The optical pony express

Suppose you want to send messages as fast as possible. What’s the best way to do it? That is what Polina Bayvel, a Professor at UCL has dedicated her research career to: exploring the limits of how fast information can be sent over networks. It’s not just messages that it’s about nowadays of course, but videos, pictures, money, music, books – anything you can do over the Internet.

Cowboys at dawn crossing the range

Send a text message and it arrives almost instantly. Sending message hasn’t always been that quick, though. The Greeks used runners – in fact the Marathon athletic event originally commemorated a messenger who supposedly ran from a battlefield at Marathon to Athens to deliver the message “We won” before promptly dying. The fastest woman in the world at the time of writing, 2011, Paula Radcliffe, at her quickest could deliver a message a marathon distance away in 2 hours 15 minutes and 25 seconds (without dying!) … ( now in 2020, Brigid Kosgei, a minute or so faster).

Horses improved things (and the Greeks in fact normally used horseback messengers, but hey it was a good story). Unfortunately, even a horse can’t keep up the pace for hundreds of miles. The Pony Express pushed horse technology to its limits. They didn’t create new breeds of genetically modified fast horses, or anything like that. All it took was to create an organised network of normal ones. They set up pony stations every 10 miles or so right across North America from Missouri to Sacramento. Why every 10 miles? That’s the point a galloping horse starts to give up the ghost. The mail came thundering in to each station and thundered out with barely a break as it was swapped to a new fresh pony.

The pony express was swiftly overtaken by the telegraph. Like the switch to horses, this involved a new carrier technology – this time copper wire. Now the messages had to be translated first though, here into electrical signals in Morse code. The telegraph was followed by the telephone. With a phone it seems like you just talk and the other person just hears but of course the translation of the message into a different form is still happening. The invention of the telephone was really just the invention of a way to turn sound into an electrical code that could be sent along copper cables and then translated back again.

The Internet took things digital – in some ways that’s a step back towards Morse code. Now, everything, even sound and images, are turned into a code of ones and zeros instead of dots and dashes. In theory images could of course have been sent using a telegraph tapper in the same way…if you were willing to wait months for the code of the image to be tapped in and then decoded again. Better to just wait for computers that can do it fast to be invented.

In the early Internet, the message carrier was still good old copper wire. Trouble is, when you want to send lots of data, like a whole movie, copper wire and electricity are starting to look like the runners must have done to horse riders: slow out-of-date technology. The optical fibre is the modern equivalent of the horse. They are just long thin tubes of glass. Instead of sending pulses of electricity to carry the coded messages, they now go on the back of a pulse of light.

Up to this point it’s been mainly men taking the credit, but this is where Polina’s work comes in. She is both exploring the limits of what can be done with optical fibres in theory and building ever faster optical networks in practice. How much information can actually be sent down fibres and what is the best way to do it? Can new optical materials make a difference? How can devices be designed to route information to the right place – such ‘routers’ are just like mail sorting depots for pulses of light. How can fibre optics best be connected into networks so that they work as efficiently as possible – allowing you and everyone else in your street to be watching different movies at the same time, for example, without the film going all jerky? These are all the kinds of questions that fascinate Polina and she has built up an internationally respected team to help her answer them.

Multiple streams of binary data flowing in an optical cable.

Why are optical fibres such a good way to send messages? Well the obvious answer is that you can’t get much faster than light! Well actually you can’t get ANY faster than light. The speed of light is the fastest anything, including information, can travel according to Einstein’s laws. That’s not the end of the story though. Remember the worn out Marathon runner. It turns out that signals being sent down cables do something similar. Well, not actually getting out of breath and dying but they do get weaker the further they travel. That means it gets harder to extract the information at the other end and eventually there is a point where the message is just garbled noise. What’s the solution? Well actually it’s exactly the one the Pony Express came up with. You add what are called ‘repeaters’ every so often. They extract the message from the optical fibre and then send it down the next fibre, but now back at full strength again. One of the benefits of fibre optics is that signals can go much further before they need a repeater. That means the message gets to its destination faster because those repeaters take time extracting and resending the message. That, in turn, leaves scope for improvement. The Pony Express made their ‘repeaters’ faster by giving the rider a horn to alert the stationmaster that they were arriving. He would then have time to get the next horse ready so it could leave the moment the mail was handed over. Researchers like Polina are looking for similar ways to speed up optical repeaters.

