ThingSpeak

Seguir

Hello, I trained a machine learning model on MatLab Desktop and the App Classification Learner. Now I want to upload the trained model to the ThingSpeak Cloud, so that I can make predictions with new data in the cloud. How can I do this ? Thank you in advance!

I used the 'Download files from your DropBox API folder using MATLAB' code in thingspeak's matlab analysis, to get a training model.mat file from dropbox, but it just keeps showing not enough input arguments. how do I solve this please? I checked and it went wrong during "narginchk(2,3)" but I just am not sure how and what to do function downloadFromDropbox(dropboxAccessToken,fileNames,varargin) dropboxAccessToken='xxx'; %xxx to hide the actual token fileNames='TrainingModel.mat'; % Check to input arguments narginchk(2,3); % If no file specified, pop up the dialog for the user to select one if isequal(nargin,2) %Set default downloadPath to workspace location downloadPath = pwd; elseif isequal(nargin,3) % If downloadPath is provided, check if the given path exists if ~exist(varargin{1},'dir') throw(MException('downloadFromDropbox:pathNotFound','Download path does not exist.')); else downloadPath = varargin{1}; end end

Hi all! I have been using Matlab and Thingspeak for several years. What began as a hobby for personal use is turning into a potential business but I am running into questions about how to scale my application in Thingspeak and Matlab. For example, I am collecting data from a series of Arduino devices, each of which is assigned to a different customer. I need to train a machine learning model for each customer and store the trained weights for each customer - and then apply the weights in real time as new data arrives in Thingspeak. I have done this successfully for one user - by storing the weights in the Metadata field in a Thingspeak channel. This feels ineffiient however and I'm hoping there is a better way in Thingspeak - an application I am already so familiar and comfortable with. Also, I have done a lot of experimenting with Amazon AWS but I find it extremely complicated and frankly potentiall quite expensive - so I'm hoping someone else may have tackled this in a similar problem. Thank you! Ben

I am currently working on my training model for a neural network on MATLAB desktop. When I am done, I would like to be able to predict new outcomes that weren't from the original dataset using this model and the new data will be collected using Arduino or ESP. My issue is getting this neural network onto a place where it can collect data wirelessly. ThingSpeak looks promising but I don't want to have to retrain my network every time the code executes. Does anyone know of a way to upload a neural network structure to ThingSpeak or something similar?

Example code that forecasts astronomical tides and wind-driven water levels using neural networks