The models Support Vector Regression (SVR) and Non-linear Canonical Correlation Analysis by Neural Networks (n-CCA) are both able to accurately predict the severity of three common symptoms faced by cancer patients -- depression, anxiety and sleep disturbance.
All three symptoms are associated with severe reduction in cancer patients' quality of life, said researchers from the University of Surrey in the UK.
"These exciting results show that there is an opportunity for machine learning techniques to make a real difference in the lives of people living with cancer," said Payam Barnaghi, Professor from the varsity.
"They can help clinicians identify high-risk patients, help and support their symptom experience and preemptively plan a way to manage those symptoms and improve quality of life," said Barnaghi.
For the study, published in the journal PLOS One, the team analysed existing data of the symptoms experienced by over 2,000 cancer patients during the course of computed tomography x-ray treatment.
They used different time periods during this data to test whether the machine learning algorithms are able to accurately predict when and if symptoms surfaced.
The team found that the actual reported symptoms were very close to those predicted by the machine learning methods.
While depression occurred in up to 60 per cent of cancer patients, sleep disturbance was reported in 30 to 50 per cent of patients.
In addition, between 35 per cent and 53 per cent of patients reported anxiety during cancer treatment and 45 per cent experienced both these symptoms.
These types of predictive models can be used to identify high risk patients, educate them about their symptom experience, and improve the timing of preemptive and personalised symptom management interventions, the researchers noted.
The announcement comes as part of the "ROSCon 2018" that is being in Madrid, Spain where Microsoft is demonstrating a "ROBOTIS Turtlebot 3" robot that recognises and steers towards the person closest to it and runs on the "Windows 10 IoT Enterprise" solution.
"This development will bring the manageability and security of 'Windows 10 Internet of Things (IoT) Enterprise' solutions to the 'ROS' ecosystem," Lou Amadio, Principal Software Engineer, Windows IoT, Microsoft wrote in a blog-post late on Friday.
"ROS" is a set of libraries and tools that are used to build complex robots and "Windows 10 IoT Enterprise" delivers enterprise manageability and security solutions to industry based IoT devices used in retail, manufacturing, healthcare and other industries.
The tech giant has joined the ROS Industrial Consortium --an open source project that extends the advanced capabilities of the ROS software to manufacturing -- to extend and improve the productivity and return on investment of industrial robots.
"Windows has been a trusted partner of robotic and industrial systems for decades and we're looking forward to bringing the intelligent edge to robotics by bringing more advanced features," Amadio added.
With the advancements of robots, Microsoft plans to experiment into advanced development tools.
"Microsoft will host the Windows builds for 'ROS1' and shortly 'ROS2', as well as provide documentation, development and deployment solutions for Windows," wrote Amadio.
Fast radio bursts are bright pulses of radio emission mere milliseconds in duration, thought to originate from distant galaxies.
"This work is exciting not just because it helps us understand the dynamic behavior of fast radio bursts in more detail, but also because of the promise it shows for using machine learning to detect signals missed by classical algorithms," said lead researcher Andrew Siemion, from the University of California, Berkeley.
While most fast radio bursts are one-offs, the source here, FRB 121102, is unique in emitting repeated bursts. This behaviour has drawn the attention of many astronomers hoping to pin down the cause and the extreme physics involved in fast radio bursts.
The results are described in The Astrophysical Journal.
The AI algorithms dredged up the radio signals from data were recorded over a five-hour period on Aug 26, 2017, by the Green Bank Telescope in West Virginia.
An earlier analysis of the 400 terabytes of data employed standard computer algorithms to identify 21 bursts during that period.
Reanalysing the 2017 data, the team found an additional 72 bursts not detected originally. This brings the total number of detected bursts from FRB 121102 to around 300 since it was discovered in 2012.
"This work is only the beginning of using these powerful methods to find radio transients," said Gerry Zhang, doctoral student at the varsity.
"We hope our success may inspire other serious endeavours in applying machine learning to radio astronomy," Zhang added.
For the discovery, the team trained an algorithm known as a convolutional neural network to recognise bursts, and then set it loose on the dataset to find bursts that the classical approach missed.
The device maker also announced it will launch its upcoming Panasonic "P85 NXT" and "Eluga Ray 710" devices with "Arbo Hub" built-in.
