Статті в журналах: "Module clustering"

1

Alshareef, Haya, and Mashael Maashi. "Application of Multi-Objective Hyper-Heuristics to Solve the Multi-Objective Software Module Clustering Problem." Applied Sciences 12, no. 11 (June 2, 2022): 5649. http://dx.doi.org/10.3390/app12115649.

Повний текст джерела

Анотація:

Software maintenance is an important step in the software lifecycle. Software module clustering is a HHMO_CF_GDA optimization problem involving several targets that require minimization of module coupling and maximization of software cohesion. Moreover, multi-objective software module clustering involves assembling a specific group of modules according to specific cluster criteria. Software module clustering classifies software modules into different clusters to enhance the software maintenance process. A structure with low coupling and high cohesion is considered an excellent software module structure. In this study, we apply a multi-objective hyper-heuristic method to solve the multi-objective module clustering problem with three objectives: (i) minimize coupling, (ii) maximize cohesion, and (iii) ensure high modularization quality. We conducted several experiments to obtain optimal and near-optimal solutions for the multi-objective module clustering optimization problem. The experimental results demonstrated that the HHMO_CF_GDA method outperformed the individual multi-objective evolutionary algorithms in solving the multi-objective software module clustering optimization problem. The resulting software, in which HHMO_CF_GDA was applied, was more optimized and achieved lower coupling with higher cohesion and better modularization quality. Moreover, the structure of the software was more robust and easier to maintain because of its software modularity.

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Hou, Jie, Xiufen Ye, Chuanlong Li, and Yixing Wang. "K-Module Algorithm: An Additional Step to Improve the Clustering Results of WGCNA Co-Expression Networks." Genes 12, no. 1 (January 12, 2021): 87. http://dx.doi.org/10.3390/genes12010087.

Повний текст джерела

Анотація:

Among biological networks, co-expression networks have been widely studied. One of the most commonly used pipelines for the construction of co-expression networks is weighted gene co-expression network analysis (WGCNA), which can identify highly co-expressed clusters of genes (modules). WGCNA identifies gene modules using hierarchical clustering. The major drawback of hierarchical clustering is that once two objects are clustered together, it cannot be reversed; thus, re-adjustment of the unbefitting decision is impossible. In this paper, we calculate the similarity matrix with the distance correlation for WGCNA to construct a gene co-expression network, and present a new approach called the k-module algorithm to improve the WGCNA clustering results. This method can assign all genes to the module with the highest mean connectivity with these genes. This algorithm re-adjusts the results of hierarchical clustering while retaining the advantages of the dynamic tree cut method. The validity of the algorithm is verified using six datasets from microarray and RNA-seq data. The k-module algorithm has fewer iterations, which leads to lower complexity. We verify that the gene modules obtained by the k-module algorithm have high enrichment scores and strong stability. Our method improves upon hierarchical clustering, and can be applied to general clustering algorithms based on the similarity matrix, not limited to gene co-expression network analysis.

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Hu, Hai Yan, and You Qiao Zhang. "The Study and Realization of Energy-Aware Routing Algorithm of Wireless Sensor Networks." Applied Mechanics and Materials 201-202 (October 2012): 767–72. http://dx.doi.org/10.4028/www.scientific.net/amm.201-202.767.

Повний текст джерела

Анотація:

Based on the analysis of routing algorithm of typical wireless sensor networks, the author puts forward with the objectives of routing algorithm and designs energy-aware routing algorithm to reduce energy consumption and extend life cycle of the whole network. The algorithm constitutes four modules: clustering module, dynamic cluster head election module, dormant state module and inter-cluster routing module. Aiming at effectively using the energy of sensor nodes, the paper makes use of honeycomb-like two-level clustering structure to increase coverage rate of nodes. Also, studies of routing are discussed on the two aspects, being the inter-clustering dynamic cluster head election and introduction of dormant mechanism, and secondly, the inter-clustering reliable routing.The routing algorithm has its prototype realized and effectively verified on the test bed provided by the laboratory.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Kirve, Shraddha. "Clustering Techniques in Wireless Sensor Networks: A Practical Study." International Journal for Research in Applied Science and Engineering Technology 9, no. VI (June 10, 2021): 536–38. http://dx.doi.org/10.22214/ijraset.2021.34990.

