Machine Learning
The goal of our research is to identify malicious advertisement URLs and to apply adversarial attack on ensembles. We extract lexical and web-scrapped features from using python code. And then 4 machine learning algorithms are applied for the classification process and then used the K-Means clustering for the visual understanding. We check the vulnerability of the models by the adversarial examples. We applied Zeroth Order Optimization adversarial attack on the models and compute the attack accuracy.
- Categories:
2149 Views
ASSIST2009 was collected during the school year 2009-2010. Due to including duplicates when first released, the dataset was updated later. Based on the latest updated version, we remove users with less than three records, and remove the records without skills as well as scaffolding problems. After preprocessing, the dataset used in this article contains 283,104 interactions given by 4,151 students to a total of 16,891 distinct exercises and 101 skills.
- Categories:
103 Views
Air travel is one of the most used ways of transit in our daily lives. So it's no wonder that more and more people are sharing their experiences with airlines and airports using web-based online surveys. This dataset aims to do topic modeling and sentiment analysis on Skytrax (airlinequality.com) and Tripadvisor (tripadvisor.com) postings where there is a lot of interest and engagement from people who have used it or want to use it for airlines.
- Categories:
669 Views
This dataset's data is from the Alibaba-Security-Algorithm-Challenge, and the related web site is: https://tianchi.aliyun.com/competition/entrance/231694/information
- Categories:
306 Views
This is the data for the paper "Fusion of Human Gaze and Machine Vision for Predicting Intended Locomotion Mode" published on IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022.
- Categories:
252 Views
This dataset is used to illustrate an application of the "klm-based profiling and preventing security attack (klm-PPSA)" system. The klm-PPSA system is developed to profile, detect, and then prevent known and/or unknown security attacks before a user access a cloud. This dataset was created based on “a.patrik” user logical attempts scenarios when accessing his cloud resources and/or services. You will find attached the CSV file associated with the resulted dataset. The dataset contains 460 records of 13 attributes (independent and dependent variables).
- Categories:
348 Views
StEduCov, a dataset annotated for stances toward online education during the COVID-19 pandemic. StEduCov has 17,097 tweets gathered over 15 months, from March 2020 to May 2021, using Twitter API. The tweets are manually annotated into agree, disagree or neutral classes. We used a set of relevant hashtags and keywords. Specifically, we utilised a combination of hashtags, such as '#COVID 19' or '#Coronavirus' with keywords, such as 'education', 'online learning', 'distance learning' and 'remote learning'.
- Categories:
777 Views
We collect IMU measurements under three different patterns: Fixing a smartphone in front of his chest (chest), swing a smartphone while holding it in his hand (swing), and putting a smartphone in his pocket (pocket). We use Google Pixel 3XL for the pattern of chest and Google Pixel 3a for the patterns of swing and pocket. The sampling frequency of each measurement is fixed to 15Hz. We collect the measurement of 111 paths in total, categorized into 4 types. We partition them into 84 and 27 paths, used for training and testing, respectively. It takes 10 hours to collect all datasets.
- Categories:
201 Views
This dataset includes the relevant data for the journal article titled 'A Novel LSTM Pipeline to Detect Anomalies in Manufacturing Production'. In this paper, we present a novel anomaly detection method using a semi-supervised LSTM forecasting approach to highlight process anomalies in a complex, real-world dataset in an automotive manufacturing setting. This data includes two time-series subsets, each with 5000 labeled observations.
- Categories:
74 Views
Visual systems can improve transitions between different locomotion mode controllers (e.g., level-ground walking to stair ascent) by sensing the walking environment prior to physical interactions. Here we developed StairNet to support the development of vision-based stair recognition systems for robotic leg control. The dataset builds on ExoNet – the largest open-source dataset of egocentric images of real-world walking environments.
- Categories:
2659 Views