Privacy preserving clustering (c-mean, K-mean) for spatio temporal data using distributed computing (MapReduce, Spark)

- For step 1, I will use the symmetric directional chamfer distance as a similarity measure and I will use k-medoids as a clustering algorithm. I will test the accuracy of the clustering algorithm using the Between-Like and Within-Like criteria as in the paper (file: [login to view URL]), where the exemplary trajectory here will be the medoid for every cluster and the distance as our new symmetric directional chamfer distance measure. This will ensure that trajectory A is similar to B if (a) spatially close and (b) directions are similar even if trajectory A is a subset of B or vice versa.

I am Prajwal Bhatt, a final year undergraduate student at IIT Roorkee. I am a creative, flexible and focused individual who is passionate about Data Science, Natural Language Processing and the entire Analytics space. I have acquired knowledge of R programming, Python and C++. Further, I have exposure to Machine Learning algorithms like Neural Network, Regression, Decision Trees, and Clustering algorithms etc. I have experience of working as a data science intern in various recognized companies and start-ups before, Schlumberger, Razorpay, KUAI (Israel, Remote intern); to name a few.

Hi, I already implemented K-means algorithm using Mapreduce and spark I will share you the codes Contact me for more details Relevant Skills and Experience Please review my profile Proposed Milestones $222 AUD - Project fee

Python and few other skills required to get this done are within my reach and i will appreciate you allow me do this Relevant Skills and Experience Cryptography, Data Science, Map Reduce, Python, Spark Proposed Milestones $100 AUD - initial milestone deadline??

A proposal has not yet been provided