Повний текст джерела

Анотація:

Our Solution for the Mentioned Problem Statement Comprised of Different Modules such as Alert &Notification Module, Real-Time Data Collection Module from Authenticated Source, Precaution Module to Define and Broadcast Protocol to Disaster Affected Areas, Social Media Message Circulation (SMMC) Module. IENS (Indian Early Notification System) has been designed by our team to Get & Fetch Notification System as soon as Disaster Stuck or Popped-Up (Introduce/Originated) and notifies as well as channelize Related Information via Different Social Media Official Platforms.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Karayiannis, Dimitrios, and Spyros Tragoudas. "Clustering Network Modules with Different Implementations for Delay Minimization." VLSI Design 7, no. 1 (January 1, 1998): 1–13. http://dx.doi.org/10.1155/1998/69289.

Повний текст джерела

Анотація:

In recent years there has been an extensive interest in clustering the modules of a network so that the maximum delay from any primary input to any primary output is minimized [8, 7, 6]. Clusters have a maximum capacity and modules may have different implementations. All existing CAD frameworks initially select an implementation of each module, and at a later stage they cluster the modules. We present an approach that clusters the nodes, while considering their alternative implementations, so that we further minimize the maximum delay after the clustering. Our approach is based on optimal algorithms for restricted versions of this complex problem in circuit design, and outperforms the conventional approach, which first obtains an implementation for each circuit module without considering clustering and then, in a later step, performs clustering.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Mohammad Shahid, Sunil Gupta, and MS. Sofia Pillai. "Machine Learning-Based False Positive Software Vulnerability Analysis." Global Journal of Innovation and Emerging Technology 1, no. 1 (June 15, 2022): 29–35. http://dx.doi.org/10.58260/j.iet.2202.0105.

Повний текст джерела

Анотація:

Measurements and fault data from an older software version were used to build the fault prediction model for the new release. When past fault data isn't available, it's a problem. The software industry's assessment of programme module failure rates without fault labels is a difficult task. Unsupervised learning can be used to build a software fault prediction model when module defect labels are not available. These techniques can help identify programme modules that are more prone to errors. One method is to make use of clustering algorithms. Software module failures can be predicted using unsupervised techniques such as clustering when fault labels are not available. Machine learning clustering-based software failure prediction is our approach to solving this complex problem.

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Strauch, Martin, Jochen Supper, Christian Spieth, Dierk Wanke, Joachim Kilian, Klaus Harter, and Andreas Zell. "A Two-Step Clustering for 3-D Gene Expression Data Reveals the Main Features of the Arabidopsis Stress Response." Journal of Integrative Bioinformatics 4, no. 1 (March 1, 2007): 81–93. http://dx.doi.org/10.1515/jib-2007-54.

Повний текст джерела

Анотація:

Summary We developed an integrative approach for discovering gene modules, i.e. genes that are tightly correlated under several experimental conditions and applied it to a threedimensional Arabidopsis thaliana microarray dataset. The dataset consists of approximately 23000 genes responding to 9 abiotic stress conditions at 6-9 different points in time. Our approach aims at finding relatively small and dense modules lending themselves to a specific biological interpretation. In order to detect gene modules within this dataset, we employ a two-step clustering process. In the first step, a k-means clustering on one condition is performed, which is subsequently used in the second step as a seed for the clustering of the remaining conditions. To validate the significance of the obtained modules, we performed a permutation analysis and determined a null hypothesis to compare the module scores against, providing a p-value for each module. Significant modules were mapped to the Gene Ontology (GO) in order to determine the participating biological processes.As a result, we isolated modules showing high significance with respect to the p-values obtained by permutation analysis and GO mapping. In these modules we identified a number of genes that are either part of a general stress response with similar characteristics under different conditions (coherent modules), or part of a more specific stress response to a single stress condition (single response modules). We also found genes clustering within several conditions, which are, however, not part of a coherent module. These genes have a distinct temporal response under each condition. We call the modules they are contained in individual response modules (IR).

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Yu, Limin, Xianjun Shen, Jincai Yang, Kaiping Wei, Duo Zhong, and Ruilong Xiang. "Hypergraph Clustering Based on Game-Theory for Mining Microbial High-Order Interaction Module." Evolutionary Bioinformatics 16 (January 2020): 117693432097057. http://dx.doi.org/10.1177/1176934320970572.