You can do more than play with repeaters to speed things up though. You can also bump up the amount of information you carry in one go. In particular you can send lots of messages at the same time over an optical fibre as long as they use different wavelengths. You can think of this as though one person is using a torch with a blue bulb to send a Morse code message using flashes of blue light (say), while someone else is doing the same thing with a red torch and red light. If two people at the other end are wearing tinted sunglasses then depending on the tint they will each see only the red pulses or only the blue ones and so only get the message meant for them. Each new frequency of light used gives a new message that can be sent at the same time.

The tricky bit is not so much in doing that but in working out which people can use which torch at any particular time so their aren’t any clashes, bearing in mind that at any instant messages could be coming from anywhere in the network and trying to go anywhere. If two people try to use the same torch on the same link at the same time it all goes to pot. This is complicated further by the fact that at any time particular links could be very busy, or broken, meaning that different messages may also travel by different routes between the same places, just as you might go a different way to normal when driving if there is a jam. All this, and together with other similar issues, means there are lots of hairy problems to worry about if coming up with a the best possible optical network as Polina is aiming to do.

Polina’s has been highly successful working in this area. She has been made a Fellow of the Royal Academy of Engineering for her work and is also a Royal Society Wolfson Research Merit Award holder. It is only given to respected scientists of outstanding achievement and potential. She has also won the prestigious Patterson Medal awarded for distinguished research in applied physics. It’s important to remember that modern engineering is a team game, though. As she notes she has benefited hugely by having inspiring and supporting mentors, as well as superb students and colleagues. It is her ability to work well with other people that allowed her build a critical mass in her research and so gain all the accolades. All that achieved and she is a mother of two boys to boot. Bringing up children is, of course, a team game too.

Paul Curzon, Queen Mary University of London, Autumn 2011

Download the special issue of the cs4fn magazine “The women are here”.

Download Electronic Engineering For Fun Magazine Issue 1.

Smart bags

In our stress-filled world with ever increasing levels of anxiety, it would be nice if technology could sometimes reduce stress rather than just add to it. That is the problem that QMUL’s Christine Farion set out to solve for her PhD. She wanted to do something stylish too, so she created a new kind of bag: a smart bag.

Christine realised that one thing that causes anxiety for a lot of people is forgetting everyday things. It is very common for us to forget keys, train tickets, passports and other everyday things we need for the day. Sometimes it’s just irritating. At other times it can ruin the day. Even when we don’t forget things, we waste time unpacking and repacking bags to make sure we really do have the things we need. Of course, the moment we unpack a bag to check, we increase the chance that something won’t be put back!

Electronic bags

Christine wondered if a smart bag could help. Over the space of several years, she built ten different prototypes using basic electronic kits, allowing her to explore lots of options. Her basic design has coloured lights on the outside of the bag, and a small scanner inside. To use the bag, you attach electronic tags to the things you don’t want to forget. They are like the ones shops use to keep track of stock and prevent shoplifting. Some tags are embedded into things like key fobs, while others can be stuck directly on to an object. Then when you pack your bag, you scan the objects with the reader as you put them in, and the lights show you they are definitely there. The different coloured lights allow you to create clear links – natural mappings – between the lights and the objects. For her own bag, Christine linked the blue light to a blue key fob with her keys, and the yellow light to her yellow hayfever tablet box.

In the wild

One of the strongest things about her work was she tested her bags extensively ‘in the wild’. She gave them to people who used them as part of their normal everyday life, asking them to report to her what did and didn’t work about them. This all fed in to the designs for subsequent bags and allowed her to learn what really mattered to make this kind of bag work for the people using it. One of the key things she discovered was that the technology needed to be completely simple to use. If it wasn’t both obvious how to use and quick and simple to do it wouldn’t be used.

