ScienceFather, Author at ScienceFather

5 Ways Metaverse And Artificial Intelligence Influence Avatar 2

Posted on 02/01/2023 by ScienceFatherLeave a Comment

[ad_1]

<br />

The newest technology is a hallmark of James Cameron’s films. No matter if it’s the Titanic, the Terminator, or the Magnum Opus Avatar 2. During the global transition to the internet. He made a significant step by creating the metaverse-based film avatar. Despite the audience’s lack of familiarity with the idea at the time, it was warmly accepted. The movie Avatar quickly gained popularity and rose to the top of the box office.

He understands what makes a story seem realistic as a storyteller, and cutting-edge technologies are a significant part of his toolkit. It takes a genius to design a planet that no one has ever seen before while making it understandable. He repeatedly emphasized the part artificial intelligence (AI) can play in improvised filmmaking. He used sophisticated artificial intelligence and machine learning algorithms in his film Avatar 2.

5 ways Metaverse and Artificial Intelligence influence Avatar 2

Virtual Reality

The viewer has a genuine underwater immersion experience. Evaluating the various facets of human perception and how they relate to one another is imperative. In order to explore and interact with the fictional Pandora in real-time, the production team and actors wore VR headsets.

Also Read: Year Ender: Top 3 Metaverse Trends To Watch Of 2022

Invent new scenes

Before the movie is finally released, new storylines are always possible. During the movie’s editing process, it is thought that dialogue or facial expressions need to be improved. It was previously accomplished by taking a wide shot or a headshot, which runs the risk of having an improper lipsync. To get around this, Cameron invented a brand-new technique for overlaying new dialogue or facial scans onto a scene that had already been performed.

Augmented Reality

A product of augmented reality(AR), the world of Pandora’s planet appears realistic in the film. With AR, elements from the real world are essentially superimposed, creating a sense of interaction and immersion. The presence of alien creatures with intricate anatomies makes the contribution AR made to this movie impossible to ignore.

Examine movie scripts

Recently, algorithms have developed the ability to comprehend story flow and adapt to various storytelling techniques. It makes sense that a VFX-heavy film like Avatar would use AI to analyze the plot. The script for Avatar 2 is written exquisitely, as can be seen by the audience.

Motion Capture

This technology, also known as performance capture, enables the recording of motions made by people or objects and the transfer of those motions to animated objects in a virtual environment. Usually, heavy equipment is needed for this process, but a machine-learning algorithm can easily take its place. It can increase the story’s pace, predictability, and analytics impact.

Avatar 2 earned more than $400 million at the global box office after debuting with $134 million in domestic ticket sales. Slowly and steadily gained popularity, earning more than $1 billion in its third weekend. After Top Gun 2, Avatar 2 is the second 2022 film to gross over a billion dollars. At the end of the New Year’s weekend, Avatar 2 brought in $1.379 billion at the global box office.

Also Read: Top 5 Technologies That Power The Metaverse

CoinGape comprises an experienced team of native content writers and editors working round the clock to cover news globally and present news as a fact rather than an opinion. CoinGape writers and reporters contributed to this article.

The presented content may include the personal opinion of the author and is subject to market condition. Do your market research before investing in cryptocurrencies. The author or the publication does not hold any responsibility for your personal financial loss.

[ad_2]

Source link

NVIDIA DRIVE OS earns safety certification

Posted on 01/01/2023 by ScienceFatherLeave a Comment

[ad_1]

NVIDIA DRIVE OS is an operating system for in-vehicle accelerating computing power. | Source: NVIDIA

TÜV SÜD has determined that NVIDIA’s DRIVE OS 5.2 software meets the International Organization for Standardization (ISO) 26262 Automotive Safety Integrity Level (ASIL) B standard, which targets functional safety in road vehicles’ systems, hardware and software.

NVIDIA DRIVE OS is an operating system for in-vehicle accelerating computing powered by the NVIDIA DRIVE platform. DRIVE OS is the foundation of NVIDIA’s DRIVE SDK, which includes NVIDIA’s CUDA libraries for efficient parallel computing, the NVIDIA Tensor RT SDK for real-time AI inferencing and the NvMedia library for sensor input processing, among other developer tools and modules.

To meet the standard, NVIDIA’s software had to be able to detect failures during operation, and be developed in a process that handles potential systematic faults along the whole V-model, this includes everything from safety requirements definition to coding, analysis, verification and validation. Essentially, the software has to avoid failures whenever possible, and detect and respond to them if they can’t be avoided.

TÜV SÜD’s team determined that DRIVE OS 5.2 complies with its strict testing criteria and is suitable for safety-related use in applications up to ASIL B. ISO 26262 identifies four ASILs, A, B, C and D, with A being the lowest degree and D being the highest degree of automotive hazard.

