Artificial Intelligence
"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:
1017 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:
384 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:
270 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:
1060 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:
362 Views
This dataset webpage contains datasets of exisiting and proposed models:
- 12cell.zip
- 16cell.zip
- 36cell.zip
- Proposed_
Presented in my 3rd last Speaker Presentation in Conference - 2025*.
Model of Fault And Short-Circuit Analysis of Lithium Battery Bank
- Categories:
548 Views
This dataset webpage contains datasets of existing and proposed models
- 4cell.zip
- 6cell.zip
- 8cell.zip
Presented in my 3rd Speaker Presentation in Conference - 2025*.
- Categories:
305 Views
This dataset webpage contains datasets of exisiting and proposed models:
- tubular.zip
- tubular2.zip
- tubular3.zip
B Model of Fault And Short-Circuit Analysis of Synchronous Generator
presented in my 3rd Probably last Speaker Presentation in Conference - 2025*.
- Categories:
417 Views
This dataset webpage contains datasets of exisiting and proposed models:
- centrifugalpump1.zip
- centrifugalpump2.zip
- centrifugalpump3.zip
B Model of Fault And Short-Circuit Analysis of Centrifugal Pump
presented in my last Speaker Presentation in Conference - 2025*.
- Categories:
445 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:
2569 Views