The similarity-trust centrality collective experts’ preference relation is the aggregation result of the application of the STC-IOWA operator of dimension m, Φ ST C w , to the individual preferences of the experts: pij c = ΦST w D A(e 1 ), pij 1 E , D A(e 2 ), pij 2 E , . . . , D A(e m), pij m E什么意思
时间: 2024-04-18 21:27:08 浏览: 26
根据您的描述,相似信任中心度集体专家偏好关系是将STC-IOWA算子 ΦSTCw 应用于各个专家的个人偏好之后的聚合结果。
假设有m个专家,每个专家对于每个项目的偏好值分别为 pij1, pij2, ..., pijm。
那么,相似信任中心度集体专家偏好关系 pijc 可以通过将STC-IOWA算子 ΦSTCw 应用于各个专家的个人偏好值 D A(e1), pij1E, D A(e2), pij2E, ..., D A(em), pijmE 来计算得到。
具体计算公式如下:
pijc = ΦSTCw(D A(e1), pij1E, D A(e2), pij2E, ..., D A(em), pijmE)
这样,通过应用STC-IOWA算子 ΦSTCw 到各个专家的个人偏好值上,可以得到相似信任中心度集体专家偏好关系 pijc。这个集体偏好关系考虑了各个专家的权重和偏好值,从而得出了整体的偏好结果。
相关问题
Thus, an IOWA reorder the values to aggregate, {p1, . . . , pn }, by using the corresponding ordering of an auxiliary set of associated numbers , {u1, . . . , un }, known as order inducing values. Using the network GST similarity-trust centrality index values, A(e 1 ), A(e 2 ), . . . , A(e m) , as the set of order inducing values of the experts’ preference relations,the similarity-trust centrality IOWA (STC-IOWA) operator, Φ ST C w , and similarity-trust centrality collective preference relation are obtained.什么意思
根据您提供的描述,使用IOWA算子进行聚合时,可以使用一个与顺序相关的辅助集合 {u₁, ..., uₙ},称为引导顺序值,对要聚合的值 {p₁, ..., pₙ} 进行重新排序。其中,引导顺序值是专家偏好关系的相似信任中心度指标值 A(e₁), A(e₂), ..., A(eₘ)。
通过使用网络GST相似信任中心度指标值作为专家偏好关系的引导顺序值,可以得到相似信任中心度IOWA (STC-IOWA)算子 ΦSTCw 和相似信任中心度集体偏好关系。
简单来说,使用IOWA算子时,通过引导顺序值对要聚合的值进行排序,其中引导顺序值可以是专家偏好关系的相似信任中心度指标值。通过这样的排序方式,可以得到相似信任中心度IOWA算子和相似信任中心度集体偏好关系。
请把这篇文献《Accelerating Similarity-Based Model Matching Using On-The-Fly Similarity Preserving Hashing》翻译成中文
加速基于相似性模型匹配的On-The-Fly相似性保持哈希
摘要:
在软件工程中,模型匹配是一项核心任务,广泛应用于模型驱动工程、软件重构、需求管理、代码检查等领域。由于模型通常包含大量的元素和复杂的结构,模型匹配问题变得越来越具有挑战性。相似性匹配是一种流行的模型匹配方法,它通过计算语义相似度来匹配模型元素。然而,由于相似性匹配算法的计算复杂度很高,导致它们的效率低下。
为了提高相似性匹配的效率,我们提出了一种基于On-The-Fly相似性保持哈希的加速方法。该方法利用哈希表将元素映射到桶中,并在桶中使用相似性保持哈希函数计算相似性,从而避免了在匹配过程中进行昂贵的相似性计算。此外,我们还提出了一种基于哈希冲突的剪枝策略,以进一步提高匹配效率。
我们在多个数据集上进行了实验,并与现有相似性匹配算法进行了比较。实验结果表明,我们的方法可以显著提高匹配效率,同时保持高精度。
关键词:模型匹配,相似性匹配,哈希,剪枝
Abstract:
In software engineering, model matching is a core task widely applied in model-driven engineering, software refactoring, requirement management, code inspection, etc. Due to the fact that models usually contain a large number of elements and complex structures, model matching problems become increasingly challenging. Similarity-based matching is a popular model matching approach that matches model elements by computing semantic similarities. However, due to the high computational complexity of similarity-based matching algorithms, they suffer from poor efficiency.
To improve the efficiency of similarity-based matching, we propose an acceleration method based on On-The-Fly similarity preserving hashing. This method uses a hash table to map elements to buckets and employs similarity preserving hash functions to compute similarities within buckets, thus avoiding expensive similarity computations during the matching process. In addition, we propose a hash conflict-based pruning strategy to further improve the matching efficiency.
We conduct experiments on multiple datasets and compare our method with existing similarity-based matching algorithms. Experimental results show that our method can significantly improve the matching efficiency while maintaining high accuracy.
Keywords: Model matching, similarity-based matching, hashing, pruning.
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![.pdf](https://img-home.csdnimg.cn/images/20210720083646.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)