To catch cancer earlier, we need to predict who is going to get it in the future. The complex nature of forecasting risk has been bolstered by artificial intelligence (AI) tools, but the adoption of AI in medicine has been limited by poor performance on new patient populations and neglect to racial minorities.

Two years ago, a team of scientists from MITs Computer Science and Artificial Intelligence Laboratory (CSAIL) and Jameel Clinic (J-Clinic) demonstrated a deep learning system to predict cancer risk using just a patients mammogram. The model showed significant promise and even improved inclusivity: It was equally accurate for both white and Black women, which is especially important given that Black women are 43 percent more likely to die from breast cancer.

But to integrate image-based risk models into clinical care and make them widely available, the researchers say the models needed both algorithmic improvements and large-scale validation across several hospitals to prove their robustness.

To that end, they tailored their new Mirai algorithm to capture the unique requirements of risk modeling. Mirai jointly models a patients risk across multiple future time points, and can optionally benefit from clinical risk factors such as age or family history, if they are available. The algorithm is also designed to produce predictions that are consistent across minor variances in clinical environments, like the choice of mammography machine.

The team trained Mirai on the same dataset of over 200,000 exams from Massachusetts General Hospital (MGH) from their prior work, and validated it on test sets from MGH, the Karolinska Institute in Sweden, and Chang Gung Memorial Hospital in Taiwan. Mirai is now installed at MGH, and the teams collaborators are actively working on integrating the model into care.

Mirai was significantly more accurate than prior methods in predicting cancer risk and identifying high-risk groups across all three datasets. When comparing high-risk cohorts on the MGH test set, the team found that their model identified nearly two times more future cancer diagnoses compared the current clinical standard, the Tyrer-Cuzick model. Mirai was similarly accurate across patients of different races, age groups, and breast density categories in the MGH test set, and across different cancer subtypes in the Karolinska test set.

Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection, and less screening harm than existing guidelines, says Adam Yala, CSAIL PhD student and lead author on a paper about Mirai that was published this week in Science Translational Medicine. Our goal is to make these advances part of the standard of care. We are partnering with clinicians from Novant Health in North Carolina, Emory in Georgia, Maccabi in Israel, TecSalud in Mexico, Apollo in India, and Barretos in Brazil to further validate the model on diverse populations and study how to best clinically implement it.

How it works

Despite the wide adoption of breast cancer screening, the researchers say the practice is riddled with controversy: More-aggressive screening strategies aim to maximize the benefits of early detection, whereas less-frequent screenings aim to reduce false positives, anxiety, and costs for those who will never even develop breast cancer.

Current clinical guidelines use risk models to determine which patients should be recommended for supplemental imaging and MRI. Some guidelines use risk models with just age to determine if, and how often, a woman should get screened; others combine multiple factors related to age, hormones, genetics, and breast density to determine further testing. Despite decades of effort, the accuracy of risk models used in clinical practice remains modest.

Recently, deep learning mammography-based risk models have shown promising performance. To bring this technology to the clinic, the team identified three innovations they believe are critical for risk modeling: jointly modeling time, the optional use of non-image risk factors, and methods to ensure consistent performance across clinical settings.

1. Time

Inherent to risk modeling is learning from patients with different amounts of follow-up, and assessing risk at different time points: this can determine how often they get screened, whether they should have supplemental imaging, or even consider preventive treatments.

Although its possible to train separate models to assess risk for each time point, this approach can result in risk assessments that dont make sense like predicting that a patient has a higher risk of developing cancer within two years than they do within five years. To address this, the team designed their model to predict risk at all time points simultaneously, by using a tool called an additive-hazard layer.

The additive-hazard layer works as follows: Their network predicts a patients risk at a time point, such as five years, as an extension of their risk at the previous time point, such as four years. In doing so, their model can learn from data with variable amounts of follow-up, and then produce self-consistent risk assessments.

2. Non-image risk factors

While this method primarily focuses on mammograms, the team wanted to also use non-image risk factors such as age and hormonal factors if they were available but not require them at the time of the test. One approach would be to add these factors as an input to the model with the image, but this design would prevent the majority of hospitals (such as Karolinska and CGMH), which dont have this infrastructure, from using the model.

For Mirai to benefit from risk factors without requiring them, the network predicts that information at training time, and if it's not there, it can use its own predictive version. Mammograms are rich sources of health information, and so many traditional risk factors such as age and menopausal status can be easily predicted from their imaging. As a result of this design, the same model could be used by any clinic globally, and if they have that additional information, they can use it.

3. Consistent performance across clinical environments

To incorporate deep-learning risk models into clinical guidelines, the models must perform consistently across diverse clinical environments, and its predictions cannot be affected by minor variations like which machine the mammogram was taken on. Even across a single hospital, the scientists found that standard training did not produce consistent predictions before and after a change in mammography machines, as the algorithm could learn to rely on different cues specific to the environment. To de-bias the model, the team used an adversarial scheme where the model specifically learns mammogram representations that are invariant to the source clinical environment, to produce consistent predictions.

To further test these updates across diverse clinical settings, the scientists evaluated Mirai on new test sets from Karolinska in Sweden and Chang Gung Memorial Hospital in Taiwan, and found it obtained consistent performance. The team also analyzed the models performance across races, ages, and breast density categories in the MGH test set, and across cancer subtypes on the Karolinska dataset, and found it performed similarly across all subgroups.

