Exam MLS-C01 All QuestionsBrowse all questions from this exam
Go to Exam
Question 330

A company that operates oil platforms uses drones to photograph locations on oil platforms that are difficult for humans to access to search for corrosion.

Experienced engineers review the photos to determine the severity of corrosion. There can be several corroded areas in a single photo. The engineers determine whether the identified corrosion needs to be fixed immediately, scheduled for future maintenance, or requires no action. The corrosion appears in an average of 0.1% of all photos.

A data science team needs to create a solution that automates the process of reviewing the photos and classifying the need for maintenance.

Which combination of steps will meet these requirements? (Choose three.)

    Correct Answer: A, D, E

    To automate the process of reviewing photos and classifying the need for maintenance, the most suitable steps are: (1) Use an object detection algorithm to train a model to identify corrosion areas in a photo. This will help in pinpointing the exact locations of corrosion. (2) Use an XGBoost algorithm to classify the severity of corrosion once the areas are identified. XGBoost is effective for classification problems, especially after preprocessing through object detection. (3) Perform image augmentation on photos that contain corrosion to improve the model’s ability to generalize by increasing the diversity of the training data. Image augmentation techniques like rotation, scaling, and flipping can enhance the robustness of the detection and classification algorithms. Using Amazon Rekognition might not be sufficient for such specialized detection, and k-means clustering is not suitable for this type of classification task.

Discussion
butamanOptions: ADE

A. Use an object detection algorithm: This can help identify corrosion areas in a photo. E. Perform image augmentation on photos with corrosion: This can improve the model’s ability to generalize by increasing the diversity of the training data. D. Use an XGBoost algorithm: This can classify the severity of the corrosion after the areas of corrosion have been identified. It’s effective for multi-class classification problems.

vkbajoriaOptions: ABE

This is object detection problem, which Rekognitation can do since they have 0.1% corrosion photos, augmentation is necessary

cloudera3Options: ADE

Detecting corrosion is too specialized a task for Rekognition - trying transfer learning would literally mean re-training. AWS blog explaining suitability of Object Detection/Semantic Segmentation (though they prefer the color classification approach using XGBoost): https://aws.amazon.com/blogs/machine-learning/rust-detection-using-machine-learning-on-aws/ The enhancement step may be needed to contrast enhance/sharpen images.

3eb0542Options: ABE

The combination of steps that would meet the requirements is indeed A, B, and E

AIWaveOptions: ABE

A: Yes - train a model that identifies corrosion areas within the photos B: Yes - identify and label objects, including corrosion, in the images. C: No - Not for classification D: No - XGBoost doesn't work on images E: Yes - rotation, scaling, and flipping, can enhance the model’s ability to generalize and improve its performance F: not required

KAST_424Options: ADE

Object detection algorithm can be trained to identify corrosion rather than too customize Rekognition