August 15, 2018
How can smart home AI support assisted living?
As health and social care services strain under the pressure of an ageing population, we are starting to see trials of smart home devices in the USA and UK that help to assist people with additional needs at home, such as the elderly and those with disabilities, poor physical health or mental health issues. Recent reports also suggest that both Amazon and Google are also looking at how their respective technologies and products could provide assisted living services for the elderly.
In our recent smart home survey of 6,000 consumers in the US and UK we asked people how willing they would be for their smart home products to help them monitor friends or family with special needs. Our findings suggest that there is strong demand from consumers for intelligent devices to take an active role in assisted living.
We asked consumers: “Assuming all of your privacy concerns were met, would you give permission for your smart home to automatically monitor the health and wellbeing of friends or family with special needs (e.g. the elderly)?”. 60% of consumers aged between 18 and 44 were very likely or likely to give permission and this increased to 64% among those in this age range with children at home.
So, what kind of things could the intelligent smart home do if you want to monitor family members or close friends?
What’s worth highlighting is that in assisted living situations, somebody is likely to be at home for large periods of time. In these situations motion detection via a camera has limited use as motion is likely to be detected all the time. It does play a role. For example, a camera or doorbell could alert a carer that an elderly relative has returned home from the shops or has got out of bed (or that it hasn’t detected any motion) but 24 hour video surveillance around the home is unlikely to be popular among the majority of consumers.
As a result, brands selling products and services into this space need to consider the product form-factor and privacy concerns. This means that they need to investigate alternative intelligent sensing capabilities beyond vision-based systems, such as sound recognition.
The consumer proposition around assisted living is about peace-of-mind. The consumer making the purchase wants to know that the user of the device is safe and well, knowing that should anything happen or not happen then they will know about it or the home will take steps to help the occupant. This raises another issue. The person buying the product is not always the person using it, so brands need to communicate a range of different benefits to both audiences.
Let’s imagine the types of scenarios where smart home AI through sound recognition could deliver significant benefits to carers and occupants…
Security and safety:
- Detect sounds that suggest a break-in is taking place or could be about to take place (detect the sound of a window breaking, intruder alarm, person talking or dog barking) – alerting the carer/occupant and turning on lights, playing alarm sounds (to deter the intruder), or sending video and audio clips to the cloud
- Detect the sound of a smoke or CO alarm which suggests an imminent risk to life or property – alerting the carer/occupant, unlocking the door and turning on lights to help them escape, or sounding loud alarm sounds to get the attention of neighbours or occupants
- Sudden sounds at unexpected times (such as a fall during the night) could trigger an alert to a carer
Health and wellbeing
- Detect prolonged or repeated coughing or sneezing, providing early indicators of poor health and alerting the carer/occupant, offering advice, turning on air purifiers or tracking activity in an appropriate app
- Detect shouting, crying or calls for help and alerting the carer with associated audio clip
- Detecting the sound of a doorbell or door knock and pausing music or TV content to alert the occupant
Out of sight, out of mind
As mentioned earlier, it is conceivable that the occupier being monitored would not feel comfortable having cameras focused on them in all rooms around the home. And as many important events have a sound associated with them, monitoring could be conducted using intelligent sound recognition, which is more discrete than video and can be trained to recognise specific target sounds, so that only relevant audio is shared with carers, rather than all sounds or motion.
So if a product only needs a microphone to monitor somebody within their home then this capability can be added to other products or discrete products could be designed that perform this function yet sit in the background and even out of sight. Alternatively, smart speakers, which can often be found in multiple rooms around the home including bedrooms, kitchens and living areas could be enabled with such a capability.
Analyst firm Ovum forecasts that in 2022 assisted living services in the smart home will generate $4bn in revenues, on top of device sales. So as well as device sales, tech brands can offer services, perhaps bundled with general home security packages (or extended whole-family monitoring) to increase the monthly revenue generated by each household.
To learn more about how consumers reacted to the concept of AI in the smart home, and in particular assisted living, then you can download the survey report for free here.
Like this? You can subscribe to our blog and receive an alert every time we publish an announcement, a comment on the industry or something more technical.
About Audio Analytic
Audio Analytic is the pioneer of AI sound recognition software. The company is on a mission to map the world of sounds, offering our sense of hearing to consumer technology. By transferring our sense of hearing to consumer products and digital personal assistants we give them the ability to react to the world around us, helping satisfy our entertainment, safety, security, wellbeing and communication needs.
Audio Analytic’s ai3™ sound recognition software enables device manufacturers and chip companies to equip products with Artificial Audio Intelligence, recognizing and automatically responding to our growing list of sound profiles.