African-American women continue to present with breast cancer at younger ages, and often at later stages, says Salewai Oseni, a breast surgeon at Massachusetts General Hospital who was not involved with the work. This, coupled with the higher instance of triple-negative breast cancer in this group, has resulted in increased breast cancer mortality. This study demonstrates the development of a risk model whose prediction has notable accuracy across race. The opportunity for its use clinically is high.

Here's how Mirai works:

1. The mammogram image is put through something called an "image encoder."

2. Each image representation, as well as which view it came from, is aggregated with other images from other views to obtain a representation of the entire mammogram.

3. With the mammogram, a patient's traditional risk factors are predicted using a Tyrer-Cuzick model (age, weight, hormonal factors). If unavailable, predicted values are used.

4. With this information, the additive-hazard layer predicts a patients risk for each year over the next five years.

Improving Mirai

Although the current model doesnt look at any of the patients previous imaging results, changes in imaging over time contain a wealth of information. In the future the team aims to create methods that can effectively utilize a patient's full imaging history.

In a similar fashion, the team notes that the model could be further improved by utilizing tomosynthesis, an X-ray technique for screening asymptomatic cancer patients. Beyond improving accuracy, additional research is required to determine how to adapt image-based risk models to different mammography devices with limited data.

We know MRI can catch cancers earlier than mammography, and that earlier detection improves patient outcomes, says Yala. But for patients at low risk of cancer, the risk of false-positives can outweigh the benefits. With improved risk models, we can design more nuanced risk-screening guidelines that offer more sensitive screening, like MRI, to patients who will develop cancer, to get better outcomes while reducing unnecessary screening and over-treatment for the rest.

Were both excited and humbled to ask the question if this AI system will work for African-American populations, says Judy Gichoya, MD, MS and assistant professor of interventional radiology and informatics at Emory University, who was not involved with the work. Were extensively studying this question, and how to detect failure.

Yala wrote the paper on Mirai alongside MIT research specialist Peter G. Mikhael, radiologist Fredrik Strand of Karolinska University Hospital, Gigin Lin of Chang Gung Memorial Hospital, Associate Professor Kevin Smith of KTH Royal Institute of Technology, Professor Yung-Liang Wan of Chang Gung University, Leslie Lamb of MGH, Kevin Hughes of MGH, senior author and Harvard Medical School Professor Constance Lehman of MGH, and senior author and MIT Professor Regina Barzilay.

The work was supported by grants from Susan G Komen, Breast Cancer Research Foundation, Quanta Computing, and the MIT Jameel Clinic. It was also supported by Chang Gung Medical Foundation Grant, and by Stockholm Lns Landsting HMT Grant.

See more here:
Robust artificial intelligence tools to predict future cancer - MIT News

By Opinion 1h ago

Share this article:

Looking back, 2020 and the Covid-19 pandemic has been extremely difficult and disruptive to business and our personal lives.

However, 2020 was not only deleterious at least not with regard to technology. In many technology fields progress has accelerated significantly. Two of these areas are artificial intelligence (AI) and robotics, which will play a prominent role in 2021 and following years.

Ubiquitous AI

Over the last few years AI has grown in importance in a wide variety of fields such as healthcare, bioscience, education, transport, marketing, finance, cybersecurity and many more. We are increasingly surrounded by AI, which will further proliferate in 2021.

During the Covid-19 pandemic AI played an important role in finding a solution to the Covid-19 virus by elucidating unexplored viral pathways. Machine learning-based models, trained on specific biomolecules, have offered inexpensive and rapid implementation methods for the discovery of effective viral therapies. AI was also used in the quest for a suitable Covid-19 vaccine by helping researchers understand the virus and its structure, and by predicting which of its components will provoke an immune response.

But as AI tools become more powerful in the coming years, computational methods could help scientists solve our most difficult vaccine challenges, such as finding an effective HIV vaccine, or creating a flu vaccine that will last for multiple years.

AI enters video conferencing

An exciting new development is Nvidias Broadcast app and its Omniverse Machinima (an app that lets characters and voices come to life) that uses AI to significantly enhance the voice and video of regular video conferencing software - our lifeline while working from home.

People spending hours in virtual meetings will know that the background can be problematic, especially if there are more than one member of the family busy with video conferencing and you have to work from your bedroom or an untidy room. Nvidia uses Graphics Processing Unit or GPU-centric capabilities to provide virtual backgrounds, which entails technologies like AI greenscreen effects and deepfakes (synthetic media in which a person in an existing image of video is replaced with someone elses likeness) to give a more desirable and realistic virtual office than the very basic backgrounds currently available in video conferencing software.

In fact AI even has the ability to make you look younger and dress you virtually so that you appear more professional on the screen when working from home. People unfortunately judge us by our appearance and during the pandemic wrinkled clothing, a lack of makeup, partial beards, and uncut hair became quite common in virtual meetings.

With Nvidias Omniverse Machinima it is possible to create 3D scans of yourself dressed for business, and then use your camera to sync them with your body. Dynamic virtual clothing will advance in the years to come so that we could even be dressed in culturally correct ways for each country that we are having a meeting with.