TÜV SÜD, based in Munich, Germany, assesses compliance to national and international standards for safety, durability and quality in various applications, including cars, factories, buildings, bridges and other infrastructure.

NVIDIA DRIVE is an open platform, which means that experts from top car companies can build upon the company’s industrial-strength system.

Earlier this year, NVIDIA filed a patent for a system that would help solve one of the biggest issues in autonomous driving: how self-driving cars identify and react to emergency vehicles.

Nvidia’s patent filing, which was published by the US Patent and Trademark Office in May 2022, seeks to help self-driving cars to avoid situations where an autonomous vehicle doesn’t how know to react to emergency vehicles, which could result in a slowed response time, meaning more property damage and personal injuries.

The patent describes a system involving microphones attached to an autonomous or semi-autonomous car to capture the sounds of nearby emergency response vehicles’ sirens. The microphones will work with a Deep Neural Network (DNN) to create audio signals that correspond to the sirens detected.

NVIDIA won a 2022 RBR50 Robotics Innovation Award from our sister publication Robotics Business Review. The company won for its Omniverse Replicator, a data generation engine that produces synthetic data for training deep neural networks based on physical simulations in photorealistic, physically-accurate virtual environments.

The post NVIDIA DRIVE OS earns safety certification appeared first on The Robot Report.

from The Robot Report – Robotics News, Analysis & Research https://ift.tt/ZYhMiUG
via artificialconference

[ad_2]

Source link

Inferring gene regulatory networks from single-cell gene expression data via deep multi-view contrastive learning

Posted on 31/12/2022 by ScienceFatherLeave a Comment

[ad_1]

doi: 10.1093/bib/bbac586.

Online ahead of print.

Affiliations

Item in Clipboard

Zerun Lin et al.

Brief Bioinform.

2022.

doi: 10.1093/bib/bbac586.

Online ahead of print.

Affiliation

¹ Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Media Security, and Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ), College of Electronics and Information Engineering, Shenzhen University, Shenzhen, 518060, China.

Item in Clipboard

Abstract

The inference of gene regulatory networks (GRNs) is of great importance for understanding the complex regulatory mechanisms within cells. The emergence of single-cell RNA-sequencing (scRNA-seq) technologies enables the measure of gene expression levels for individual cells, which promotes the reconstruction of GRNs at single-cell resolution. However, existing network inference methods are mainly designed for data collected from a single data source, which ignores the information provided by multiple related data sources. In this paper, we propose a multi-view contrastive learning (DeepMCL) model to infer GRNs from scRNA-seq data collected from multiple data sources or time points. We first represent each gene pair as a set of histogram images, and then introduce a deep Siamese convolutional neural network with contrastive loss to learn the low-dimensional embedding for each gene pair. Moreover, an attention mechanism is introduced to integrate the embeddings extracted from different data sources and different neighbor gene pairs. Experimental results on synthetic and real-world datasets validate the effectiveness of our contrastive learning and attention mechanisms, demonstrating the effectiveness of our model in integrating multiple data sources for GRN inference.

Keywords:

contrastive learning; deep learning; network inference; single-cell RNA-Sequencing.

[ad_2]

Source link

Artificial Intelligence changing the future of fashion – FOX 32 Chicago

Posted on 30/12/2022 by ScienceFatherLeave a Comment

[ad_1]

Artificial Intelligence changing the future of fashion FOX 32 Chicago

[ad_2]

Source link

Is Artificial Intelligence Replacing Our Radiology Stars in Prostate Magnetic Resonance Imaging? The Stars Do Not Look Big, But They Can Look Brighter

Posted on 29/12/2022 by ScienceFatherLeave a Comment

[ad_1]

Eur Urol Open Sci. 2022 Dec 16;48:12-13. doi: 10.1016/j.euros.2022.11.021. eCollection 2023 Feb.

NO ABSTRACT

PMID:36578461 | PMC:PMC9791603 | DOI:10.1016/j.euros.2022.11.021

[ad_2]

Source link

10 most memorable robotics stories of 2022

Posted on 29/12/2022 by ScienceFatherLeave a Comment

[ad_1]

The Robotics industry had its fair share of memorable moments in 2022. Here we take a look back at our picks for the most memorable Robotics stories of the year.

The list is comprised of moments that made us laugh and cringe, as well as moments that left us surprised or amazed at the capabilities of various robots. What did we miss? Please let us know in the comments what you’ll remember most from 2022.

Subscribe to The Robot Report Newsletter to stay updated on the Robotics stories you need to know about.

First audio of Martian dust devil

According to NASA, nearly every Mars rover has experienced dust devils. But the Perseverance rover is the first to capture audio of one. In December 2022, NASA released the audio, adding that it could help scientists better understand how dust might affect future Mars missions.

NASA said capturing a passing dust devil takes some luck, adding that this first-of-its-kind recording was around a 1-in-200 shot. Scientists can’t predict when they’ll pass by, so rovers like Perseverance routinely monitor in all directions for them.

