X-CANIDS Dataset (In-Vehicle Signal Dataset)In March 2024

Here you find an example research data dataset for the automotive demonstrator within the "AEGIS - Advanced Big Data Value Chain for Public Safety and Personal Security" big data project, which has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732189. The time series data has been collected during trips conducted by three drivers driving the same vehicle in Austria. The dataset contains 20Hz sampled CAN bus data from a passenger vehicle, e.g. WheelSpeed FL (speed of the front left wheel), SteerAngle (steering wheel angle), Role, Pitch, and accelerometer values per direction. GPS data from the vehicle (see signals 'Latitude_Vehicle' and 'Longitude_Vehicle' in h5 group 'Math') and GPS data from the IMU device (see signals 'Latitude_IMU', 'Longitude_IMU' and 'Time_IMU' in h5 group 'Math') are included. However, as it had to be exported with single-precision, we lost some precision for those GPS values. For data analysis we use R and R Studio (https://www.rstudio.com/) and the library h5. e.g. check file with R code: library(h5) f <- h5file("file path/20181113_Driver1_Trip1.hdf") summary(f["CAN/Yawrate1"][,]) summary(f["Math/Latitude_IMU"][,]) h5close(f)

This dataset provides the following on road testing data: - Videos - In-vehicle dash camera videos during different testing scenarios. - Signal controller data - NTCIP log data and processed signal timing data from the corresponding signal controllers - Vehicle data - Vehicle data recorded during the testing, including GNSS, communication, CAN signals.

Although ubiquitous in modern vehicles, Controller Area Networks (CANs) lack basic security properties and are easily exploitable. A rapidly growing field of CAN security research has emerged that seeks to detect intrusions or anomalies on CANs. Producing vehicular CAN data with a variety of intrusions is a difficult task for most researchers as it requires expensive assets and deep expertise. To illuminate this task, we introduce the first comprehensive guide to the existing open CAN intrusion detection system (IDS) datasets. We categorize attacks on CANs including fabrication (adding frames, e.g., flooding or targeting and ID), suspension (removing an ID’s frames), and masquerade attacks (spoofed frames sent in lieu of suspended ones). We provide a quality analysis of each dataset; an enumeration of each datasets’ attacks, benefits, and drawbacks; categorization as real vs. simulated CAN data and real vs. simulated attacks; whether the data is raw CAN data or signal-translated; number of vehicles/CANs; quantity in terms of time; and finally a suggested use case of each dataset. State-of-the-art public CAN IDS datasets are limited to real fabrication (simple message injection) attacks and simulated attacks often in synthetic data, lacking fidelity. In general, the physical effects of attacks on the vehicle are not verified in the available datasets. Only one dataset provides signal-translated data but is missing a corresponding “raw” binary version. This issue pigeon-holes CAN IDS research into testing on limited and often inappropriate data (usually with attacks that are too easily detectable to truly test the method). The scarcity of appropriate data has stymied comparability and reproducibility of results for researchers. As our primary contribution, we present the Real ORNL Automotive Dynamometer (ROAD) CAN IDS dataset, consisting of over 3.5 hours of one vehicle’s CAN data. ROAD contains ambient data recorded during a diverse set of activities, and attacks of increasing stealth with multiple variants and instances of real (i.e. non-simulated) fuzzing, fabrication, unique advanced attacks, and simulated masquerade attacks. To facilitate a benchmark for CAN IDS methods that require signal-translated inputs, we also provide the signal time series format for many of the CAN captures. Our contributions aim to facilitate appropriate benchmarking and needed comparability in the CAN IDS research field.

This software tool generates simulated radar signals and creates RF datasets. The datasets can be used to develop and test detection algorithms by utilizing machine learning/deep learning techniques for the 3.5 GHz Citizens Broadband Radio Service (CBRS) or similar bands. In these bands, the primary users of the band are federal incumbent radar systems. The software tool generates radar waveforms and randomizes the radar waveform parameters. The pulse modulation types for the radar signals and their parameters are selected based on NTIA testing procedures for ESC certification, available at http://www.its.bldrdoc.gov/publications/3184.aspx. Furthermore, the tool mixes the waveforms with interference and packages them into one RF dataset file. The tool utilizes a graphical user interface (GUI) to simplify the selection of parameters and the mixing process. A reference RF dataset was generated using this software. The RF dataset is published at https://doi.org/10.18434/M32116.

The Real ORNL Automotive Dynamometer (ROAD) CAN IDS dataset consistis of over 3.5 hours of one vehicle's CAN data. ROAD contains ambient data recorded during a diverse set of activities, and attacks of increasing stealth with multiple variants and instances of real (i.e. non-simulated) fuzzing, fabrication, unique advanced attacks, and simulated masquerade attacks. In addition to the "raw" CAN format, the data is also provided in a the signal time series format for many of the CAN captures.

