-spotting-future-unicorns-apple-airtags-teardown/

Continue Reading

AI

AI-driven hedge fund rules out Bitcoin for lack of ‘fundamentals’

Published

on

A Swedish hedge fund that returned roughly four times the industry average last year using artificial intelligence won’t touch Bitcoin, based on an assessment that the cryptocurrency doesn’t lend itself to sensible analysis.

Photo by Bloomberg Mercury

Patrik Safvenblad, the chief investment officer of Volt Capital Management AB, says the problem with Bitcoin and other crypto assets is that they “do not have accessible fundamentals that we could build a model on.”

“When there is a crisis, markets generally move toward fundamentals. Not the old fundamentals but new, different fundamentals,” he said in an interview. So if an asset doesn’t provide that basic parameter, “we stay away from that,” he said.

The role of Bitcoin in investment portfolios continues to split managers, as the world’s most popular cryptocurrency remains one of its most volatile asset classes. One coin traded at less than $40,000 on Friday, compared with an April peak of $63,410. This time last year, a single Bitcoin cost around $10,000.

Among Volt’s best-known investors is Bjorn Wahlroos, the former Nordea Bank Abp chairman. His son and former professional poker player, Thomas Wahlroos, is Volt’s board chairman. The fund currently manages assets worth just $73 million, on which it returned 41% in 2020, four times the industry average.

Bitcoin enthusiasts recently received a boost when hedge fund manager Paul Tudor Jones told CNBC he likes it “as a portfolio diversifier.” He went on to say that the “only thing” he’s “certain” about is that he wants “5% in gold, 5% in Bitcoin, 5% in cash, 5% in commodities.”

Meanwhile, Bank of America Corp. research shows that Bitcoin is about four times as volatile as the Brazilian real and Turkish lira. And the International Monetary Fund has warned that El Salvador’s decision to adopt Bitcoin as legal tender “raises a number of macroeconomic, financial and legal issues that require very careful analysis.”

Safvenblad says it’s more than just a matter of Bitcoin’s lack of fundamentals. He says he’s not ready to hold an asset that’s ultimately designed to dodge public scrutiny.

Volt would “much prefer to be in a regulated market with regulated trading,” he said. “And Bitcoin is not yet fully regulated.”

The hedge-fund manager has chosen 250 models it thinks will make money, and its AI program then allocates daily weightings. Volt’s investment horizon is relatively short, averaging about 10-12 trading days. It holds roughly 60 positions at any given time, and its current analysis points toward what Safvenblad calls a “nervous long.”

“In the past few weeks the program has turned more bearish,” he said. We have some positions that anticipate a slowdown, for example long fixed-income, and the models have now trimmed our long positions in commodities. Today, the portfolio reflects a more balanced outlook.”

Safvenblad says the advantage to Volt’s AI model is that it’s unlikely to miss any signals. “We don’t say that we know where the world is heading. But we have a system that monitors everything that could mean something.”

— Jonas Cho Walsgard, Bloomberg Mercury

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://bankautomationnews.com/allposts/wealth/ai-driven-hedge-fund-rules-out-bitcoin-for-lack-of-fundamentals/

Continue Reading

AI

Digital twins help transform the construction industry

Published

on

Elevate your enterprise data technology and strategy at Transform 2021.


Digital twins promise to be a key enabler as the construction industry races to catch up with demand for new facilities and new layouts in the wake of COVID-19. Use of such technology, which creates a digital representation of real-world systems and components, is important for an industry seen as slow to adopt digital technology relative to others.

Construction is a complex undertaking, with legacy processes that span regulators, architects, contractors, and building owners. Digital transformation requires finding ways to bridge these divides — not just within elements of each participant’s domain, but also between them.

Still, practical benefits will come from harmonizing the way different groups create and manage data, according to John Turner, vice president of innovative solutions at Gafcon, a digital twin systems integrator.

Growing demand, increased complexity, and more sophisticated design authoring tools will drive the change, according to Rich Humphrey, vice president of construction at infrastructure software maker Bentley Systems. He estimates that the construction software market is currently upwards of $10 billion and could grow significantly thanks to the adoption of digital twins. “The industry is already seeing value in managing risk, reducing rework, and driving efficiencies in the way they deliver projects using digital twins,” Humphrey told VentureBeat.

Change could be far-reaching in an industry that represents one of the largest asset classes in the world.

“There are more than 4 billion buildings in the world today, which is twice as many as websites are online,” said RJ Pittman, CEO of Matterport, a reality capture service for buildings. The rush is on, not only to build more efficiently, but also to increase the value of existing buildings, which today represent a $230 trillion asset class.

