Editorial Feature

Wearable Sensors and Big Data: Today's Challenges and Tomorrow's Potential

Image Credit: AK Fotos321/Shutterstock.com

Wearable sensors – as well as numerous other “passive” sensor applications in the Internet of Things (IoT) – are hoovering up vast amounts of data that can be used to improve our daily lives dramatically. However, this aspect of wearables and the IoT presents significant challenges. Data management and privacy must be tackled well to ensure the potential of wearables, IoT and all smart devices can be fully realized.

What is Big Data?

Big Data refers to the vast data sets generated with digital technology, and the methods, processes and techniques used to understand them. These data sets are becoming more extensive as information technology advances, and this exponential increase is showing no signs of slowing down.

The IDC predicts there will be 163 zettabytes of data generated by 2025. Meanwhile, data management and analytics firms are in high demand from global technology companies such as IBM, Microsoft, SAP, HP, Dell, and Software AG who have spent more than $15 billion on their services.

It is clear that Big Data is an essential field of research and immediate application, and one which will only grow as our symbiotic relationship with information technology continues to progress.

How is Big Data Captured? Wearables, Smart Devices and IoT

Big data sets are being captured in a variety of settings today. Increasingly, this is happening “passively”, meaning that no action is required from data subjects to share their information with the data-gathering device.

Wearables equipped with sensors – such as the Fit Bit watch – can passively gather large sums of information from their users, while in situ sensors are passively gathering information from people in a variety of locations, including homes, workplaces, hospitals and schools.

Smart devices ranging from fridges to cellphones are also becoming sources of vast sets of personal information from their users. As well as wearables and in situ sensors, these devices are making up the growing IoT – growing not only in terms of connected devices but also in terms of the data being gathered and shared.

The Challenges of Big Data

The result of this increasingly passive data capture is vast data sets that defy conventional data storage, analysis and privacy methods. Not only this, but with increasingly large data sets – captured passively by wearables, in situ sensors and smart devices – the reliability and quality of the information gathered is increasingly becoming a concern. Data management is the field of research tasked with overcoming these challenges.

Data management specialists must continue to find efficient methods of storing data. This is especially important now, as data sets have evolved to include not just alphanumeric text databases and static images, but video, audio and even 3D modeling.

Conventional data analysis software is inadequately equipped to tackle the large sets of Big Data currently being captured – primarily due to limitations of computer processing power. This challenge is being tackled through innovative techniques that can “skim” large data sets while ensuring accurate and robust analyses. Research in this field combines information technology with cutting-edge mathematics and theory.

Privacy and other ethical concerns pose the biggest threat to our effective utilization of Big Data. Public problems with privacy could stall the progress of Big Data and significantly limit its potential. Data management researchers must work together with government agencies, privacy rights groups, and the general public to ensure privacy concerns are addressed appropriately.

There are other ethical concerns with Big Data that must be addressed. Notably, in healthcare settings, the large sets of data containing people’s most personal information must be carefully safeguarded and managed. The dangers of these data sets falling into unscrupulous commercial – or even criminal – hands are clear. Misusing these data sets would further alienate the public from the value of Big Data.

Find out more about the different types of sensors available on the market today.

The Opportunities of Big Data

Despite these challenges, the opportunities of Big Data’s useful application are wide and varied. While commercial applications are always being developed (and providing a key testing ground for data management, as in the cases of advertising and marketing, insurance, and fintech), some of the most beneficial applications of Big Data have not been fully explored.

In healthcare, wearables and IoT can provide large data sets that can significantly improve people’s quality of life, and even save lives. With these data sets, personalized medicine becomes possible – where medicine is no longer prescribed on a “best fit for all” basis, but individually tailored to the unique biological characteristics of each person.

Predictive analytics can be applied to large sets of data on a patient’s symptoms and vital characteristics, and help doctors to diagnose diseases early on – significantly increasing the chances of appropriate care, prevention or recovery.

Exploratory biomedical research is bolstered by data-driven analysis. Where traditional hypothesis-driven research tends to move slowly through hypotheses and tests, data can provide a head start for researchers trying to find commonalities or connections between various aspects of biomedicine. This can then be tested again through traditional methods, and eventually brought forward to clinical research stages.

Big Data can be – and often already is – used to benefit society as a whole through government and international development settings. Data sets dealing with population health, employment, education and skills, infrastructure, and many more matters of public concern are being grown alongside the IoT.

These data sets – when appropriately managed – can help policy-makers to better understand complex and critical decisions of investment and intervention. Using Big Data in combination with traditional service management enables decision-making from a reliable and robust evidence base.

As well as improving decision-making with evidence, Big Data can also be seen to give voice to the majority of people who are traditionally excluded from such decision-making processes. With user-generated data featuring in the decisions, a more democratic process that takes into account more experiences and perspectives is inevitable.

References and Further Reading

Banaee, Hadi, Mobyen Ahmed, and Amy Loutfi (2013). “Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges.” Sensors. https://doi.org/10.3390/s131217472.

Lovell, N. H., G. Z. Yang, A. Horsch, P. Lukowicz, L. Murrugarra, M. Marschollek, and S. J. Redmond (2014). “What Does Big Data Mean for Wearable Sensor Systems?” Yearbook of Medical Informatics. https://doi.org/10.15265/iy-2014-0019.

O’Donoghue, John, and John Herbert (2012). “Data Management within MHealth Environments.” Journal of Data and Information Quality. https://doi.org/10.1145/2378016.2378021.

Reinsel, David, John Gantz, and John Rydning (2018). “The Digitization of the World From Edge to Core.” IDC. https://www.seagate.com/files/www-content/our-story/trends/files/idc-seagate-dataage-whitepaper.pdf.

Thierer, Adam D. (2014). “The Internet of Things & Wearable Technology: Addressing Privacy & Security Concerns Without Derailing Innovation.” SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2494382.

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Ben Pilkington

Written by

Ben Pilkington

Ben Pilkington is a freelance writer who is interested in society and technology. He enjoys learning how the latest scientific developments can affect us and imagining what will be possible in the future. Since completing graduate studies at Oxford University in 2016, Ben has reported on developments in computer software, the UK technology industry, digital rights and privacy, industrial automation, IoT, AI, additive manufacturing, sustainability, and clean technology.


Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Pilkington, Ben. (2020, September 07). Wearable Sensors and Big Data: Today's Challenges and Tomorrow's Potential. AZoSensors. Retrieved on November 30, 2023 from https://www.azosensors.com/article.aspx?ArticleID=2005.

  • MLA

    Pilkington, Ben. "Wearable Sensors and Big Data: Today's Challenges and Tomorrow's Potential". AZoSensors. 30 November 2023. <https://www.azosensors.com/article.aspx?ArticleID=2005>.

  • Chicago

    Pilkington, Ben. "Wearable Sensors and Big Data: Today's Challenges and Tomorrow's Potential". AZoSensors. https://www.azosensors.com/article.aspx?ArticleID=2005. (accessed November 30, 2023).

  • Harvard

    Pilkington, Ben. 2020. Wearable Sensors and Big Data: Today's Challenges and Tomorrow's Potential. AZoSensors, viewed 30 November 2023, https://www.azosensors.com/article.aspx?ArticleID=2005.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this article?

Leave your feedback
Your comment type