The Qualcomm 8cx platform has a unique AI feature that adjusts your eyes in real time, so that it will appear to the remote audience that you are looking directly at them.

Another major problem with video conferencing is the constant background noise that led to the practice continually muting and unmuting the microphone. Nvidia, Qualcomm and Intel (Tiger Lake and Evo platforms) succeeded in eliminating background noise such as keyboard typing, microphone static, noisy computer fans, and thus the constant muting and unmuting.

Nvidia Broadcast also dynamically tracks your movements in real-time with Auto Frame, automatic cropping and zooming to keep the speaker in the centre of the picture. Unfortunately the NVIDIA virtual greenscreen technology is currently only available for machines with a NVIDIA GPU and the Windows operating system.

Really smart digital assistants

Digital assistants are becoming much more mature and increasingly integrate with office devices to provide a seamless service. Cisco expanded their intelligent Webex device portfolio with Webex Desk Hub to simplify hotdesking in the new hybrid work environment involving a combination of remote and on-site interactions. It is important for the worker to have seamless, smart experiences whether they are at home, in the office or somewhere in between. The Webex Desk Hub is wrapped with AI to provide a consistent experience to enable people to get their work done in a hybrid work environment.

Future digital assistants will be somewhat familiar to the familiar Alexa experience, except that the AI technologies are much more mature as in the case of IBMs Watson and would provide far more deeper insights and useful solutions to business challenges.

It would be much easier to find the person responsible for a specific issue when you need urgent approval or whom you should be collaborating with in a large organisation. The AI assistant could also keep you out of trouble by alerting you far more timely if you are doing anything against company policy or the law of a particular country.

AI health monitoring

Although many people may not realise it, the popular health monitors build into our smart phones and watches are driven by AI and advanced algorithms. I believe that in 2021 we will see important developments in health monitoring. The current heart and pulse, oxygen saturation and sleep monitors will become more accurate and reliable. Blood pressure and glucose monitoring will be added. And all our vital signs will be linked directly to healthcare monitoring services for faster medical assistance during emergencies.

Advanced prosthetics

We will see more embedded technology and advanced prosthetics such as brain interfaces. A team working to restore capacity to people with spinal injuries have recently released a video of the quadriplegic Robert Chmielewski feeding himself by manipulating a pair of advanced prosthetic arms using signals from his brain through an implanted brain-computer interface (BCI) and the help of AI.

Robots everywhere

It may be problematic to some, but we will increasingly be surrounded by robots the years to come. And if the Boston Dynamics robots are anything to go by, we are in for an interesting ride since the new generation of robots are becoming extremely capable.

Drones

Very significantly, towards the end of 2020 the USA Federal Aviation Authority (FAA) approved drone delivery, including flights during night time and over populated areas. Although drones represent the fastest-growing segment in the transportation sector in many countries, in South Africa we will probably see it in the future in rural areas where conventional deliveries are not economical. After successful tests during the Covid-19 pandemic the supermarket chain Walmart will soon start delivering groceries and health and wellness products by air in major USA cities.

Walmart further partnered with Quest Diagnostics and DroneUp for the delivery of collection kits to take a self-administered test for Covid-19 infection. Tissue and organ delivery services are also considering drone delivery services.

Autonomous vehicles

Autonomous or self-driving vehicles are very much in the news since many companies worldwide are experimenting with driverless cars and trucks. Autonomous vehicles will certainly change the face of the transportation industry in 2021. After successful trials since 2019 the state of California is one of the first to implement large automated delivery vehicles. After testing over 564000 kilometres and 4 million street crossings, Starship Technologies started in the middle of 2020 with the deployment of thousands of its six-wheeled delivery robots on university campuses to deliver food and other products.

Many more companies are focusing on autonomous delivery using automated minivans (e.g. Nuro), mini-robotic cars, or delivery robots. Automated delivery and robotaxis will soon be part of our everyday life, despite the fierce protest from unions.

But in South Africa self-driving trucks and delivery vehicles are in the distant future. The AI behind automated driving is based on the traffic rules, which is used to anticipate certain behaviour from other vehicles and to make decisions. Unfortunately, South African drivers, and in particular our mini taxi-buses, often do not follow the traffic rules. They pass on the yellow line on the left, drive through a red traffic light, do not stop at stop streets and do not keep to the speed limit. An AI-based automated vehicle thus find it difficult to drive in such an erratic environment.

Large-scale automation

Automation will not be limited to automated vehicles and drones, but will expand in 2021 to many industries. Covid-19 forced us to rethink the way we do business. Some restaurants and hotels over the world are therefore automating, since robots do not catch or spread viruses and can also operate 24/7 without demanding an increase in pay or leave.

The automated restaurant are blending industrial robots with food preparation and delivery. Especially in the fast food industry speed is important. Robots are therefore used to optimise some processes such as the burger flipper, Flippy, of White Castle in Chicago that manages both the grill and fryers. Currently many dough kneading and pizza-bots are being used and can turn out 120 pizzas per hour.

In the USA Dominos used a DOM Pizza Checker an AI-powered imaging technology to limit customers complaints by checking if it is the correct pizza and toppings and if it is evenly distributed.

Automation could address two major problems - overcoming the shortage of reliable restaurant staff experienced in many countries and helping to keep restaurants and fast-food outlets open during a pandemic.

