![]() Third, we will do some data exploration and data processing, so we can understand patterns and trends. Second, we will then use some code to parse and process our raw Apple Health logs into more usable formats. First, we will look at some methods for exporting your Apple Health data, either using Apple’s raw export or an aggregated version using QS Access app. In this post, we will be exploring Apple Health Data. If you also regularly wear an Apple Watch during the day, during workouts and at night, then you have even more data, like Heart Rate, VO2 Max, and possibility even Sleep. Others are logged via other health apps that store their data into the Apple Health repository. If you are an Apple user, then your iPhone has been tracking your steps and a host of other health metrics. In later posts, we will look at a few other data points and tracking services. For example, how to export, parse and do some data analysis on your Apple Health data using Python. In this post, I want to look at Apple Health. The end goal is to build a personal data dashboard and hopefully one day leverage it for more sophisticated data science and machine learning. The initial goal is to collect and aggregate various self-tracking data. These are a collection of Python scripts that help to collect, process and aggregate data from various services like Fitbit, Apple Health, RescueTime and more. I recently created an open source project called Quantified Self Ledger. Interestingly, there are dozens of other devices with a much smaller marketshare but which offer an additional array of sensors to track other data points like blood pressure and HRV. According to a Statista infographic, the most used wearables today are Fitbit, Apple Watch, Garmin, Mi-Band from XiaoMi, and Fossil. There are various ways and reasons why people track their lives, but when it comes to recording their daily movements, the most common method is with a wearable, activity tracker or smart watch. If you use a wearable with a Heart Rate Sensor, you can also capture your resting, active and sleeping heart rate and even know how long you slept too. ![]() Leveraging a few sensors, our phones and wearables are able to interpret our movement patterns and tell us how many steps we took, how many stairs we climbed, how often we stood up, and many other activities. So, while the bulk of the discussion these days is about personal data is on the negative’s, like data leaks and data privacy, I believe it’s a good time to try to understand the actual data we do have and how personal data and self-tracking might be used for self-improvement and even self-transformation.įor example, one of the most robust repositories about human health is on our smartphones, wearables and activity trackers. We should promote greater data protection and privacy, but we shouldn’t ignore the incredible opportunities we can gain from personal data too. People seem worried about privacy and personal data, even though few know what data they actually have. On the bad side, a lot of talk centers on privacy concerns, especially in relation to social media and internet usage but also go back to revelations about government surveillance and our smart phone data too. On the good side, they can be used to help us know more about our health and behaviors. Our smartphones are incredible mini-trackers that can be used for both good and bad. Our phones contain sensors that detect movements, determine magnetic north, and even pinpoint us in relation to rotating satellites. We call these devices “smartphones,” and they have more computing power and memory than the Apollo Space Capsules did when they went to the moon. ![]() ![]() Most of us walk around carrying a small, sensor-infused computer. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |