{"id":3368,"date":"2020-10-23T23:56:16","date_gmt":"2020-10-23T23:56:16","guid":{"rendered":"https:\/\/techclot.com\/index.php\/2020\/10\/23\/deep-science-alzheimers-screening-forest-mapping-drones-machine-learning-in-space-more\/"},"modified":"2020-10-23T23:56:16","modified_gmt":"2020-10-23T23:56:16","slug":"deep-science-alzheimers-screening-forest-mapping-drones-machine-learning-in-space-more","status":"publish","type":"post","link":"https:\/\/techclot.com\/index.php\/2020\/10\/23\/deep-science-alzheimers-screening-forest-mapping-drones-machine-learning-in-space-more\/","title":{"rendered":"Deep Science: Alzheimer’s screening, forest-mapping drones, machine learning in space, more"},"content":{"rendered":"

Deep Science: Alzheimer’s screening, forest-mapping drones, machine learning in space, more<\/a><\/p>\n

Research papers come<\/span> out far too rapidly for anyone to read them all, especially in the field of machine learning, which now affects (and produces papers in) practically every industry and company. This column aims to collect the most relevant recent discoveries and papers \u2014 particularly in but not limited to artificial intelligence \u2014 and explain why they matter.<\/p>\n

This week, a startup that\u2019s using UAV drones for mapping forests, a look at how machine learning can map social media networks and predict Alzheimer\u2019s, improving computer vision for space-based sensors and other news regarding recent technological advances.<\/p>\n

Predicting Alzheimer\u2019s through speech patterns<\/h2>\n

Machine learning tools are being used to aid diagnosis in many ways, since they\u2019re sensitive to patterns that humans find difficult to detect. IBM researchers have potentially found such patterns in speech that are predictive of the speaker developing Alzheimer\u2019s disease<\/a>.<\/p>\n

The system only needs a couple minutes of ordinary speech in a clinical setting. The team used a large set of data (the Framingham Heart Study) going back to 1948, allowing patterns of speech to be identified in people who would later develop Alzheimer\u2019s. The accuracy rate is about 71% or 0.74 area under the curve for those of you more statistically informed. That\u2019s far from a sure thing, but current basic tests are barely better than a coin flip in predicting the disease this far ahead of time.<\/p>\n

This is very important because the earlier Alzheimer\u2019s can be detected, the better it can be managed. There\u2019s no cure, but there are promising treatments and practices that can delay or mitigate the worst symptoms. A non-invasive, quick test of well people like this one could be a powerful new screening tool and is also, of course, an excellent demonstration of the usefulness of this field of tech.<\/p>\n

(Don\u2019t read the paper expecting to find exact symptoms or anything like that \u2014 the array of speech features aren\u2019t really the kind of thing you can look out for in everyday life.)<\/p>\n

So-cell networks<\/h2>\n

Making sure your deep learning network generalizes to data outside its training environment is a key part of any serious ML research. But few attempt to set a model loose on data that\u2019s completely foreign to it. Perhaps they should!<\/p>\n

Researchers from Uppsala University<\/a> in Sweden took a model used to identify groups and connections in social media, and applied it (not unmodified, of course) to tissue scans. The tissue had been treated so that the resultant images produced thousands of tiny dots representing mRNA.<\/p>\n

Normally the different groups of cells, representing types and areas of tissue, would need to be manually identified and labeled. But the graph neural network, created to identify social groups based on similarities like common interests in a virtual space, proved it could perform a similar task on cells. (See the image at top.)<\/p>\n

\u201cWe\u2019re using the latest AI methods \u2014 specifically, graph neural networks, developed to analyze social networks \u2014 and adapting them to understand biological patterns and successive variation in tissue samples. The cells are comparable to social groupings that can be defined according to the activities they share in their social networks,\u201d said Uppsala\u2019s Carolina W\u00e4hlby.<\/p>\n

It\u2019s an interesting illustration not just of the flexibility of neural networks, but of how structures and architectures repeat at all scales and in all contexts. As without, so within<\/em>, if you will.<\/p>\n

Drones in nature<\/h2>\n

The vast forests of our national parks and timber farms have countless trees, but you can\u2019t put \u201ccountless\u201d on the paperwork. Someone has to make an actual estimate of how well various regions are growing, the density and types of trees, the range of disease or wildfire, and so on. This process is only partly automated, as aerial photography and scans only reveal so much, while on-the-ground observation is detailed but extremely slow and limited.<\/p>\n

Treeswift<\/a> aims to take a middle path by equipping drones with the sensors they need to both navigate and accurately measure the forest. By flying through much faster than a walking person, they can count trees, watch for problems and generally collect a ton of useful data. The company is still very early-stage, having spun out of the University of Pennsylvania and acquired an SBIR grant<\/a> from the NSF.<\/p>\n