d) (6 pts.) Online crowdsourcing has become a popular way to tackle problems that are (cur- rently) too complex to be pe

Business, Finance, Economics, Accounting, Operations Management, Computer Science, Electrical Engineering, Mechanical Engineering, Civil Engineering, Chemical Engineering, Algebra, Precalculus, Statistics and Probabilty, Advanced Math, Physics, Chemistry, Biology, Nursing, Psychology, Certifications, Tests, Prep, and more.
Post Reply
answerhappygod
Site Admin
Posts: 899603
Joined: Mon Aug 02, 2021 8:13 am

d) (6 pts.) Online crowdsourcing has become a popular way to tackle problems that are (cur- rently) too complex to be pe

Post by answerhappygod »

D 6 Pts Online Crowdsourcing Has Become A Popular Way To Tackle Problems That Are Cur Rently Too Complex To Be Pe 1
D 6 Pts Online Crowdsourcing Has Become A Popular Way To Tackle Problems That Are Cur Rently Too Complex To Be Pe 1 (104.5 KiB) Viewed 99 times
d) (6 pts.) Online crowdsourcing has become a popular way to tackle problems that are (cur- rently) too complex to be performed by an algorithm but relatively simple for humans, such as detecting sarcasm on social media, solving protein folding puzzles, and classifying galax- ies. One project used crowdsourcing to classify night-time photographs taken by astronauts onboard the International Space Station. Volunteers were asked to identify what the pho- tographs contained: a city, stars, or an aurora. It is thought that 65% of the photos are of a city and 30% of the photos are of stars, with the remaining photos containing an aurora. Suppose that the photos with an aurora are always classified correctly and that photos with a city or stars are classified correctly 85% of the time. Photos with a city are classified as containing an aurora 2% of the time and photos with stars are classified as containing an aurora 6% of the time. If a photo is classified as containing stars, what is the probability that it actually shows a city? Be sure to show your work. e) (16 pts.) A galaxy cluster is an astronomical structure that contains anywhere from hun- dreds to thousands of galaxies bound together by gravity. Measurements of log-intensity (log number of photons) from small patches of the sky can be used to determine whether or not a galaxy cluster exists at a certain location. Galaxy clusters will emit a log-intensity that follows a normal distribution with mean 10 units and standard deviation 3 units. A log- intensity measurement from a part of the sky with no galaxy cluster present is distributed normally with mean 1 unit and standard deviation 1 unit. While there is no way of actually knowing if a galaxy cluster is located in a particular patch, an observation will be considered as having a galaxy cluster if the measured log-intensity has less than 0.02 probability of having come from a patch without a galaxy cluster. It is thought that the probability of a measurement actually being from a galaxy cluster is 0.01. i. Calculate the probability that an observation is considered as having a galaxy cluster. ii. Calculate the probability that an observation with log-intensity measurement greater than 3 units is from a galaxy cluster.
Join a community of subject matter experts. Register for FREE to view solutions, replies, and use search function. Request answer by replying!
Post Reply