Artificial Intelligence
The datasets needed to train the model ((a)-(d) shown in the figure) are stored here.
- Categories:
109 Views
All data were randomly selected from the CSE-CIC-IDS2018 dataset. The data fields were censored after going through the analysis and 64 valid features were retained.
There are 5 types of data, they are Benign, DoS, DDoS, Botnet and Infiltration.
- Categories:
190 Views
Slow-rate DDoS attacks are recent threats targeting next-generation networks such as IoT, 5G, etc. Unlike conventional high-rate DDoS, slow-rate DDoS have not been deeply studied, mainly due to the limited number of existing datasets with real traces.
- Categories:
2119 Views
AHT2D dataset is composed of Handwritten Arabic letters with diacritics. In this dataset, we have 28 letter classes according to the number of Arabic letters. Each class contains a multiple letter form. We have different letter images from different sources such as the internet, our writers, etc. The AHT2D dataset includes only isolated letters. In addition, this dataset contains different writing styles, orientations, colors, thicknesses, sizes, and backgrounds, which makes it a very large and rich dataset.
- Categories:
769 Views
This data is for deep reinforcement leaming in real-time security constrained ecomomic dispatch on IEEE 118-bus system. The data includes system topology, wind generation and power demand for 1000 days with 5 min temporal resolution.
- Categories:
133 Views
This is the largest database of hyperspectral face images containing hyperspectral image cubes of 78 subjects imaged in multiple sessions. The data was captured with the CRI's VariSpec LCTF (Liquid Crystal Tunable Filter) integrated with a Photon Focus machine vision camera. There are 33 spectral bands comering the 400 - 720nm range with a 10nm step. The noise level in the dataset is relatively lower because we adapted the camera exposure time to the transmittance of the filter illumination intensity as well as CCD sensitivity in each band.
- Categories:
508 Views
This dataset was collected in our lab using Kinect to emphasize three points: (1) Larger number of human activities. (2) Each subject performed all actions in a continuous manner with no breaks or pauses. Therefore, the start and end positions of body for the same actions are different. (3) Each subject performed the same actions four times while imaged from four different views: front view, left and right side views, and top view.
- Categories:
1112 Views
The femur dataset is our internal dataset, which
was collected from the clinical data of the Affiliated Hospital
of Capital Medical University, including 41 knee joint CT
scans, with a total of 7121 axial enhanced knee joint clinical
CT images. The dataset is shown in Fig. 5, which can be
downloaded in our github.
- Categories:
358 Views
Reference Evapotranspiration (ETo) is the basic element of smart irrigation water management for sustainable developments in agriculture. Penman-Monteith (FAO-56 PM) is the standard method of ETo. The FAO-56 PM is complex in nature due to the requirements of many climatic conditions. Many existing machine learning-based solutions for simplification of ETo are limited to a specific area and not in accordance with the standard method FAO-56 PM.
- Categories:
166 Views
SWAN is a large-scale outdoor point cloud semantic segmentation, instance segmentation and object detection dataset. The dataset is targeted explicitly at the challenging urban environment, which aligns well with the needs of the intelligent transportation systems. The data is collected in the Central Business District (CBD) of Perth city in Australia, covering nearly 150km. It additionally used specialized equipment (portable trolley) to capture scenes of no-through roads and narrow streets.
- Categories:
606 Views