Повний текст джерела

Анотація:

Microbial community is ubiquitous in nature, which has a great impact on the living environment and human health. All these effects of microbial communities on the environment and their hosts are often referred to as the functions of these communities, which depend largely on the composition of the communities. The study of microbial higher-order module can help us understand the dynamic development and evolution process of microbial community and explore community function. Considering that traditional clustering methods depend on the number of clusters or the influence of data that does not belong to any cluster, this paper proposes a hypergraph clustering algorithm based on game theory to mine the microbial high-order interaction module (HCGI), and the hypergraph clustering problem naturally turns into a clustering game problem, the partition of network modules is transformed into finding the critical point of evolutionary stability strategy (ESS). The experimental results show HCGI does not depend on the number of classes, and can get more conservative and better quality microbial clustering module, which provides reference for researchers and saves time and cost. The source code of HCGI in this paper can be downloaded from https://github.com/ylm0505/HCGI .

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Alam, M. K., Azrina Abd Aziz, S. A. Latif, and Azlan Awang. "Error-Aware Data Clustering for In-Network Data Reduction in Wireless Sensor Networks." Sensors 20, no. 4 (February 13, 2020): 1011. http://dx.doi.org/10.3390/s20041011.

Повний текст джерела

Анотація:

A wireless sensor network (WSN) deploys hundreds or thousands of nodes that may introduce large-scale data over time. Dealing with such an amount of collected data is a real challenge for energy-constraint sensor nodes. Therefore, numerous research works have been carried out to design efficient data clustering techniques in WSNs to eliminate the amount of redundant data before transmitting them to the sink while preserving their fundamental properties. This paper develops a new error-aware data clustering (EDC) technique at the cluster-heads (CHs) for in-network data reduction. The proposed EDC consists of three adaptive modules that allow users to choose the module that suits their requirements and the quality of the data. The histogram-based data clustering (HDC) module groups temporal correlated data into clusters and eliminates correlated data from each cluster. Recursive outlier detection and smoothing (RODS) with HDC module provides error-aware data clustering, which detects random outliers using temporal correlation of data to maintain data reduction errors within a predefined threshold. Verification of RODS (V-RODS) with HDC module detects not only random outliers but also frequent outliers simultaneously based on both the temporal and spatial correlations of the data. The simulation results show that the proposed EDC is computationally cheap, able to reduce a significant amount of redundant data with minimum error, and provides efficient error-aware data clustering solutions for remote monitoring environmental applications.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Wu, Yong Liang, Bao Quan Mao, Li Xu, Dong Ming Dai, and Yan Chao Liu. "The Evaluation of Module Division Programme Based on Information Entropy." Advanced Materials Research 479-481 (February 2012): 1592–95. http://dx.doi.org/10.4028/www.scientific.net/amr.479-481.1592.

Повний текст джерела

Анотація:

Firstly, analysis product’s customer demand correlation, function correlation, geometric correlation, structure the corresponding correlation matrix, distribute the respective weighting factor, and then establish an integrated correlation matrix. Application of fuzzy clustering, the establishment of cluster map, the program has been divided into different modules. Based on information entropy theory, select product’s design and manufacturing complexity, cost, maintenance as the optimization objective, establish mathematical evaluation model of module division. Evaluating a number of options get from the fuzzy clustering method, which gain the most reasonable module division program. Finally, taking the seat frame of the Remote Control Weapon Station(RCWS) for example, verify the validity and reasonableness of the evaluation method.

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Li, Lianwei, Cunjin Xue, Yangfeng Xu, Chengbin Wu, and Chaoran Niu. "PoSDMS: A Mining System for Oceanic Dynamics with Time Series of Raster-Formatted Datasets." Remote Sensing 14, no. 13 (June 22, 2022): 2991. http://dx.doi.org/10.3390/rs14132991.