Christine also used the bags herself, keeping a detailed diary of incidents related to the bags and their design. This is called ‘autoethnography’. She even used one bag as her own main bag for a year and a half, building it completely into her life, fixing problems as they arose. She took it to work, shopping, to coffee shops … wherever she went.

Suspicious?

When she had shown people her prototype bags, one of the common worries was that the electronics would look suspicious and be a problem when travelling. She set out to find out, taking her bag on journeys around the country, on trains and even to airports, travelling overseas on several occasions. There were no problems at all.

Fashion matters

As a bag is a personal item we carry around with us, it becomes part of our identity. She found that appropriate styling is, therefore, essential in this kind of wearable technology. There is no point making a smart bag that doesn’t fit the look that people want to carry around. This is a problem with a lot of today’s medical technology, for example. Objects that help with medical conditions: like diabetic monitors or drug pumps and even things as simple and useful as hearing aids or glasses, while ‘solving’ a problem, can lead to stigma if they look ugly. Fashion on the other hand does the opposite. It is all about being cool. Christine showed that by combining design of the technology with an understanding of fashion, her bags were seen as cool. Rather than designing just a single functional smart bag, ideally you need a range of bags, if the idea is to work for everyone.

Now, why don’t I have my glasses with me?

– Paul Curzon, Queen Mary University of London, Autumn 2018

Download Issue 25 of the cs4fn magazine “Technology Worn Out (and about) on Wearable Computing here.

Punk robots learn to pogo

It’s the second of three punk gigs in a row for Neurotic and the PVCs, and tonight they’re sounding good. The audience seem to be enjoying it too. All around the room the people are clapping and cheering, and in the middle of the mosh pit the three robots are dancing. They’re jumping up and down in the style of the classic punk pogo, and they’ve been doing it all night whenever they like the music most. Since Neurotic came on the robots can hardly keep still. In fact Neurotic and the PVCs might be the best, most perfect band for these three robots to listen to, since their frontman, Fiddian, made sure they learned to like the same music he does.

Programming punks

It’s a tough task to get a robot to learn what punk music sounds like, but there are lots of hints lurking in our own brains. Inside your brain are billions of connected cells called neurons that can send messages to one another. When and where the messages get sent depends on how strong each connection is, and we forge new connections whenever we learn something.

What the robots’ programmers did was to wire up a network of computerised connections like the ones in a real brain. Then they let the robots sample lots of different kinds of music and told them what it was, like reggae, pop, and of course, Fiddian’s collection of classic punk. That way the connections in the neural network got stronger and stronger – the more music the robots listened to, the easier it got for them to recognise what kind of stuff it was. When they recognised a style they’d been told to look out for, they would dance, firing a cylinder of compressed air to make them jump up and down.

The robots’ first gig

The last step was to tell the robots to go out and enjoy some punk. The programmers turned off the robots’ neural connections to other kinds of music, so no Kylie or Bob Marley would satisfy them. They would only dance to the angry, churning sound of punk guitars. The robots got dressed up in spray-painted leather, studded belts and safety pins, so with their bloblike bodies they looked like extra-tough boxing gloves on sticks. Then the three two-metre tall troublemakers went to their first gig.

Whenever a band begins to play, the robots’ computer system analyses the sound coming from the stage. If the patterns in it look the same as the idea of punk music they’ve learned, the robots begin to dance. If the pattern isn’t quite right, they stand still. For lots of songs they hardly dance at all, which might seem weird since all the bands that are playing the gig call themselves punk bands. Except there are many different styles of punk music, and the robots have been brought up listening to Fiddian’s favourites. The other styles aren’t close enough to the robots’ idea of punk – they’ve developed taste, and it’s the same as Fiddian’s. Which is why the robots go crazy for Neurotic and the PVCs. Fiddian’s songs are influenced by classic punk like the Clash, the Sex Pistols and Siouxsie & the Banshees, which is exactly the music he’s taught the robots to love. As the robots jump wildly up and down, it’s clear that Neurotic and the PVCs now have three tall, tough, computerised superfans.

