Amazon MLS-C01 Exam - Topic 7 Question 59 Discussion

Actual exam question for Amazon's MLS-C01 exam

Question #: 59
Topic #: 7

A company has video feeds and images of a subway train station. The company wants to create a deep learning model that will alert the station manager if any passenger crosses the yellow safety line when there is no train in the station. The alert will be based on the video feeds. The company wants the model to detect the yellow line, the passengers who cross the yellow line, and the trains in the video feeds. This task requires labeling. The video data must remain confidential.

A data scientist creates a bounding box to label the sample data and uses an object detection model. However, the object detection model cannot clearly demarcate the yellow line, the passengers who cross the yellow line, and the trains.

Which labeling approach will help the company improve this model?

AUse Amazon Rekognition Custom Labels to label the dataset and create a custom Amazon Rekognition object detection model. Create a private workforce. Use Amazon Augmented AI (Amazon A2I) to review the low-confidence predictions and retrain the custom Amazon Rekognition model.

BUse an Amazon SageMaker Ground Truth object detection labeling task. Use Amazon Mechanical Turk as the labeling workforce.

CUse Amazon Rekognition Custom Labels to label the dataset and create a custom Amazon Rekognition object detection model. Create a workforce with a third-party AWS Marketplace vendor. Use Amazon Augmented AI (Amazon A2I) to review the low-confidence predictions and retrain the custom Amazon Rekognition model.

DUse an Amazon SageMaker Ground Truth semantic segmentation labeling task. Use a private workforce as the labeling workforce.

Show Suggested Answer

Suggested Answer: B

by Derick at Jun 27, 2022, 09:19 PM

Limited Time Offer

25%

Off

Get Premium MLS-C01 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

William

4 months ago

Not sure if a private workforce is the way to go... seems risky.

upvoted 0 times

...

Emiko

4 months ago

Totally agree with D! Semantic segmentation is key here.

upvoted 0 times

...

Phyliss

4 months ago

Wait, can Amazon Rekognition even handle that level of detail?

upvoted 0 times

...

Zana

4 months ago

I think B could work too, but not as effectively.

upvoted 0 times

...

Mitsue

4 months ago

Option D sounds like the best choice for precise labeling.

upvoted 0 times

...

Lorrie

5 months ago

I recall that using a private workforce can help maintain data confidentiality, but I’m not sure if that’s enough for this specific case. I need to think more about the best labeling approach.

upvoted 0 times

...

Karl

5 months ago

I practiced a similar question where we had to choose between different labeling methods. I think using Amazon SageMaker Ground Truth for semantic segmentation could really improve the model's accuracy.

upvoted 0 times

...

Gretchen

5 months ago

I'm not entirely sure, but I feel like using Amazon Rekognition Custom Labels could work too. It seems like a good option for object detection, but I'm not confident about the yellow line detection.

upvoted 0 times

...

Ciara

5 months ago

I remember studying about different labeling techniques, and I think semantic segmentation might be the best approach here since it can help with precise boundary detection.

upvoted 0 times

...

Sheridan

5 months ago

I'm a bit confused on this one. I know Netezza is a data warehousing appliance, but I'm not sure about the specific file system they use. I'll have to eliminate the options that don't seem to fit and then make an educated guess.

upvoted 0 times

...

Armando

5 months ago

Alright, I'm feeling pretty confident about this one. I'm going to carefully consider each option and select the one that best fits the description of what is not kept in the Business Unit Master table.

upvoted 0 times

...

Lanie

5 months ago

I feel uncertain about option C, but I thought we could iterate mappings in some way, possibly with a loop or something.

upvoted 0 times

...

Shonda

5 months ago

Easy to deploy, security, less ports opened on firewall - those all sound like potential advantages. I'll have to weigh the options.

upvoted 0 times

...