Dataset Search

This dataset provides 6D magnetic localization data for surgical instrument tracking, focusing on position and orientation estimation in minimally invasive procedures. It includes various trajectory experiments such as square, circular, saddle-shaped, and helical paths, along with simulated minimally invasive knee surgery and needle sampling experiments. Additionally, it contains dynamic error correction verification data. Data is collected using 16 LIS3MDL magnetometers at 300 Hz, offering both raw and filtered data for algorithm validation.

The Tiny-ImageNet dataset contains 200 categories and approximately 120,000 samples. The CIFAR-10 and CIFAR-100 datasets respectively contain 10 and 100 categories. 

All experiments were conducted on a server equipped with two NVIDIA A100 GPUs (each with 80GB memory), running the Ubuntu 20.04 operating system and the CUDA 11.8 computing platform under the Pytorch 1.8 framework. The server has 256GB of memory and is powered by a 64-core Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz.

The ORSSD dataset consists of 800 optical remote sensing images with corresponding pixel-level annotations, divided into a training set of 600 images and a test set of 200 images. The EORSSD dataset is an extension of ORSSD, adding 1200 ORSIs for a total of 2000 images, and is split into 1400 training images and 600 test images. 

Real-time microwave frequency variation (MFV) measurement is crucial for a wide range of applications. However, current solutions often fall short in terms of resolution, speed and range. We present a novel technique that leverages the sine-cosine encoder principle, enabled by a photonic delay line (PhDL), to detect rapid MFV in real-time with ultra-high resolution.

Real-time microwave frequency variation (MFV) measurement is crucial for a wide range of applications. However, current solutions often fall short in terms of resolution, speed and range. We present a novel technique that leverages the sine-cosine encoder principle, enabled by a photonic delay line (PhDL), to detect rapid MFV in real-time with ultra-high resolution.

Real-time microwave frequency variation (MFV) measurement is crucial for a wide range of applications. However, current solutions often fall short in terms of resolution, speed and range. We present a novel technique that leverages the sine-cosine encoder principle, enabled by a photonic delay line (PhDL), to detect rapid MFV in real-time with ultra-high resolution.

Real-time microwave frequency variation (MFV) measurement is crucial for a wide range of applications. However, current solutions often fall short in terms of resolution, speed and range. We present a novel technique that leverages the sine-cosine encoder principle, enabled by a photonic delay line (PhDL), to detect rapid MFV in real-time with ultra-high resolution.

Transportation mode recognition has always been an important task in trajectory data mining. Trajectories are essentially sequences of trajectory points, so many studies have chosen sequence structures for modeling trajectories. However, sequence models cannot capture the higher-order structural features in trajectory. In this context, we propose a novel graph model Trajectory Feature Graph (TF-Graph) for capturing trajectory features. Core words are usually extracted to express the main meaning of a sentence in the field of Natural Language Processing.

This dataset provides synchronized recordings of electroencephalography (EEG) and accelerometer (ACC) signals collected during controlled passive lower limb movements. The data were acquired to facilitate analysis of corticokinematic coherence (CKC), aiming to quantify cortical responses associated with proprioceptive input. EEG signals were recorded from healthy participants using a standardized electrode layout according to the international 10-20 system, while tri-axial accelerometers captured precise limb movement kinematics.

Large Language Models (LLMs) have been widely used to automate programming tasks. Their capabilities have been evaluated by assessing the quality of generated code through tests or proofs. The extent to which they can reason about code is a critical question revealing important insights about their true capabilities.

Advanced Metering Infrastructure is prone to cyber threats and Distributed Denial of Service is renowned attack that threatens critical infrastructure. Intrusion detection schemes proposed in earlier works consider the network specific parameters for intrusion detection rather than physical layer parameters. Hence, the proposal considers the physical layer parameters in detecting distributed denial of service attack through abnormal energy consumption pattern of the Data concentrator in the advanced metering infrastructure.

To promote the development of camouflaged object detection technology, an visible-infrared artificial camouflage dataset (VIAC) is constructed. To simulate and replicate real-world scenarios, we customize and procure a set of metal models and camouflage materials to construct artificial camouflage environments. Utilizing DJI drones equipped with a dual-mode (visible and infrared) imaging system, we conduct coordinated aerial photography in complex outdoor settings, thereby comprehensively acquiring 1,500 pairs of high-quality visible and infrared images.

A rapid growth of wireless communication networks, particularly in 5G Non-Standalone (NSA) deployments, has necessitated advanced multiple access techniques to enhance spectral efficiency, interference management, and energy optimization [1-3]. Rate-Splitting Multiple Access (RSMA) has arisen as a strong candidate to replace conventional Non-Orthogonal Multiple Access (NOMA) by efficiently splitting user data into common and private components. [1-2].