"Arbo Hub" adapts to the users' specific needs and provides services on one single platform, de-cluttering multiple apps on smartphones, the company said in a statement.
The company has also partnered with online service providers such as Ola, AccuWeather, MobiKwik and Gamezop to provide different platforms to its smartphone users.
"We have struck all the right chords with 'Arbo', our virtual assistant, that was launched a year ago. Now, users do not have to download multiple apps and clutter their phones as 'Arbo Hub' will give all services on a single platform," said Pankaj Rana, Business Head-Mobility Division, Panasonic India.
"Arbo Hub" will be rolled out for Eluga Ray 700 smartphone via an over the air update.
"Learn with Google AI" comes with existing content as well as the new Machine Learning Crash Course (MLCC).
"We believe it's important that the development of AI reflects as diverse a range of human perspectives and needs as possible. So, Google AI is making it easier for everyone to learn ML by providing a huge range of free, in-depth educational content," Zuri Kemp, Programme Manager for Google's machine learning education, said in a statement.
"This is for everyone -- from deep ML experts looking for advanced developer tutorials and materials, to curious people who are ready to try to learn what ML is in the first place," Kemp added.
The course features videos from ML experts at Google, interactive visualisations illustrating ML concepts, coding exercises using cutting-edge TensorFlow APIs and a focus that teaches how practitioners implement ML in the real world.
Originally developed by Google's engineering education team, more than 18,000 Googlers have enrolled in MLCC so far.
"Six Indian start-ups have been selected for the two-week mentorship bootcamp to help them learn more on AI and ML by leveraging our latest technologies to scale their apps," said Google in a statement.
The six start-ups -- EdGE Network, Fast Filmz, IndiaLends, RailYatri, Recipe Book and SigTuple will join their counterparts from Asia, Africa, Europe and Latin America for the fourth class Google Accelerator Programme.
With the latest batch onboard, 26 Indian start-ups have so far participated in the accelerator programme.
"The start-ups were short-listed for their unique value proposition and use of AI and ML to build high-impact solutions for internet users and the government's flagship initiative Digital India. We look forward to working with them over the next six months," said Google India Programme Manager Paul Ravindranath in the statement.
EdGE Network provides human resource solutions using AI; Fast Filmz offers super app for super fans of South Indian movies; IndiaLends is a credit underwriting and analytics platform for unsecured consumer lending; RailYatri is an intelligent, big data platform for long-distance travellers; Recipe Book provides intelligent solutions in food and retail and SigTuple is a smart screen solutions provider.
The start-ups also include B2B firms that use AI or ML for image recognition capabilities to aid medical diagnosis, providing solutions for talent acquisition and workforce optimisation.
In the six-month programme, the start-ups will undergo mentoring from Google teams and mentors from top technology firms and venture Capitalists) in the Silicon Valley.
In addition, the start-ups will receive equity-free support and credits for Google products. On return, they will work with Google's Indian subsidiary.
The 'Foundations for Artificial Intelligence and Machine Learning' would be executed in association with TalentSprint, a technology-driven organisation involved in skill development.
"Every corporate, every company is investing very heavily into artificial intelligence and machine learning. You would have heard about the efforts by the big corporates...," IIIT-H director P J Narayanan told reporters.
"But, beyond that, every company, whether you are working in banking, whether you are working in manufacturing, whether you are working in services, artificial intelligence (AI) and machine learning (ML) can do a lot for you, can make your work far more efficient," he said.
The institute had earlier conducted two-day classes for senior people from the industry on artificial intelligence and it wanted to scale up the effort in view of the heavy demand, the director said.
The four-month programme, with its hands-on teaching approach, would enable engineers in the industry to build "deep ML programming capabilities in their companies", a release issued on the occasion said.
"It has been repeatedly said in the last year that AI/ML is the next industrial revolution. We believe this programme is a bridge that will help today's technology professionals successfully cross over to the new era of automation and intelligent systems," Santanu Paul, the co-founder and CEO of TalentSprint, said.
Researchers from the University of Michigan in the US have shown that identifying multiple biomarkers can provide a more accurate diagnosis for patients with Latent Tuberculosis Infection (LTBI).
LTBI is when a person is infected with Mycobacterium tuberculosis but does not have active tuberculosis.
"A multi-array test can provide a more detailed, disease specific glimpse into patient's infection and likely outcome," said Ryan Bailey, Professor at the varsity.
"Using a precision medicine approach reveals previously obscured diagnostic signatures and reactivation risk potential," said Bailey.
The new diagnostic tools will help identify patients with the highest risk of reactivation and will benefit from therapy, said the researchers.
In addition, the tools will reduce some of the side effects of over treatment and can be used in the detection of other diseases like autoimmune diseases and cancer, according to the study, published in Integrative Biology.
Currently, LTBI is tested through a skin scratch test or a blood test that can identify one biomarker but cannot distinguish between memory immune response, vaccine-initiated response, and non-tuberculous mycobacteria exposure.
The possibility of correctly identifying the disease through these tests is less than five per cent.
LTBI affects nearly two billion individuals around the world and about 10 per cent of those cases result in active tuberculosis. The reactivation from latency can happen anytime and the mechanism for it is not well-understood.
For the study, the team included 50 people.
Technology titans Nadella and Adobe CEO Shantanu Narayen, the two schoolmates from Hyderabad, also gave a glimpse of the data initiative that was announced in 2018 by Microsoft with Adobe and SAP as the next big thing.
"I am very excited about ODI (Open Data Initiative)," said Nadella highlighting at the Adobe Summit here how close the project is to his heart and how 5G streaming and mixed reality with touch, gaze and speech functions across all platforms is the most significant technology enhancements in the future.
"The most important asset that everyone in this room has is data, which is yours. Except it is locked up in silos. The partnership we formed with SAP was to unlock this data and help each of you enrich it," said Nadella in conversation with Narayen at the summit attended by 16,000 participants.
ODI is aimed at allowing customers to exploit data in a more comprehensive manner.
The three companies intend to create a data lake chosen by the customers enabling the companies to provide real time solutions.
Adobe Experience Cloud, Microsoft Dynamics 365 and Office 365 and SAP C/4HANA form this data bank is enriched by Artificial Intelligence (AI) and machine learning (ML).
Unilever, one of the first big companies to go on ODI announced at the summit it will get rid of plastic packaging and shift to recycled products completely by 2025 with the help of AI driven processing.
Based on Nadella's vision, Microsoft's HoloLens2 makes mixed reality experience more instinctual and human combining touch, gaze and voice, showing mark improvement from HoloLens1, which was more of an experiment.
Researchers at the U.S. Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) are using ML to create a model for rapid control of plasma -- the state of matter composed of free electrons and atomic nuclei, or ions.
The Sun and most stars are giant balls of plasma that undergo constant fusion reactions. Here on Earth, scientists must heat and control the plasma to cause the particles to fuse and release their energy.
Researchers now show ML can facilitate such control.
The team led by physicist Dan Boyer trained neural networks -- the core of ML software -- on data produced in the first operational campaign of the National Spherical Torus Experiment-Upgrade (NSTX-U), the flagship fusion facility at PPPL.
The trained model accurately reproduced predictions of the behaviour of the energetic particles produced by powerful neutral beam injection (NBI) that is used to fuel NSTX-U plasmas and heat them to million-degree, fusion-relevant temperatures.
"The new ML software reduces the time needed to accurately predict the behavior of energetic particles to under 150 microseconds -- enabling the calculations to be done online during the experiment," the findings showed.
The rapid evaluations will also help operators make better-informed adjustments between experiments that are executed every 15-20 minutes during operations.
"Accelerated modeling capabilities could show operators how to adjust NBI settings to improve the next experiment," said Boyer, lead author of a paper in the journal Nuclear Fusion.
The study presented at the fourth conference of Digital Humanities in the Nordic Countries shows that the application is able to detect auto-generated tweets independent of the language used.
"This enhances the quality of data and paints a more accurate picture of the reality," said Mikko Laitinen, Professor at the University of Eastern Finland.
In recent years, big data from various social media applications have turned the web into a user-generated repository of information in the ever-increasing number of areas, said the researchers.
Twitter has become a popular source of data for investigations of a number of phenomena Because of the relatively easy access to tweets and their meta-data.
Twitter Bots are non-personal and automated accounts that post content to online social networks.
