Oops!

Seems that I haven't yet written any post here.
But you may find some nice quote or artwork in this category →

April 23rd: a jugglable date. Juggling is fun, juggling with numbers: even more. The notation called siteswaps, describing juggling patterns as a sequence of number is well known among jugglers. In th...

 in juggling

Machine learner overfit Machine learning texts are quite dense. Packaging as much information into as little as possible text. Quasi a min-max-problem. Minimizing the amount of text while trying to ma...

 in machine-learning

The question of what is creativity is an enormously fascinating and at the same time very complex one. Although, it got progressively more into focus when it comes to generative models. Machines "crea...

 in machine-learning

When people here about juggling, their first picture in their head is probably the one of a clown with a red nose n > 2 objects simultaneously in the air. However, behind this entertaining art hide...

 in juggling
Hej, I'm Jayjay and in this blog you can find some thoughts of mine.
It is a random collection of some project mixed with thoughts of computational devices, algorithms, and the humans' personal deep neural network: the brain.
Hope you enjoy :) more →
General Topics of mine
HCI & ML
In Human-Computer Interaction (HCI) it is of high interest to understanding users behaviour since this can be used to personalise the user interface and ensure a satisfying user experience. At this, I try to leverage machine learning techniques to investigate data from mouse movements to identify single users and predict the short- and long-term behaviour of users.
logo_mousemovement.svg

Mouse Movement Analysis

The evaluation of the mouse information is usable to measure the users’ mood, draw conclusions about a users’ satisfaction, or get information about a users’ working behaviour and performance.
logo_anomalydetection.svg

Anomaly Detection/ One Class Approaches

Mouse cursor movements are highly influences by many factors (eg. hardware, mood or user interface (UI)) Independent of those influences we try to identify the idiosyncratic movements within the mouse trajectory to autheticate users.
logo_motifs.svg

Motif discovery

Similar to gestures, mouse cursor movement encompasses individual components for every user. Likewise some motifs are not user, but task or cognition load dependent.
logo_timeseries.svg

Time-series analysis

Regarding mouse cursor movements as a sequence of data points collected over time, can deliver valuable information about the point anomalies or other time dependent behaviour.