Spiderman robot crashes at Disneyland

On June 9, 2022, the Spider-Man robot at Disneyland momentarily lost its Spidey-Sense. The Spider-Man robot failed in mid-air and crashed into the W.E.B. facility that is part of the stunt setup. And it was all caught on video.

“Here goes something,” narrated the attraction’s soundtrack as Spidey took flight. According to Disney, the robot makes its own, real-time decisions when to tuck, somersault and slow down while soaring 85 feet in the air. But halfway through, the robot’s limbs locked up, rendering it a mere projectile. It crashed right into W.E.B. building. Nobody was hurt during the crash, and the attraction was up and running again a few hours later.

Tesla uveils working humanoid prototype

Elon Musk unveiled at Tesla AI Day the company’s much-anticipated Optimus humanoid robot. Last year, of course, the “robot” was simply a human dressed in a robot suit. This time, Tesla, albeit briefly, actually demoed a working prototype that walked, waved, and danced on stage. Tesla also played videos that showcased the Optimus prototype doing different tasks, such as picking up boxes in a warehouse and watering a plant in an office.

Musk unabashedly claimed Tesla will be able to leapfrog other humanoid developers, such as Agility Robotics and Boston Dynamics, in part because Optimus uses the same neural networks as Tesla’s Autopilot technology. The Robotics industry watched Tesla AI Day in earnest to see exactly what Optimus would be this time around. Many experts agreed the technology inside Optimus lags behind the competition, but they were impressed with how quickly Optimus was built.

Riding in a Waymo around SF

I’ve been fortunate enough to ride in several robotaxis over the years, but none were better than my ride with Waymo around San Francisco in October. It was a roughly 9-mile ride that took just under 30 minutes. Because I’m not a Waymo employee, there was a human safety driver behind the wheel.

The route we took had a myriad of obstacles, including multiple unprotected left turns, pedestrians crossing streets and sidewalks, bicyclists, narrow streets, double-parked Amazon delivery trucks and construction vehicles cutting us off. As you would hope, the trip was flawless and uneventful. Actually, it was quite boring.

First science images from James Webb

NASA released the first science image from the James Webb Space Telescope in July 2022 during a press conference with President Joe Biden. The image was of SMACS J0723.3-7327. What you see in the image is an area of space that includes the faintest objects ever observed in the infrared.

This slice of the vast universe covers a patch of sky approximately the size of a grain of sand held at arm’s length by someone on the ground. The light in this region goes back 13+ billion years.

Cruise robotaxi interacts with SF police

In April 2022, a video surfaced of an interesting interaction between a Cruise robotaxi and San Francisco police officers. The Cruise robotaxi is stopped at a red light, with a police car behind it. As the light turns green, a member of the SF police officer gets out of his car and approaches the robotaxi, apparently because the vehicle’s headlights weren’t on. The police officer tries to open the driver’s side door, but it’s locked. As he heads back to his police car, the Cruise robotaxi drives off before quickly pulling over and flashing its hazard lights less than 10 seconds later.

The internet went crazy with all kinds of jokes about police chases, but Cruise said things went according to plan.

“Our AV yielded to the police vehicle, then pulled over to the nearest safe location for the traffic stop, as intended. An officer contacted Cruise personnel and no citation was issued,” Cruise tweeted. “We work closely with the SFPD on how to interact with our vehicles, including a dedicated phone number for them to call in situations like this.”

Chess-playing robot breaks 7-year-old’s finger

A seven-year-old boy’s finger was broken by a chess-playing robot during a tournament in Russia back in July 2022. The video shows the robot playing on three chessboards simultaneously. The boy makes a move when the robotic arm lowers onto his hand. Four men rush in to help, the boy’s finger is freed, and he is taken away.

The story captured the world’s attention, and tournament officials at one point blamed the child for making a move the robot didn’t understand.

We discussed this incident at length on The Robot Report Podcast with Nima Fazelli, an assistant professor of Robotics at the University of Michigan. Fazelli created a famous Jenga-playing robot during his days at MIT. He discussed the lack of basic safety protocols with the chess-playing robot, the poor choice of using an industrial robot, the system’s lack of intelligence and much more.

Turning dead spiders into robot grippers

Just when you think you’ve seen it all, along comes an idea to use dead spiders as robotic grippers. Engineers at Rice University introduced the world to the concept of “necrobotics” explaining why turning dead wolf spiders into mechanical grippers.

According to the researchers, unlike people and other mammals that move their limbs by synchronizing opposing muscles, spiders use hydraulics. A chamber near their heads contracts to send blood to limbs, forcing them to extend. When the pressure is relieved, the legs contract. Internal valves in the spiders’ hydraulic chamber, or prosoma, allow them to control each leg individually.

The researchers ran one dead spider through 1,000 open-close cycles to see how well its limbs held up, and found it to be fairly robust.

