Machine Learning
We provide a large benchmark dataset consisting of about: 3.5 million keystroke events; 57.1 million data-points for accelerometer and gyroscope each; and 1.7 million data-points for swipes. Data was collected between April 2017 and June 2017 after the required IRB approval. Data from 117 participants, in a session lasting between 2 to 2.5 hours each, performing multiple activities such as: typing (free and fixed text), gait (walking, upstairs and downstairs) and swiping activities while using desktop, phone and tablet is shared.
- Categories:
9599 Views
Overview
- Categories:
989 Views
Hepatitis B virus (HBV) causes chronic infection in 250 million people worldwide. Chronic HBV carriers have a high risk of fibrosis, cirrhosis, and hepatocellular carcinoma. Drug resistance often develops during long-term antiviral treatment using HBV polymerase/reverse transcriptase inhibitors, making anti-HBV therapies as well as drug development more complicated. In this paper, a machine learning method based on large scale of gene expression profiles was used for anti-HBV drug screening.
- Categories:
191 Views
Traditional Static Timing Analysis (STA) assumes only single input switches at a time with the side input held at non-controlling value. This introduces unnecessary pessimism or optimism which may cause degradation of performance or chip failure. Modeling Multi-Input Switching (MIS) requires a good amount of simulations hence we provide a dataset comprising of SPICE simulations done on 2 input NAND and NOR gate.
- Categories:
242 Views
Summary: The archive of DCLN project (https://sourceforge.net/projects/dcln/) is provided.
Code & Script: Written in C/C++, run Shell scripts on Linux system. Mature DCLNv2 package available for download. Check './dcln.sh' for usage info.
Document: Details of hyperparameters tuning, data preprocessing and code compiling are given.
Data: Four nonlinear simulation datasets are provided (Fig. 2 of the main paper). Each study has ~2000 training samples and ~2000 test samples.
---
- Categories:
1749 Views
This data contains EMG records of forearm movements. this data can be used for the learning process for students and lecturers or researchers. The sensor used to record data is "Myo Arm-Band". The data is equipped with eight features and ends with the arm movement label still using the Indonesian language term.
- Categories:
626 Views
The development of technology also influences changes in campaign patterns. Campaign activities are part of the process of Election of Regional Heads. The aim of the campaign is to mobilize public participation, which is carried out directly or through social media. Social media becomes a channel for interaction between candidates and their supporters. Interactions that occur during the campaign period can be one indicator of the success of the closeness between voters and candidates. This study aims to get the pattern of campaign interactions that occur on Twitter social media channels.
- Categories:
232 Views
This data consists of ten gestures. The format is CSV, arranged in thirty features that end with a label. Each movement is repeated five times and the coordinates are obtained. The sensor used is LeapMotion. This data can be used as a means of machine learning exercises. can be used for students learning machine learning subjects. articles that have used this data can be seen at the link: https://doi.org/10.1109/CENIM.2018.8711397
- Categories:
1018 Views
This dataset is part of my PhD research on malware detection and classification using Deep Learning. It contains static analysis data: Top-1000 imported functions extracted from the 'pe_imports' elements of Cuckoo Sandbox reports. PE malware examples were downloaded from virusshare.com. PE goodware examples were downloaded from portableapps.com and from Windows 7 x86 directories.
- Categories:
6226 Views
This dataset is part of my PhD research on malware detection and classification using Deep Learning. It contains static analysis data: Raw PE byte stream rescaled to a 32 x 32 greyscale image using the Nearest Neighbor Interpolation algorithm and then flattened to a 1024 bytes vector. PE malware examples were downloaded from virusshare.com. PE goodware examples were downloaded from portableapps.com and from Windows 7 x86 directories.
- Categories:
2757 Views