2021 a fascinating year

It is apparent that AI and robotic technologies are maturing, becoming more powerful and can add tremendous value to business. But 2021 may see many more innovative technologies such as flying cars, suits and motorcycles. Two startups, JetPack Aviation and Gravity Industries, are both focusing on vertical take-off and landing (VTOL) and human propulsion. Gravity Industries has developed a real-life Iron Man flying suit while JetAviation is prototyping the Speeder, a fully stabilized flying autonomous motorcycle that can fly one or two individuals at over 400 km/h and the JB12 personal aerial Jetpack used by the US Navy Special Forces for short-distance troop transportation. However, besides military and paramedic use, these technologies will take time to mature into the mainstream commercial market.

Despite a difficult start due to the second Covid-19 wave, technology-wise 2021 will be a fascinating year. South Africa may unfortunately in some cases have to wait a bit longer for some of these technologies.

Prof Louis C H Fourie is a Technology Strategist

BUSINESS REPORT

Read the rest here:
Tech News: 2021 the year of artificial intelligence and robots - IOL

(The Center Square) The California Department of Motor Vehicles has officially issued a permit to Baidu USA to begin testing driverless vehicles on public roads in Sunnyvale, California.

According to the state Department of Motor Vehicles (DMV), as of January 27, 2021, the agency has issued Autonomous Vehicle Driverless Testing Permits to six companies: Autox Technologies, Baidu, Cruise, Nuro, Waymo and Zoox.

It announced in a news release that "while Baidu has had state authority to test autonomous vehicles with safety drivers since 2016, the new permit allows the company to test three autonomous vehicles without a driver behind the wheel on specified streets within Sunnyvale, located in Santa Clara County."

According to the DMV, Baidu's vehicles "are designed to operate on roads with posted speed limits not exceeding 45 miles per hour."

Companies are allowed to test their driverless cars at any time during the day or night and are prohibited from operating the cars during "heavy fog or rain."

In order to qualify for a driverless testing permit, a company must meet certain guidelines, including proving that it has insurance or a bond equal to $5 million. A company must also verify that the vehicles it tests are capable of operating without a driver and have been tested under controlled conditions that simulate the planned area of operation.

With no one inside the car driving, the cars must still meet federal Motor Vehicle Safety Standards or have an exemption from the National Highway Traffic Safety Administration, and be at a SAE Level 4 or 5.

Driverless cars operate through an artificial intelligence system designed to sense surroundings, process visual data to avoid collisions, operate the steering and brake, and use GPS tracking.

Companies like Googles Waymo have put AI inside virtual cars and have the vehicles 'drive' billions of virtual miles, throwing every perceivable obstacle and situation at the cars to see how they respond, Tech Radar reports.

Nearly every major car manufacturer, ride-sharing service and tech company from Apple to Google has bought into the driverless car industry, it adds.

Google wants to have a self-driving ride-hailing service on the road by the end of this year. Apple self-driving cars, meanwhile, are spotted regularly, driving down the road with rigs housing everything that's needed to run a self-driving experience.

Californias Autonomous Vehicle Tester Program was created in 2014 "to allow manufacturers to test autonomous vehicles with a human in the driver seat." In 2018, the DMV established the Autonomous Vehicle Driverless Tester Program for manufacturers to test their technology without a driver.

According to the DMV, local governments must be notified of planned testing in their respective areas when the cars will be driving.

Companies are also required to develop a Law Enforcement Interaction Plan to provide information to law enforcement and other first responders on how to interact with driverless test vehicles.

"Driverless testing permit holders must also report to the DMV any collisions involving a driverless test vehicle within 10 days and submit an annual report of disengagements," the release states.

In 2018, after a fatal accident in Tempe, Arizona, the ridesharing company Uber suspended all self-driving car tests on public roads in North America.

In 2016, the National Transportation Safety Board investigated a fatal Tesla Autopilot crash in Florida to determine if the automaker was at fault. It determined that the Tesla driver's "inattention due to overreliance on vehicle automation" was partially responsible for the crash and suggested safety recommendations.

Tesla is not participating in Californias autonomous driverless program.

Read more:
California to license driverless cars operated by Artificial Intelligence - The Center Square

New York, Jan. 29, 2021 (GLOBE NEWSWIRE) -- Reportlinker.com announces the release of the report "Artificial Intelligence in Cybersecurity Market Research Report by Function, by Type, by Technology, by Industry, by Deployment - Global Forecast to 2025 - Cumulative Impact of COVID-19" - https://www.reportlinker.com/p06015709/?utm_source=GNW

Market Statistics:The report provides market sizing and forecast across five major currencies - USD, EUR GBP, JPY, and AUD. This helps organization leaders make better decisions when currency exchange data is readily available.

1. The Global Artificial Intelligence in Cybersecurity Market is expected to grow from USD 9,246.79 Million in 2020 to USD 25,354.64 Million by the end of 2025.2. The Global Artificial Intelligence in Cybersecurity Market is expected to grow from EUR 8,107.76 Million in 2020 to EUR 22,231.43 Million by the end of 2025.3. The Global Artificial Intelligence in Cybersecurity Market is expected to grow from GBP 7,207.81 Million in 2020 to GBP 19,763.78 Million by the end of 2025.4. The Global Artificial Intelligence in Cybersecurity Market is expected to grow from JPY 986,866.80 Million in 2020 to JPY 2,705,982.57 Million by the end of 2025.5. The Global Artificial Intelligence in Cybersecurity Market is expected to grow from AUD 13,427.56 Million in 2020 to AUD 36,818.30 Million by the end of 2025.

