̽��ֱ�� of Cambridge - Luigi Occhipinti

Scientists develop ‘smart pyjamas’ to monitor sleep disorders

sc604 — Tue, 18 Feb 2025 11:06:44 +0000

̽��ֱ��team, led by the ̽��ֱ�� of Cambridge, developed printed fabric sensors that can monitor breathing by detecting tiny movements in the skin, even when the pyjamas are worn loosely around the neck and chest.

̽��ֱ��sensors embedded in the smart pyjamas were trained using a ‘lightweight’ AI algorithm and can identify six different sleep states with 98.6% accuracy, while ignoring regular sleep movements such as tossing and turning. ̽��ֱ��energy-efficient sensors only require a handful of examples of sleep patterns to successfully identify the difference between regular and disordered sleep.

̽��ֱ��researchers say that their smart pyjamas could be useful for the millions of people in the UK who struggle with disordered sleep to monitor their sleep, and how it might be affected by lifestyle changes. ̽��ֱ��results are reported in the Proceedings of the National Academy of Sciences (PNAS).

Sleep is vital for human health, yet more than 60% of adults experience poor sleep quality, leading to the loss of between 44 and 54 annual working days, and an estimated one percent reduction in global GDP. Sleep behaviours such as mouth breathing, sleep apnoea and snoring are major contributors to poor sleep quality, and can lead to chronic conditions such as cardiovascular disease, diabetes and depression.

“Poor sleep has huge effects on our physical and mental health, which is why proper sleep monitoring is vital,” said Professor Luigi Occhipinti from the Cambridge Graphene Centre, who led the research. “However, the current gold standard for sleep monitoring, polysomnography or PSG, is expensive, complicated and isn’t suitable for long-term use at home.”

Home devices that are simpler than PSG, such as home sleep tests, typically focus on a single condition and are bulky or uncomfortable. Wearable devices such as smartwatches, while more comfortable to wear, can only infer sleep quality, and are not effective for accurately monitoring disordered sleep.

“We need something that is comfortable and easy to use every night, but is accurate enough to provide meaningful information about sleep quality,” said Occhipinti.

To develop the smart pyjamas, Occhipinti and his colleagues built on their earlier work on a smart choker for people with speech impairments. ̽��ֱ��team re-designed the graphene-based sensors for breath analysis during sleep, and made several design improvements to increase sensitivity.

“Thanks to the design changes we made, the sensors are able to detect different sleep states, while ignoring regular tossing and turning,” said Occhinpinti. “ ̽��ֱ��improved sensitivity also means that the smart garment does not need to be worn tightly around the neck, which many people would find uncomfortable. As long as the sensors are in contact with the skin, they provide highly accurate readings.”

̽��ֱ��researchers designed a machine learning model, called SleepNet, that uses the signals captured by the sensors to identify sleep states including nasal breathing, mouth breathing, snoring, teeth grinding, central sleep apnoea (CSA), and obstructive sleep apnoea (OSA). SleepNet is a ‘lightweight’ AI network, that reduces computational complexity to the point where it can be run on portable devices, without the need to connect to computers or servers.

“We pruned the AI model to the point where we could get the lowest computational cost with the highest degree of accuracy,” said Occhinpinti. “This way we are able to embed the main data processors in the sensors directly.”

̽��ֱ��smart pyjamas were tested on healthy patients and those with sleep apnoea, and were able to detect a range of sleep states with an accuracy of 98.6%. By treating the smart pyjamas with a special starching step, they were able to improve the durability of the sensors so they can be run through a regular washing machine.

̽��ֱ��most recent version of the smart pyjamas are also capable of wireless data transfer, meaning the sleep data can be securely transferred to a smartphone or computer.

“Sleep is so important to health, and reliable sleep monitoring can be key in preventative care,” said Occhipinti. “Since this garment can be used at home, rather than in a hospital or clinic, it can alert users to changes in their sleep that they can then discuss with their doctor. Sleep behaviours such as nasal versus mouth breathing are not typically picked up in an NHS sleep analysis, but it can be an indicator of disordered sleep.”

̽��ֱ��researchers are hoping to adapt the sensors for a range of health conditions or home uses, such as baby monitoring, and have been in discussions with different patient groups. They are also working to improve the durability of the sensors for long-term use.