Call me close-minded, but I don’t see necrobotics going mainstream.

SF votes in favor of police using robots with lethal force

In late November 2022, San Francisco’s Board of Supervisors voted to allow the San Francisco Police Department to use remote-controlled and potentially lethal robots in emergency situations. The board voted 8-3 in favor of giving police the option to deploy robots as a last resort in emergency situations.

This made a lot of people inside and outside the Robotics industry quite angry. And just a week later the decision was unanimously reversed. The proposal would have allowed officers to use robots to kill a suspect “when risk of loss of life to members of the public or officers is imminent and officers cannot subdue the threat after using alternative force options or de-escalation tactics.”

Digit helps human coworkers unload trailers

While Tesla’s humanoid prototype could do little more than walk and wave, Agility Robotics showed us that bipedal robots working alongside humans might not be as far off as we think. In April 2022, Agility Robotics gave us a look at the capabilities of its bipedal robot Digit, which brought in $150 million in funding that month. The video shows Digit handling packages and bins, loading them onto trucks, picking them up from shelving and even taking totes from human workers.

Digit has a max speed of 1.5 m/s and can run for 3 hours doing light work. Doing heavy work, the robot will last 1.5 hours. While right now Digit can only be used to move totes and packages and unload trailers, the company hopes to expand its capabilities to last-mile deliveries soon.

The post Robotics-stories-of-2022/”>10 most memorable Robotics stories of 2022 appeared first on The Robot Report.

from The Robot Report – Robotics News, Analysis & Research https://ift.tt/rgvAN1M
via artificialconference

[ad_2]

Robotics-stories-of.html”>Source link

AI (Artificial Intelligence) Image Recognition Market Size, Growth | Examination Forecast [2023-2028] | Latest Inclinations, Future Developments, TOP Players Revenue, and Industry Demand Analysis

Posted on 28/12/2022 by ScienceFatherLeave a Comment

[ad_1]

AI (Artificial Intelligence) Image Recognition Market 2023 Report [Report Pages-100] Insights – By Applications (Automotive, Healthcare, BFSI, Retail, Security, Other), By Types (Hardware, Software, Services), By Segmentation analysis, Regions and Forecast to 2028.

The Global AI (Artificial Intelligence) Image Recognition market Report provides Detailed analysis on the market position of the AI (Artificial Intelligence) Image Recognition Top players with stastical data, SWOT analysis, PESTAL analysis, latest developments across the globe. the AI (Artificial Intelligence) Image Recognition Market Report contains Complete TOC, Tables and Figures, and Pre and Post COVID-19 Market Outbreak Impact Analysis.

Top Key Players of AI (Artificial Intelligence) Image Recognition Market are as follows:

NVIDIA Corp.
Cortica
Procter and Co.
Microsoft Corp.
Samsung Electronics Co., Ltd.
Intel, Inc.
Qualcomm Corp.
Amazon Web Services, Inc.
Xilinx, Inc.
Vee Technologies, Inc.
Webtunix
Softech, Ltd.
Visenze
Aether, Inc.
Cortexica Vision Systems, Ltd.
MICRON Technology, Inc.
Pixelab
LPixel, Inc.
Google, LLC
IBM Corp.
Clarifai, Inc.

And More….

{Moving Compound annual growth rate (CAGR) In terms of Revenue in Million}

Get a Sample Copy of the AI (Artificial Intelligence) Image Recognition Market Report 2023: https://www.marketgrowthreports.com/enquiry/request-sample/21403011

Brief description about AI (Artificial Intelligence) Image Recognition Market Growth 2028:

The global AI (Artificial Intelligence) Image Recognition market size was valued at USD 2698.43 million in 2021 and is expected to expand at a CAGR of 24.69% during the forecast period, reaching USD 10140.15 million by 2027.

Image recognition, in the context of machine vision, is the ability of software to identify objects, places, people, writing and actions in images. Computers can use machine vision technologies in combination with a camera and artificial intelligence software to achieve image recognition.

The report combines extensive quantitative analysis and exhaustive qualitative analysis, ranges from a macro overview of the total market size, industry chain, and market dynamics to micro details of segment markets by type, application and region, and, as a result, provides a holistic view of, as well as a deep insight into the AI (Artificial Intelligence) Image Recognition market covering all its essential aspects.

For the competitive landscape, the report also introduces players in the industry from the perspective of the market share, concentration ratio, etc., and describes the leading companies in detail, with which the readers can get a better idea of their competitors and acquire an in-depth understanding of the competitive situation. Further, mergers and acquisitions, emerging market trends, the impact of COVID-19, and regional conflicts will all be considered.

In a nutshell, this report is a must-read for industry players, investors, researchers, consultants, business strategists, and all those who have any kind of stake or are planning to foray into the market in any manner.