Market Segmentation & Coverage:This research report categorizes the Artificial Intelligence in Cybersecurity to forecast the revenues and analyze the trends in each of the following sub-markets:

Based on Function, the Artificial Intelligence in Cybersecurity Market studied across Advanced Threat Detection, Data Loss Prevention, Encryption, Identity and Access Management, Intrusion Detection/Prevention Systems, Proactive Defense and Threat Mitigation, and Risk and Compliance Management.

Based on Type, the Artificial Intelligence in Cybersecurity Market studied across Application Security, Cloud Security, Endpoint Security, and Network Security.

Based on Technology, the Artificial Intelligence in Cybersecurity Market studied across Context Awareness Computing, Machine Learning, and Natural Language Processing. The Machine Learning further studied across Deep Learning, Reinforcement Learning, Supervised Learning, and Unsupervised Learning.

Based on Industry, the Artificial Intelligence in Cybersecurity Market studied across Aerospace & Defense, Automotive & Transportation, Banking, Financial Services & Insurance, Building, Construction & Real Estate, Consumer Goods & Retail, Education, Energy & Utilities, Government & Public Sector, Healthcare & Life Sciences, Information Technology, Manufacturing, Media & Entertainment, Telecommunication, and Travel & Hospitality.

Based on Deployment, the Artificial Intelligence in Cybersecurity Market studied across On-Cloud and On-Premises.

Based on Geography, the Artificial Intelligence in Cybersecurity Market studied across Americas, Asia-Pacific, and Europe, Middle East & Africa. The Americas region surveyed across Argentina, Brazil, Canada, Mexico, and United States. The Asia-Pacific region surveyed across Australia, China, India, Indonesia, Japan, Malaysia, Philippines, South Korea, and Thailand. The Europe, Middle East & Africa region surveyed across France, Germany, Italy, Netherlands, Qatar, Russia, Saudi Arabia, South Africa, Spain, United Arab Emirates, and United Kingdom.

Company Usability Profiles:The report deeply explores the recent significant developments by the leading vendors and innovation profiles in the Global Artificial Intelligence in Cybersecurity Market including Acalvio Technologies, Inc., Amazon.com, Inc., Argus Cyber Security, Bitsight Technologies, Cylance, Inc., Darktrace Limited, Deep Instinct, Feedzai S.A., Fortscale Security, Inc., High-Tech Bridge, Indegy Ltd., Intel Corporation, International Business Machines Corp., Micron Technology, Inc., Nozomi Networks, NVIDIA Corporation, Samsung Electronics Co., Ltd., Securonix, Inc., Sentinelone Inc., Sift Science Inc., Skycure Ltd., SparkCognition Inc., Threatmetrix, inc., Vectra Networks, Xilinx, Inc., and Zimperium, Inc..

Cumulative Impact of COVID-19:COVID-19 is an incomparable global public health emergency that has affected almost every industry, so for and, the long-term effects projected to impact the industry growth during the forecast period. Our ongoing research amplifies our research framework to ensure the inclusion of underlaying COVID-19 issues and potential paths forward. The report is delivering insights on COVID-19 considering the changes in consumer behavior and demand, purchasing patterns, re-routing of the supply chain, dynamics of current market forces, and the significant interventions of governments. The updated study provides insights, analysis, estimations, and forecast, considering the COVID-19 impact on the market.

360iResearch FPNV Positioning Matrix:The 360iResearch FPNV Positioning Matrix evaluates and categorizes the vendors in the Artificial Intelligence in Cybersecurity Market on the basis of Business Strategy (Business Growth, Industry Coverage, Financial Viability, and Channel Support) and Product Satisfaction (Value for Money, Ease of Use, Product Features, and Customer Support) that aids businesses in better decision making and understanding the competitive landscape.

360iResearch Competitive Strategic Window:The 360iResearch Competitive Strategic Window analyses the competitive landscape in terms of markets, applications, and geographies. The 360iResearch Competitive Strategic Window helps the vendor define an alignment or fit between their capabilities and opportunities for future growth prospects. During a forecast period, it defines the optimal or favorable fit for the vendors to adopt successive merger and acquisition strategies, geography expansion, research & development, and new product introduction strategies to execute further business expansion and growth.

The report provides insights on the following pointers:1. Market Penetration: Provides comprehensive information on the market offered by the key players2. Market Development: Provides in-depth information about lucrative emerging markets and analyzes the markets3. Market Diversification: Provides detailed information about new product launches, untapped geographies, recent developments, and investments4. Competitive Assessment & Intelligence: Provides an exhaustive assessment of market shares, strategies, products, and manufacturing capabilities of the leading players5. Product Development & Innovation: Provides intelligent insights on future technologies, R&D activities, and new product developments

The report answers questions such as:1. What is the market size and forecast of the Global Artificial Intelligence in Cybersecurity Market?2. What are the inhibiting factors and impact of COVID-19 shaping the Global Artificial Intelligence in Cybersecurity Market during the forecast period?3. Which are the products/segments/applications/areas to invest in over the forecast period in the Global Artificial Intelligence in Cybersecurity Market?4. What is the competitive strategic window for opportunities in the Global Artificial Intelligence in Cybersecurity Market?5. What are the technology trends and regulatory frameworks in the Global Artificial Intelligence in Cybersecurity Market?6. What are the modes and strategic moves considered suitable for entering the Global Artificial Intelligence in Cybersecurity Market?Read the full report: https://www.reportlinker.com/p06015709/?utm_source=GNW

About ReportlinkerReportLinker is an award-winning market research solution. Reportlinker finds and organizes the latest industry data so you get all the market research you need - instantly, in one place.