̽��ֱ��research was supported in part by the EU Graphene Flagship, Haleon, and the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI).

Reference:
Chenyu Tang, Wentian Yi et al. ‘A deep learning-enabled smart garment for accurate and versatile monitoring of sleep conditions in daily life.’ PNAS (2025). DOI: 10.1073/pnas.2420498122

Researchers have developed comfortable, washable ‘smart pyjamas’ that can monitor sleep disorders such as sleep apnoea at home, without the need for sticky patches, cumbersome equipment or a visit to a specialist sleep clinic.

We need something that is comfortable and easy to use every night, but is accurate enough to provide meaningful information about sleep quality

Luigi Occhipinti

Illustration and photograph of 'smart pyjamas'

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

‘Smart choker’ uses AI to help people with speech impairment to communicate

sc604 — Fri, 13 Sep 2024 13:40:19 +0000

̽��ֱ��smart choker, developed by researchers at the ̽��ֱ�� of Cambridge, incorporates electronic sensors in a soft, stretchable fabric, and is comfortable to wear. ̽��ֱ��device could be useful for people who have temporary or permanent speech impairments, whether due to laryngeal surgery, or conditions such as Parkinson’s, stroke or cerebral palsy.

By incorporating machine learning techniques, the smart choker can also successfully recognise differences in pronunciation, accent and vocabulary between users, reducing the amount of training required.

̽��ֱ��choker is a type of technology known as a silent speech interface, which analyses non-vocal signals to decode speech in silent conditions – the user only needs to mouth the words in order for them to be captured. ̽��ֱ��captured speech signals can then be transferred to a computer or speaker to facilitate conversation.

Tests of the smart choker showed it could recognise words with over 95% accuracy, while using 90% less computational energy than existing state-of-the art technologies. ̽��ֱ��results are reported in the journal npj Flexible Electronics.

“Current solutions for people with speech impairments often fail to capture words and require a lot of training,” said Dr Luigi Occhipinti from the Cambridge Graphene Centre, who led the research. “They are also rigid, bulky and sometimes require invasive surgery to the throat.”

̽��ֱ��smart choker developed by Occhipinti and his colleagues outperforms current technologies on accuracy, requires less computing power, is comfortable for users to wear, and can be removed whenever it’s not needed. ̽��ֱ��choker is made from a sustainable bamboo-based textile, with strain sensors based on graphene ink incorporated in the fabric. When the sensors detect any strain, tiny, controllable cracks form in the graphene. ̽��ֱ��sensitivity of the sensors is more than four times higher than existing state of the art.

“These sensors can detect tiny vibrations, such as those formed in the throat when whispering or even silently mouthing words, which makes them ideal for speech detection,” said Occhipinti. “By combining the ultra-high sensitivity of the sensors with highly efficient machine learning, we’ve come up with a device we think could help a lot of people who struggle with their speech.”

Vocal signals are incredibly complex, so associating a specific signal with a specific word requires a high level of computational processing. “On top of that, every person is different in terms of the way they speak, and machine learning gives us the tools we need to learn and adapt the interpretation of signals from person to person,” said Occhipinti.

̽��ֱ��researchers trained their machine learning model on a database of the most frequently used words in English, and selected words which are frequently confused with each other, such as ‘book’ and ‘look’. ̽��ֱ��model was trained with a variety of users, including different genders, native and non-native English speakers, as well as people with different accents and different speaking speeds.

Thanks to the device’s ability to capture rich dynamic signal characteristics, the researchers found it possible to use lightweight neural network architectures with simplified depth and signal dimensions to extract and enhance the speech information features. This resulted in a machine learning model with high computational and energy efficiency, ideal for integration in battery-operated wearable devices with real-time AI processing capabilities.

“We chose to train the model with lots of different English speakers, so we could show it was capable of learning,” said Occhipinti. “Machine learning has the capability to learn quickly and efficiently from one user to the next, so the retraining process is quick.”

Tests of the smart choker showed it was 95.25% accurate in decoding speech. “I was surprised at just how sensitive the device is,” said Occhipinti. “We couldn’t capture all the signals and complexity of human speech before, but now that we can, it unlocks a whole new set of potential applications.”