To Know How Covid-19 Pandemic and Russia Ukraine War Will Impact This Market- REQUEST SAMPLE

AI (Artificial Intelligence) Image Recognition Market – Competitive and Segmentation Analysis:

As well as providing an overview of successful marketing strategies, market contributions, and recent developments of leading companies, the report also offers a dashboard overview of leading companies’ past and present performance. Several methodologies and analyses are used in the research report to provide in-depth and accurate information about the AI (Artificial Intelligence) Image Recognition Market.

The current market dossier provides market growth potential, opportunities, drivers, industry-specific challenges and risks market share along with the growth rate of the global AI (Artificial Intelligence) Image Recognition market. The report also covers monetary and exchange fluctuations, import-export trade, and global market

Based on types, the AI (Artificial Intelligence) Image Recognition market from 2017 to 2028 is primarily split into:

Hardware
Software
Services

Based on applications, the Same Day Delivery market from 2017 to 2028 covers:

Automotive
Healthcare
BFSI
Retail
Security
Other

Get a Sample Copy of the AI (Artificial Intelligence) Image Recognition Market Report 2023: https://www.marketgrowthreports.com/enquiry/request-sample/21403011

Key highlights of the report

AI (Artificial Intelligence) Image Recognition market share appraisals for the country and regional level segments
Combative landscape planning the significant customary trends
AI (Artificial Intelligence) Image Recognition Market tendencies that involve product and technological analysis, drivers and constraints, PORTER’s five forces analysis
Premeditated advice in essential business segments based on the market estimations
Intentional guidance for new entrants
AI (Artificial Intelligence) Image Recognition market prophesies all hinted segments, sub-segments, and regional market

Reasons for Buying this Report

This report provides pin-point analysis for changing competitive dynamics
It provides a forward looking perspective on different factors driving or restraining market growth
It provides a six-year forecast assessed on the basis of how the market is predicted to grow
It helps in understanding the key product segments and their future
It provides pin point analysis of changing competition dynamics and keeps you ahead of competitors

Top countries data covered in this report:

North America (U.S., Canada, Mexico)
Europe (U.K., France, Germany, Spain, Italy, Central and Eastern Europe, CIS)
Asia Pacific (China, Japan, South Korea, ASEAN, India, Rest of Asia Pacific)
Latin America (Brazil, Rest of L.A.)
Middle East and Africa (Turkey, GCC, Rest of Middle East)

Inquire more and share questions if any before the purchase on this report at-https://www.marketgrowthreports.com/enquiry/pre-order-enquiry/21403011

Major Points from Table of Contents:

Global AI (Artificial Intelligence) Image Recognition Market Research Report 2023- 2028, by Manufacturers, Regions, Types and Applications

1 Introduction

1.1 Objective of the Study

1.2 Definition of the Market

1.3 Market Scope

1.3.1 Market Segment by Type, Application and Marketing Channel

1.3.2 Major Regions Covered (North America, Europe, Asia Pacific, Mid East and Africa)

1.4 Years Considered for the Study (2015- 2028)

1.5 Currency Considered (U.S. Dollar)

1.6 Stakeholders

2 Key Findings of the Study

3 Market Dynamics

3.1 Driving Factors for this Market

3.2 Factors Challenging the Market

3.3 Opportunities of the Global Restaurant Online Ordering System Market (Regions, Growing/Emerging Downstream Market Analysis)

3.4 Technological and Market Developments in the Restaurant Online Ordering System Market

3.5 Industry News by Region

3.6 Regulatory Scenario by Region/Country

3.7 Market Investment Scenario Strategic Recommendations Analysis

Get a Sample PDF of report –https://www.marketgrowthreports.com/enquiry/request-sample/21403011

4 Value Chain of the AI (Artificial Intelligence) Image Recognition Market

4.1 Value Chain Status

4.2 Upstream Raw Material Analysis

4.3 Midstream Major Company Analysis (by Manufacturing Base, by Product Type)

4.4 Distributors/Traders

4.5 Downstream Major Customer Analysis (by Region)

5 Global AI (Artificial Intelligence) Image Recognition Market-Segmentation by Type

6 Global AI (Artificial Intelligence) Image Recognition System Market-Segmentation by Application

7 Global AI (Artificial Intelligence) Image Recognition Market-Segmentation by Marketing Channel

7.1 Traditional Marketing Channel (Offline)

7.2 Online Channel

8 Competitive Intelligence Company Profiles

9 Global AI (Artificial Intelligence) Image Recognition Market-Segmentation by Geography

9.1 North America

9.2 Europe

9.3 Asia-Pacific

9.4 Latin America

9.5 Middle East and Africa

Get a Sample PDF of report –https://www.marketgrowthreports.com/enquiry/request-sample/21403011

10 Future Forecast of the Global AI (Artificial Intelligence) Image Recognition Market from 2023-2028

10.1 Future Forecast of the Global AI (Artificial Intelligence) Image Recognition Market from 2023- 2028Segment by Region

10.2 Global AI (Artificial Intelligence) Image Recognition Production and Growth Rate Forecast by Type (2023-2028)

10.3 Global AI (Artificial Intelligence) Image Recognition Consumption and Growth Rate Forecast by Application (2023- 2028)

11 Appendix

11.1 Methodology

12.2 Research Data Source

Continued….

