Firmiana danxiaensis (F. danxiaensis) is a special native species with narrow distribution. More than 90 % of the plant in genus that F. belongs to are rare The main distribution area Mount Danxia, representative China Danxia where many endemic landform have been bred. We carried out gap analysis by overlapping nature reserves potential habitat danxiaensis. results show that: (1) 6,255.28 km2 simulated Biomod2 ensemble model and 4,114.19 Maxent, respectively, which accounted for 3.48 2.29...

To address the problems of error and omission detection in remote sensing image caused by diverse scale changes object scales abundant proportion small-scale objects, as well global dense distribution a improvement method based on YOLOv5-S is proposed. First, according to characteristics data enhancement strategy adopted expand dataset samples for objects improve generalization ability model. Second, contextual transformer module introduced backbone feature extraction network fusion ensure...

Purpose Maximum k vertex cover problem is a significant combinatorial optimization with various applications, such as transportation planning, social networks and sensor placement. Up to now, no practical algorithm has ever been proposed solve this problem. Therefore, paper aims present an efficient local search LSKVC combining three methods for it. Design/methodology/approach First, the quick incremental evaluation method update related scores following each addition or removal...

The detection of fabric defects is an important part quality control, and hence thus a research hotspot in the textile industry. With aim effectively detecting defects, this paper describes improved defect method based on membership degree each region (TPA). By analyzing regional features surface saliency regions can be determined using extreme point density map image function region. A threshold iterative morphological processing are used to ensure precise accurate defects. Experimental...

The minimum connected dominating set (MCDS) problem is a very significant NP-hard combinatorial optimization problem, and it has been used in many fields such as wireless sensor networks ad hoc networks. In this paper, we propose novel multi-start local search algorithm (MSLS) to tackle the problem. Firstly, present fitness mechanism design vertex score so that our can jump out of optimum. Secondly, use configuration checking (CC) avoid cycling Then, flipping change state by combing CC with...

Abstract Low resolution of input data and equifinality in model calibration can lead to inaccuracy insufficient reflection spatial differences, thereby increasing errors. However, the impact accuracy, catchment threshold area, algorithm on uncertainty reduction has not yet been well understood. The sequential fitting version 2 (SUFI‐2) that is linked with Soil Water Assessment Tool (SWAT) package called SWAT Calibration Uncertainty Programs (SWAT‐CUP) was introduced quantify effects...

The maximum edge weighted clique problem (MEWCP), an extension of the classical problem, is important NP-hard combinatorial optimization problem. has been widely used in various areas. objective this paper to design efficient local search algorithm solve MEWCP. First, proposed scoring strategy evaluate benefit adding and swapping operators. Second, vertex weighting increase diversity solutions configuration checking avoid cycling By combining these three strategies, we propose multiple rules...

The multi-objective minimum weighted vertex cover problem aims to minimize the sum of different single type weights simultaneously. In this paper, we focus on bi-objective and propose a algorithm integrating iterated neighborhood search with decomposition technique solve problem. Initially, adopt method divide into several scalar optimization sub-problems. Meanwhile, find more possible optimal solutions, design mixed score function according feature, which is applied in initializing...

The Maximum k-Defective Clique Problem (MDCP), as a clique relaxation model, has been used to solve various problems. Because it is hard computational task, previous works can hardly the MDCP for massive sparse graphs derived from real-world applications. In this work, we propose novel branch-and-bound algorithm based on several new techniques. First, two upper bounds of well corresponding reduction rules remove redundant vertices and edges. proposed are particularly useful graphs. Second,...

Given an undirected, connected and edge-weighted graph, the dominating tree problem consists of finding a with minimum total edge weight such that for each vertex is either in or adjacent to tree. In this paper, we propose hybrid framework combining genetic algorithm iterated local search (GAITLS) solving problem. The main components our are as follows: (1) score functions D s c o r e W applied initialization phase; (2) procedure restricted candidate list (RCL) by controlling parameter...

In the task of camouflaged human target detection, is highly integrated with complex environment background, which difficult to identify and leads false detection missed detection. A algorithm MC-YOLOv5s proposed for characteristics targets. The takes YOLOv5s as basic framework. First, a multispectral channel attention module embedded in backbone feature extraction network, enhances network's ability extract features, weakens surrounding effectively improves algorithm's antibackground...