Authors: Miki E. Verma, Robert A. Bridges, Michael D. Iannacone, Samuel C. Hollifield, Pablo Moriano, Bill Kay, Steven Hespeler and Frank L. Combs

Citation: Please cite the paper with full description (preprint https://arxiv.org/abs/2012.14600, PLoS ONE publication to appear in 2024)

The Signal Media One-Million News Articles Dataset dataset by Signal Media was released to facilitate researching news articles. It can be used for submissions to the NewsIR'16 workshop, but it is intended to serve the community for research on news retrieval in general.

This dataset contains electromyography (EMG) signals for use in human-computer interaction studies. The dataset includes 4-channel surface EMG data from 40 participants with an equal gender distribution. The gestures in the data are rest or neutral state, extension of the wrist, flexion of the wrist, ulnar deviation of the wrist, radial deviation of the wrist, grip, abduction of all fingers, adduction of all fingers, supination, and pronation. Data were collected from 4 forearm muscles when simulating 10 unique hand gestures and recorded with the BIOPAC MP36 device using Ag/AgCl surface bipolar electrodes. Each participant's data contains five repetitive cycles of ten hand gestures. A demographic survey was applied to the participants before the signal recording process. This data can be utilized for recognition, classification, and prediction studies in order to develop EMG-based hand movement controller systems. The dataset can also be useful as a reference to create an artificial intelligence model (especially a deep learning model) to detect gesture-related EMG signals. Additionally, it is encouraged to use the proposed dataset for benchmarking of current datasets or for validation of machine learning and deep learning models created with different datasets in accordance with the participant-independent validation strategy.

Vehicle And Turn Signal

## Overview

Vehicle And Turn Signal is a dataset for object detection tasks - it contains Vehicles annotations for 942 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The dataset contains location and attributes of traffic signals, a power-operated traffic control device by which traffic is warned or directed to take some specific action, located at each intersection in the District of Columbia. These devices do not include power-operated signs, steadily-illuminated pavement markers, warning lights, or steady burning electric lamps. The dataset is related to the traffic pole data.

This dataset production would not be possible without the work of Morales Ferre, Ruben, Lohan, Elena Simona, & De la Fuente, Alberto. (2019). Image datasets for jammer classification in GNSS [Data set]. Zenodo. http://doi.org/10.5281/zenodo.3783969 .

Raw IQ Dataset –

Contains 1000 training samples and 250 testing samples for DME, narrowband, single AM, single chirp, single FM jamming signals and no jamming signal present.

To generate new raw files –

Download and extract ‘Jamming_Classifier.zip’ from https://zenodo.org/record/3783969

Place ‘signal_generation.m’ into the ‘Jamming_Classifier’ folder.

When you run signal generation you can choose whether to create training or test data and the number of samples. They will be saved in the folders Image_training_database and Image_testing_database.

This LTE_RFFI project sets up an LTE device radio frequency fingerprint identification system using deep learning techniques. The LTE uplink signals are collected from ten different LTE devices using a USRP N210 in different locations. The sampling rate of the USRP is 25 MHz. The received signal is resampled to 30.72 MHz in Matlab and is saved in the MAT file form. The corresponding processed signals are included in the dataset. More details about the datasets can be found in the README document.

Here are a few use cases for this project:

1. Traffic Instruction Learning Application: This model could be used for developing an application that helps people study and learn traffic signals for driving exams. Users can simply upload a photo of traffic signal, and the model can identify it, providing information about the rules associated with each signal.

2. Autonomous Vehicle Systems: The model could be integrated into autonomous driving systems to enhance understanding of visual cues on the road. The system could then make proper navigational decisions based on the recognized signs.

3. Traffic Management Systems: Traffic management authorities can use this model to monitor traffic signals in their city. They can detect potential issues or malfunctions when incorrect signals are identified.

4. Virtual Reality Driving Simulators: These simulators can use this model to accurately represent real-world driving scenarios. They can use the model for generating accurate and diverse traffic signals, contributing to a more realistic driving experience.

5. Safety Assessments: The model can be used for performing safety audits of cities, identifying areas where either important road signs are missing, or incorrect signs are placed. This can help reduce the chances of accidents due to misinterpretation of signals.

Please note that the example image mentioned (room with chairs and table) is unrelated to traffic signals, and therefore, it seems that the data set might contain unrelated images. For better performance, a dataset consistent with traffic signs should be used.

