Google’s Project Loon may sound loony on paper, but it’s seeming less and less loony as time goes by. In fact, the latest update from the project’s team suggest that Project Loon could become a reality much sooner than anyone expects.
Project Loon intends to bring internet connectivity to internet-less areas via hot air balloons in the sky. The idea is that clusters of these balloons will hover over an area that needs internet and beam it down.
In practice, this was turning out to be difficult. Keeping the balloons in one place, for example, was proving to be very hard. Primarily as a result of this, Project Loon’s engineers determined that they’d need 200-300 balloons to cover a particular area. Their latest breakthrough, however, brings that number down to 20 or 30. This say the engineers, will result in a 100x reduction in the number of balloons needed.
As Google explains, the earlier model relied on balloons floating in the jet stream in the atmosphere. This consists of winds moving in different directions at varying speeds depending on altitude. The original design would use these winds to move balloons around and to put them in a specific spot. The updated system used AI and machine learning techniques to figure out how to command clusters of balloons.
Now, engineers will be able to send an entire cluster of balloons to a particular region and provide internet access, and all of this autonomously.
This clustering technique is what reduces the number of balloons as it concentrates the numbers at a given location. Fewer balloons will need to remain in transit.
An artificial intelligence (AI) system manages navigation and helps set routes for the balloons.
By: Tech2, India
Source: tech.firstpost.comRead More
Deep learning-based system could be further developed for smartphones, increasing access to screening and aiding early detection of cancers
Computers can classify skin cancers as successfully as human experts, according to the latest research attempting to apply artificial intelligence to health.
The US-based researchers say the new system, which is based on image recognition, could be developed for smartphones, increasing access to screening and providing a low-cost way to check whether skin lesions are cause for concern.
“We hope that this is a first step towards early detection,” said Andre Esteva, an electrical engineering PhD student from Stanford University and co-author of the research.
According to the World Health Organisation, skin cancer accounts for one in every three cancers diagnosed worldwide, with global incidence on the rise.
In the UK alone, 131,772 cases of non-melanoma skin cancer were recorded in 2014. In the same year there were 15,419 new cases of the deadliest skin cancer, melanoma, making it the fifth most common cancer, according to Cancer Research UK.
As the disease is often initially spotted by a visual examination, Esteva teamed up with colleagues in fields ranging from dermatology to artificial intelligence to create a computer system that would aid screening.
Their approach, described in the journal Nature, is based on deep learning – a class of algorithms used for artificial intelligence. When fed with a large set of ready-sorted data these algorithms pick out and “learn” patterns and relationships. Once trained, the algorithms can then be used to categorise new, unsorted data.
To create the system, the team harnessed a deep learning algorithm built by Google that had already been presented with 1.28 million images of objects such as cats, dogs and cups. Esteva and colleagues then fed the system more than 127,000 clinical images of skin lesions, each already labelled, encompassing many different skin diseases.
Once trained, the team then tested the system’s ability to classify skin cancer by presenting it with just under 2,000 previously unseen images of skin lesions, whose nature had previously been determined by biopsy, and further compared the results for nearly 400 of the images against the judgement of at least 21 dermatologists.
The results reveal that the system is on a par with – if not better than – the experts in telling apart carcinomas from common benign skin growths and melanomas from moles.
For melanomas, the average dermatologist classified around 95% of malignant lesions and 76% of harmless moles correctly. By comparison, the algorithm is capable of correctly classifying 96% of malignant lesions, and correspondingly 90% of benign lesions.
“The aim is absolutely not to replace doctors nor to replace diagnosis,” said Esteva. “What we are replicating [is] sort of the first two initial screenings that a dermatologist might perform.”
While Esteva and colleagues admit the system needs further testing in clinical settings they believe the approach has great promise, suggesting it could be applied to a host of other medical fields.
Boguslaw Obara, a computer scientist at Durham University and expert in image processing, said that the size and complexity of the dataset used to train the system was impressive. The work, he adds, shows we are likely to see algorithms cropping up more and more in everyday life.
Dr Anjali Mahto, consultant dermatologist and spokesperson for the British Skin Foundation also welcomed the research. “This is an exciting new technology that has the potential to increase access to dermatology at a time where there is a national shortage in this speciality and the rates of skin cancer continue to rise,” she said.
But, Mahto warned, the system will need to be carefully assessed for its benefits before it can be rolled out. The approach is also unlikely to replace the role of dermatologists, she adds, pointing out that during a full-body examination experts often discover skin cancer at different sites to those that initially concerned the patient. “There is therefore a possibility that if you rely on people to self-report what they are worried about, other skin cancers – particularly in hard to see sites, e.g. the back – may be missed,” she said.
By: The Guardian, UK
Source: www.theguardian.comRead More