Machine Learning
Human facial data hold tremendous potential to address a variety of classification problems, including face recognition, age estimation, gender identification, emotion analysis, and race classification. However, recent privacy regulations, such as the EU General Data Protection Regulation, have restricted the ways in which human images may be collected and used for research.
- Categories:
349 Views
The dataset provides an end-to-end (E2E) perspective of the performance of 360-video services over mobile networks. The data was collected using a network-in-a-box setup in conjunction with a Meta Quest 2 head-mounted display (HMD) and a customer premises equipment (CPE) to provide 5G connectivity to the glasses (WiFi-native).
- Categories:
157 Views
The development of metaverses and virtual worlds on various platforms, including mobile devices, has led to the growth of applications in virtual reality (VR) and augmented reality (AR) in recent years. This application growth is paralleled by a growth of interest in analyzing and understanding AR/VR applications from security and performance standpoints. Despite this growing interest, benchmark datasets are lacking to facilitate this research pursuit.
- Categories:
348 Views
This is the pest image dataset. With this data set at hand, scientists or software engineers may create programs capable of recognizing when creatures harm farm produce. This breadth extends not only across different plants but also covers many types of bugs like aphids, leafhoppers, beetles , caterpillars etcetera providing a large diverse pool from which one can train models designed to detect pests. Arranging photos by pest species makes it easy for people looking into them understand what they should expect find.
- Categories:
1364 Views
The original data includes structured and unstructured impact factors. The structured impact factors are from the wind database, and the unstructured impact factors are from the official Baidu Index website, obtained through the Python 3.8 crawler.
The preprocessed data is filled with the original data after excluding outliers and some missing values, which is used to screen influencing factors.
- Categories:
134 Views
The "CloudPatch-7 Hyperspectral Dataset" comprises a manually curated collection of hyperspectral images, focused on pixel classification of atmospheric cloud classes. This labeled dataset features 380 patches, each a 50x50 pixel grid, derived from 28 larger, unlabeled parent images approximately 4402-by-1600 pixels in size. Captured using the Resonon PIKA XC2 camera, these images span 462 spectral bands from 400 to 1000 nm.
- Categories:
509 Views
The data was collected by outfitting one of the players with the experimental balloon, which incorporated the embedded circuit and sensors. The sensors positioned at the top-right to the player within the bubble balloon, where a player stand inside. The sensors' data were collected at specific sampling frequencies (Accelerometer: 1000Hz, Gyroscope: 1000Hz, and Pressure: 40Hz). The experiment was conducted involving five different players. This approach allowed for the inclusion of diverse data samples, taking into account variations in player metrics, movements, and gameplay dynamics.
- Categories:
180 Views
Early detection of kidney illness can be achieved by training machine learning algorithms to discover patterns in patient data, such as imaging, test results, and medical history. This will enable rapid diagnosis and start of treatment regimens, which can improve patient outcomes. With 98.97% accuracy in CKD detection, the suggested TrioNet with KNN imputer and SMOTE fared better than other models. This comprehensive research highlights the model's potential as a useful tool in the diagnosis of chronic kidney disease (CKD) and highlights its capabilities.
- Categories:
1005 Views
The Chattel Text was obtained by personnel on-site through the camera in the perception cap due to the lack of open source data. Among them, the Chattel Text dataset is 828 sheets. The Chattel Text dataset in this paper is labeled by labelImg to calibrate the text box and get the labeled document. The label document contains 8 numbers and a text, where the 8 numbers are the horizontal and vertical coordinates of the four vertices of the rectangular text box in the picture. Due to the randomized environment, some of the texts in the picture will be skewed and other characteristics.
- Categories:
136 Views
Flow to image conversion is a pivotal preprocessing step in intrusion detection systems (IDS) where the representation of network flow data significantly influences classifier performance. In this study, we explore the effects of three distinct methods of transforming flow data into images on classifier performance.
- Categories:
228 Views