__________________________

Go here to read the rest:
Artificial Intelligence in Cybersecurity Market Research Report by Function, by Type, by Technology, by Industry, by Deployment - Global Forecast to...

DUBLIN--(BUSINESS WIRE)--The "Artificial Intelligence in Epidemiology Market by AI Type, Infrastructure, Deployment Model, and Services 2021 - 2026" report has been added to ResearchAndMarkets.com's offering.

This global AI epidemiology and public health market report provides a comprehensive evaluation of the positive impact that AI technology will produce with respect to healthcare informatics, and public healthcare management, and epidemiology analysis and response. The report assesses the macro factors affecting the market and the resulting need for hardware and software technology used in the public healthcare and epidemiology informatics.

The macro factors include the growth drivers and challenges of the market along with the potential application and usage areas in public health industry verticals. The report also provides the anticipated market value of AI in the public health and epidemiology informatics market globally and regionally. This includes core technology and AI-specific technologies. Market forecasts cover the period of 2021 - 2026.

The Center for Disease Control and Prevention sees epidemiology as the study and analysis of the distribution, patterns and determinants of health and disease conditions in defined populations. It is a cornerstone of public health and shapes policy decisions and evidence-based practice by identifying risk factors for disease and targets for preventive healthcare.

This includes identification of the factors involved with diseases transmitted by food and water, acquired during travel or recreational activities, bloodborne and sexually transmitted diseases, and nosocomial infections such as hospital-acquired illnesses. Epidemiology is also concerned with the identification of trends and predictive capabilities to prevent diseases.

Sources of disease data include medical claims data (commercial claims, Medicare), electronic healthcare records (EHR) including medical treatment facilities and pharmacies, death registries and socioeconomic data. It is important to note that some data is highly structured whereas other data elements are highly unstructured, such as data gathered from social media and Web scraping.

Artificial Intelligence (AI) will increasingly be relied upon to improve the efficiency and effectiveness of transforming data correlation to meaningful insights and information. For example, machine learning has been used to gather Web search and location data as a means of identifying potential unsafe areas, such as restaurants involved in food-borne illnesses.

The combination of data aggregation from multiple sources with machine learning and advanced analytics will greatly improve the efficacy of epidemiology predictive models. For example, machine learning allows epidemiologists to evaluate as many variables as desired without increasing statistical error, a problem that often arises with multiple testing bias, which is a condition that occurs when each additional test run on the data increases the possibility for error against a hypothetical target result.

Another example of AI in epidemiology is the use of natural language processing to capture clinical notes for preservation in EHR databases. As part of data capture and identification of most important information, AI will also be used to validate key terms to identify conditions, diagnoses and exposures that are otherwise difficult to capture/identify through traditional data source mining. This will be used for data discovery and validation as well as knowledge representation.

An extremely important and high growth area for AI in epidemiology is drug discovery, safety, and risk analysis, which we anticipate will be a $699 million global market by 2026. Other high opportunity areas for AI are disease and syndromic surveillance, infection prediction and forecasting, monitoring population and incidence of disease, and use of AI in Immunization Information Systems (IIS). In addition to mapping vaccinations to disease incidence, the IIS will leverage AI to identify the impact of public sentiment analysis and for public safety services such as mass notification.

Select Report Findings:

Report Benefits:

Key Topics Covered:

1.0 Executive Summary

2.0 Introduction

3.0 Technology and Application Analysis

4.0 Company Analysis

5.0 Market Analysis and Forecasts 2021 - 2026

6.0 Conclusions and Recommendations

Companies Mentioned

For more information about this report visit https://www.researchandmarkets.com/r/bwvnfe

See more here:
Artificial Intelligence in Epidemiology Market by AI Type, Infrastructure, Deployment Model, and Services - Global Forecast to 2026 -...

Increasing adoption of new technologies is transforming the industry's business model from product-based solutions to leak management as a service (LMaaS), finds Frost & Sullivan

SANTA CLARA, Calif., Jan. 28, 2021 /PRNewswire/ -- Frost & Sullivan's recent analysis, Data Analytics and AI Boost Accuracy to Drive Global Smart Water and Wastewater Leak Detection Solutions Market, finds that the wastewater leak detection market has witnessed a significant rate of innovation and digital transformation. Internet of Things (IoT) sensors, machine learning (ML), artificial intelligence (AI), and cloud- or edge-based data analytics platforms are boosting the market. By 2026, the market is estimated to garner a revenue of $1.99 billion from $1.23 billion in 2020, up at a compound annual growth rate (CAGR) of 8.4%.

