Refering to the link at here, about the timedelaynet(inputDelays,hiddenSizes,trainFcn), what is the unit for inputDelays? Is in in seconds?
The unit is cardinal, i.e. unitless. MATLAB doesn't understand units, it only understands numbers. Thus, whatever units your data have, will be what inputDelays will be. If your data is in seconds, so will inputDelays be, if your data is in years, so will inputDelays be, etc..
Related
I would like to predict the switching behavior of time-dependent signals. Currently the signal has 3 states (1, 2, 3), but it could be that this will change in the future. For the moment, however, it is absolutely okay to assume three states.
I can make the following assumptions about these states (see picture):
the signals repeat periodically, possibly with variations concerning the time of day.
the duration of state 2 is always constant and relatively short for all signals.
the duration of states 1 and 3 are also constant, but vary for the different signals.
the switching sequence is always the same: 1 --> 2 --> 3 --> 2 --> 1 --> [...]
there is a constant but unknown time reference between the different signals.
There is no constant time reference between my observations for the different signals. They are simply measured one after the other, but always at different times.
I am able to rebuild my model periodically after i obtained more samples.
I have the following problems:
I can only observe one signal at a time.
I can only observe the signals at different times.
I cannot trigger my measurement with the state transition. That means, when I measure, I am always "in the middle" of a state. Therefore I don't know when this state has started and also not exactly when this state will end.
I cannot observe a certain signal for a long duration. So, i am not able to observe a complete period.
My samples (observations) are widespread in time.
I would like to get a prediction either for the state change or the current state for the current time. It is likely to happen that i will never have measured my signals for that requested time.
So far I have tested the TimeSeriesPredictor from the ML.NET Toolbox, as it seemed suitable to me. However, in my opinion, this algorithm requires that you always pass only the data of one signal. This means that assumption 5 is not included in the prediction, which is probably suboptimal. Also, in this case I had problems with the prediction not changing, which should actually happen time-dependently when I query multiple predictions. This behavior led me to believe that only the order of the values entered the model, but not the associated timestamp. If I have understood everything correctly, then exactly this timestamp is my most important "feature"...
So far, i did not do any tests on Regression-based approaches, e.g. FastTree, since my data is not linear, but keeps changing states. Maybe this assumption is not valid and regression-based methods could also be suitable?
I also don't know if a multiclassifier is required, because I had understood that the TimeSeriesPredictor would also be suitable for this, since it works with the single data type. Whether the prediction is 1.3 or exactly 1.0 would be fine for me.
To sum it up:
I am looking for a algorithm which is able to recognize the switching patterns based on lose and widespread samples. It would be okay to define boundaries, e.g. state duration 3 of signal 1 will never last longer than 30s or state duration 1 of signal 3 will never last longer 60s.
Then, after the algorithm has obtained an approximate model of the switching behaviour, i would like to request a prediction of a certain signal state for a certain time.
Which methods can I use to get the best prediction, preferably using the ML.NET toolbox or based on matlab?
Not sure if this is quite what you're looking for, but if detecting spikes and changes using signals is what you're looking for, check out the anomaly detection algorithms in ML.NET. Here are two tutorials that show how to use them.
Detect anomalies in product sales
Spike detection
Change point detection
Detect anomalies in time series
Detect anomaly period
Detect anomaly
One way to approach this would be to first determine the periodicity of each of the signals independently. This could be done by looking at the frequency distribution of time differences between measurements of state 2 only and separately for each signal.
This will give a multinomial distribution. The shortest time difference will be the duration of the switching event (after discarding time differences less than the max duration of state 2). The second shortest peak will be the duration between the end of one switching event and the start of the next.
When you have the 3 calculations of periodicity you can simply calculate the difference between each of them. Given you have the timestamps of the measurements of state 2 for each signal you should be able to calculate the time of switching for all other signals.
I intend to run a Matlab Simulink model (of 400 ODEs i.e. 400 ODE models) with a fixed step size of 200e-06 and a simulation/stop time of 52 hours. As per my understanding, the Simulink stop time unit is in seconds. Does it mean that I need to run the simulation for (52*3600) 187200 seconds?? Further, I realized that running the Simulink model with a simulation time of 187200 seconds will take a very large time (maybe a couple of months which is not a feasible option), irrespective, of high computer configuration or vectorized/parallelized model structure.
Can someone please let me know the relationship between stepsize and simulation/stop time??
Thank you for you time.
Regards
Step size and simulation duration are independent parameters.
For a fixed step simulation, you have the following relation :
NumberSteps = Duration / StepSize
The designer of the model should decide what is the time unit and design it accordingly.
It can be anything, seconds, hours, weeks,..., you only have to make sure that the calculations in the model are consistent with the unit you chose.