Purchase this report (Price 3250 USD for a single-user license)- https://www.marketgrowthreports.com/purchase/21403011

About Us:

Market is changing rapidly with the ongoing expansion of the industry. Advancement in the technology has provided today’s businesses with multifaceted advantages resulting in daily economic shifts. Thus, it is very important for a company to comprehend the patterns of the market movements in order to strategize better. An efficient strategy offers the companies with a head start in planning and an edge over the competitors. Market Growth Reports is the credible source for gaining the market reports that will provide you with the lead your business needs.

Contact Us:

Market growth reports

Phone: US +1 424 253 0946

UK +44 203 239 8187

Email: [email protected]

Web: https://www.marketgrowthreports.com/21403011

For More Related Reports Click Here :

Blow Torch Market

Outdoor Gear Market

Single-use Prepaid Card Market

Government Cloud Market

Tomato Paste Market

Loose Leaf Tea Market

Portland Limestone Cements Market

All Vaccine Market

Business-to-Business ECommerce Market

Swimwear or Beachwear Market

Photocatalytic Coatings Market

SCADA in Process Industries Market

Crop Protection (Agrochemicals) Market

Aluminum Pigments Market

Polio Vaccine Market

COFFEE GROUNDS Market

Bi-Metal Band Saw Blade Market

Glass Cosmetics Packaging Market

Astronomical Telescope Market

Hunting Apparel Market

Hair Hygiene and Cosmetology Appliances Market

Press Release Distributed by The Express Wire

To view the original version on The Express Wire visit AI (Artificial Intelligence) Image Recognition Market Size, Growth | Examination Forecast [2023-2028] | Latest Inclinations, Future Developments, TOP Players Revenue, and Industry Demand Analysis

[ad_2]

Source link

Feasibility of using AI to auto-catch responsible frames in ultrasound screening for breast cancer diagnosis

Posted on 26/12/2022 by ScienceFatherLeave a Comment

[ad_1]

. 2022 Dec 5;26(1):105692.

doi: 10.1016/j.isci.2022.105692.

eCollection 2023 Jan 20.

Jing Chen¹, Yitao Jiang², Keen Yang¹, Xiuqin Ye¹, Chen Cui³, Siyuan Shi³, Huaiyu Wu¹, Hongtian Tian¹, Di Song¹, Jincao Yao⁴, Liping Wang⁴, Sijing Huang¹, Jinfeng Xu¹, Dong Xu⁴, Fajin Dong¹

Affiliations

¹ Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China.
² Research and Development Department, Microport Prophecy, Shanghai 201203, China.
³ Research and Development Department, Illuminate, LLC, Shenzhen, Guangdong 518000, China.
⁴ The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang 310022, China.

Item in Clipboard

Jing Chen et al.

iScience.

2022.

. 2022 Dec 5;26(1):105692.

doi: 10.1016/j.isci.2022.105692.

eCollection 2023 Jan 20.

Authors

Affiliations

¹ Department of Ultrasound, Shenzhen People’s Hospital (The Second Clinical School of Medicine, Jinan University; The First Affiliated Hospital of Southern University of Science and Technology), Shenzhen, Guangdong 518020, China.
² Research and Development Department, Microport Prophecy, Shanghai 201203, China.
³ Research and Development Department, Illuminate, LLC, Shenzhen, Guangdong 518000, China.
⁴ The Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital), Institute of Basic Medicine and Cancer (IBMC), Chinese Academy of Sciences, Hangzhou, Zhejiang 310022, China.

Item in Clipboard

Abstract

The research of AI-assisted breast diagnosis has primarily been based on static images. It is unclear whether it represents the best diagnosis image.To explore the method of capturing complementary responsible frames from breast ultrasound screening by using artificial intelligence. We used feature entropy breast network (FEBrNet) to select responsible frames from breast ultrasound screenings and compared the diagnostic performance of AI models based on FEBrNet-recommended frames, physician-selected frames, 5-frame interval-selected frames, all frames of video, as well as that of ultrasound and mammography specialists. The AUROC of AI model based on FEBrNet-recommended frames outperformed other frame set based AI models, as well as ultrasound and mammography physicians, indicating that FEBrNet can reach level of medical specialists in frame selection.FEBrNet model can extract video responsible frames for breast nodule diagnosis, whose performance is equivalent to the doctors selected responsible frames.

Keywords:

Artificial intelligence; Cancer; Computer-aided diagnosis method.