Photo - https://mma.prnewswire.com/media/1428835/smart_water.jpg

For further information on this analysis, please visit: http://frost.ly/54b

"The high rate of urbanization in most developing countries has increased the pressure on existing water and wastewater infrastructure, which has pushed the demand for leak detection solutions, partly to improve asset efficiency and partly to meet water conservation goals," said Paul Hudson, Energy & Environment Research Analyst at Frost & Sullivan. "To tap into this growth prospect, leak detection solution providers should integrate their technologies and customize services to meet customers' demands and exploit investments made for the development of Smart Cities and resilient infrastructure."

Hudson added: "The increasing adoption of cloud-based data analytics, ML and AI is transforming the industry's business model from product-based solutions to leak detection services. Further, utilities' emphasis on a 'one-stop solution provider' for leak detection in both their water and wastewater networks is encouraging solution providers to embrace new business models such as technology-as-a-service (TaaS) and leak (or non-revenue water (NRW)) management-as-a-service (LMaaS). TaaS enables service providers to fully control and strategically expand and enhance their technology offerings, whereas LMaaS could help focus on the growth and market penetration of smart solutions such as continual leak monitoring and proactive prevention."

The move toward a circular economy and holistic sustainability will present immense growth opportunities for market participants, varying considerably depending on the region:

Data Analytics and AI Boost Accuracy to Drive Global Smart Water and Wastewater Leak Detection Solutions Market is part of Frost & Sullivan's Global Energy and Environment Growth Partnership Service program.

About Frost & Sullivan

For six decades, Frost & Sullivan has been world-renowned for its role in helping investors, corporate leaders and governments navigate economic changes and identify disruptive technologies, Mega Trends, new business models, and companies to action, resulting in a continuous flow of growth opportunities to drive future success.Contact us: Start the discussion

Data Analytics and AI Boost Accuracy to Drive Global Smart Water and Wastewater Leak Detection Solutions Market

MF9F-15

Contact:

Srihari Daivanayagam, Corporate CommunicationsM: +91 9742676194; P: +91 44 6681 4412E: [emailprotected]http://ww2.frost.com

http://www.frost.com

SOURCE Frost & Sullivan

Read the original here:
Data Analytics and Artificial Intelligence to Propel Smart Water and Wastewater Leak Detection Solutions Market - PR Newswire India

Artificial intelligence has been making waves in recent years, enabling us to solve problems faster than traditional computing could ever allow. Recently, for example, Googles artificial intelligence subsidiary DeepMind developed AlphaFold2, a program which solved the protein-folding problem. This is a problem which has had baffled scientists for 50 years.

Advances in AI have allowed us to make progress in all kinds of disciplines and these are not limited to applications on this planet. From designing missions to clearing Earths orbit of junk, here are a few ways artificial intelligence can help us venture further in space.

Do you remember Tars and Case, the assistant robots from the film Interstellar? While these robots dont exist yet for real space missions, researchers are working towards something similar, creating intelligent assistants to help astronauts. These AI-based assistants, even though they may not look as fancy as those in the movies, could be incredibly useful to space exploration.

A recently developed virtual assistant can potentially detect any dangers in lengthy space missions such as changes in the spacecraft atmosphere for example increased carbon dioxide or a sensor malfunction that could be potentially harmful. It would then alert the crew with suggestions for inspection.

An AI assistant called Cimon was flown to the international space station (ISS) in December 2019, where it is being tested for three years. Eventually, Cimon will be used to reduce astronauts stress by performing tasks they ask it to do. NASA is also developing a companion for astronauts aboard the ISS, called Robonaut, which will work alongside the astronauts or take on tasks that are too risky for them.

Read more: Astronauts are experts in isolation, here's whatthey can teach us

Planning a mission to Mars is not an easy task, but artificial intelligence can make it easier. New space missions traditionally rely on knowledge gathered by previous studies. However, this information can often be limited or not fully accessible.

This means the technical information flow is constrained by who can access and share it among other mission design engineers. But what if all the information from practically all previous space missions were available to anyone with authority in just a few clicks. One day there may be a smarter system similar to Wikipedia, but with artificial intelligence that can answer complex queries with reliable and relevant information to help with early design and planning of new space missions.

Researchers are working on the idea of a design engineering assistant to reduce the time required for initial mission design which otherwise takes many human work hours. Daphne is another example of an intelligent assistant for designing Earth observation satellite systems. Daphne is used by systems engineers in satellite design teams. It makes their job easier by providing access to relevant information including feedback as well as answers to specific queries.

Earth observation satellites generate tremendous amounts of data. This is received by ground stations in chunks over a large period of time, and has to be pieced together before it can be analysed. While there have been some crowdsourcing projects to do basic satellite imagery analysis on a very small scale, artificial intelligence can come to our rescue for detailed satellite data analysis.

For the sheer volume of data received, AI has been very effective in processing it smartly. Its been used to estimate heat storage in urban areas and to combine meteorological data with satellite imagery for wind speed estimation. AI has also helped with solar radiation estimation using geostationary satellite data, among many other applications.

AI for data processing can also be used for the satellites themselves. In recent research, scientists tested various AI techniques for a remote satellite health monitoring system. This is capable of analysing data received from satellites to detect any problems, predict satellite health performance and present a visualisation for informed decision making.

One of the biggest space challenges of the 21st century is how to tackle space debris. According to ESA, there are nearly 34,000 objects bigger than 10cm which pose serious threats to existing space infrastructure. There are some innovative approaches to deal with the menace, such as designing satellites to re-enter Earths atmosphere if they are deployed within the low Earth orbit region making them disintegrate completely in a controlled way.

Another approach is to avoid any possible collisions in space, preventing the creation of any debris. In a recent study, researchers developed a method to design collision avoidance manoeuvres using machine-learning (ML) techniques.

Another novel approach is to use the enormous computing power available on Earth to train ML models, transmit those models to the spacecraft already in orbit or on their way, and use them on board for various decisions. One way to ensure safety of space flights has recently been proposed using already trained networks on board the spacecraft. This allows more flexibility in satellite design while keeping the danger of in orbit collision at a minimum.

On Earth, we are used to tools such as Google Maps which use GPS or other navigation systems. But there is no such a system for other extraterrestrial bodies, for now.

We do not have any navigation satellites around the Moon or Mars but we could use the millions of images we have from observation satellites such as the Lunar Reconnaissance Orbiter (LRO). In 2018, a team of researchers from NASA in collaboration with Intel developed an intelligent navigation system using AI to explore the planets. They trained the model on the millions of photographs available from various missions and created a virtual Moon map.

As we carry on to explore the universe, we will continue to plan ambitious missions to satisfy our inherent curiosity as well as to improve the human lives on Earth. In our endeavours, artificial intelligence will help us both on Earth and in space make this exploration possible.

Read more:
Five ways artificial intelligence can help space exploration - The Conversation UK

Spurred by the demands of the COVID-19 pandemic, researchers at Princeton and Google are applying mechanical engineering and artificial intelligence to increase the availability and effectiveness of ventilation treatments worldwide.

Ventilators and their support equipment are expensive and complex devices that require expert attention from doctors and other highly trained medical workers. The devices must be carefully calibrated and monitored to ensure they are meeting a range of parameters pressure, volume, breath rate tuned to each individual patient. Often, these measures change during treatment, requiring further tuning.

If that monitoring and adjustment is handled by artificial intelligence, it could ease the burden on medical workers and allow ventilators to be deployed in areas with staffing shortages. That was the logic that led Elad Hazan, a professor of computer science and director of Google AI Princeton, and Daniel Cohen, an assistant professor of mechanical and aerospace engineering, to launch the project.

Graduate student Daniel Suo and senior Paula Gradu are part of a team of researchers using AI to improve the way ventilators assist patients.

Photo by

Aaron Nathans, Office of Engineering Communications

Modern ventilators seek to maximize clinical outcomes while at the same time protecting patients from excessive levels of pressure and volume, said Daniel Notterman, a board certified pediatric intensive care physician with experience managing patients with respiratory failure, who is also a lecturer with the rank of professor in molecular biology. Although conceptually simple, the regulation of ventilator performance is extremely complex. This effort provided the opportunity for experts in programming, engineering and clinical medicine to rethink many of the usual solutions, under the leadership of Professor Cohen.

Since the initial COVID-19 outbreak last spring, Cohens team had been working to design low-cost ventilators using readily available parts. Initially, Cohen met with Hazan to discuss a control system for the new design. But the researchers realized that artificial intelligence could improve controls for all ventilators, not just the type designed at Princeton.

The hypothesis is that applying AI tools can make systems more robust and safer, Hazan said.

Access to Cohens ventilator has been critical, Hazan said. The physics underlying breathing is complex, and breaking the fluid dynamics down into working equations is generally impractical and inaccurate. So instead of approaching the control problem through the physics of the lungs, the researchers ran experiments on the Cohen teams ventilators and applied machine learning to uncover patterns in the data that would guide the safe and effective operation of the ventilator.

Tom Zajdel, a post doctoral researcher, was part of the team that designed and built a new ventilator at Princeton. The open-source design uses readily available parts.

The development of the ventilator began as part of an effort by Cohen and Notterman to design a new system that was inexpensive and could be assembled from off-the-shelf parts.

It basically goes together like Legos, said Julienne LaChance, a graduate student in Cohens lab who led the prototype construction efforts from her garage. I picture my high school robotics team putting this together.

The ventilator is now fully built and meets key FDA performance standards, while costing less than $1,500 a tenth or twentieth the price of commercial ventilators, Cohen said. The team is now actively seeking manufacturing partners to help push for regulatory approval, especially in less affluent countries in need of ventilators.

We have been using robust, simple parts that we put together with a lot of very well done software and coding, said Cohen. We are trying to develop a generalized platform that anyone can work with, or improve upon, anywhere in the world, even after the pandemic.

Researchers from Hazans lab include senior Paula Gradu; graduate studentsXinyi Chen, Udaya Ghai, Edgar Minasyan,Karan SinghandDaniel Suo; and recent Ph.D. graduatesNaman AgarwalandCyril Zhang. In addition to LaChance, Notterman and Cohen, the local Princeton ventilator team includes postdoctoral researchersTom ZajdelandManuel Schottdorf, senior research software engineer Grant Wallace, and graduate studentsSophie DvaliandZhenyu Song, as well as a number of external collaborators.

Editors note: For the full version of this story, visitthe Engineering website.

Read more:
Engineering and artificial intelligence combine to safeguard COVID-19 patients - Princeton University