It has been estimated that around 5 to 10 per cent of all users are bots and these accounts generate about 20-25 per cent of all tweets posted.
For the study, the researchers analysed 15,000 tweets in Finnish, Swedish and English. Finnish and Swedish were mainly used for training, whereas tweets in English were used to evaluate the language independence of the application.
According to the researchers, the app is light, making it possible to classify vast amounts of data quickly and relatively efficiently.
"Bots are relatively harmless, whereas trolls do harm as they spread fake news and come up with made-up stories. This is why there's a need for increasingly advanced tools for social media monitoring", said Laitinen.
"While there is a growing understanding that bats play a role in the transmission of Nipah virus in Southeast Asia, less is known about which species pose the most risk.
"Our goal was to help pinpoint additional species with a high likelihood of carrying Nipah, to target surveillance and protect public health," said Barbara Han from Cary Institute of Ecosystem Studies in the US.
India is home to an estimated 113 bat species. Just 31 of these species have been sampled for the Nipah virus, and 11 have been found to have antibodies that signal host potential, according to the study published in the journal PLOS Neglected Tropical Diseases.
The Nipah virus is a highly lethal, emerging henipa virus that can be transmitted to people from the body fluids of infected bats. Eating fruit or drinking date palm sap that has been contaminated by bats has been flagged as a transmission pathway. Domestic pigs are also bridging hosts that can infect people.
Once infected, people can spread the virus directly to other people, sparking an outbreak. There is no vaccine and the virus has a high mortality rate.
For the study, Machine Learning, a form of Artificial Intelligence, was used to flag bat species with the potential to harbour Nipah.
"By looking at the traits of bat species known to carry Nipah globally, our model was able to make predictions about additional bat species residing in India with the potential to carry the virus and transmit it to people. These bats are currently not on the public health radar and are worthy of additional study," Han said.
For the study, the research team compiled published data on bat species known to carry Nipah and other henipa viruses globally.
Data included 48 traits of 523 bat species, including information on foraging methods, diet, migration behaviours, geographic ranges and reproduction.
During the study, their algorithm identified known Nipah-positive bat species with 83 per cent accuracy.
It also identified six bat species that occur in Asia, Australia and Oceania that have traits that could make them competent hosts and should be prioritised for surveillance. Four of these species occur in India, two of which are found in Kerala.
"We set out to make trait-based predictions of likely henipavirus reservoirs near Kerala. Our focus was narrow, but the model was successful in identifying Nipah hosts, demonstrating that this method could serve as a powerful tool in guiding surveillance for Nipah and other disease systems," said Raina K. Plowright from Montana State University in the US.
"Identifying which species harbour disease is an important first step in surveillance planning. We also need to prioritise research on which virus strains pose the greatest risk to people. Ultimately, the goal is to extinguish risk, not fight fires," Han concluded.
To help identify depression early, scientists have now enhanced a technology that uses Artificial Intelligence (AI) to sift through sound of your voice to gauge whether you are depressed or not.
Computing science researchers from University of Alberta in Canada have improved technology for identifying depression through vocal cues.
The study, conducted by Mashrura Tasnim and Professor Eleni Stroulia, builds on past research that suggests that the timbre of our voice contains information about our mood.
Using standard benchmark data sets, Tasnim and Stroulia developed a methodology that combines several Machine Learning (ML) algorithms to recognize depression more accurately using acoustic cues.
A realistic scenario is to have people use an app that will collect voice samples as they speak naturally.
"The app, running on the user's phone, will recognize and track indicators of mood, such as depression, over time. Much like you have a step counter on your phone, you could have a depression indicator based on your voice as you use the phone," said Stroulia.
Depression is ranked by WHO as the single largest contributor to global disability. It is also the major contributor to suicide deaths.
The ultimate goal, said researchers, is to develop meaningful applications from this technology.
Such a tool could prove useful to support work with care providers or to help individuals reflect on their own moods over time.
"This work, developing more accurate detection in standard benchmark data sets, is the first step," added Stroulia while presenting the paper at the Canadian Conference on Artificial Intelligence recently.
Amazon Web Services (AWS), which is retail behemoth Amaozn's Cloud arm, is currently busy enabling precision agriculture capabilities in farmers in India to help them make informed decisions about the soil, pest infestation and diseases and no predictability of yield, thus extracting more from their farms.