Warp speed ahead

COVID is accelerating the demand for digital twin technology. CRB, a construction provider for the biotech industry, recently turned to Matterport to help design and build new vaccine plants as part of Operation Warp Speed. They used Matterport to capture the layout of existing plants, as well as to improve the design and layout of new ones. A digital twin also allowed them to model the workflow and safety properties of the new facilities to identify and rectify any bottlenecks before the new facilities were started.

“Tools like Matterport enable seamless collaboration in the same space because it’s browser-based,” said Chris Link, virtual design and construction manager at CRB. Data is not lost from multiple handoffs between a designer, builder, and owner.

Digital twins also dramatically reduced the need for engineers to travel to existing or new plants. On one project, CRB reduced the number of onsite engineers from 10 to 1, reduced travel costs by 33%, and expedited design by three weeks. One key benefit is that Matterport can capture and harmonize data across different participants and enable people to collaborate within a single platform instead of what was previously a handoff scenario between design and engineering.

Digital twins can reduce the operational expenditures associated with a facility occurring after facility handoff, accounting for 80% or more of the total facility lifetime cost.

“A digital twin is a goldmine to a facility owner because there is currently a significant data loss in engineering and construction,” Link said. Building managers can use digital twins to understand why things were engineered and designed in the manner they were, and this understanding translates to simplified maintenance. For example, maintenance technicians called in to repair a broken pump can utilize the digital twin to understand the design and intent of the pump. They can see the bigger picture, not just the broken pump in front of them.

Reshape, rewire, rethink

Construction-related spending accounts for about 14% of the world GDP and is expected to grow from $10 trillion in 2017 to $14 trillion in 2025, according to McKinsey. The consulting firm also says that about $1.6 trillion in additional value could be created through higher productivity. McKinsey identified seven best practices that could use digital twins to boost productivity by 50 to 60%:

  1. Reshape regulation — Accelerate approvals with testable plans and enable the adoption of performance-based requirements.
  2. Rewire contracts — Improved information sharing enables new contractual models.
  3. Rethink design — New designs could be tested and iterated more efficiently.
  4. Improve onsite execution — Easier detection of scheduling clashes.
  5. Infuse technology and innovation — Improve orchestration with IoT, drones, and AI planning.
  6. Reskill workers — Facilitate new training programs for innovative technologies using VR.
  7. Improve procurement and supply chain — Better harmonization between current progress and deliveries.

McKinsey predicts that firms could see further productivity gains by adopting a manufacturing system of mass production, with much more standardization appearing across global factory sites. These efforts require greater harmonization between design, manufacturing, and construction, as well as much tighter tolerances. Some early successes include: Barcelona Housing Systems estimates it can reduce labor 5 to 10 times for multi-story homes;
Finnish industrial company Outotec has created a process for small mines that reduces labor by 30%, capital by 20%, and time by 30%; and Broad Sustainable Buildings of China erected a 30-story hotel in 15 days.

Digital twins mind the gaps

“Digital twins are about connecting to real-life objects or information,” said Connor Christian, senior product manager at Procore, a construction software provider. That is a key issue in an area that combines so many different engineering facets.

In fact, the construction industry has evolved a piecemeal approach to managing different data sources, including GIS for location data, building information modeling (BIM) for 3D data, and virtual design and construction (VDC) for project management. This challenges digital twin implementation.

While any job site with sensors or cameras has the potential to create digital twins that allow for access, control, and reporting from those devices, the fact is that not all data is good data, so there must be standards, processes, and verifications in place to help filter out unnecessary data, Christian said.

Different processing stages are involved in turning raw data into the higher-level abstractions required to improve construction processes, said David McKee, CEO, CTO, and founder at Slingshot Simulations and co-chair at the Digital Twin Consortium. For example, Slingshot recently deployed a workflow that combined European Space Agency Sentinel-1 InSAR data from SatSense that looks at ground movement, merged this with infrastructure data, correlated this with traffic data, and presented that back to stakeholders to understand the risks to transport infrastructure.

McKee has found it helpful to adopt IBM Design Thinking approach and Agile software engineering practices for building and deploying digital twins.

“This approach means that even in some of the biggest infrastructure projects, you can start engaging stakeholders within a couple of weeks,” McKee said. For example, his team has recently kicked off a project to improve the transport network in one of the busiest shipping hubs in the UK in the wake of Brexit.

Digital twins can also help fill in the semantic gaps in traditional BIM and GIS tools, said Remi Dornier, vice president of construction, cities, and territories at Dassault Systemes. Digital twins also provide a way to include all the necessary details to perform purchasing and construction assembly. And they can also improve ergonomics. For example, Dassault has been working on a simulation for nursing homes to help eliminate heavy lifting associated with caring for patients.

DevOps for construction

Gafcon’s Turner said the next era of digital twins involves using digital twins to bring a DevOps-like approach to construction. That can transform the entire construction lifecycle.

But teams need to rethink the entire construction and management process to see the highest efficiencies. For example, mass timber construction is a new approach to building that uses standardized manufactured wood products with different properties than traditional wood. It involves gluing small pieces of wood together in the proper orientation.

If teams treat the material like traditional timber, they might see marginal improvements in costs, productivity, and speed. But more dramatic improvement may be possible. The kinship to IT DevOps should be apparent. Digital transformation for construction will mean including test and ops teams earlier in the process. This collaboration can sort out issues like defining assembly steps and how components must be delivered to create, hopefully, far better results.

It is not entirely clear how the construction industry will evolve from a patchwork of different tools to the well-orchestrated CI/CD-like pipelines transforming software development.

But vendors are in the hunt. Leading vendors include a patchwork of companies expanding beyond their core strengths in fields such as GIS (Trimble, ESRI), BIM (Autodesk, Bentley, Dassault), construction management (Procore, and Oracle Construction), reality capture (Matterport and SiteAware), and supply chain management (SiteSense). Digital twins integrators such as Swinerton, Gafcon, and Lendlease Podium help to meld these tools into well-orchestrated workflows that span the design, construction, and operations lifecycle.

Construction ahead

This industry’s attempts at transformation are complicated, and a lot of subsidiary elements need to successfully evolve in order for digital twins to gain traction. The recent Katerra bankruptcy underscores the challenges that even high-profile operations face in trying to transform the construction industry.

For one thing, the industry needs better data quality and context, Oracle senior director of new products, BIM, and innovation Frank Weiss told VentureBeat. The technology to gather and integrate data to create an ecosystem of digital twins is available today.

But it comes from many different sources in different formats, which can be challenging for analysis. “It’s going to take vendors, governments, and other stakeholders to work together,” Weiss said.

In addition, the industry will also have to find consensus on what defines digital twins and how they plug into existing processes. “There is still a general lack of understanding of what a digital twin is,” said Procore’s Christian. Right now, any virtual object associated with data is being called a digital twin, he suggested.

And more challenges are in the offing, including the lack of a common data interchange environment that would allow data to easily flow from software to software.

“Even with all the great APIs, cloud-based data, and platform solutions, there still remains a massive amount of data stuck in silos that are not able to be fully accessed,” Christian said.

Assembly required

Today, experts believe enterprises are barely scratching the surface of what digital twins can accomplish, Steve Holzer, principal at Holzer, an architectural and planning consultancy and member of the infrastructure working group at the Digital Twin Consortium, told VentureBeat.

While much attention focuses on the bright shiny side of digital twins, pragmatic considerations are coming into greater play, and guides from other industries are being studied. In the long run, the industry will need to adopt a new mindset to replace most legacy construction methods and processes with the product-driven mindset used in other industries.

“Once we have project thinking replaced with product thinking, construction will be replaced with assembly,” Holzer said.

VentureBeat

VentureBeat’s mission is to be a digital town square for technical decision-makers to gain knowledge about transformative technology and transact. Our site delivers essential information on data technologies and strategies to guide you as you lead your organizations. We invite you to become a member of our community, to access:

  • up-to-date information on the subjects of interest to you
  • our newsletters
  • gated thought-leader content and discounted access to our prized events, such as Transform 2021: Learn More
  • networking features, and more

Become a member

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://venturebeat.com/2021/06/18/digital-twins-help-transform-the-construction-industry/

Continue Reading

AI

8 Open-source NLP Tools You Should Try

Published

on

image

Gaurav Hacker Noon profile picture

@gauravsharmaGaurav

A technical writer with Cogito, who writes about AI. National basketball player. Photographer.

Innovative technologies like voice assistants, predictive text, autocorrect, chatbots, and others have rapidly evolved in recent years, and the force behind it is Natural Language Processing (NLP).

NLP is a sub-field of Artificial Intelligence, which aims to emulate human intelligence and focuses on the interactions between computers and human language.

It typically allows computers to process and carefully analyze massive
amounts of natural language data.

Through effective implementation of NLP, one can naturally access relevant information in just seconds. Several businesses have implemented this technology by building customized chatbots, voice assistants and using their optical character & text simplification techniques to reap maximum benefits.

To help the businesses, there are several open-source NLP tools available which businesses can utilize according to their specific
requirements.

These open-source tools will not only help businesses to systemize the unstructured text but will also combat several other problems.

Below are the open-source NLP toolkit platforms anyone can use :

1. Natural Language Toolkit (NLTK)

It is an open-source platform used for python programming. It gives over 50 corpora and lexical resources like WordNet, along with a suite of text processing libraries for classification, tokenization, stemming, tagging,
parsing, and semantic reasoning, wrappers for industrial-strength NLP
libraries.