The following dataset includes two types of RF IQ samples: Synthetic and Indoor Over-The-Air datasets.This dataset has been used in a conference paper published in 2025 DySPAN: I Can’t Believe It’s Not Real: CV-MuSeNet: Complex-Valued Multi-Signal Segmentation.Paper abstract:

The location of electronic traffic signals, designed, owned and or controlled and maintained by Main Roads Western Australia, that control vehicle and pedestrian traffic at an intersection or on a road are identified in this data set. The signal can be red, yellow, green or white light displays, and can include circular and arrow signals, pedestrian signals, bicycle crossing signals, B (bus) signals, overhead lane control signals, and twin red or yellow signals.

This dataset was developed to identify the location of Main Roads' controlled electronic signals across Western Australia and assist in the management of this asset. Additionally, it records attribute information which includes the LM No (Asset ID.), Service Status, Signal Type, Intersection Name and Intersection Description. Note that you are accessing this data pursuant to a Creative Commons (Attribution) Licence which has a disclaimer of warranties and limitation of liability. You accept that the data provided pursuant to the Licence is subject to changes.Pursuant to section 3 of the Licence you are provided with the following notice to be included when you Share the Licenced Material:- The Commissioner of Main Roads is the creator and owner of the data and Licenced Material, which is accessed pursuant to a Creative Commons (Attribution) Licence, which has a disclaimer of warranties and limitation of liability.Creative Commons CC BY 4.0 https://creativecommons.org/licenses/by/4.0/

Turn Signal 1

## Overview

Turn Signal 1 is a dataset for object detection tasks - it contains Car Tail annotations for 1,757 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This is a set of signals-pairs, univariate and multivariate, that can be used to test alignment algorithms. Signals are morphologically different.

Signal data is synchronized, but the provided timestamp is shifted with small time-jumps.

Visual LED Status Dataset is a collection of high-quality images of LEDs captured in different environments and under various lighting conditions. The dataset includes images of normal LEDs, bike and car lights, signal lights, and LEDs of different colors. The images were captured using a high-end resolution camera to ensure high-quality images suitable for machine learning applications. The dataset is divided into five sub-folders containing images of normal LEDs, colored LEDs, bike lights, car lights, and signal lights labeled accordingly. The purpose of this dataset is to develop an image classification model that can accurately determine whether an LED is on or off based on its visual appearance. It is designed to support the development of machine-learning models for LED status classification and recognition. The dataset can be used for training, testing, and validation of machine learning models, as well as for research and educational purposes. The proposed dataset provides a valuable resource for industries that use LED technology, particularly in quality control and manufacturing settings. The dataset could be used to develop automated inspection systems for vehicles, electronic devices, or other products that incorporate LEDs. Overall, the LED Status Classification Dataset can be used to improve quality control and efficiency in various industries that use LED technology.

Dataset is outsourced from here. Please give credit to the original authors for your work. Jaideep, Jaideep Bhagwan Rajput; CHOUDHARY, CHETAN; Kale, Atharva ; Deshmukh, Gopal; Meshram, Vishal; Meshram, Vidula (2023), “Visual LED Status Dataset for Machine Learning Applications”, Mendeley Data, V2, doi: 10.17632/f6d39287km.2

The dataset used in this work is composed by four participants, two men and two women. Each of them carried the wearable device Empatica E4 for a total number of 15 days. They carried the wearable during the day, and during the nights we asked participants to charge and load the data into an external memory unit. During these days, participants were asked to answer EMA questionnaires which are used to label our data. However, some participants could not complete the full experiment or some days were discarded due to data corruption. Specific demographic information, total sampling days and total number of EMA answers can be found in table I.

Table I. Summary of participants' collected data.

This dataset provides three different type of labels. Activeness and happiness are two of these labels. These are the answers to EMA questionnaires that participants reported during their daily activities. These labels are numbers between 0 and 4.
These labels are used to interpolate the mental well-being state according to [1] We report in our dataset a total number of eight emotional states: (1) pleasure, (2) excitement, (3) arousal, (4) distress, (5) misery, (6) depression, (7) sleepiness, and (8) contentment.

The data we provide in this repository consist of two type of files:

• CSV files: These files contain physiological signals recorded during the data collection process. The first line of each CSV file defines the timestamp by which data started being sampled. The second line defines the sampling frequency used for gathering the signal. From the third line until the end of the file, one can find sampled datapoints.
  
• Excel files: These files contain the labels obtained from EMA answers. It is indicated the timestamp at which the answer was registered. Labels for pleasure, activeness and mood can be found in this file.

NOTE: Files are numbered according to each specific sampling day. For example, ACC1.csv corresponds to the signal ACC for sampling day 1. The same applied to excel files.

Code and a tutorial of how to labelled and extract features can be found in this repository: https://github.com/edugm94/temporal-feat-emotion-prediction

References:

[1] . A. Russell, “A circumplex model of affect,” Journal of personality and social psychology, vol. 39, no. 6, p. 1161, 1980

Signal

## Overview

Signal is a dataset for object detection tasks - it contains Signal annotations for 730 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).