Teresa Carlson, Vice President, Worldwide Public Sector, AWS who met Union Agriculture Minister Narendra Singh Tomar and Amitabh Kant, CEO of Niti Aayog last week, is keen to create smart farmers who form 70 per cent of the Indian population.
"I was ecstatic to see the level of energy and engagement in the government this time towards empowering farmers in new-age Cloud computing technologies and help local farming become a sustainable and profit-yielding enterprise," Carlson told IANS during his India visit last week.
"I belong to the farming community so understand how important it is to drive innovation and provide digital infrastructure to enable real-time access to farmers in India. I see several start-ups doing precision, smart farming in the country. They can utilize our ML-driven Cloud capabilities and scale to new levels," she elaborated.
Agri-tech start-ups in India received more than $248 million funding in the first half of 2019, a growth of 300 per cent as compared to the same period in the previous year, according to IT industry body Nasscom.
Growing at the rate of 25 per cent year-on-year, the country currently hosts more than 450 start-ups in the agritech sector, said the report titled "Agritech in India - Emerging Trends in 2019".
Take the example of CropIn -- an agriculture technology solutions start-up that is delivering future-ready farming solutions to the agricultural sector in 48 countries.
The start-up has touched the lives of nearly 2.1 million farmers and 70 per cent of those are in India.
"With capabilities of live reporting, analysis, interpretation and insight that span across geographies, we're digitizing every farm, while data-managing the entire ecosystem. Our smarter agri solutions are powered in real-time; for farmers to archive patterns, predict trends, to make a blueprint for their business in the times to come," Kunal Prasad, Co-Founder & COO, CropIn, told IANS.
The idea of providing Software-as-a-Service (SaaS)-based services to agribusinesses came to Krishna Kumar, the Founder and CEO of CropIn, after observing the agrarian crisis looming large on the rural areas of Karnataka in 2010.
Kumar then set up CropIn that would address several pain points of millions of farmers across the country.
According to Carlson, the AWS Cloud is also enabling the Indian Farmers Fertiliser Cooperative Limited (IFFCO) to improve its IT operations efficiency, digitize agriculture across the country and empower farmers with e-commerce accessibility.
"IFFCO has improved its IT operations efficiency by 80 per cent with AWS, generating cost savings by 50 per cent. The next aim for us is to educate the farmers in Cloud-related information," said Carlson who reports directly to AWS CEO Andy Jassy.
One of India's biggest cooperative societies, the IFFCO is wholly-owned by Indian Cooperatives has a vast marketing network e about 36,000 cooperative societies and 55 million farmers.
In India, new emerging areas like market linkage, digital agriculture, better access to inputs, function-as-a-service (FaaS) and financing are gaining traction.
With more and more local farmers accepting the innovative start-up solutions, there has been a considerable shift witnessed from B2C (business to consumer) to B2B (business to business) start-ups, said the Nasscom report.
It is estimated that by 2020, the agritech sector would be at the centre of innovation and will lead India's journey towards overall transformation.
For Carlson, this is so natural for India which is an agriculture-dominated country to infuse new-age technologies for smart, intelligent farming.
On the other hand, new-age technologies like Artificial Intelligence (AI) and Machine Learning (ML), data analytics, Internet of Things (IoT), content streaming, automation, robotics and 5G are not only here to stay but are growing in leaps and bounds to make our lives better.
Let us go through 5 tech trends that will explode in the decade that has just begun.
1. Quantum Computing
Imagine a chip that can perform target computation in 200 seconds, which would otherwise take the world's fastest supercomputer 10,000 years.
A quantum computer can solve complex problems that would otherwise take billions of years for today's computers to solve. This has massive implications for research in health care, energy, environmental systems, smart materials and more.
The team at Google AI has achieved sort of "quantum supremacy" with developing such chip -- a new 54-qubit processor named "Sycamore" that is comprised of fast, high-fidelity quantum logic gates in order to perform the benchmark testing.
Not just Google but several tech giants like Microsoft, IBM and Intel have joined the race to build a scalable quantum computer. IBM recently unveiled its quantum computer with 53 qubits.
