Influence of rainfall factors and tree structure on rainfall partitioning for typical trees in Linpan settlements, the typical agroforestry ecosystem of the Chengdu Plain

In the process of land consolidation in Chengdu Plain, Linpan protection is an important content. At present, some protection types of Linpan have been formed in Chengdu area, such as agriculture, rural tourism, special industry and settlement type and so on. Many protected modes were explored, such as the natural subsidies, in situ conservation, comprehensive development, off-site reconstruction, etc. But there are still some questions, do not pay attention to protect Linpan ecological pattern plate function transformation, the architectural style of hybrid, protection methods are not flexible, evaluation standard is not perfect, the public participation is not enough and other issues, these problems need to be continuously optimized and improved in the future.

Download Full-text

Adaptive Dual Tree Structure For Screen Content Coding

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp39728.2021.9414002 ◽

2021 ◽

Author(s):

Weijia Zhu ◽

Jizheng Xu ◽

Li Zhang ◽

Yue Wang

Keyword(s):

Tree Structure ◽

Screen Content ◽

Screen Content Coding

Download Full-text

Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning

2020 IEEE International Conference on Data Mining (ICDM) ◽

10.1109/icdm50108.2020.00052 ◽

2020 ◽

Author(s):

Ziyue Qiao ◽

Pengyang Wang ◽

Yanjie Fu ◽

Yi Du ◽

Pengfei Wang ◽

...

Keyword(s):

Metric Learning ◽

Representation Learning ◽

Tree Structure ◽

Graph Representation ◽

Hierarchical Aggregation

Download Full-text

Multi-GPU approach to global induction of classification trees for large-scale data mining

Applied Intelligence ◽

10.1007/s10489-020-01952-5 ◽

2021 ◽

Author(s):

Krzysztof Jurczuk ◽

Marcin Czajkowski ◽

Marek Kretowski

Keyword(s):

Data Mining ◽

Large Scale ◽

Real Life ◽

Population Based ◽

Tree Structure ◽

Global Approach ◽

Data Parallel ◽

Large Scale Data ◽

The Impact ◽

Scale Data

AbstractThis paper concerns the evolutionary induction of decision trees (DT) for large-scale data. Such a global approach is one of the alternatives to the top-down inducers. It searches for the tree structure and tests simultaneously and thus gives improvements in the prediction and size of resulting classifiers in many situations. However, it is the population-based and iterative approach that can be too computationally demanding to apply for big data mining directly. The paper demonstrates that this barrier can be overcome by smart distributed/parallel processing. Moreover, we ask the question whether the global approach can truly compete with the greedy systems for large-scale data. For this purpose, we propose a novel multi-GPU approach. It incorporates the knowledge of global DT induction and evolutionary algorithm parallelization together with efficient utilization of memory and computing GPU’s resources. The searches for the tree structure and tests are performed simultaneously on a CPU, while the fitness calculations are delegated to GPUs. Data-parallel decomposition strategy and CUDA framework are applied. Experimental validation is performed on both artificial and real-life datasets. In both cases, the obtained acceleration is very satisfactory. The solution is able to process even billions of instances in a few hours on a single workstation equipped with 4 GPUs. The impact of data characteristics (size and dimension) on convergence and speedup of the evolutionary search is also shown. When the number of GPUs grows, nearly linear scalability is observed what suggests that data size boundaries for evolutionary DT mining are fading.

Download Full-text