Computers Math

Researchers at UCL and University of Ghana have successfully predicted whether children have anaemia using only a set of smartphone images.
The study, published in PLOS ONE, brought together researchers and clinicians at UCL Engineering, UCLH and Korle Bu Teaching Hospital, Ghana to investigate a new non-invasive diagnostic technique using smartphone photographs of the eye and face.
The advance could make anaemia screening more widely available for children in Ghana (and other low- and middle-income countries) where there are high rates of the condition due to iron deficiency, as the screening tool is much cheaper than existing options and delivers results in one sitting.
The paper builds on previous successful research undertaken by the same team exploring use of an app – neoSCB – to detect jaundice in newborn babies.
Anaemia is a condition causing a reduced concentration of haemoglobin in the blood, which means oxygen is not transported efficiently around the body.
It affects two billion people globally and can have a significant impact on developmental outcomes in children, increasing their susceptibility to infectious diseases and impairing their cognitive development.

The most common cause of anaemia globally is iron deficiency, but other conditions such as blood loss, malaria and sickle-cell disease also contribute.
First author, PhD candidate Thomas Wemyss (UCL Medical Physics & Biomedical Engineering) said: “Smartphones are globally popular, but research using smartphone imaging to diagnose diseases shows a general trend of experiencing difficulty when transferring results to different groups of people.
“We are excited to see these promising results in a group which is often underrepresented in research into smartphone diagnostics. An affordable and reliable technique to screen for anaemia using a smartphone could drive long-term improvements in quality of life for a large amount of people.”
Traditionally, diagnosis of anaemia requires blood samples to be taken, which can be costly for patients and healthcare systems. It can create inequalities related to the expense of travelling to hospital for a blood test. Often families need to make two trips, to have a blood sample taken and then to collect their results, due to samples being transported between the clinic and the laboratory for analysis.
In the 1980s a handheld device, the HemoCue, was developed to provide more immediate results, but this carries significant upfront and ongoing costs, as well as still needing a finger-prick blood sample.

The researchers knew that haemoglobin has a very characteristic colour due to the way it absorbs light, so aimed to develop a procedure to take smartphone photographs and use them to predict whether anaemia is present.
They analysed photos taken from 43 children aged under four who were recruited to take part in the study in 2018. The images were of three regions where minimal skin pigmentation occurs in the body (the white of the eye, the lower lip and the lower eyelid).
The team found that when these were evaluated together to predict blood haemoglobin concentration, they were able to successfully detect all cases of individuals with the most severe classification of anaemia, and to detect milder anaemia at rates which are likely to be clinically useful.
Principal investigator Dr Terence Leung (UCL Medical Physics & Biomedical Engineering) said: “Since 2018, we’ve been working with University of Ghana on affordable ways to improve healthcare using smartphones. Following our success in screening neonatal jaundice, we are so excited to see that the smartphone imaging technique can also apply to anaemia screening in young children and infants.”
Senior author Dr Judith Meek (UCLH) added: “Anaemia is a significant problem for infants, especially in low- and middle-income countries, and we hope this sort of technology will lead to earlier detection and treatment in the near future.”
The study was funded by the EPSRC via the UCL Global Challenges Research Fund and UCL Centre for Doctoral Training in Intelligent, Integrated Imaging in Healthcare. More

Modern fabrication tools such as 3D printers can make structural materials in shapes that would have been difficult or impossible using conventional tools. Meanwhile, new generative design systems can take great advantage of this flexibility to create innovative designs for parts of a new building, car, or virtually any other device.
But such “black box” automated systems often fall short of producing designs that are fully optimized for their purpose, such as providing the greatest strength in proportion to weight or minimizing the amount of material needed to support a given load. Fully manual design, on the other hand, is time-consuming and labor-intensive.
Now, researchers at MIT have found a way to achieve some of the best of both of these approaches. They used an automated design system but stopped the process periodically to allow human engineers to evaluate the work in progress and make tweaks or adjustments before letting the computer resume its design process. Introducing a few of these iterations produced results that performed better than those designed by the automated system alone, and the process was completed more quickly compared to the fully manual approach.
The results are reported this week in the journal Structural and Multidisciplinary Optimization, in a paper by MIT doctoral student Dat Ha and assistant professor of civil and environmental engineering Josephine Carstensen.
The basic approach can be applied to a broad range of scales and applications, Carstensen explains, for the design of everything from biomedical devices to nanoscale materials to structural support members of a skyscraper. Already, automated design systems have found many applications. “If we can make things in a better way, if we can make whatever we want, why not make it better?” she asks.
“It’s a way to take advantage of how we can make things in much more complex ways than we could in the past,” says Ha, adding that automated design systems have already begun to be widely used over the last decade in automotive and aerospace industries, where reducing weight while maintaining structural strength is a key need.

