scholarly journals An Indoor Crowd Movement Trajectory Benchmark Dataset

2021 ◽  
pp. 1-13
Author(s):  
Ying Zhao ◽  
Xin Zhao ◽  
Siming Chen ◽  
Zhuo Zhang ◽  
Xin Huang
Keyword(s):  
Benchmark Dataset ◽  
Movement Trajectory ◽  
Crowd Movement

Improving the Accuracy of Protein-Ligand Binding Affinity Prediction by Deep Learning Models: Benchmark and Model

2019 ◽  
Author(s):  
Mohammad Rezaei ◽  
Yanjun Li ◽  
Xiaolin Li ◽  
Chenglong Li
Keyword(s):  
Deep Learning ◽  
Drug Design ◽  
Binding Affinity ◽  
Benchmark Dataset ◽  
Rational Drug Design ◽  
Learning Models ◽  
Structure Based Drug Design ◽  
Binding Affinity Prediction ◽  
Affinity Prediction ◽  
Rational Drug

<b>Introduction:</b> The ability to discriminate among ligands binding to the same protein target in terms of their relative binding affinity lies at the heart of structure-based drug design. Any improvement in the accuracy and reliability of binding affinity prediction methods decreases the discrepancy between experimental and computational results.<br><b>Objectives:</b> The primary objectives were to find the most relevant features affecting binding affinity prediction, least use of manual feature engineering, and improving the reliability of binding affinity prediction using efficient deep learning models by tuning the model hyperparameters.<br><b>Methods:</b> The binding site of target proteins was represented as a grid box around their bound ligand. Both binary and distance-dependent occupancies were examined for how an atom affects its neighbor voxels in this grid. A combination of different features including ANOLEA, ligand elements, and Arpeggio atom types were used to represent the input. An efficient convolutional neural network (CNN) architecture, DeepAtom, was developed, trained and tested on the PDBbind v2016 dataset. Additionally an extended benchmark dataset was compiled to train and evaluate the models.<br><b>Results: </b>The best DeepAtom model showed an improved accuracy in the binding affinity prediction on PDBbind core subset (Pearson’s R=0.83) and is better than the recent state-of-the-art models in this field. In addition when the DeepAtom model was trained on our proposed benchmark dataset, it yields higher correlation compared to the baseline which confirms the value of our model.<br><b>Conclusions:</b> The promising results for the predicted binding affinities is expected to pave the way for embedding deep learning models in virtual screening and rational drug design fields.

A Benchmark Dataset for RGB-D Sphere Based Calibration

2019 ◽  
Author(s):  
D.J.T. Boas ◽  
S. Poltaretskyi ◽  
J.-Y. Ramel ◽  
J. Chaoui ◽  
J. Berhouet ◽  
...  
Keyword(s):  
Benchmark Dataset

Plant Disease Recognition: A Large-Scale Benchmark Dataset and a Visual Region and Loss Reweighting Approach

2021 ◽  
Vol 30 ◽  
pp. 2003-2015
Author(s):  
Xinda Liu ◽  
Weiqing Min ◽  
Shuhuan Mei ◽  
Lili Wang ◽  
Shuqiang Jiang
Keyword(s):  
Large Scale ◽  
Plant Disease ◽  
Benchmark Dataset ◽  
Visual Region

scholarly journals SUM: A benchmark dataset of Semantic Urban Meshes

2021 ◽  
Vol 179 ◽  
pp. 108-120
Author(s):  
Weixiao Gao ◽  
Liangliang Nan ◽  
Bas Boom ◽  
Hugo Ledoux
Keyword(s):  
Benchmark Dataset

scholarly journals DLR HySU—A Benchmark Dataset for Spectral Unmixing

2021 ◽  
Vol 13 (13) ◽  
pp. 2559
Author(s):  
Daniele Cerra ◽  
Miguel Pato ◽  
Kevin Alonso ◽  
Claas Köhler ◽  
Mathias Schneider ◽  
...  
Keyword(s):  
Spectral Unmixing ◽  
Benchmark Dataset ◽  
Data Sets ◽  
Endmember Extraction ◽  
Imaging Spectrometer ◽  
Hyperspectral Unmixing ◽  
Processing Step ◽  
German Aerospace ◽  
Spectrometer Data ◽  
First Time

Spectral unmixing represents both an application per se and a pre-processing step for several applications involving data acquired by imaging spectrometers. However, there is still a lack of publicly available reference data sets suitable for the validation and comparison of different spectral unmixing methods. In this paper, we introduce the DLR HyperSpectral Unmixing (DLR HySU) benchmark dataset, acquired over German Aerospace Center (DLR) premises in Oberpfaffenhofen. The dataset includes airborne hyperspectral and RGB imagery of targets of different materials and sizes, complemented by simultaneous ground-based reflectance measurements. The DLR HySU benchmark allows a separate assessment of all spectral unmixing main steps: dimensionality estimation, endmember extraction (with and without pure pixel assumption), and abundance estimation. Results obtained with traditional algorithms for each of these steps are reported. To the best of our knowledge, this is the first time that real imaging spectrometer data with accurately measured targets are made available for hyperspectral unmixing experiments. The DLR HySU benchmark dataset is openly available online and the community is welcome to use it for spectral unmixing and other applications.

scholarly journals A Feasibility Study of Kinematic Characteristics on the Upper Body According to the Shooting of Elite Disabled Archery Athletes

2021 ◽  
Vol 18 (6) ◽  
pp. 2962
Author(s):  
Tae-Whan Kim ◽  
Jae-Won Lee ◽  
Seoung-Ki Kang ◽  
Kyu-Yeon Chae ◽  
Sang-Hyup Choi ◽  
...  
Keyword(s):  
The Body ◽  
Lower Limbs ◽  
Upper Body ◽  
Movement Trajectory ◽  
Phase 2 ◽  
Kinematic Characteristics ◽  
Significant Difference ◽  
Athletes With Disabilities ◽  
Body Center ◽  
Time Required

The purpose of this study is to compare and analyze the kinematic characteristics of the upper limb segments during the archery shooting of Paralympic Wheelchair Class archers (ARW2—second wheelchair class—paraplegia or comparable disability) and Paralympic Standing Class archers (ARST—standing archery class—loss of 25 points in the upper limbs or lower limbs), where archers are classified according to their disability grade among elite disabled archers. The participants of this study were selected as seven elite athletes with disabilities by the ARW2 (n = 4) and ARST (n = 3). The analysis variables were (1) the time required for each phase, (2) the angle of inclination of the body center, (3) the change of trajectory of body center, and (4) the change of the movement trajectory of the bow center by phase when performing six shots in total. The ARW2 group (drawing phase; M = 2.228 s, p < 0.05, holding phase; M = 4.414 s, p < 0.05) showed a longer time than the ARST group (drawing phase; M = 0.985 s, holding phase; M = 3.042 s), and the angle of the body did not show a significant difference between the two groups. Additionally, in the direction of the anteroposterior axis in the drawing phase, the change in the movement trajectory of the body center showed a more significant amount of change in the ARW2 group than in the ARST group, and the change in the movement trajectory of the bow center did not show a significant difference between the two groups.

Sign in / Sign up

Export Citation Format

Share Document