Machine Learning

Anonymous network traffic is more pervasive than ever due to the accessibility of services such as virtual private networks (VPN) and The Onion Router (Tor). To address the need to identify and classify this traffic, machine and deep learning solutions have become the standard. However, high-performing classifiers often scale poorly when applied to real-world traffic classification due to the heavily skewed nature of network traffic data.

This dataset accurately models the internal behavior of an IoT spectrum sensor (belonging to the ElectroSense platform and consisting of a Raspberry Pi 3 with a software-defined radio kit) when it is functioning normally and under attack. To accomplish it, the system calls of the IoT sensor are monitored under normal behavior, gathered, cleaned, and stored in a centralized directory. Then, the device is infected with current malware affecting IoT devices, such as the Bashlite botnet, Thetick backdoor, Bdvl rootkit, and a Ransomware proof of concept.

The EegDoc data set collected using a Cerebus neural signal acquisition equipment involved 2 types of odors (smelling like roses and rotten odors), each with 5 concentrations. Five concentrations of the rose odor are expressed as A10-3.0 (A30), A10-3.5 (A35), A10-4.0 (A40), A10-4.5 (A45) and A10-5.0 (A50), and five concentrations of the rotten odor are expressed as C10-4.0 (C40), C10-4.5 (C45), C10-5.0 (C50), C10-5.5 (C55) and C10-6.0 (C60).

This repository contains code to apply the ESPER method to quasi-continuum models of biomolecules exhibiting multiple degrees of freedom, as described in Seitz et al. (2022, IEEE TCI). As inputs into ESPER, detailed instructions are also provided for generating custom synthetic datasets with increasing complexity to mirror known cryo-EM image attributes.