Improving deep convolutional neural networks with mixed maxout units by Hui-zhen ZHAO, Fu-xian LIU, Long-yue LI, Chang LUO

“…The maxout units have the problem of not delivering non-max features， resulting in the insufficient of pooling operation over a subspace that is composed of several linear feature mappings,when they are applied in deep convolutional neural networks.The mixed maxout (mixout) units were proposed to deal with this constrain.Firstly,the exponential probability of the feature mappings getting from different linear transformations was computed.Then,the averaging of a subspace of different feature mappings by the exponential probability was computed.Finally,the output was randomly sampled from the max feature and the mean value by the Bernoulli distribution,leading to the better utilizing of model averaging ability of dropout.The simple models and network in network models was built to evaluate the performance of mixout units.The results show that mixout units based models have better performance.…”
Get full text

CCD-Rice: a long-term paddy rice distribution dataset in China at 30 m resolution by R. Shen, Q. Peng, X. Li, X. Chen, W. Yuan

“…Based on 394 753 validation samples, the overall accuracy of the distribution maps in each provincial administrative region averaged 89.61 %. …”
Get full text

Modeling TEC Irregularities in the Arctic Ionosphere Using Empirical Orthogonal Function Method by Yaqi Jin, Wojciech J. Miloch, Daria Kotova, Knut Stanley Jacobsen, Đorđe Stevanović, Lasse B. N. Clausen, Nicholas Ssessanga, Federico DaDalt

“…Abstract We develop a climatological model for the Arctic ionosphere based on more than one solar cycle of data (2010–2021) of the rate of change of the total electron content index (ROTI) maps from the International GNSS Service (IGS). The IGS ROTI maps are daily averaged in magnetic latitude and local time coordinates. …”
Get full text

Steepest-Descent Approach to Triple Hierarchical Constrained Optimization Problems by Lu-Chuan Ceng, Cheng-Wen Liao, Chin-Tzong Pang, Ching-Feng Wen

“…We introduce and analyze a hybrid steepest-descent algorithm by combining Korpelevich’s extragradient method, the steepest-descent method, and the averaged mapping approach to the gradient-projection algorithm. …”
Get full text

THE DISTRIBUTION AND RELATIVE ABUNDANCE OF WILD TURKEYS IN FLORIDA by David S. Nicholson, Larry S. Perrin, Cory Morea, Roger Shields

“…Associated maps were digitized into a geographic information system (GIS) and ordinal responses (i.e., categorical abundance scores) were averaged for each 30‐m × 30‐m pixel. …”
Get full text

Geolocation error compensation method for geocoded SAR images using pixel-offset series without control points by Liqun Liu, Zhiwei Li, Yan Zhu, Yifan Zhang, Chenglong Cao, Xun Du, Kun Han, Haiqiang Fu

“…The planimetric geolocation accuracy of the SAR image was better than one pixel, improved by 65% compared with Google satellite maps. These results demonstrate the applicability of the proposed method.…”
Get full text

What Does the LMC Look Like? It Depends on [M/H] and Age by Neige Frankel, Rene Andrae, Hans-Walter Rix, Joshua Povick, Vedant Chandra

“…This results in the first area-complete, metallicity- and age-differentiated stellar maps of any disk galaxy. Azimuthally averaged, these maps reveal a surprisingly simple picture of the Milky Way's largest satellite galaxy. …”
Get full text

Generating synthetic as-built additive manufacturing surface topography using progressive growing generative adversarial networks by Junhyeon Seo, Prahalada Rao, Bart Raeymaekers

“…We qualitatively and quantitatively demonstrate good agreement between synthetic and experimental as-built LPBF surface topography maps using areal and deterministic surface topography parameters, radially averaged power spectral density, and material ratio curves. …”
Get full text

Hybrid Iterative Scheme for Triple Hierarchical Variational Inequalities with Mixed Equilibrium, Variational Inclusion, and Minimization Constraints by Lu-Chuan Ceng, Cheng-Wen Liao, Chin-Tzong Pang, Ching-Feng Wen

“…We introduce and analyze a hybrid iterative algorithm by combining Korpelevich's extragradient method, the hybrid steepest-descent method, and the averaged mapping approach to the gradient-projection algorithm. …”
Get full text

Blind Source Separation of Hemodynamics from Magnetic Resonance Perfusion Brain Images Using Independent Factor Analysis by Yen-Chun Chou, Chia-Feng Lu, Wan-Yuo Guo, Yu-Te Wu