For example, you can model speed in m/s, km/h, miles/h, ... and make the same 1 s calculations either with 1 (s) step or 1/3600 (h) step.
The question is to know in which time unit the model you use was designed?
If the model uses a 1 second logic, then :
NumberSteps = 52 * 3600 / (200e-6) = 936e6
This is an unusual high number of steps and explains the too long run time.
I would question the need to have such a small step size for such a long duration.
It's also possible to model the same system with a 1 hour logic.
In this case :
NumberSteps = 52 / (200e-6) = 260e3
Stepsize = 200e-6 h = 0.72 s
This becomes an usual number of steps for a simulation and should run in a few seconds or minutes depending on model complexity
I have a problem that I don't have enough training data for my NN. It is trying to predict the result of a soccer game given the last games which I woulf say is a regression task.
The training data are results of soccer games of the last 15 seasons (which are about 4500 games). Getting to new data would be hard and would take a lot of time.
What should I do now?
Is it good to duplicate the data?
Should I input randomized data? (Maybe noise but I'm not quite sure what that is)
If there is no way of creating more data,
I should probably turn up the learning rate right? (I have it sitting at 0.01 and the momentum at 0.9)
I am using mini batches consisting of 32 training datas in training. Since I don't have a lot of training I don't have a lot of mini batches. Should I stop using them?
To start from the beginning: This is a very theoretical question and is not directly related to programming, which I recommend (in future) to post over at the Data Science Stackexchange.
To go into your problem: 4500 samples is not as bad as it sounds, depending on the exact task at hand. Are you trying to predict the match results (i.e. which team is the winner?), are you looking for more specific predictions (across a lot of different, specific teams)?
If you can make sure that you have a reasonable amount of data per class, one can work with a number of samples lower than what you have. Simply duplicating the data will not help you much, since you are very likely to just overfit on the samples you are seeing, without much of an improvement; Or rather, you will get the same results as training over a longer period (since essentially you see every sample twice per epoch, instead of one).
Again, what usually happens after long training periods is overfitting, so nothing gained here.
Your second suggestion is generally called data augmentation. Instead of simply copying samples, you alter them enough to make it look "different" to the network. But be careful! Data augmentation works well for some inputs, like images, since the change in input is significant enough to not represent the same sample, but still contains meaningful information about the class (a horizontally mirrored image of a cat still shows a "valid cat", unlike a vertically mirrored image, which is more unrealistic in the real world).
Essentially, it depends on your input features to determine where it makes sense to add noise. If you are only changing the results of the previous game, a minor change in input (adding/subtracting one goal at random) can significantly change the prediction you make.
If you slightly scramble ELO scores by a random number, on the other hand, the input value will not be too different, "but different enough" to use it as a novel example.
Turning up the learning rate is not a good idea, since you are essentially just letting the network converge more towards the specific samples. On the contrary, I would argue that the current learning rate is still too high, and you should certainly not increase it.
Regarding mini batches, I think I have referenced this a million times now, but always consider smaller minibatches. From a theoretical point of view, you are more likely to converge to a local minimum.
I have used ANNs to classify data before, but not for time series data. Basically I want to know the possibility (relative ease) for a neural network to take a bunch of previous time series data, then be able to predict into the future for not just a single point in time (for which it's been trained), but for an arbitrary point in time (up to certain limits, of course)
is the best/simplest way to train a bunch of ANNs, each one targeting different time horizons (e.g. 1 hours, 2 hours, 5 hours, 24 hours), then if you want a prediction for another time, say 3 hours, use something like interpolation to try and forecast?
How can I structure my problem to handle this? Is there a particular neural network design that is suited to this application. Please let me know your thoughts.
Good morning,
I have a question about the time execution of a script on Matlab. Is it possible to know previously how long spend the execution of a script before running it (an estimated time, for example)? I know that with tic and toc command, among others, is it possible to know the time at the end but I don't know if it's possible to know it before.
Thanks in advance,
It is not too hard to make an estimate of how long your calculation will take.
You already know how to record calculation times with tic and toc, so now you can do this:
Start with a small scale test (example, n=1) and record the calculation time
Multiply n with a constant k (I usually choose 2 or 10 for easy calculations), record the calculation time
Keep multiplying with n untill you find a consistent relation: 'If I multiply my input size with k, my calculation time changes like so ...'
Now you can extrapolate your estimated calculation time by:
calculating how many times you need to multiply input size of the biggest small scale example to get your real data size
Applying the consistent relation that you found exactly that many times to the calculation time of your biggest small scale example
Of course this combines well with some common sense, like if you do certain things t times they will take about t times as long. This can easily be used when you have to perform a certain calculation a million times. Just interrupt the loop after a minute or so, if it is still in the first ten calculations you may want to give up!