Повний текст джерела

Анотація:

Many effective and advanced methods have been developed to explore oceanic dynamics using time series of raster-formatted datasets; however, they have generally been designed at a scale suitable for data observation and used independently of each other, despite the potential advantages of combining different modules into an integrated system at a scale suited for dynamic evolution. From raster-formatted datasets to marine knowledge, we developed and integrated several mining algorithms at a dynamic evolutionary scale and combined them into six modules: a module of raster-formatted dataset pretreatment; a module of process-oriented object extraction; a module of process-oriented representation and management (process-oriented graph database); a module of process-oriented clustering; a module of process-oriented association rule mining; and a module of process-oriented visualization. On the basis of such modules, we developed a process-oriented spatiotemporal dynamic mining system named PoSDMS (Process-oriented Spatiotemporal Dynamics Mining System). PoSDMS was designed to have the capacity to deal with at least six environments of marine anomalies with 40 years of raster-formatted datasets, including their extraction, representation, storage, clustering, association and visualization. The effectiveness of the integrated system was evaluated in a case study of sea surface temperature datasets during the period from January 1982 to December 2021 in global oceans. The main contribution of this study was the development of a mining system at a scale suited for dynamic evolution, providing an analyzing platform or tool to deal with time series of raster-formatted datasets to aid in obtaining marine knowledge.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Ling, Yawen, Jianpeng Chen, Yazhou Ren, Xiaorong Pu, Jie Xu, Xiaofeng Zhu, and Lifang He. "Dual Label-Guided Graph Refinement for Multi-View Graph Clustering." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 8791–98. http://dx.doi.org/10.1609/aaai.v37i7.26057.

Повний текст джерела

Анотація:

With the increase of multi-view graph data, multi-view graph clustering (MVGC) that can discover the hidden clusters without label supervision has attracted growing attention from researchers. Existing MVGC methods are often sensitive to the given graphs, especially influenced by the low quality graphs, i.e., they tend to be limited by the homophily assumption. However, the widespread real-world data hardly satisfy the homophily assumption. This gap limits the performance of existing MVGC methods on low homophilous graphs. To mitigate this limitation, our motivation is to extract high-level view-common information which is used to refine each view's graph, and reduce the influence of non-homophilous edges. To this end, we propose dual label-guided graph refinement for multi-view graph clustering (DuaLGR), to alleviate the vulnerability in facing low homophilous graphs. Specifically, DuaLGR consists of two modules named dual label-guided graph refinement module and graph encoder module. The first module is designed to extract the soft label from node features and graphs, and then learn a refinement matrix. In cooperation with the pseudo label from the second module, these graphs are refined and aggregated adaptively with different orders. Subsequently, a consensus graph can be generated in the guidance of the pseudo label. Finally, the graph encoder module encodes the consensus graph along with node features to produce the high-level pseudo label for iteratively clustering. The experimental results show the superior performance on coping with low homophilous graph data. The source code for DuaLGR is available at https://github.com/YwL-zhufeng/DuaLGR.

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Jeet, Kawal, and Renu Dhir. "Software Module Clustering Using Hybrid SocioEvolutionary Algorithms." International Journal of Information Engineering and Electronic Business 8, no. 4 (July 8, 2016): 43–53. http://dx.doi.org/10.5815/ijieeb.2016.04.06.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Sun, Jiaze, and Beilei Ling. "Software Module Clustering Algorithm Using Probability Selection." Wuhan University Journal of Natural Sciences 23, no. 2 (March 19, 2018): 93–102. http://dx.doi.org/10.1007/s11859-018-1299-9.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Chen, F. Y., and G. W. Zhang. "The Module Partition Approach for the Personalized Products and Production." Materials Science Forum 697-698 (September 2011): 650–55. http://dx.doi.org/10.4028/www.scientific.net/msf.697-698.650.

Повний текст джерела

Анотація:

The rational and effective partition of the module has been the vital significance to the product design and manufacture. In this paper, a deficiency about the existing module partition can’t satisfy customer personalized is pointed out. Therefore, a method is put forward based on the design method of axiomatic, by analyzing the correlation among the parts, combining the dynamical clustering and mathematical statistic calculation to achieve the rough-to-fine division according to the principles of module partition. Finally, the based modules and the personalized modules are determined through the choice of based parameters and personalized parameters. The basic module and personalized module are integrated on a personalized product platform base on Internet. Customer can directly involved the product design by personalized product platform. The model was explained with example of the gantry grinding machine tool.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Samrin, Rafath, and Devara Vasumathi. "Hybrid Weighted K-Means Clustering and Artificial Neural Network for an Anomaly-Based Network Intrusion Detection System." Journal of Intelligent Systems 27, no. 2 (March 28, 2018): 135–47. http://dx.doi.org/10.1515/jisys-2016-0105.

