classification
Human activity recognition, which involves recognizing human activities from sensor data, has drawn a lot of interest from researchers and practitioners as a result of the advent of smart homes, smart cities, and smart systems. Existing studies on activity recognition mostly concentrate on coarse-grained activities like walking and jumping, while fine-grained activities like eating and drinking are understudied because it is more difficult to recognize fine-grained activities than coarse-grained ones.
- Categories:
624 Views
The data is collected in the form of csv file containing three attributes of X, Y, Z which represents the three coordinates of the graph x, y and z. The csv file is collected from the three signals generated by using a mobile app G sensor logger available publicly from google playstore. The data is generated for the first five Telugu language characters. The data is stored in the form of five folders where each folder represents the respective Telugu character. This dataset can be used for evaluating machine learning algorithms.
- Categories:
110 Views
<p>Anonymized data used in the study of "<span style="font-family: Calibri, sans-serif; font-size: 11pt;">Administrative data processing, Clustering, classification, and association rules, Human factors and ergonomics, Machine learning"</span></p>
- Categories:
251 Views
This is the dataset we collected for the article "Scalable Undersized Dataset RF Classification: Using Convolutional Multistage Training". 17 objects were collected in the laboratory and scanned using a 'cw radar' setup featuring 2x UWB antennas (1 transmit antenna, 1 receive antenna), inside anechoic chamber. There was no clutter added in the experiment.
- Categories:
1380 Views
This dataset is comprised of two parts. In dataset 1, we provide Buddha images, along with positions of hands and faces. Dataset 2 provides Buddha images only and can be used for Buddha statue classification.
- Categories:
455 Views
This article presents the details of the Cardinal RF (CardRF) dataset. CardRF is acquired to foster research in RF- based UAV detection and identification or RF fingerprinting. RF signals were collected from UAV controllers, UAV, Bluetooth, and Wi-Fi devices. Signals are collected at both visual line-of-sight and beyond-line-of-sight. The assumptions and procedure for the data acquisition are presented. A detailed explanation of how the data can be utilized is discussed. CardRF is over 65 GB in storage memory.
- Categories:
8537 Views
This dataset is a collection of images and their respective labels containing multiple Indian coins of different denominations and their variations. The dataset only contains images of one side of each coin (Tail side) which contains the denomination value.
The samples were collected with the help of a mobile phone while the coins were placed on top of a white sheet of A4-sized paper.
- Categories:
3435 Views
This dataset consists of real paddy field images taken from various heights under variable natural lighting conditions. Also, this dataset consists of images with water and soil background removed and annotated images, representing different kinds of plants (paddy, weeds of paddy such as grass, broadleaved weed, sedges) in different color for groundtruth.
- Categories:
4242 Views
The DREAM (Data Rang or EArth Monitoring): a multimode database including optics, radar, DEM and OSM labels for deep machine learning purposes.
DREAM, is a multimodal remote sensing database, developed from open-source data.
The database has been created using the Google Earth Engine platform, the GDAL python library; the “pyosm” python package developed by Alexandre Mayerowitz (Airbus, France). If you want to use this dataset in your study, please cite:
- Categories:
765 Views