Machine Learning
The proliferation of efficient edge computing has enabled a paradigm shift of how we monitor and interpret urban air quality. Coupled with the dense spatiotemporal resolution realized from large-scale wireless sensor networks, we can achieve highly accurate realtime local inference of airborne pollutants. In this paper, we introduce a novel Deep Neural Network architecture targeted at latent time-series regression tasks from continuous, exogenous sensor measurements, based on the Transformer encoder scheme and designed for deployment on low-cost power-efficient edge processors.
- Categories:
This dataset contains a collection of videos consisting of satellite imagery augmented with 3D ship models, accompanied by the ships' corresponding AIS data. The intention of this dataset is for detecting dark ships, which are sea vessels acting maliciously, often while spoofing their AIS data. Multiple datasets exist that consist of satellite imagery of ships, however this dataset has the advantage of including each ships' corresponding AIS data. The simulated ships include both normal and anomalous behavior, whether the anomalous behavior is benign or malicious.
- Categories:
The greatest challenge of machine learning problems is to select suitable techniques and resources such as tools and datasets. Despite the existence of millions of speakers around the globe and the rich literary history of more than a thousand years, it is expensive to find the computational linguistic work related to Punjabi Shahmukhi script, a member of the Perso-Arabic context-specific script low-resource language family. The selection of the best algorithm for a machine learning problem heavily depends on the availability of a dataset for that specific task.
- Categories:
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:
With the modern day technological advancements and the evolution of Industry 4.0, it is very important to make sure that the problem of Intrusion detection in Cloud , IoT and other modern networking environments is addressed as an immediate concern. It is a fact that Cloud and Cyber Physical Systems are the basis for Industry 4.0. Thus, intrusion detection in cyber physical systems plays a crucial role in Industry 4.0. Here, we provide the an intrusion detection dataset for performance evaluation of machine learning and deep learning based intrusion detection systems.
- Categories:
Human intention is an internal, mental characterization for acquiring desired information. From
interactive interfaces, containing either textual or graphical information, intention to perceive desired
information is subjective and strongly connected with eye gaze. In this work, we determine such intention by
analyzing real-time eye gaze data with a low-cost regular webcam. We extracted unique features (e.g.,
Fixation Count, Eye Movement Ratio) from the eye gaze data of 31 participants to generate the dataset
- Categories:
This dataset is the supplementary material of an IEEE RAL paper named "Design of Fully Controllable and Continuous Programmable Surface Based on Machine Learning". It includes the z-displacement data derived from the FEA simulation, voltage input data derived from Matlab, and dataset for inverse application. The detailed description can be found in that paper.
- Categories:
This dataset includes the rotor geometry image (*.png) and motor parameters (*.csv) of interior permanent magnet synchronous motors. The rotor geometry covers three structures: 2D-, V-, and Nabla-structures. The motor parameters are generated by machine learning based on the finite element analysis results. The software JMAG Designer 19.1 was used for the finite element analysis.
- Categories:
We introduce a novel dataset of bee piping audio signals which was built by collecting 44 different recordings which were published by various beekeepers on the YouTube platform.
Each recording has a duration varying from 2 to 13 seconds and is annotated according to the beekeeper comment respectively as Tooting or Quacking.
- Categories: