Segmenting accelerometer data from daily life with unsupervised machine learning

Unsupervised Learning from Dyadic Data

Dyadic data refers to a domain with two nite sets of objects in which observations are made for dyads, i.e., pairs with one element from either set. This includes event co-occurrences, histogram data, and single stimulus preference data as special cases. Dyadic data arises naturally in many applications ranging from computational linguistics and information retrieval to preference analysis and ...

Unsupervised Machine Learning

Segmenting Descending Aorta using Machine Learning

The descending aorta is one of the most important vessel structures in the body. It is the largest artery in the body that runs down through the chest and the abdomen. The descending aorta begins below the arch of the aorta and ends by splitting into two great arteries (the common iliac arteries), which go to the legs. It has been observed that atherosclerosis of the descending aorta is a usefu...

Unsupervised Learning with Permuted Data

We consider the problem of unsupervised learning from a matrix of data vectors where in each row the observed values are randomly permuted in an unknown fashion. Such problems arise naturally in areas such as computer vision and text modeling where measurements need not be in correspondence with the correct features. We provide a general theoretical characterization of the difficulty of “unscra...

How to Quantitatively Compare Data Dissimilarities for Unsupervised Machine Learning?

For complex data sets, the pairwise similarity or dissimilarity of data often serves as the interface of the application scenario to the machine learning tool. Hence, the final result of training is severely influenced by the choice of the dissimilarity measure. While dissimilarity measures for supervised settings can eventually be compared by the classification error, the situation is less cle...