Although the choker will have to undergo extensive testing and clinical trials before it is approved for use in patients with speech impairments, the researchers say that their smart choker could also be used in other health monitoring applications, or for improving communication in noisy or secure environments.

̽��ֱ��research was supported in part by the EU Graphene Flagship and the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI).

Reference:
Chenyu Tang et al. ‘Ultrasensitive textile strain sensors redefine wearable silent speech interfaces with high machine learning efficiency.’ npj Flexible Electronics (2024). DOI: 10.1038/s41528-024-00315-1

Researchers have developed a wearable ‘smart choker’ that uses a combination of flexible electronics and artificial intelligence techniques to allow people with speech impairments to communicate by detecting tiny movements in the throat.

Luigi Occhipinti

Smart Choker

Yes

Cheaper method for making woven displays and smart fabrics – of any size or shape

sc604 — Fri, 21 Apr 2023 17:37:37 +0000

Researchers have developed next-generation smart textiles – incorporating LEDs, sensors, energy harvesting, and storage – that can be produced inexpensively, in any shape or size, using the same machines used to make the clothing we wear every day.

Scientists develop fully woven, smart display

sc604 — Thu, 10 Feb 2022 13:17:14 +0000

An international team of scientists have produced a fully woven smart textile display that integrates active electronic, sensing, energy and photonic functions. ̽��ֱ��functions are embedded directly into the fibres and yarns, which are manufactured using textile-based industrial processes.

̽��ֱ��researchers, led by the ̽��ֱ�� of Cambridge, say their approach could lead to applications that sound like sci-fi: curtains that are also TVs, energy-harvesting carpets, and interactive, self-powered clothing and fabrics.

This is the first time that a scalable large-area complex system has been integrated into textiles using an entirely fibre-based manufacturing approach. Their results are reported in the journal Nature Communications.

Despite recent progress in the development of smart textiles, their functionality, dimensions and shapes are limited by current manufacturing processes.

Integrating specialised fibres into textiles through conventional weaving or knitting processes means they could be incorporated into everyday objects, which opens up a huge range of potential applications. However, to date, the manufacturing of these fibres has been size limited, or the technology has not been compatible with textiles and the weaving process.

To make the technology compatible with weaving, the researchers coated each fibre component with materials that can withstand enough stretching so they can be used on textile manufacturing equipment. ̽��ֱ��team also braided some of the fibre-based components to improve their reliability and durability. Finally, they connected multiple fibre components together using conductive adhesives and laser welding techniques.

Using these techniques together, they were able to incorporate multiple functionalities into a large piece of woven fabric with standard, scalable textile manufacturing processes.

̽��ֱ��resulting fabric can operate as a display, monitor various inputs, or store energy for later use. ̽��ֱ��fabric can detect radiofrequency signals, touch, light and temperature. It can also be rolled up, and because it’s made using commercial textile manufacturing techniques, large rolls of functional fabric could be made this way.

̽��ֱ��researchers say their prototype display paves the way to next-generation e-textile applications in sectors such as smart and energy-efficient buildings that can generate and store their own energy, Internet of Things (IoT), distributed sensor networks and interactive displays that are flexible and wearable when integrated with fabrics.

“Our approach is built on the convergence of micro and nanotechnology, advanced displays, sensors, energy and technical textile manufacturing,” said Professor Jong min Kim, from Cambridge’s Department of Engineering, who co-led the research with Dr Luigi Occhipinti and Professor Manish Chhowalla. “This is a step towards the full exploitation of sustainable, convenient e-fibres and e-textiles in daily applications. And it’s only the beginning.”

“By integrating fibre-based electronics, photonic, sensing and energy functionalities, we can achieve a whole new class of smart devices and systems,” said Occhipinti, also from Cambridge’s Department of Engineering. “By unleashing the full potential of textile manufacturing, we could soon see smart and energy-autonomous Internet of Things devices that are seamlessly integrated into everyday objects and many other sector applications.”

̽��ֱ��researchers are working with European collaborators to make the technology sustainable and useable for everyday objects. They are also working to integrate sustainable materials as fibre components, providing a new class of energy textile systems. Their flexible and functional smart fabric could eventually be made into batteries, supercapacitors, solar panels and other devices.