“You can take a lot of weight out of components, and in these two industries, everything is driven by weight,” he says. In some cases, such as internal components that aren’t visible, appearance is irrelevant, but for other structures aesthetics may be important as well. The new system makes it possible to optimize designs for visual as well as mechanical properties, and in such decisions the human touch is essential.
As a demonstration of their process in action, the researchers designed a number of structural load-bearing beams, such as might be used in a building or a bridge. In their iterations, they saw that the design has an area that could fail prematurely, so they selected that feature and required the program to address it. The computer system then revised the design accordingly, removing the highlighted strut and strengthening some other struts to compensate, and leading to an improved final design.
The process, which they call Human-Informed Topology Optimization, begins by setting out the needed specifications — for example, a beam needs to be this length, supported on two points at its ends, and must support this much of a load. “As we’re seeing the structure evolve” on the computer screen in response to initial specification, Carstensen says, “we interrupt the design and ask the user to judge it. The user can select, say, ‘I’m not a fan of this region, I’d like you to beef up or beef down this feature size requirement.’ And then the algorithm takes into account the user input.”
While the result is not as ideal as what might be produced by a fully rigorous yet significantly slower design algorithm that considers the underlying physics, she says it can be much better than a result generated by a rapid automated design system alone. “You don’t get something that’s quite as good, but that was not necessarily the goal. What we can show is that instead of using several hours to get something, we can use 10 minutes and get something much better than where we started off.”
The system can be used to optimize a design based on any desired properties, not just strength and weight. For example, it can be used to minimize fracture or buckling, or to reduce stresses in the material by softening corners.
Carstensen says, “We’re not looking to replace the seven-hour solution. If you have all the time and all the resources in the world, obviously you can run these and it’s going to give you the best solution.” But for many situations, such as designing replacement parts for equipment in a war zone or a disaster-relief area with limited computational power available, “then this kind of solution that catered directly to your needs would prevail.”
Similarly, for smaller companies manufacturing equipment in essentially “mom and pop” businesses, such a simplified system might be just the ticket. The new system they developed is not only simple and efficient to run on smaller computers, but it also requires far less training to produce useful results, Carstensen says. A basic two-dimensional version of the software, suitable for designing basic beams and structural parts, is freely available now online, she says, as the team continues to develop a full 3D version.
“By integrating engineering ‘intuition’ (or engineering ‘judgement’) into a rigorous yet computationally efficient topology optimization process, the human engineer is offered the possibility of guiding the creation of optimal structural configurations in a way that was not available to us before,” he adds. “Her findings have the potential to change the way engineers tackle ‘day-to-day’ design tasks.” More

Have you ever wondered how pedestrians ‘know’ to fall into lanes when they are moving through a crowd, without the matter being discussed or even given conscious thought?
A new theory developed by mathematicians at the University of Bath in the UK led by Professor Tim Rogers explains this phenomenon, and is able to predict when lanes will be curved as well as straight. The theory can even describe the tilt of a wonky lane when people are in the habit of passing on one side rather than the other (for instance, in a situation where they are often reminded to ‘pass on the right’).
This mathematical analysis unifies conflicting viewpoints on the origin of lane formation, and it reveals a new class of structures that in daily life may go unnoticed. The discovery, reported this week (Friday, March 3) in the journal Science, constitutes a major advance in the interdisciplinary science of ‘active matter’ — the study of group behaviours in interacting populations ranging in scale from bacteria to herds of animals.
Tested in arenas
To test their theory, the researchers asked a group of volunteers to walk across an experimental arena that mimicked different layouts, with changes to entrance and exit gates.
One arena was set up in the style of King’s Cross Station in London. When the researchers looked at the video footage from the experiment, they observed mathematical patterns taking shape in real life.

Professor Rogers said: “At a glance, a crowd of pedestrians attempting to pass through two gates might seem disorderly but when you look more closely, you see the hidden structure. Depending on the layout of the space, you may observe either the classic straight lanes or more complex curved patterns such as ellipses, parabolas, and hyperbolas.”
Lane formation
The single-file processions formed at busy zebra crossings are only one example of lane formation, and this study is likely to have implications for a range of scientific disciplines, particularly in the fields of physics and biology. Similar structures can also be formed by inanimate molecules, such as charged particles or organelles in a cell.
Until now, scientists have given several different explanations for why human crowds and other active systems naturally self-organise into lanes, but none of these theories have been verified. The Bath team used a new analytical approach, inspired by Albert Einstein’s theory of Brownian motion, which makes predictions that can be tested.
Encouraged by the way their theory agreed with the numerical simulations of colliding particles, they then teamed up with Professor Bogdan Bacik — an experimentalist from the Academy of Physical Education in Katowice, Poland — and ran a series of experiments (such as the one modelled on King’s Cross) using human crowds.

Lead author Dr Karol Bacik said: “Lane formation doesn’t require conscious thought — the participants of the experiment were not aware that they had arranged themselves into well-defined mathematical curves.
“The order emerges spontaneously when two groups with different objectives cross paths in a crowded space and try to avoid crashing into each other. The cumulative effect of lots of individual decisions inadvertently results in lanes forming.”
The researchers also tested the effects of externally imposed traffic rules — namely, they instructed the participants to pass others on the right. In agreement with the theoretical prediction, adding this rule changed the lane structure.
“When pedestrians have a preference for right turns, the lanes end up tilting and this introduces frustration that slows people down,” said Dr Bacik.
“What we’ve developed is a neat mathematical theory that forecasts the propensity for lane formation in any given system,” said Professor Rogers, adding: “We now know that much more structure exists than previously thought.” More