The computer vs the casino: Wearable tech cheating

What happened when a legend of computer science took on the Las Vegas casinos? The answer, surprisingly, was the birth of wearable computing.

There have always been people looking to beat the system, to get that little bit extra of the odds going their way to allow them to clean up at the casino. Over the years maths and technology have been used, from a hidden mechanical arm up your sleeve allowing you to swap cards, to the more cerebral card counting. In the latter, a player remembers a running total of the cards played so they can estimate when high value cards will be dealt. One popular game to try and cheat was Roulette.

A spin of the wheel

Roulette, which comes from the French word ‘little wheel’, involves a dish containing a circular rotating part marked into red and black numbers. A simple version of the game was developed by the French mathematician, Pascal, and it evolved over the centuries to become a popular betting game. The central disc is spun and as it rotates a small ball is thrown into the dish. Players bet on the number that the ball will eventually stop at. The game is based on probability, but like most games there is a house advantage: the probabilities mean that the casino will tend to win more money than it loses.

Gamblers tried to work out betting strategies to win, but the random nature of where the ball stops thwarted them. In fact, the pattern of numbers produced from multiple roulette spins was so random that mathematicians and scientists have used these numbers as a random-number generator. Methods using them are even called Monte Carlo methods after the famous casino town. They are ways to calculate difficult mathematical functions by taking thousands of random samples of their value at different random places.

A mathematical system of betting wasn’t going to work to beat the game, but there was one possible weakness to be exploited: the person who ran the game and threw the ball into the wheel, the croupier.

No more bets please

There is a natural human instinct to spin the wheel and throw the ball in a consistent pattern. Each croupier who has played thousands of games has a slight bias in the speed and force with which they spin the wheel and throw the ball in. If you could just see where the wheel was when the spin started and the ball went in, you could use the short time before betting was suspended to make a rough guess of the area where the ball was more likely to land, giving you an edge. This is called ‘clocking the wheel’, but it requires great skill. You have to watch many games with the same croupier to gain a tiny chance of working out where their ball will go. This isn’t cheating in the same way as physically tampering with the wheel with weights and magnets (which is illegal), it is the skill of the gambler’s observation that gives the edge. Casinos became aware of it, so frequently changed the croupier on each game, so the players couldn’t watch long enough to work out the pattern. But if there was some technological way to work this out quickly perhaps the game could be beaten.

Blackjack and back room

Enter Ed Thorpe, in the 1950s, a graduate student in physics at MIT. Along with his interest in physics he had a love of gambling. Using his access to one of the world’s few room filling IBM computers at the university he was able to run the probabilities in card games and using this wrote a scientific paper on a method to win at Blackjack. This paper brought him to the attention of Claude Shannon, the famous and rather eccentric father of information theory. Shannon loved to invent things: the flame throwing trumpet, the insult machine and other weird and wonderful devices filled the basement workshop of his home. It was there that he and Ed decided to try and take on the casinos at Roulette and built arguably the first wearable computer.

Sounds like a win

The device comprised a pressure switch hidden in a shoe. When the ball was spun and passed a fixed point on the wheel, the wearer pressed the switch. A computer timer, strapped to the wrist, started and was used to track the progress of the ball as it passed around the wheel, using technology in place of human skill to clock the wheel. A series of musical tones told the person using the device where the ball would stop, each tone represented a separate part of the wheel. They tested the device in secret and found that using it gave them a 44% increased chance of correctly predicting the winning numbers. They decided to try it for real … and it worked! However, the fine wires that connected the computer to the earpiece kept breaking, so they gave up after winning only a few dollars. The device, though very simple and for a single purpose, is in the computing museum at MIT. The inventors eventually published the detail in a scientific paper called “The Invention of the First Wearable Computer,” in 1998.

The long arm of the law reaches out

Others followed with similar systems built into shoes, developing more computers and software to help cheat at Blackjack too, but by the mid 1980’s the casino authorities became wise to this way to win, so new laws were introduced to prevent the use of technology to give unfair advantages in casino games. It definitely is now cheating. If you look at the rules for casinos today they specifically exclude the use of mobile phones at the table, for example, just in case your phone is using some clever app to scam the casinos.