“…We employed independent factor analysis to blindly separate such dynamic images into different maps, that is, artery, gray matter, white matter, vein and sinus, and choroid plexus, in conjunction with corresponding signal-time curves. …”
Get full text

On Introduction to q1,q2-Linear Diophantine Fuzzy Sets and Their Applications by Muhammad Bilal Khan, Adrian Marius Deaconu, Javad Tayyebi, Bandar Bin-Mohsin, Loredana Ciurdariu, Miguel Vivas Cortez, Nurnadiah Zamri

“…The primary benefit of q1,q2LDFSs, which are useful in a variety of decision-making situations, is that they are able to characterize a greater number of uncertainties with respect to reference parameter mappings q1 and q2 than LDFSs. Next, we propose several geometric and averaging operators for a q1,q2 linear Diophantine fuzzy numbers, based on established operating rules. …”
Get full text

Evaluating the Potential to Quantify Salmon Habitat via UAS‐Based Particle Image Velocimetry by Lee R. Harrison, Carl J. Legleiter, Brandon T. Overstreet, James S. White

“…We evaluated the potential for UAS‐based mapping of hydraulic habitats using spectrally based depth retrieval and particle image velocimetry (PIV) by comparing these methods to a more well‐established flow modeling approach. …”
Get full text

Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition by Huilan LUO, Kang TONG

“…Aiming at the shortcomings of shallow networks and general deep models in two-stream network structure,which could not effectively learn spatial and temporal information,a squeeze-and-excitation residual network was proposed for action recognition with a spatial stream and a temporal stream.Meanwhile,the long-term temporal dependence was captured by injecting the identity mapping kernel into the network as a temporal filter.Spatiotemporal feature multiplication fusion was used to further enhance the interaction between spatial information and temporal information of squeeze-and-excitation residual networks.Simultaneously,the influence of spatial-temporal stream multiplication fusion methods,times and locations on the performance of action recognition was studied.Given the limitations of performance achieved by a single model,three different strategies were proposed to generate multiple models,and the final recognition result was obtained by integrating these models through averaging and weighted averaging.The experimental results on the HMDB51 and UCF101 datasets show that the proposed spatiotemporal squeeze-and-excitation residual multiplier networks can effectively improve the performance of action recognition.…”
Get full text

Updated plant hardiness zones for Canada and assessment of change over time by Daniel W. McKenney, John H. Pedlar, Kevin Lawrence, Kaitlin DeBoer, Heather MacDonald

“…Here we report on efforts to update hardiness zone maps for Canada using both the Canadian and US approaches and using climate data for the 1991–2020 period. …”
Get full text

The random free field scalar theory by Alessandro Piazza, Marco Serone, Emilio Trevisani

“…The maps are non-trivial and show that conformal behaviour is manifest only when considering suitable linear combinations of averages of products of correlators. …”
Get full text

The conformal primon gas at the end of time by Sean A. Hartnoll, Ming Yang

“…Abstract The Belinksy-Khalatnikov-Lifshitz dynamics of gravity close to a spacelike singularity can be mapped, at each point in space separately, onto the motion of a particle bouncing within half the fundamental domain of the modular group. …”
Get full text

Remote work – the new normal needs more research by Annina Ropponen

“…Studying digital disconnection: A mapping review of empirical contributions to disconnection studies. …”
Get full text

Unravelling urban carbon dynamics: a multi-source data study on Nanchang city's carbon dioxide emissions by Lingyun Yao, Li Wang, Ke Wang, Zheng Niu

“…However, it is challenging to achieve an optimal balance between the quality and quantity with existing mapping methods. The objective of this study is to develop a rapid mapping method for urban CO2 with high spatiotemporal resolution based on multi-source data. …”
Get full text

7 Tesla multimodal MRI dataset of ex-vivo human brain by Qinfeng Zhu, Sihui Li, Zuozhen Cao, Yao Shen, Haoan Xu, Guojun Xu, Haotian Li, Zhaopeng Cui, Keqing Zhu, Zhiyong Zhao, Jing Zhang, Dan Wu

“…This database included structural MRI, high-angular resolution diffusion MRI, quantitative susceptibility mapping, and quantitative T1 and T2 maps, which enabled multifaceted depiction of brain microstructure and connectivity. …”
Get full text

Non-Linear Super-Stencils for turbulence model corrections by Jonas Luther, Patrick Jenny

“…Here, we introduce the Non-Linear Super-Stencil (NLSS), that is, a compact stencil sampling local mean flow features and mapping them to a corrective force term by employing a neural network. …”
Get full text