The  Sentinel-2 L2A multispectral data cubes include two regions of interest (roi1 and roi2) each of them containing 92 scenes across Switzerland within T32TLT, between 2018 and 2022, all band at 10m resolution These areas of interest show a diverse landscape, including regions covered by forests that have undergone changes, agriculture and urban areas.


This study proposes a more competitive and sample-efficient algorithm: Memory-GIC-PPO, specifically to address POMDPs in UAV path planning. The effectiveness of the proposed algorithm is thoroughly evaluated through simulations conducted on the Airsim platform. The results convincingly demonstrate that Memory-GIC-PPO enables the UAV to achieve optimal path planning in complex environments and outperforms the benchmark algorithms in terms of sampling efficiency and success rates.


The dataset consists of undirected weighted multi-graphs stored in .pkl or .net formats. These undirected graphs form instances for the multi-trip multi-depot rural postman problem. The Multi-trip multi-depot Rural Postman Problem is a variant of the Capacitated Arc Routing Problem which is to find a set of routes for vehicles having limited capacity to traverse a set of arcs from a node called depot in an undirected graph in the least possible time. The dataset consists of instances generated by modifying instances from the literature and also real-world road networks.


The dataset consists of NumPy arrays for each alphabet in Indian Sign Language, excluding 'R'. The NumPy arrays denote the (x,y,z) coordinates of the skeletal points of the left and right hand (21 skeletal points each) for each alphabet. Each alphabet has 120 sequences, split into 30 frames each, giving 3600 .np files per alphabet, using MediaPipe.

The dataset is created on the basis of skeletal-point action recognition and key-point collection.


Development of the Complex-Valued (CV) deep learning architectures has enabled us to exploit the amplitude and phase components of the CV Synthetic Aperture Radar (SAR) data. However, most of the available annotated SAR datasets provide only the amplitude information (Only detected SAR data) and disregard the phase information. The lack of high-quality and large-scale annotated CV-SAR datasets is a significant challenge for developing CV deep learning algorithms in remote sensing.


Simulation data for the following paper

DS2MA: A Deep Learning-Based Spectrum Sensing Scheme for a Multi-Antenna Receiver (K. Chae and Y. Kim)


Radar-based dynamic gesture recognition has a broad prospect in the field of touchless Human-Computer Interaction (HCI) due to its advantages in many aspects such as privacy protection and all-day working. Due to the lack of complete motion direction information, it is difficult to implement existing radar gesture datasets or methods for motion direction sensitive gesture recognition and cross-domain (different users, locations, environments, etc.) recognition tasks.


Future mobile communication systems include millimeter wave (mmWave) frequency bands and high mobility scenarios. To learn how wave propagation and scattering effects change from classical sub 6 GHz to mmWave frequencies, measurements in both bands have to be conducted. We perform wireless channel measurements at 2.55 GHz and 25.5 GHz center frequency at velocites of 40 km/h and 100 km/h. To ensure a fair comparison between these two frequency bands, we perform repeatable measurements in a controlled environment.


Good knowledge about a radio environment, especially about the radio channel, is a prerequisite to design and operate ultra-reliable communications systems. Radio Environment Maps (REMs) are therefore a helpful tool to gain channel awareness. Based on a user’s location, the channel conditions can be estimated in the surrounding of the user by extracting the information from the radio map. This data set contains two measured high-resolution REMs of an indoor environment.


The experiment is based on the open source RSRP data provided by Huawei Technologies Co., LTD. It measures RSRP of 415,244 signal receiving points in 180 dense urban communication cells.