Conflict of interest statement

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Figures

**Figure 1**

Flow chart and statistical results Note: R Frames: responsible frame; Phy Images: doctor frame selection; Fix Frames: fixed interval frame selection; All Frames: all frames of video; Ultrasound: Diagnosis by senior ultrasound doctors; Mammography: Diagnosis by senior mammography doctors; p: R Frames vs. others; AUC: area under the curve; NA: Not Applicable.

**Figure 2**

3-fold cross-validation results of training set Note: (A) R_Frames: responsible frame; (B) Phy_Images: doctor frame selection; (C) Fix_Frames: fixed interval frame selection; (D) All_Frames: all frames of video.

**Figure 3**

Comparison of the effectiveness of FEBrNet’s responsible frame and others in the independent testing set Note: AUC:area under the curve, 95% CI: 95% confidence Interval; (A) R_Frames: responsible frame; (B) Phy_Images: doctor frame selection; (C) Fix_Frames: fixed interval frame selection; (D) All_Frames: all frames of video; (E)Ultrasound: Diagnosis by senior ultrasound specialists; (F) Mammography: Diagnosis by senior mammography specialists.

**Figure 4**

A case study of responsible frames selected by FEBrNet Note: (A) and (B) The top 3 frames sorted by FScore are relatively similar in time sequence, visually identical, and contribute comparable characteristics; (C) and (D) The top 3 frames chosen by Entropy Reduce method show more diverse image characteristics and scattered on 2D feature plot.

**Figure 5**

Ultrasound video preprocessing

**Figure 6**

FEBrNet model structure Note: The backbone model is a feature extractor and weights of fully connected layer from pre-trained ultrasound image dataset filtered MobileNet_224. FEBrNet uses a feature extractor and weights from a pre-trained fully connected layer to generate a feature matrix that identifies responsible frames and makes diagnostic predictions.

**Figure 7**

An example of selecting responsible frames Step 1: MaxPool the three frame feature matrices and yield the video feature matrix. Step 2: choose frame1 as the first responsible frame for it minimizing the difference between *FScore*_video and *FScore*_framei. Step 3: add another frame to the responsible frame collection, whereas step 2 already chose one. Since the *FScore* difference between the responsible frame collections of frame1 and frame3 is the smallest, frame3 is picked as the second responsible frame. Example Figure 1 Schematic diagram of automatic stop of responsible frame selection. Note: RF_1: The first responsibility frame, and so on; When the model selects the video responsibility frame, it gradually rises from the initial malignant prediction value to RF_9 (0.93), from RF_10 starts to decline gradually, so the model is selected to RF_9 stop.

References

1. Sung H., Ferlay J., Siegel R.L., Laversanne M., Soerjomataram I., Jemal A., Bray F. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA. Cancer J. Clin. 2021;71:209–249.
  
  –
  
  PubMed
1. Siegel R.L., Miller K.D., Fuchs H.E., Jemal A. Cancer statistics, 2021. CA. Cancer J. Clin. 2021;71:7–33.
  
  –
  
  PubMed
1. Siegel R.L., Miller K.D., Fuchs H.E., Jemal A. Cancer statistics, 2022. CA. Cancer J. Clin. 2022;72:7–33.
  
  –
  
  PubMed
1. Maliszewska M., Maciążek-Jurczyk M., Pożycka J., Szkudlarek A., Chudzik M., Sułkowska A. Fluorometric investigation on the binding of letrozole and resveratrol with serum albumin. Protein Pept. Lett. 2016;23:867–877.
  
  –
  
  PubMed
1. Chen W., Zheng R., Zhang S., Zeng H., Xia C., Zuo T., Yang Z., Zou X., He J. Cancer incidence and mortality in China, 2013. Cancer Lett. 2017;401:63–71.
  
  –
  
  PubMed

[ad_2]

Source link

Queensland pilot brings artificial intelligence to people in assisted living

Posted on 25/12/2022 by ScienceFatherLeave a Comment

[ad_1]

Can AI help people living with chronic illness?

Two Queensland universities have teamed up with a tech start-up to see how “care bots” can improve the lives of people who need high-level care.

The technology responds to sounds, eye movements and gestures, and can flag seizures, fevers and falls.

Russell Conyar is unable to speak after two strokes, and also has epilepsy.

He and his partner Karen Caddis have been together since 2007. He proposed just months before his first stroke, in 2013.

a man in a blue shirt and sunglasses sits in a wheelchair with his partner leaning in, smiling beside him — Russell and Karen in 2014, a year after his first stroke. (Supplied: Karen Caddies)

They joined the pilot, run by QUT, the University of Queensland and Brisbane-based start-up Ariel Care, hoping to make their lives “easier and safer”.

Mr Conyar needs 24-hour care and knowing what he wants is like a “guessing game”, Ms Caddis said.