This dataset contains raw FMCW radar signals collected for human localization and activity monitoring in indoor environments. The data was recorded using mmWave radar sensors across two different laboratory settings, designed to simulate real-life scenarios for human detection and localization tasks.

The dataset includes experiments with 1, 2, and 3 people, covering various positions, walking trajectories, and intermediate locations to evaluate model generalization. Ground truth information is embedded in the folder names, indicating the true distance and angle of the targets.

This dataset contains raw FMCW radar signals collected for human localization and activity monitoring in indoor environments. The data was recorded using mmWave radar sensors across two different laboratory settings, designed to simulate real-life scenarios for human detection and localization tasks.

The dataset includes experiments with 1, 2, and 3 people, covering various positions, walking trajectories, and intermediate locations to evaluate model generalization. Ground truth information is embedded in the folder names, indicating the true distance and angle of the targets.

This dataset contains raw FMCW radar signals collected for human localization and activity monitoring in indoor environments. The data was recorded using mmWave radar sensors across two different laboratory settings, designed to simulate real-life scenarios for human detection and localization tasks.

The dataset includes experiments with 1, 2, and 3 people, covering various positions, walking trajectories, and intermediate locations to evaluate model generalization. Ground truth information is embedded in the folder names, indicating the true distance and angle of the targets.

This dataset contains raw FMCW radar signals collected for human localization and activity monitoring in indoor environments. The data was recorded using mmWave radar sensors across two different laboratory settings, designed to simulate real-life scenarios for human detection and localization tasks.

The dataset includes experiments with 1, 2, and 3 people, covering various positions, walking trajectories, and intermediate locations to evaluate model generalization. Ground truth information is embedded in the folder names, indicating the true distance and angle of the targets.

About Dataset

Context

The Breast Cancer Histopathological Image Classification (BreakHis) is composed of 9,109 microscopic images of breast tumor tissue collected from 82 patients using different magnifying factors (40X, 100X, 200X, and 400X). To date, it contains 2,480 benign and 5,429 malignant samples (700X460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format).

The spectrum of the Laplace-Beltrami (LB) operator is central in geometric deep learning tasks, capturing intrinsic properties of the shape of the object under consideration. The best established method for its estimation, from a triangulated mesh of the object, is based on the Finite Element Method (FEM), and computes the top k LB eigenvalues with a complexity of O(Nk), where N is the number of points.

The system consists of an UAVs remote sensing system and an edge computing system. The core components of the UAVs remote sensing system mainly consist of the imaging system K510 development board and a 5G module. The K510 comes equipped with a camera and an LCD screen. The edge computing system constructed in this paper utilizes the NVIDIA Jetson series development kit, which comes with a GPU module to enhance digital image processing capabilities. The captured raw images are stitched and displayed on the NVIDIA Jetson edge computing platform using our designed improved SFIT algorithm.

Synthetic image data set using a generative model with explicit control over the head pose. HPGEN offers a promising solution to address data set bias in the head pose estimation as current benchmarks suffer from a limited number of images, imbalanced data distributions, the high cost of annotation, and ethical concerns.

  A invisibility cloak designed with three-dimensional (3D) microwave circuit assistance is proposed in this letter. Conformally wrapped around a square tube, the cloak achieves substantial radar cross-section (RCS) reduction while preserving the integrity of the incident electromagnetic wavefront. A microwave circuit model in 3D space is proposed, and combined with the current distribution of full-wave simulation, the mechanism of the proposed structure is revealed.

High-quality annotated datasets from diverse scenarios play a crucial role in the development of deep learning algorithms. However, due to the strict access limitations of space-based infrared satellite platforms, space-based infrared small target datasets are scarce. Therefore, we have developed the MIRSat-QL dataset, based on a space-based infrared satellite platform, for space-based dynamic scene infrared target detection. Our data is synthesized from space-based infrared satellite images and ground-based infrared cameras capturing airborne targets. The specifics are as follows。

High-quality annotated datasets from diverse scenarios play a crucial role in the development of deep learning algorithms. However, due to the strict access limitations of space-based infrared satellite platforms, space-based infrared small target datasets are scarce. Therefore, we have developed the MIRSat-QL dataset, based on a space-based infrared satellite platform, for space-based dynamic scene infrared target detection. Our data is synthesized from space-based infrared satellite images and ground-based infrared cameras capturing airborne targets. The specifics are as follows。