The current bits in computers store information as either 1 or 0, thus limiting the potential to make sense when faced with gigantic volumes of data.
If all goes well, Microsoft is also confident about having one such scalable super machine within the next five years.
"We are looking at a five-year time-frame to build a quantum computer and what we need are roughly 100-200 good qubits with a low-error rate," Krysta Svore, Principal Research Manager, Microsoft Quantum Computing, told IANS recently.
Microsoft has also partnered with the Indian Institute of Technology (IIT), Roorkee to conduct lectures on quantum computing for a full semester.
2. Self-Driving 'Electric' Cars
The global revenues from "connected" cars -- the precursor to fully-autonomous or self-driving cars -- are growing at an annual rate of 27.5 per cent and are expected to touch $21 billion by 2020.
Tesla helped create that market and remains an industry leader. The Elon Musk-run company surprised Wall Street by registering a profitable third quarter last year with total revenue of $6.3 billion riding on sales of its Model S, Model X and Model 3 electric cars.
Tesla expected to deliver between 360,000 and 400,000 vehicles in 2019, representing 45-65 per cent growth.
Other automobile companies who will join Tesla in the next decade are Audi e-Tron Sportback; BMW iX3; Ford Mustang Mach-E; Mercedes EQC 400 4Matic; Porsche's Taycan 4S; Volvo XC40 Recharge and Byton M-Byte SUV, to name a few.
India is also planning to replace a significant portion of its conventional internal combustion engine fleet by electric vehicles in the next one decade, particularly to reduce pollution and also to create jobs through the manufacturing of such vehicles.
3. 5G-Connected Homes
With 75 billion Internet of Things (IoT) devices expected to be in place by 2025, the world is at the cusp of experiencing a technology that will change the way live today.
Being able to download a full-length HD movie in seconds and share your wow-moments with friends -- that's just the beginning. Commercial 5G networks are starting to go live across the world.
With 5G commercial networks being switched on, the first use cases are enhanced mobile broadband, which will bring better experiences for smartphone users with 100 times faster data and fixed wireless access, providing fiber speeds without fiber to homes.
5G Services have already begun in the US, South Korea and some European countries, including Switzerland, Finland and the UK. CSPs in Canada, France, Germany, Hong Kong, Spain, Sweden, Qatar and the United Arab Emirates have announced plans to accelerate 5G network building through 2020.
4. Voice As A New Interface
Voice is slowly becoming the new human-computer interface and the Indian masses -- be it a 3-year-old toddler or a 95-year-old grandpa -- are finally going to leverage voice to interact with the devices and digitally control their lives.
Alexa, Google Home, Siri and others are changing the way we speak with devices and the next decade will see digital assistants becoming all-pervasive.
Soon, you will be talking to your refrigerator, electric bulbs, washing machine, microwave, coffee machine and what not.
According to Adam Berns, Director of Business Development, Alexa Voice Service (AVS) at Amazon, India is now ready for voice as a core experience.
"Voice today is powering several devices -- PCs, wearables, smartphones, car accessories and smart home devices -- helping people streamline their lives. I firmly believe voice is the next interface with computing and Amazon with its Alexa offerings is here to change the world," Berns told IANS in a recent interview.
5. Internet TV 24/7
An over-the-top (OTT) viewer in India is spending approximately 70 minutes a day on video streaming platforms, with a consumption frequency of 12.5 times a week, according to a recent Eros Now-KPMG report.
In India, the Internet video traffic is projected to reach 13.5 Exabytes (EB) per month by 2022 -- up from 1.5 EB a month in 2017 -- with video contributing 77 per cent of all Internet traffic by 2022.
"Unlike the common thought that urbanites are watching more content online, 65 per cent video consumption is coming from the rural parts of the country thanks to cheap data plans, especially from Reliance Jio, and affordable smartphones. Those who cannot afford to buy a smart, connected TV are now streaming OTT content on phones," TV Ramachandran, President, Broadband India Forum (BIF) told IANS.
There are currently more than 32 online content and video streaming platforms in the country and the market is expected to hit $5 billion by 2023, according to the global management-consulting firm Boston Consulting Group (BCG).
Within no time, you will see Indians throwing set-top boxes into dustbins as data becomes further cheap and Internet TV takes over our drawing rooms completely.
(IANS)