Artificial Intelligence
The datasets are sourced from the Caltrans Performance Measurement System (PeMS) in California, which monitors and collects real-time traffic data from over 39,000 sensors deployed on major highways throughout the state. The PeMS system collects data every 30 seconds and aggregates it into 5-minute interval, with each sensor generating data for 288 time steps daily. Additionally, road network structure data is derived from the connectivity status and actual distances between sensors.
- Categories:
72 Views
The TiHAN-V2X Dataset was collected in Hyderabad, India, across various Vehicle-to-Everything (V2X) communication types, including Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), Infrastructure-to-Vehicle (I2V), and Vehicle-to-Cloud (V2C). The dataset offers comprehensive data for evaluating communication performance under different environmental and road conditions, including urban, rural, and highway scenarios.
- Categories:
248 Views
Abstract—Most reinforcement learning algorithms for robotic arm control in sparse reward environments are primarily optimized for end-effector displacement control mode.
- Categories:
23 Views
This dataset includes two 2D medical image segmentation benchmark.
1. OD/OC Segmentation in Fundus Image
This dataset conprises five sub-datasets: Drishti-GS, RIM-ONE-r3, ORIGA, REFUGE, and the validation set of REFUGE2. Each image is cropped around the optic disc area. The size of all images is 512×512. The manual pixel-wise annotation is stored as a PNG image with the same size as the corresponding fundus image with the following labels:
128: Optic Disc (Grey color)
0: Optic Cup (Black color)
255: Background (White color)
- Categories:
38 Views
"Recent advancements in deep learning and generative models have significantly enhanced text-to-image (T2I) synthesis, allowing for the creation of highly realistic images based on textual inputs. While this progress has expanded the creative and practical applications of AI, it also presents new challenges in distinguishing between authentic and AI-generated images. This challenge raises serious concerns in areas such as security, privacy, and digital forensics.
- Categories:
141 Views
In this research, a newly modified UNet (Fast-UNet) was implemented to segment winter wheat from time series Sentinel-2 images for the years 2021 and 2023. These images were converted to NDVI and utilized to identify wheat fields by tracking the wheat phenology from sowing to harvesting. The main satellite image that was used in this research was Sentinel-2. It is considered important, and free optical remote sensing satellite data is provided by the European Space Agency (ESA). Sentinel-2A and Sentinel-2B were launched in June 2015 and March 2017, respectively.
- Categories:
117 Views
The dataset is derived from the ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) domain, which plays a crucial role in drug discovery and development. This dataset comprises a comprehensive collection of chemical compounds with associated ADMET properties, providing a rich resource for evaluating the efficacy of machine learning models in predicting drug behavior. Specifically, the dataset includes diverse features representing molecular structures, physicochemical properties, and biological activity profiles, allowing for robust modeling of classification tasks.
- Categories:
35 Views
To download this dataset without purchasing an IEEE Dataport subscription, please visit: https://zenodo.org/records/13896353
Please cite the following paper when using this dataset:
- Categories:
499 Views
Due to the lack of publicly available injection-molded product defect datasets and the diversity of defects in terms of shapes, sizes, and textures, we collects defect samples from injection molding factories to ensure the model performs well in real industrial scenarios. To ensure the quality and usability of the data, after analyzing the sample data, data cleaning is performed to remove the irregular images.
- Categories:
72 Views
The Unified Multimodal Network Intrusion Detection System (UM-NIDS) dataset is a comprehensive, standardized dataset that integrates network flow data, packet payload information, and contextual features, making it highly suitable for machine learning-based intrusion detection models. This dataset addresses key limitations in existing NIDS datasets, such as inconsistent feature sets and the lack of payload or time-window-based contextual features.
- Categories:
529 Views