Повний текст джерела

Анотація:

AbstractDespite the rapid developments in data technology, intruders are among the most revealed threats to security. Network intrusion detection systems are now a typical constituent of network security structures. In this paper, we present a combined weighted K-means clustering algorithm with artificial neural network (WKMC+ANN)-based intrusion identification scheme. This paper comprises two modules: clustering and intrusion detection. The input dataset is gathered into clusters with the usage of WKMC in clustering module. In the intrusion detection module, the clustered information is trained with the utilization of ANN and its structure is stored. In the testing process, the data are tested by choosing the most suitable ANN classifier, which corresponds to the closest cluster to the test data, according to distance or similarity measures. For experimental evaluation, we used the benchmark database, and the results clearly demonstrated that the proposed technique outperformed the existing technique by having better accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Hwa, Jimin, Shin Yoo, Yeong-Seok Seo, and Doo-Hwan Bae. "Search-Based Approaches for Software Module Clustering Based on Multiple Relationship Factors." International Journal of Software Engineering and Knowledge Engineering 27, no. 07 (September 2017): 1033–62. http://dx.doi.org/10.1142/s0218194017500395.

Повний текст джерела

Анотація:

Software remodularization seeks to cluster software modules with high cohesion and low coupling: such a structure can help the comprehension and maintenance of complex systems. The modularization quality is usually captured using either structural, semantic, or history-based factors. All existing techniques apply a single factor to the entire system, which raises the following issues. First, a single factor may fail to capture the quality across the entire project: some modules may form semantic bondings, while others may form more structural ones. Second, the user of the technique has to choose a factor without knowing which one would perform the best. To resolve these issues, we propose a multi-factor module clustering, in which module clusters can be formed based on different factors. Our technique not only allows module clusters of different natures, but also relieve users from having to select a single factor. The paper introduces two different search-based formulations of multi-factor remodularization, and compares these against single-factor remodularization using four heterogeneous factors and six open source projects. The evaluation results show that the multi-factor remodularization can produce solutions that are 10.69% closer to the actual modularization adopted by the developers as compared with those produced by single-factor remodularization on average.

Стилі APA, Harvard, Vancouver, ISO та ін.

18

You, Ying, Zhiqiang Liu, Youqian Liu, Ning Peng, Jian Wang, Yizhe Huang, and Qibai Huang. "K-Means Module Division Method of FDM3D Printer-Based Function–Behavior–Structure Mapping." Applied Sciences 13, no. 13 (June 23, 2023): 7453. http://dx.doi.org/10.3390/app13137453.

Повний текст джерела

Анотація:

Product performance, function, cost, and the level of module generalization are all significantly influenced by product modular design, but different goods require different division indicators and techniques. The purpose of this study is to provide a set of appropriate modular division techniques for FDM 3D printers. This research offers an ecologically friendly module division index and uses module clustering as the module division principle in accordance with the current industrial development trend and the fundamental requirements of FDM 3D printer consumers in the current market. The K-means algorithm is used to use the Jaccard similarity coefficient as the metric of similarity of the DSM clustering process to realize the module division of the FDM 3D printer after studying the function–behavior–structure mapping model of the 3D printer. Additionally, the elbow method–cluster error variance and average contour coefficient evaluation systems were built, respectively, in order to verify the viability of the FDM 3D printer module division method and obtain the best module division results. By analyzing these two systems, it was discovered that when the FDM 3D printer was divided into three modules, the in-cluster error variance diagram obviously had an inflection point, and the average profile coefficient and other modular approaches that need to be adjusted to their respective goods can use this division method as a theoretical foundation and point of reference.

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Arasteh, Bahman, Peri Gunes, Asgarali Bouyer, Farhad Soleimanian Gharehchopogh, Hamed Alipour Banaei, and Reza Ghanbarzadeh. "A Modified Horse Herd Optimization Algorithm and Its Application in the Program Source Code Clustering." Complexity 2023 (December 27, 2023): 1–16. http://dx.doi.org/10.1155/2023/3988288.

