Convolution with sign function

In summary, the conversation discusses a problem with calculating a convolution and the suggestion to look at two separate cases and try a different approach using ##\tau-t## as the argument of sgn. The person trying the suggestion reports getting an incorrect answer.
  • #1
PhysicsGirl90
17
0
Hello all,

I am having some trouble calculating a convolution. For the question, and my attempt at a solution, please take a look at the pic. Can someone please point me in the right direction?
 

Attachments

  • question1.png
    question1.png
    6.4 KB · Views: 713
Physics news on Phys.org
  • #2
I didn't check your work closely. If it's correct, you probably want to now look at two cases separately: t<0 and t>0.

The other suggestion I'd have is to try using ##\tau-t## as the argument of sgn instead of the exponential. It might make the integral easier to analyze.
 
  • #3
Ok, I will try it and see what i get
 
  • #5


Sure, I'd be happy to help. Convolution with the sign function can be a bit tricky, but here are some steps you can follow to calculate it:

1. Start by writing out the definition of convolution: (f * g)(t) = ∫f(τ)g(t-τ)dτ, where * represents convolution, f and g are functions, and τ is a dummy variable for integration.

2. In this case, our functions are the sign function, sgn(x), and another function, h(x). So the convolution will be (sgn * h)(t) = ∫sgn(τ)h(t-τ)dτ.

3. Next, we need to consider the limits of integration. Since the sign function is only defined for positive and negative numbers, we can split the integral into two parts: one for positive τ and one for negative τ. This gives us (sgn * h)(t) = ∫sgn(τ)h(t-τ)dτ = ∫[sgn(τ)h(t-τ)]dτ + ∫[sgn(τ)h(t-τ)]dτ.

4. Now, we can use the definition of the sign function to simplify the integrands. For positive τ, sgn(τ) = 1, and for negative τ, sgn(τ) = -1. So our integral becomes (sgn * h)(t) = ∫h(t-τ)dτ - ∫h(t-τ)dτ.

5. Finally, we can use a change of variables to simplify the integrals. Let u = t-τ, so du = -dτ. This gives us (sgn * h)(t) = ∫h(u)du - ∫h(u)du = 0.

So the convolution of the sign function with any other function will always be 0. I hope this helps! Let me know if you have any further questions or need clarification. Good luck!
 

Related to Convolution with sign function

What is "Convolution with sign function"?

"Convolution with sign function" refers to a mathematical operation used in signal processing and image analysis that combines two functions to create a third function. It involves multiplying one function by a flipped and shifted version of the other function, and then integrating the product over their overlapping domain. The resulting function is called the convolution of the two original functions.

What is the sign function?

The sign function is a mathematical function that returns the sign of a given number, indicating whether it is positive, negative, or zero. It is usually denoted as "sgn(x)" and is defined as:

sgn(x) = 1, if x > 0

sgn(x) = 0, if x = 0

sgn(x) = -1, if x < 0

What is the purpose of using the sign function in convolution?

The sign function is used in convolution to assign a weight to each point in the overlapping domain of the two functions being convolved. This weight is either 1 or -1, depending on the sign of the other function at that point. This helps to emphasize or de-emphasize certain parts of the resulting convolution function, depending on the alignment of the two original functions.

What are some practical applications of convolution with sign function?

Convolution with sign function has various applications in signal processing, image analysis, and computer vision. It is commonly used for edge detection, noise reduction, feature extraction, and pattern recognition. It is also used in machine learning algorithms, such as convolutional neural networks, for image and speech recognition tasks.

What are the limitations of convolution with sign function?

One limitation of convolution with sign function is that it is sensitive to noise and outliers in the original functions. This can result in distorted or inaccurate convolution results. Additionally, the size and shape of the overlapping domain can also affect the accuracy of the convolution. Another limitation is that convolution with sign function is a computationally intensive operation, making it less suitable for real-time applications.

Similar threads

  • Advanced Physics Homework Help
Replies
0
Views
309
  • Computing and Technology
Replies
3
Views
2K
  • Advanced Physics Homework Help
Replies
4
Views
1K
  • Advanced Physics Homework Help
Replies
2
Views
1K
  • Calculus
Replies
2
Views
2K
  • Advanced Physics Homework Help
Replies
2
Views
2K
  • Calculus and Beyond Homework Help
Replies
1
Views
269
  • Engineering and Comp Sci Homework Help
Replies
2
Views
181
  • Engineering and Comp Sci Homework Help
Replies
1
Views
847
  • Calculus and Beyond Homework Help
Replies
10
Views
1K
Back
Top