“Sometimes it is like a competition. What does he want? Does he need a drink? Or the hoist to go to the toilet? He can’t verbally tell us.”

The trial focuses on people with acquired brain injuries and disabilities that require assisted living.

Mr Conyar uses a Brisbane-developed smart bed with sensors that provide a “halo-like safety net”.

A ceiling mount can detect fevers, choking, falls, moisture, seizures or elevated heart rate.

A new language

It is the eye-sensor technology that Ms Caddis is most excited about.

While it has been used in gaming, developers Ariel Care say they are creating a “new language” with algorithms that let people use an eye movement or gesture to send a message to their carer’s mobile phone or computer.

“If I am outside talking and he wants a drink, he can access the monitor with his eye and I know ‘OK, Russ wants a drink’,” Ms Caddis said.

“Instead of him screaming out, at the top of his voice, as he does sometimes, but we can’t understand what he wants.”

Close up of Russell Conyar's face. — AI systems allow Russell to communicate what he needs.(ABC News: Stephen Cavenagh)

The 61-year-old now lives in a joint care home in Ipswich, west of Brisbane. Ms Caddis comes every day and carers are on duty when she is not there.

“At least now I can go home now and know the carers who may be dealing with other residents will know if Russ has a seizure,” Ms Caddis said.

“Because when he was having seizures a lot earlier this year, the carers had to put a bed here, so they could keep an eye on him.”

Professor Mark Harvey, vice-president of QUT business development, said the trial was “revolutionary”.

“It is bringing together that high-tech into a home environment for high-need people,” he said.

“So very much re-creating the level of care that you would have in an intensive care facility in a hospital, bringing that together at home.”

Example of AI technology in assisted care setting, showing what can be detected and an example of a message sent to a phone app — Example of AI technology in assisted care setting.(Supplied: Ariel Care)

One in 10 Australians (2.65 million people) provided informal care in 2018, according to the Australian Bureau of Statistics.

Carers experience significantly higher levels of psychological distress than average Australians, and are two-and-a-half times more likely to report low wellbeing, a 2021 carers survey found.

Professor Harvey said the technology would make caring easier.

“I think it will be a huge release of burden to those high-care carers and loved ones,” he said.

“Also we just do not have the workforce in Australia and globally to have that type of care that people really need at the moment.”

man in suit smiling at camera sitting at a desk beside another man in a navy polo-tshirt — Co-director Mark Xavier (left) and QUT Avionics engineer graduate Joshua Romero. The team is writing “care bot” programs for everyone in the trial. (ABC: Lexy Hamilton-Smith)

Co-developer Mark Xavier is an aerospace specialist.

He and QUT avionics graduates are writing bespoke “care bot” programs for everyone in the trial.

“While some of it will be off-the-shelf, the engineers have been able to effectively interpret what we want and turn that into tech for each individual case,” he said.

“We have to remember that certain people have different cognitive levels and we need to provide as much support as we can across that group.”

Karen Caddis and Russell Conyar kissing while he lays in his hospital bed — Russell proposed to his fiancee Karen months before his first stroke.(ABC News: Stephen Cavenagh)

One program will not work for everyone, and people’s needs also change as they grow older, or their conditions progress, he said.

“The right collection of sensors, working within an online platform the right way, with the right algorithms will enable an individual to do the things they could not do before,” he said.

“We believe it is a world-first integration of fit-for-purpose technology in a fit-for-purpose bricks-and-mortar house for disability care.”

High-tech homes

Co-director of the start-up David Beard hopes to create a model of “smart high-care homes” that detect falls, fever, if someone has stopped eating, or wet the bed.

man in pinstripe blue shirt smiles into the camera — Ariel Care co-director David Beard says our homes have not kept up with changes in technology.(ABC News: Lexy Hamilton-Smith )

A smart home could let someone close their blinds with a blink, set their air con with a gaze, or, if they are unable to leave their bed, see who is at the door and let them in.

“There is a lot of things technology can do and really homes have not kept up with the age,” Mr Beard said.

“If you look at how far phones have come in the last 10 years, look how far cars have come in the last 10 years, and you have a look at homes … they really have not gone too far when it comes to assisted living.”

Compassionate computing

University of Queensland computer science expert Dhaval Vyas is focused on “human-centred computing”.

He has set up a “compassion lab” that develops technologies for under-served communities, to bring about social change and improve health and wellbeing.

“Rather than bringing the technology, first we ask what people want and design the technology to suit their needs,” Dr Vyas said.

“While the developers have an initial idea round what should care look like from an AI perspective, we reach out to the patients and carers, look around the house and see what technology they have, and assess how AI can fit into this particular space.

“We do not want to do anything where they feel I have a camera on my ceiling, we need to look at the fine line of having this technology in their homes.”

The project is seeking more people living with chronic health conditions, families and high-care NDIS providers to join the trial.

[ad_2]

Source link