Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 days ago.
Improve this question
I currently researching for a Digital Twin implementation of metal manufacturing production line with a large number of process steps (machines, robot).
My intention is to model the basic behaviour of the machines of the production (rolling mill, gas and induction furnace etc.) and the behavior of the product also with the target of zero defects.
I have available some sensor and historical data for each process.
The limitation of this implementation approach is the use of only free or open-source technologies/tools
What are the proper steps to start the modelling?
How can I create a model with the physics equations that occur in its process step by using sensors and historical data from the production line? can you explain how this will work?
Will be this a physics-based digital twin and can it be extended in a model-based or hybrid one if the 3d model of the production line is captured in the future?
thank you,
Alexis
Related
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 1 year ago.
Improve this question
I came across this research paper-http://www.cs.sjsu.edu/~pollett/papers/neural_net_plain.pdf.
These researchers have come up with a way to break character-based CAPTCHAs and it seems they have succeeded as they have used 13 million captchas for training the CNN they made and got accuracies higher than 95%.
How can we make a CAPTCHA secure so that it isn't bypassed by a deep learning model?
First of all, captchas are meant to stop automated users/bots. Yes, if you have the actual captcha generator, and you train a deep learning model on that distribution, chances are it will perform well.
Captchas are getting harder, they can be made even harder. But, it takes resources to generate the captchas, actual computational resources (unless they are random images and not synthetic). If it is needed to make a really bot-proof website, it can be made.
By bot, it usually means web scraping tools/automated users, who try to do things like human users, but very fast. Now, if you also integrate, deep learning models to it, it's possible to bypass the captchas (in most cases), but it may be an overkill (depending on your needs).
Saving websites from bots is less important than facial recognition, self-driving cars (relative statement).
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 1 year ago.
Improve this question
I have a few lists of movement tracking data, which looks something like this
I want to create a list of outputs where I mark these large spikes, essentially telling that there is a movement at that point.
I applied a rolling standard deviation on the data with a window size of two and got this result
Now I can see the spikes which mark the point of interest, but I am not sure how to do it in code. A statistical tool to measure these spikes, which can be used to flag these spikes.
There are several approaches that you can use for an anomaly detection task.
The choice depends on your data.
If you want to use a statistical approach, you can use some measures like z-score or IQR.
Here you can find a tutorial for these measures.
Here instead, you can find another tutorial for a statistical approach which uses mean and variance.
Last but not least, I suggest you also to check how to use a control chart, because in some cases it's enough.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 2 years ago.
Improve this question
I'm trying to design a game which is similar to Plague Inc. and it is essentially where there is a deadly virus (quite ironic) which is spreading and the aim of the game is to stop the virus from spreading.
I've split the world into 13 regions, and each region will have several key details I will need to use, such as the number of cases, the number of deaths and the population. With each of these details, I will want some of them to be dynamic, such as wanting the amount of cases and deaths to go up or down.
I'm extremely new to python, and was hoping for some particular expertise in how to design this game. Any guidance of the best ways to represent this data would be much appreciated!
Hello Aran Khalastchi,
Based off of my experiences, Python is not really a graphical programming language, and more of a text based language. I wouldn't suggest Python as your go to unless you are using a library for graphics. If not, I definitely recommend Unity or Godot, and if you want to go fully raw code (no engines/libraries) I recommend Java as it has its own graphics. If I am wrong, please forgive me :)
Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.
Closed 2 years ago.
Improve this question
I want to forecast upcoming total users on a daily basis within Python using a machine learning algorithm. Check the pattern below:
Looking at this graph, I was wondering if someone knows which forecasting method in Python I should use to predict?
Thanks!
If you have no additional data expect the user data over time which you have shown, the only thing you can do is try to find a function dependent on time which gives you a good approximation for that plot (ordinary curve fitting). I suppose that's not what you want.
To do a predection (which can be done not only by a machine learning approach), you need other data which is somehow correlated to the data you want to predict.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I am doing an end-to-end self driving car project using deep learning. After some research, I found out there are some datasets available. However, the dataset contains parameters such as steering angle, speed and the time taken.
So now, I have tried using the dataset to train my model and run the output using a road I have taken in my country. However, the training dataset road were taken in United States and my output road video is from a Malaysian road. Therefore, the steering angle accuracy is not very accurate. This is the current dataset format in .txt file: filename.jpg angle
What can I do with this. Either should I create a new dataset or take an existing one and tune according to the output video?
To create a new dataset, I require parameters such as steering angle. How should I take that without a sensor? Is it possible?
The SA would not matter when it comes to interpreting the road in your country. It will improve the more you train it It is dependable on the structure of your neural network and how you have coded it to learn. It is no mean feat!
By logic it would amend the SA by the boundaries that it will recognize and learn to avoid. It would also need to factor in different variables such as the weight, velocity, tyre, ABS, EPS, TC..etc. There is a phenomenal amount of physic behind it. That is if you want to make a fully functioning safe vehicle anyway. If your making a toy version it wont really matter too much.