From its rather strange beginning, wearable computing has spun out into new areas and applications, and quite where it will go next is anybody’s bet.

– Peter W. McOwan, Queen Mary University of London, Autumn 2018

Sick tattoos

Image by Anand Kumar from Pixabay

Researchers at MIT and Harvard have new skin in the game when it comes to monitoring people’s bodily health. They have developed a new wearable technology in the form of colour- and shape-changing tattoos. These tattoos work by using bio-sensitive inks, changing colour, fading away or appearing under different coloured illumination, depending on your body chemistry. They could, for example, change their colour, or shape as their parts fade away, depending on your blood glucose levels.

This kind of constantly on, constantly working body monitoring ensures that there is nothing to fall off, get broken or run out of power. That’s important in chronic conditions like diabetes where monitoring and controlling blood glucose levels is crucial to the person’s health. The project, called Dermal Abyss, brings together scientists and artists in a new way to create a data interface on your skin.

There are still lots of questions to answer, like how long will the tattoos last and would people be happy displaying their health status to anyone who catches a glimpse of their body art? How would you feel having your body stats displayed on your tats? It’s a future question for researchers to draw out the answer to.

– Peter W. McOwan, Queen Mary University of London, Autumn 2018

One in the eye for wearable tech

Contact lenses, normally used to simply, but usefully, correct people’s vision, could in the future do far more.

Tiny microelectronic circuits, antennae and sensors can now be fabricated and set in the plastic of contact lenses. Researchers are looking at the possibility of using such sensors to sample and transmit the glucose level in the eye moisture: useful information for diabetics. Others are looking at lenses that can change your focus, or even project data onto the lens, allowing new forms of augmented and virtual reality.

Conveniently, you can turn the frequent natural motion from the blinks of your eye into enough power to run the sensors and transmitter, doing away with the need for charging. All this means that smart contact lenses could be a real eye opener for wearable tech.

– Peter W. McOwan, Queen Mary University of London, Autumn 2018

Smart tablets to swallow

The first ever smart pill has been approved for use. It’s like any other pill except that this one has a sensor inside it and it comes with a tracking device patch you wear to make sure you take it.

A big problem with medicine is remembering to take it. It’s common for people to be unsure whether they did take today’s tablet or not. Getting it wrong regularly can make a difference to how quickly you recover from illness. Many medicines are also very, very expensive. Mass-produced electronics, on the other hand, are cheap. So could the smart pill be a new, potentially useful, solution? The pill contains a sensor that is triggered when the pill dissolves and the sensor meets your stomach acids. When it does, the patch you wear detects its signal and sends a message to your phone to record the fact. The specially made sensor itself is harmless and safe to swallow. Your phone’s app can then, if you allow it, tell your doctor so that they know whether you are taking the pills correctly or not.

Smart pills could also be invaluable for medical researchers. In medical trials of new drugs, knowing whether patients took the pills correctly is important but difficult to know. If a large number of patients don’t, that could be a reason why the drugs appeared less effective than expected. Smart pills could allow researchers to better work out how regularly a drug needs to be taken to still work. 

More futuristically still, such pills may form part of a future health artificial intelligence system that is personalised to you. It would collect data about you and your condition from a wide range of sensors recording anything relevant: from whether you’ve taken pills to how active you’ve been, your heart rate, blood pressure and so on: in fact anything useful that can be sensed. Then, using big data techniques to crunch all that data about you, it will tailor your treatment. For example, such a system may be better able to work out how a drug affects you personally, and so be better able to match doses to your body. It may be able to give you personalised advice about what to eat and drink, even predicting when your condition could be about to get better or worse. This could make a massive difference to life for those with long term illnesses like rheumatoid arthritis or multiple sclerosis, where symptoms flare up and die away unpredictably. It could also help the doctors who currently must find the right drug and dose for each person by trial and error.

Computing in future could be looking after your health personally, as long as you are willing to wear it both inside and out.