̽��ֱ��research was funded in part by the European Commission and the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI).

Reference:
HW Choi et al. ‘Smart textile lighting/display system with multifunctional fibre devices for large scale smart home and IoT applications.’ Nature Communications (2022). DOI: 10.1038/s41467-022-28459-6

Researchers have developed a 46-inch (116cm) woven display with smart sensors, energy harvesting and storage integrated directly into the fabric.

By integrating fibre-based electronics, photonic, sensing and energy functionalities, we can achieve a whole new class of smart devices and systems

Luigi Occhipinti

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

New green materials could power smart devices using ambient light

Anonymous — Tue, 17 Nov 2020 02:14:38 +0000

We are increasingly using more smart devices like smartphones, smart speakers, and wearable health and wellness sensors in our homes, offices, and public buildings. However, the batteries they use can deplete quickly and contain toxic and rare environmentally damaging chemicals, so researchers are looking for better ways to power the devices.

One way to power them is by converting indoor light from ordinary bulbs into energy, in a similar way to how solar panels harvest energy from sunlight, known as solar photovoltaics. However, due to the different properties of the light sources, the materials used for solar panels are not suitable for harvesting indoor light.

Now, researchers from the ̽��ֱ�� of Cambridge, Imperial College London and Soochow ̽��ֱ�� in China have discovered that new green materials currently being developed for next-generation solar panels could be useful for indoor light harvesting. They report their findings in Advanced Energy Materials.

“By efficiently absorbing the light coming from lamps commonly found in homes and buildings, the materials can turn light into electricity with an efficiency already in the range of commercial technologies,” said co-author Dr Robert Hoye from Imperial College London. “We have also already identified several possible improvements, which would allow these materials to surpass the performance of current indoor photovoltaic technologies in the near future.”

̽��ֱ��team investigated perovskite-inspired materials, which were created to circumvent problems with materials called perovskites, which were developed for next-generation solar cells. Although perovskites are cheaper to make than traditional silicon-based solar panels and deliver similar efficiency, perovskites contain toxic lead substances. This drove the development of perovskite-inspired materials, which are instead based on safer elements like bismuth and antimony.

Despite being more environmentally friendly, these perovskite-inspired materials are not as efficient at absorbing sunlight. However, the team found that the materials are much more effective at absorbing indoor light, with efficiencies that are promising for commercial applications. Crucially, the researchers demonstrated that the power provided by these materials under indoor illumination is already sufficient to operate electronic circuits.

" ̽��ֱ��Internet of Things is critical for many areas, such as improved healthcare, energy conservation, transportation or control of smart buildings," said co-authro Professor Judith Driscoll from Cambridge's Department of Materials Science and Metallurgy. "New generations of wireless connected IoT devices function with low-power electronics ideally suited to operate with energy-scavenging devices."

"Access to sustainable and efficient indoor photovoltaic energy harvesters offers unique opportunities to operate these IoT devices by collecting ambient energy from daily environments extending their operating lifetime and reducing maintenance costs," said co-author Dr Luigi Occhipinti from Cambridge's Department of Engineering.

“Our discovery opens up a whole new direction in the search for green, easy-to-make materials to sustainably power our smart devices,” said co-author Professor Vincenzo Pecunia from Soochow ̽��ֱ��.

In addition to their eco-friendly nature, these materials could potentially be processed onto unconventional substrates such as plastics and fabric, which are incompatible with conventional technologies. Therefore, lead-free perovskite-inspired materials could soon enable battery-free devices for wearables, healthcare monitoring, smart homes, and smart cities.

This research was funded by EPSRC and National Natural Science Foundation of China.

Reference:
Yueheng Peng et al. ‘Lead‐Free Perovskite‐Inspired Absorbers for Indoor Photovoltaics.’ Advanced Energy Material (2020). DOI: 10.1002/aenm.202002761

Originally published on the Imperial College London website.

A bold response to the world’s greatest challenge

̽��ֱ�� ̽��ֱ�� of Cambridge is building on its existing research and launching an ambitious new environment and climate change initiative. Cambridge Zero is not just about developing greener technologies. It will harness the full power of the ̽��ֱ��’s research and policy expertise, developing solutions that work for our lives, our society and our biosphere.

