Dataset Search

This dataset provides high-grade Received Signal Strength Indicator (RSSI) data collected from a set of experiments meant to estimate the number of drones present in a closed indoor space. The experiments are conducted varying the number of drones from one to seven, where all the variations in RSSI signal data are captured using a 5G transceiver setup established using Ettus E312 software-defined radio. There are seven files in the database, with a minimum of about 270 million samples.

The main goal of this research is to propose a realistic benchmark dataset to enable the development and evaluation of Internet of Medical Things (IoMT) security solutions. To accomplish this, 18 attacks were executed against an IoMT testbed composed of 40 IoMT devices (25 real devices and 15 simulated devices), considering the plurality of protocols used in healthcare (e.g., Wi-Fi, MQTT and Bluetooth).

The European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v.5 (ERA5)-Land and Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature.

This is the CSI data between the UAV and the base station in the ISAC system in an urban environment. It is generated by the raytracing module of sionna. It is used for UAV navigation.

This dataset has been compiled and derived from publicly available dermatological image collections, including the ISIC 2018 Skin Lesion Dataset and the Atlas Dermatology archive. It comprises 49,100 high-resolution, anonymized images categorized into 32 classes, including 31 dermatological diseases and an additional “Unknown” class to improve real-world generalization. Each image is labeled based on expert classification standards and curated for deep learning applications.

With the advent of 6G Open-RAN architecture, multiple operational services can be simultaneously executed in RAN, leveraging the near-Real-Time Radio Intelligent Controller (near-RT-RIC) and real-time (RT) nodes. The architecture provides an ideal platform for Federated Learning (FL): The xAPP is hosted in the near-RT-RIC to perform global aggregation, whereas the Open Radio Unit (ORU) allocates power to users to participate in FL in a RT manner. This paper identifies power and latency optimization as critical factors for enhancing FL in a stochastic environment.

针对ML-KEM的选择密文攻击数据集

Wi-Fi sensing has emerged as a promising non-intrusive approach for human activity recognition (HAR), leveraging the widespread availability of Wi-Fi-enabled devices. While machine learning tools help extract meaningful features from complex wireless propagation patterns, developing robust and domain-adaptive models remains challenging without diverse datasets.

The rapid advancement of generative neural networks has facilitated the creation of photorealistic images, raising concerns about the proliferation of misinformation. Detecting AI-generated fakes has become crucial, given their potential impact on public opinion and various sectors. This dataset presents a comparative analysis of real and AI-generated images, focusing on building a novel dataset named Realistic AI-Generated Image (RealAIGI) dataset.

The dataset covers eight types of contract vulnerabilities that QUIVERIF is capable of detecting: 1) transaction order dependency (TOD); 2) timestamp dependency (TD); 3) reentrancy; 4) gasless send; 5) overflow; 6) transferMint [19]; 7) ether strict equality; 8) gas limit DoS

In the modern era of fast-paced lifestyles and increasing psychological pressure, real-time stress identification has become a critical component of mental health monitoring systems.

Ultrasonic gas flowmeters are widely adopted in industrial applications due to their advantageous features, such as zero pressure loss and easy installation. However, the conventional threshold detection method, despite its real-time performance, suffers from degraded accuracy caused by circuit and pipeline noise, which introduces fluctuations in echo signal amplitude and phase. This paper theoretically demonstrates that doubling the ultrasonic signal frequency steepens the rising edge slope of the echo signal, reducing the time interval during which random noise affects comparator output.

The integration of Large Language Models (LLMs) into wireless communications for channel state information (CSI) prediction introduces transformative capabilities but also exposes critical security vulnerabilities, particularly backdoor attacks. This paper investigates how adversaries exploit the openness of wireless propagation where signals are inherently susceptible to eavesdropping and adversarial interference, and the black-box nature of neural networks to inject stealthy triggers (e.g., Gaussian white, narrowband, or impulse interference) into online training samples.

The video demonstration corresponding to the 100th time step in Figure 13 for the HalfCheetah controlled by the random policy and the learned
policies with different methods. MDDPG(5) denotes the model-free counterpart with 5-step TD target. FNN-Model-MDDPG(5) and ResNet-Model-MDDPG(5) denote the FNN-model-based and our ResNet-model-based schemes with 5 dynamics models, respectively.

This dataset encompasses data from the MIMIC - Ⅳ, MIMIC - Ⅲ subsets, and the eICU, focusing on patients with acute pancreatitis. It includes a comprehensive range of clinical information, such as patient demographics, and laboratory test results.

PatternCom is a composed image retrieval benchmark based on PatternNet. PatternNet is a large-scale high-resolution remote sensing image retrieval dataset. There are 38 classes and each class has 800 images of size 256×256 pixels. In PatternCom, we select some classes to be depicted in query images, and add a query text that defines an attribute relevant to that class. For instance, query images of “swimming pools” are combined with text queries defining “shape” as “rectangular”, “oval”, and “kidney-shaped”.

Social Network Datasets (SNDs) are structured data collected from social media platforms, online communities, or communication networks for the study of user behavior, information dissemination, community discovery, and so on. This kind of data usually contains nodes (users/entities) and edges (relationships/interactions), and is widely used in the fields of social network analysis (SNA), recommender systems, and public opinion monitoring.

It is a set of UAV ground surface crack datasets, containing a variety of complex factors in real-world scenes, which verifies the applicability of the proposed method on UAV images and provides important data support for the research on ground surface crack seg mentation.

come soon

Automatic Identification System (AIS) data are critical for maritime domain awareness, enabling tasks such as vessel classification, trajectory prediction, and anomaly detection. However, AIS datasets frequently suffer from domain shifts, data sparsity, and class imbalance, which limit the generalization of predictive models. To address these challenges, this paper presents AISCycleGen, a novel data augmentation framework that leverages Cycle-Consistent Generative Adversarial Networks to synthesize realistic AIS sequences through unpaired domain translation.

This dataset contains user reviews about multiple consumer IoT devices.

No Iamge

The visual sensor captures images of the crane loading operation scene, while simultaneously collecting the motion control commands from the crane's operational control end. A neural network model is trained to predict the crane's motion control commands in an end-to-end manner.