– Paul Curzon, Queen Mary University of London

i-pickpocket

Contactless payments seem magical. But don’t get caught out by someone magically scanning your card without you knowing. Almost £7 million was stolen by contactless card fraud in 2016 alone…

Victorian Hi-Tech

Contactless cards talk to the scanner by electromagnetic induction, discovered by Michael Faraday back in 1831. Changes in the current in a coil of wire, which for a contactless card is just an antenna in the form of a loop, creates a changing magnetic field. If a loop antenna on another device is placed inside that magnetic field, then a voltage is created in its circuit. As the current in the first circuit changes, that in the other circuit copies it, and information is passed from one to the other. This works up to about 10cm away.

Credit cards in a back pocket.
Image by TheDigitalWay from Pixabay 

Picking pockets at a distance

Contactless cards don’t require authentication like a PIN, to prove who is using them, for small amounts. Anyone with the card and a reader can charge small amounts to it. Worse, if someone gets a reader within 10cm of the bag holding your card, they could even take money from it without your knowledge. That might seem unlikely but then traditional pickpockets are easily capable of taking your wallet without you noticing, so just getting close isn’t hard by comparison! For that kind of fraud the crook has to have a legitimate reader to charge money. Even without doing that they can read the number and expiry date from the card and use them to make online purchases though.

A man in the middle

Security researchers have also shown that ‘relay’ attacks are possible, where a fake device passes messages between the shop and a card that is somewhere else. An attacker places a relay device near to someone’s actual card. It communicates with a fake card an accomplice is using in the shop. The shop’s reader queries the fake card which talks to its paired device. The paired device talks to the real card as though it were the one in the shop. It passes the answers from the real card back to the fake card which relays it on to the shop. Real reader and card get exactly the messages they would if the card was in the shop, just via the fake devices in between. Both shop and card think they are talking to each other even though they are a long way apart, and the owner of the real card knows nothing about it.

Block the field

How do you guard against contactless attacks? Never hand over your card, always ask for a receipt and check your statements. You can also keep your card in a blocking sleeve: a metal case that protects the card from electromagnetic fields (even using a homemade sleeve from tin foil should work). Then at least you force the pickpockets back to the Victorian, Artful Dodger style, method of actually stealing your wallet.

Of course Faraday was a Victorian, so a contactless attack is actually a Victorian way of stealing too!

– Jane Waite and Paul Curzon, Queen Mary University of London

AI Detecting the Scribes of the Dead Sea Scrolls

Computer science and artificial intelligence have provided a new way to do science: it was in fact one of the earliest uses of the computer. They are now giving new ways for scholars to do research in other disciplines such as ancient history, too. Artificial Intelligence has been used in a novel way to help understand how the Dead Sea Scrolls were written, and it turns out scribes in ancient Judea worked in teams.

The Dead Sea Scrolls are a collection of almost a thousand ancient documents written several thousand years ago that were found in caves near the Dead Sea. The collection includes the oldest known written version of the Bible.

The cave where most of the Dead Sea Scrolls were found.

Researchers from the University of Groningen used artificial intelligence techniques to analyse a digitised version of the longest scroll in the collection, known as the Great Isaiah Scroll. They picked one letter, aleph, that appears thousands of times through the document, and analysed it in detail.

Two kinds of artificial intelligence programs were used. The first, feature extraction, based on computer vision and image processing was needed to recognize features in the images. At one level this is the actual characters, but also more subtly here, the aim was that the features corresponded to ink traces based on the actual muscle movements of the scribes.

The second was machine learning. Machine Learning programs are good at spotting patterns in data – grouping the data into things that are similar and things that are different. A typical text book example would be giving the program images of cats and of dogs. It would spot the patterns of features that correspond to dogs, and the different pattern of features that corresponds to cats and group each image into one or the other pattern.

Here the data was all those alephs or more specifically the features extracted from them. Essentially the aim was to find patterns that were based on the muscle movements of the original scribe of each letter. To the human eye the writing throughout the document looks very, very uniform, suggesting a single scribe wrote the whole document. If that was the case, only one pattern would be found that all letters were part of with no clear way to split them. Despite this, the artificial intelligence evidence suggests there were actually two scribes involved. There were two patterns.