Researchers have developed environmentally friendly materials that could harvest enough energy from indoor light to power wireless smart devices.

Luis Tosta on Unsplash

Light bulbs

Yes

Easy-to-make, ultra-low-power electronics could charge out of thin air

Anonymous — Tue, 13 Oct 2020 11:25:02 +0000

Electronics that consume tiny amounts of power are key for the development of the Internet of Things, in which everyday objects are connected to the internet. Many emerging technologies, from wearables to healthcare devices to smart homes and smart cities, need cost-effective transistors and electronic circuits that can function with minimal energy use.

Printed electronics are a simple and inexpensive way to manufacture electronics that could pave the way for low-cost electronic devices on unconventional substrates – such as clothes, plastic wrap or paper – and provide everyday objects with ‘intelligence’.

However, these devices need to operate with low energy and power consumption to be useful for real-world applications. Although printing techniques have advanced considerably, power consumption has remained a challenge – the different solutions available were too complex for commercial production.

Now, researchers from the ̽��ֱ�� of Cambridge, working with collaborators from China and Saudi Arabia, have developed an approach for printed electronics that could be used to make low-cost devices that recharge out of thin air. Even the ambient radio signals that surround us would be enough to power them. Their results are published in the journal ACS Nano.

Since the commercial batteries which power many devices have limited lifetimes and negative environmental impacts, researchers are developing electronics that can operate autonomously with ultra-low levels of energy.

̽��ֱ��technology developed by the researchers delivers high-performance electronic circuits based on thin-film transistors which are ‘ambipolar’ as they use only one semiconducting material to transport both negative and positive electric charges in their channels, in a region of operation called ‘deep subthreshold’ – a phrase that essentially means that the transistors are operated in a region that is conventionally regarded as their ‘off’ state. ̽��ֱ��team coined the phrase ‘deep-subthreshold ambipolar’ to refer to unprecedented ultra-low operating voltages and power consumption levels.

If electronic circuits made of these devices were to be powered by a standard AA battery, the researchers say it would be possible that they could run for millions of years uninterrupted.

̽��ֱ��team, which included researchers from Soochow ̽��ֱ��, the Chinese Academy of Sciences, ShanghaiTech ̽��ֱ��, and King Abdullah ̽��ֱ�� of Science and Technology (KAUST), used printed carbon nanotubes – ultra-thin cylinders of carbon – as an ambipolar semiconductor to achieve the result.

“Thanks to deep-subthreshold ambipolar approach, we created printed electronics that meet the power and voltage requirements of real-world applications, and opened up opportunities for remote sensing and ‘place-and-forget’ devices that can operate without batteries for their entire lifetime,” said co-lead author Luigi Occhipinti from Cambridge’s Department of Engineering. “Crucially, our ultra-low-power printed electronics are simple and cost-effective to manufacture and overcome long-standing hurdles in the field.”

“Our approach to printed electronics could be scaled up to make inexpensive battery-less devices that could harvest energy from the environment, such as sunlight or omnipresent ambient electromagnetic waves, like those created by our mobile phones and wifi stations,” said co-lead author Professor Vincenzo Pecunia from Soochow ̽��ֱ��. Pecunia is a former PhD student and postdoctoral researcher at Cambridge’s Cavendish Laboratory.

̽��ֱ��work paves the way for a new generation of self-powered electronics for biomedical applications, smart homes, infrastructure monitoring, and the exponentially-growing Internet of Things device ecosystem.

̽��ֱ��research was funded in part by the Engineering and Physical Sciences Research Council (EPSRC).

Reference:
L. Portilla et al. ‘Ambipolar Deep-Subthreshold Printed-Carbon-Nanotube Transistors for Ultralow-Voltage and Ultralow-Power Electronics.’ ACS Nano (2020). DOI: 10.1021/acsnano.0c06619

Researchers have developed a new approach to printed electronics that allows ultra-low-power electronic devices which could recharge from ambient light or radiofrequency noise. ̽��ֱ��approach paves the way for low-cost printed electronics that could be seamlessly embedded in everyday objects and environments.

Luis Portilla

Artist's impression of a hybrid-nanodielectric-based printed-CNT transistor

Yes