From habit to digit

Jane allows elders to stay at home longer

Share on facebook
Share on twitter
Share on linkedin

Tempus Fugit

One of the few certainties in life is that time flies by for all of us. And so there comes a moment when those who raised us need to be looked after more. Eventually, a point may be reached where full-time care is needed. This often comes with a relocation that turns the elder’s world upside down. A point you want to postpone as long as possible. However, at the same time, you want to guarantee safety and well-being when no one is around. This is where Jane partnered with Faktion to help.

From habit to digit

The Jane solution includes a kit of six motion sensors, each to be mounted in a room of the elder’s home. The data from these sensors allows the one taking care of the elder to set custom alerts from the Jane App, e.g. ‘If mother doesn’t enter the kitchen between 9 AM and 11 AM, send me a notification’. The caretaker can add as many custom alerts as they consider necessary, however, setting relevant alerts for every possible scenario would be impractical. This is where smart alerts come in. Humans are creatures of habit, and when we quantify these habits, we can apply anomaly detection techniques to detect emergencies.

Figure 1: Example of expected activity pattern per location throughout the day. Lines are the median values; transparent ranges are bound by 5th and 95th quantiles.

By aggregating the per-room daily routines into minimal and maximal levels of expected activity on historical data, we can constantly check whether the current activity levels are within the expected range (see color bands in Figure 1). Once too many rooms are off, an alert is sent (see red dots in Figure 2).

Figure 2 Example expected vs actual activity pattern per location. The latter is marked with dots, red ones imply an alarming situation.

Simply counting the rooms with anomalous activity to decide if a situation is alarming turned out to be very sensitive to what was happening in rooms where hardly any activity was expected during that part of the day. To cope with this, we added weights to each room that vary during the day depending on where most activity is expected to take place (see Figure 3). The decision on whether a situation is alarming then comes down to check whether the total weight of all the rooms with anomalous activity is above a certain threshold. E.g. when most activity is expected in the living room at 3 PM, the lack of activity in that room will have a big influence on the decision to send an alert or not.

Figure 3 Proportion of expected activity per location, these proportions determine the per location weight on the decision whether a situation is alarming or not.

Dealing with per-weekday activity differences

While aggregating the expected activity pattern we first made the naïve assumption that every day of the week would be generally the same. However, from our exploratory data analysis, we knew that this assumption was not always valid.

Figure 4 Expected activity pattern aggregated per weekday. Note the unusual pattern on Wednesday morning.

What if someone visits to clean the house every Wednesday morning? These visits will have a significant impact on the registered activity pattern and will pollute the expected patterns of ‘normal’ days. To deal with this, we first calculate the expected activity pattern for each weekday individually (as in Figure 4) and then cluster weekdays that have similar patterns. For each cluster, we then recalculate the expected pattern (see Figure 5).

Figure 5 Activity patterns clustered by similar weekdays (top 2 graphs) and non-clustered (bottom graph). Due to the lack of similar weekday clustering in the bottom graph, all weekdays are assumed to be equal (hence the repetitive pattern).

Simulating emergencies

One scenario that we hope to avoid at all costs is that of a full-motion stop (such as in Figure 2). The Jane sensor kit includes a panic button that the elders can press to trigger a direct alert. Should they be unable to do so, we fall back on the smart alerts to detect the anomaly. Through simulations where the historical data is altered to include such full-motion stops, we’re able to estimate the time till the first alert. This turned out to be within 2 hours typically.

Multiple angles

In addition to the expected vs actual activity analysis discussed above, the system also derives wake-up and go-to-bed times, detects elders not returning to bed after a bathroom visit at night, and more. This multi-angled approach allows caretakers to spot issues early on.

Conclusion

The Jane smart alert system has matured through several iterations with testers providing invaluable feedback that allowed the system to reach the accuracy it has today. The result is that caretakers can follow up on their loved ones without being around all the time. Offering them peace of mind and allowing the elders to stay at home longer.

Jeroen_Boeye-IMG_6370
Jeroen Boeye, PhD
Head of Sensor Data
About the author

I enjoy unlocking the hidden value in data. The techniques I use to do so include data cleaning, wrangling and machine learning. To transfer the lessons learned I create clear and attractive visuals.

Related blog posts

With the global artificial intelligence (AI) market expected to be at almost $60 billion by 2025, many applications transform everyday life. Organizations seek ways to sustain their competitiveness in the marketplace by using AI to power what people see online, purchase products, and provide personal recommendations. As consumers realize the benefits of AI to them, they are more willing to share personal data, giving businesses a fantastic opportunity to innovate.
While simple in nature, averages are tricky and deceptive when misused, the variance in your data is a treasure!
When you throw a fresh dataset at a Python data scientist the first thing he or she will do is spin up a Jupyter notebook and dig in. Notebooks offer you the freedom to run and tweak a block of code until you’re happy with it, add some nicely formatted documentation with a plot, and then move on to the next code block.

LET'S TALK

Curious to learn what we can do for you?

Scroll to Top

We use cookies to improve user experience and analyze website traffic. For these reasons, we may share your site usage data with our analytics partners. By clicking “Accept” you consent to store on your device all the technologies described in our Cookie Policy. You can change your cookie settings at any time by clicking “Cookie Preferences” in the footer. Please read our Terms and Conditions and Privacy Policy for full details.

Inquiry for your POC

=