The research team found, by analysing the way the letters were written, that there were two clear groupings of letters. One group were written in one way and the other in a slightly different way. There were very subtle differences in the way strokes were written, such as in their thickness and the positions of the connections between strokes. This could just be down to variations in the way a single writer wrote letters at different times. However, the differences were not random, but very clearly split at a point halfway through the scroll. This suggests there were two writers who each worked on the different parts. Because the characters were otherwise so uniform, those two scribes must have been making an effort to carefully mirror each other’s writing style so the letters looked the same to the naked eye.

The research team have not only found out something interesting about the Dead Sea Scrolls, but also demonstrated a new way to study ancient hand writing. With a few exceptions, the scribes who wrote the ancient documents, like the Dead Sea Scrolls, that have survived to the modern day, are generally anonymous, but thanks to leading-edge Computer Science, we have a new way to find out more about them.

Explore the digitised version of the Dead Sea Scrolls yourself at www.deadseascrolls.org.il

– Paul Curzon, Queen Mary University of London

Losing the match? Follow the science. Change the kit!

Artificial Intelligence software has shown that two different Manchester United gaffers got it right believing that kit and stadium seat colours matter if the team are going to win.

It is 1996. Sir Alex Ferguson’s Manchester United are doing the unthinkable. At half time they are losing 3-0 to lowly Southampton. Then the team return to the pitch for the second half and they’ve changed their kit. No longer are they wearing their normal grey away kit but are in blue and white, and their performance improves (if not enough to claw back such a big lead). The match becomes infamous for that kit change: the genius gaffer blaming the team’s poor performance on their kit seemed silly to most. Just play better football if you want to win!

Jump forward to 2021, and Manchester United Manager Ole Gunnar Solskjaer, who originally joined United as a player in that same year, 1996, tells a press conference that the club are changing the stadium seats to improve the team’s performance!

Is this all a repeat of previously successful mind games to deflect from poor performances? Or superstition, dressed up as canny management, perhaps. Actually, no. Both managers were following the science.

Ferguson wasn’t just following some gut instinct, he had been employing a vision scientist, Professor Gail Stephenson, who had been brought in to the club to help improve the players’ visual awareness, getting them to exercise the muscles in their eyes not just their legs! She had pointed out to Ferguson that the grey kit would make it harder for the players to pick each other out quickly. The Southampton match was presumably the final straw that gave him the excuse to follow her advice.

She was very definitely right, and modern vision Artificial Intelligence technology agrees with her! Colours do make it easier or harder to notice things and slows decision making in a way that matters on the pitch. 25 years ago the problem was grey kit merging into the grey background of the crowd. Now it is that red shirts merge into the background of an empty stadium of red seats.

It is all about how our brain processes the visual world and the saliency of objects. Saliency is just how much an object stands out and that depends on how our brain processes information. Objects are much easier to pick out if they have high contrast, for example, like a red shirt on a black background.

Peter McOwan and Hamit Soyel at Queen Mary combined vision research and computer science, creating an Artificial Intelligence (AI) that sees like humans in the sense that it predicts what will and won’t stand out to us, doing it in real time (see DragonflyAI: I see what you see). They used the program to analyse images from that infamous football match before and after the kit change and showed that the AI agreed with Gail Stephenson and Alex Ferguson. The players really were much easier for their team mates to see in the second half (see the DragonflyAI version of the scenes below).

Dragonfly highlights areas of a scene that are more salient to humans so easier to notice. Red areas stand out the most. In the left image when wearing the grey kit, Ryan Giggs merges into the background. He is highly salient (red) in the right image where he is in the blue and white kit.

Details matter and science can help teams that want to win in all sorts of ways. That includes computer scientists and Artificial Intelligence. So if you want an edge over the opposition, hire an AI to analyse the stadium scene at your next match. Changing the colour of the seats really could make a difference.

Find out more about DragonflyAI: https://dragonflyai.co/ [EXTERNAL]

– Paul Curzon, Queen Mary University of London