NLTK is appropriate for linguists, engineers, students, educators, researchers, etc., and is available for Windows, Mac OS X, and Linux.

2. SpaCy

SpaCy is another open-source library and typically comprises pre-trained statistical models and word vectors that support over 60 languages. Licensed under MIT, anyone can use it commercially. SpaCy supports custom models in PyTorch, TensorFlow, and other frameworks.

The main USP of SpaCy is Named Entity Recognition, part-of-speech tagging, dependency parsing, sentence segmentation, text classification, lemmatization, morphological analysis, entity linking, and others.

3. OpenNLP

OpenNLP supports the tasks such as tokenization, sentence segmentation, part-of-speech tagging, named entity extraction, chunking, parsing, language detection, and coreference resolution. Apart from this, it additionally includes maximum entropy and perceptron-based machine learning.

3. CoreNLP

It is another open-source platform which is developed by the Stanford NLP group as a possible solution for NLP in Java. It is currently supporting six languages (Arabic, Chinese, English, French, German, Spanish).

The USP of CoreNLP is sentence boundaries, parts-of-speech, named entities, numeric and time values, dependency and constituency parses, coreference, sentiment, quote attributions, and relations.

5. AllenNLP

Allen is an open-source platform based on PyTorch. It is a deep learning library for NLP used for the tasks such as responding to questions, semantic role labeling, textual entailment, text to SQL.

6. Flair

Like AllenNLP, Flair is also built on PyTorch. This open-source platform allows using the platform’s state-of-art NLP models of text, such as Named Entity Recognition (NER), part-of-speech tagging, sense disambiguation and
classification.

It includes simpler interfaces where one can combine various words and document embeddings.

7. SparkNLP

SparkNLP is an open-source platform that gives over 200 pre-trained pipelines and models supporting more than 40 languages. SparkNLP supports transformers like BERT, XLNet, ELMO and carries out accurate and clear annotations for NLP.

8. Gensim

Gensim is a free and open-source python library uniquely designed to process raw texts using quality machine learning algorithms. It is used for topic modeling, document indexing.

The USP of the platform is tokenization, part-of-speech tagging, named entity recognition, spell checking, multi-class text classification, multi-class sentiment analysis.

Natural Language Processing is a crucial and revolutionary technology. I expect this technology to flourish in the possible future with the successful adoption of more personal assistants, dependencies on smartphones, and the evolution of Big Data.

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://hackernoon.com/8-open-source-nlp-tools-you-should-try-375g35bc?source=rss

Continue Reading
Energy5 days ago

Extensive Demand from the Personal Care and Cosmetics Industry Coupled with the Booming Construction Industry will Invite Impactful Growth for the Mineral Oil & Mineral Spirit Market: TMR

Esports3 days ago

World of Warcraft 9.1 Release Date: When is it?

Energy3 days ago

Biocides Market worth $13.6 billion by 2026 – Exclusive Report by MarketsandMarkets™

Esports4 days ago

Clash of Clans June 2021 Update patch notes

Big Data5 days ago

In El Salvador’s bitcoin beach town, digital divide slows uptake

Aviation5 days ago

Boeing 727 Set To Be Turned Into Luxury Hotel Experience

HRTech4 days ago

Pre-Owned Luxury Car dealer Luxury Ride to add 80 Employees across functions to boost growth

Blockchain3 days ago

Former PayPal Employees Launch Cross-Border Payment System

Blockchain2 days ago

PancakeSwap (CAKE) Price Prediction 2021-2025: Will CAKE Hit $60 by 2021?

Blockchain4 days ago

Since It Adopted Bitcoin As Legal Tender, The World Is Looking At El Salvador

Energy3 days ago

XCMG dostarcza ponad 100 sztuk żurawi dostosowanych do regionu geograficznego dla międzynarodowych klientów

Esports2 days ago

Here are the patch notes for Call of Duty: Warzone’s season 4 update

Esports3 days ago

Here are the patch notes for Brawl Stars’ Jurassic Splash update

Aerospace5 days ago

Delivering economic and societal value

Gaming4 days ago

Super Smash Bros. Ultimate – Tekken’s Kazuya Mishima is the Next Challenger pack

Esports2 days ago

How to complete Path to Glory Update SBC in FIFA 21 Ultimate Team

Blockchain2 days ago

Will Jeff Bezos & Kim Kardashian Take “SAFEMOON to the Moon”?

Blockchain3 days ago

Civic Ledger awarded as Technology Pioneers by World Economic Forum

Esports2 days ago

How to unlock the Call of Duty: Black Ops Cold War season 4 battle pass

Esports2 days ago

How to unlock the MG 82 and C58 in Call of Duty: Black Ops Cold War season 4

Trending