Idea for cycling Android app

I was out for a spin on my bike today and I had an idea for an Android app (or any other smartphone you like).
Often when cyclists are training they want to complete a certain distance. A typical training method is to complete a small number - say 2 or 3 - normal rides per week. These might be an hour long. In addition the key part of the training system is a long spin - often at the weekend. The duration of the long spin gets longer (or more intense) as the training plan proceeds.

Something like this:

  • Monday - 30km
  • Tuesday - rest
  • Wednesday - 30km
  • Thursday - rest
  • Friday - 30km
  • Sunday - 50km

Cyclists end up having to calculate routes of varying lengths near their homes, or a few small loops which they add multiples of onto the end of a training ride in order to get the correct distance. If they decide to push their mileage up in a big jump, they can end up over training or getting an injury, so this is important stuff.
My idea is an app that tracks the users mileage as they cycle. Nothing new there. However at each junction a number of options (in units of distance - say kilometres) is displayed to the cyclist indicating how far that turn will take them to get home. Give the app knowledge of the distance the cyclist is trying to achieve and it could recommend specific routes. The screen could alert when they are overdoing it.
Additionally users could be shown the names of their friends who had used a route along with their time to complete that route. If the cyclist chose that route they could be paced against their friend with overlaid speed maps. Beating a friend would gain them points as would completing a mileage close to the desired mileage.


Comments

Post a Comment

Popular posts from this blog

Building a choropleth map for Irish agricultural data

I wanted to create a choropleth map  using Irish data. The Irish Government has made a large quantity of data available at data.gov.ie. The set I chose was for Bovine TB across Ireland over a number of years. You can get geojson for a variety of countries and Ireland's county boundaries are available. All I had to do was get the data labels to match. In the data some counties are split into 2 parts. I merged and summed these data points to get the choropleth to work with normal county boundaries. You can see the results here . A link to the github is included at the top of the notebook.
Read more

Early Stopping with Keras

Steps to train a model There are a number of things you have to do when working on a Machine Learning problem. Import your data and transform it as appropriate Define  your model using something like Keras - this includes your chosen hyperparameter values Run the training phase Evaluate the model If at the end of this process the evaluation shows that your model is not sufficient for your needs you will need to make some changes and rerun the training.  Ideally you should have a way to spot that training is not going as you want and stop it. This is one of the uses of early stopping. The other is if your model has reached a sufficient quality standard for you to use and further improvements have slowed, stopped altogether or an unnecessary.  Early Stopping Keras provides a way of doing this using the EarlyStopping callback . There are a range of callbacks in Keras and you can define your own. Details are here . The EarlyStopping callback works by choosing a metric
Read more

AutoCompleteTextView backed with data from SQLite in Android

Image
This is a handy piece of code. As your database gets bigger you can allow the user to pick the correct value by typing. If the db gets very big, you can always increase the threshold, so that the query does not run until there will be a suitably sized resultset returned. Running it at a threshold of 1 is fine for very small resultsets.  Here is the code you need to back your AutoCompleteTextView with a cursor adapter. @Override protected void onResume() { super.onResume(); text = (AutoCompleteTextView) findViewById(R.id.autoCompleteTextView1); final AdapterHelper h = new AdapterHelper(this); Cursor c = h.getAllResults(); startManagingCursor(c); String[] from = new String[] { "val" }; int[] to = new int[] { android.R.id.text1 }; CursorAdapter adapter = new MyCursorAdapter(this, android.R.layout.simple_dropdown_item_1line, c, from, to); adapter.setFilterQueryProvider(new FilterQueryProvider() { public Cursor runQuery(Cha
Read more