Повний текст джерела

Анотація:

Maintenance is one of the costliest phases in the software development process. If architectural design models are accessible, software maintenance can be made more straightforward. When the software’s source code is the only available resource, comprehending the program profoundly impacts the costs associated with software maintenance. The primary objective of comprehending the source code is extracting information used during the software maintenance phase. Generating a structural model based on the program source code is an effective way of reducing overall software maintenance costs. Software module clustering is considered a tremendous reverse engineering technique for constructing structural design models from the program source code. The main objectives of clustering modules are to reduce the quantity of connections between clusters, increase connections within clusters, and improve the quality of clustering. Finding the perfect clustering model is considered an NP-complete problem, and many previous approaches had significant issues in addressing this problem, such as low success rates, instability, and poor modularization quality. This paper applied the horse herd optimization algorithm, a distinctive population-based and discrete metaheuristic technique, in clustering software modules. The proposed method’s effectiveness in addressing the module clustering problem was examined by ten real-world standard software test benchmarks. Based on the experimental data, the quality of the clustered models produced is approximately 3.219, with a standard deviation of 0.0718 across the ten benchmarks. The proposed method surpasses former methods in convergence, modularization quality, and result stability. Furthermore, the experimental results demonstrate the versatility of this approach in effectively addressing various real-world discrete optimization challenges.

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Hu, Jinyu, and Zhiwei Gao. "Modules Identification in Gene Positive Networks of Hepatocellular Carcinoma Using Pearson Agglomerative Method and Pearson Cohesion Coupling Modularity." Journal of Applied Mathematics 2012 (2012): 1–21. http://dx.doi.org/10.1155/2012/248658.

Повний текст джерела

Анотація:

In this study, a gene positive network is proposed based on a weighted undirected graph, where the weight represents the positive correlation of the genes. A Pearson agglomerative clustering algorithm is employed to build a clustering tree, where dotted lines cut the tree from bottom to top leading to a number of subsets of the modules. In order to achieve better module partitions, the Pearson correlation coefficient modularity is addressed to seek optimal module decomposition by selecting an optimal threshold value. For the liver cancer gene network under study, we obtain a strong threshold value at 0.67302, and a very strong correlation threshold at 0.80086. On the basis of these threshold values, fourteen strong modules and thirteen very strong modules are obtained respectively. A certain degree of correspondence between the two types of modules is addressed as well. Finally, the biological significance of the two types of modules is analyzed and explained, which shows that these modules are closely related to the proliferation and metastasis of liver cancer. This discovery of the new modules may provide new clues and ideas for liver cancer treatment.

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Pan, Chao, Qide Tan, and Benshuang Qin. "A new method of wind speed prediction based on weighted optimal fuzzy c-means and modular extreme learning machine." Wind Engineering 42, no. 5 (June 1, 2018): 447–57. http://dx.doi.org/10.1177/0309524x18779337.

Повний текст джерела

Анотація:

According to the characteristics of randomness, volatility, and unpredictability of wind speed, this article provides a new wind speed prediction method which includes three modules that are attribute weighting module, intelligent optimization clustering module, and wind speed prediction module based on extreme learning machine. First, the Pearson coefficient values of the attribute matrix elements are calculated and weighted considering the fluctuation characteristics of time series and influences of different weather attributes on the wind speed. Then the fuzzy c-means clustering method optimized by genetic simulated annealing algorithm is carried out on the weighted attribute matrix to cluster. Furthermore, several kinds of wind speed prediction models are built using the extreme learning machine to forecast short-term wind speed. The research on wind speed prediction is carried out by the measured data of wind farm in America (N39.91°, W105.29°). And the results show that the new prediction method of wind speed proposed in this article has higher prediction accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Wang, Li Jing, Tao Xi, Yin Feng Zhou, and Run Hua Tan. "Product Module Partition Method for Product Lifecycle Based on LSSVC." Advanced Materials Research 139-141 (October 2010): 1540–44. http://dx.doi.org/10.4028/www.scientific.net/amr.139-141.1540.

Повний текст джерела

Анотація:

Most of present product module partition methods are based on product function partition and use fuzzy clustering algorithm, but these methods are not only complex in implementation but also difficult to meet the requirements of product development oriented to product lifecycle. By analyzing interactive effects of product components in product lifecycle, a new method for product module partition is put forward. Firstly, LSSVC which has fast calculation speed and high accuracy is used to illustrate the generating process of modules, so several module partition schemes are obtained. Secondly, module partition schemes which are got by LSSVC and other methods of module partition are evaluated to get the most reasonable module partition scheme. Finally, widely-used speed reducer as an example is provided to illustrate the validity and rationality of the proposed approach.

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Lange, Danillo, Marc Ribalta, Lluís Echeverria, and Joshua Pocock. "Profiling urban water consumption using autoencoders and time-series clustering techniques." IOP Conference Series: Earth and Environmental Science 1136, no. 1 (January 1, 2023): 012005. http://dx.doi.org/10.1088/1755-1315/1136/1/012005.

Повний текст джерела

Анотація:

Abstract Nowadays, water utilities face the rising challenge of ensuring water availability amidst a rapidly growing society and a shifting climate. Our research aims to develop a household clustering solution based on water consumption behaviour in Southwest England, to enable utilities to identify different profiles and enhance customized control of household consumption, resulting in improved resource management. The solution is composed of three modules. The first one is based on a K-Means clustering model, designed to group domestic water use behaviours. This module uses the Dynamic Time Wrapping algorithm as a similarity mechanism to process the high-resolution water meter data. In parallel, the second module processes the market segmentation data through an Autoencoder, a specific Neural Network architecture used to reduce the high dimensionality of such data to a low dimension dataset by extracting its latent encoded space. Finally, to assemble the final household water use profiles, a blending K-Means algorithm is used to merge previous modules outputs, based on the Euclidean distance. The solution provides insightful information to water companies to better understand consumer behaviour, habits, and routines.

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Chen, Jianguo, Kenli Li, Keqin Li, Philip S. Yu, and Zeng Zeng. "Dynamic Planning of Bicycle Stations in Dockless Public Bicycle-sharing System Using Gated Graph Neural Network." ACM Transactions on Intelligent Systems and Technology 12, no. 2 (March 2021): 1–22. http://dx.doi.org/10.1145/3446342.

Повний текст джерела

Анотація:

Benefiting from convenient cycling and flexible parking locations, the Dockless Public Bicycle-sharing (DL-PBS) network becomes increasingly popular in many countries. However, redundant and low-utility stations waste public urban space and maintenance costs of DL-PBS vendors. In this article, we propose a Bicycle Station Dynamic Planning (BSDP) system to dynamically provide the optimal bicycle station layout for the DL-PBS network. The BSDP system contains four modules: bicycle drop-off location clustering, bicycle-station graph modeling, bicycle-station location prediction, and bicycle-station layout recommendation. In the bicycle drop-off location clustering module, candidate bicycle stations are clustered from each spatio-temporal subset of the large-scale cycling trajectory records. In the bicycle-station graph modeling module, a weighted digraph model is built based on the clustering results and inferior stations with low station revenue and utility are filtered. Then, graph models across time periods are combined to create a graph sequence model. In the bicycle-station location prediction module, the GGNN model is used to train the graph sequence data and dynamically predict bicycle stations in the next period. In the bicycle-station layout recommendation module, the predicted bicycle stations are fine-tuned according to the government urban management plan, which ensures that the recommended station layout is conducive to city management, vendor revenue, and user convenience. Experiments on actual DL-PBS networks verify the effectiveness, accuracy, and feasibility of the proposed BSDP system.

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Srivastava, Vivek, Bipin K. Tripathi, and Vinay K. Pathak. "Hybrid Computation Model for Intelligent System Design by Synergism of Modified EFC with Neural Network." International Journal of Information Technology & Decision Making 14, no. 01 (January 2015): 17–41. http://dx.doi.org/10.1142/s0219622014500813.

Повний текст джерела

Анотація:

In recent past, it has been seen in many applications that synergism of computational intelligence techniques outperforms over an individual technique. This paper proposes a new hybrid computation model which is a novel synergism of modified evolutionary fuzzy clustering with associated neural networks. It consists of two modules: fuzzy distribution and neural classifier. In first module, mean patterns are distributed into the number of clusters based on the modified evolutionary fuzzy clustering, which leads the basis for network structure selection and learning in associated neural classifier. In second module, training and subsequent generalization is performed by the associated neural networks. The number of associated networks required in the second module will be same as the number of clusters generated in the first module. Whereas, each network contains as many output neurons as the maximum number of members assigned to each cluster. The proposed hybrid model is evaluated over wide spectrum of benchmark problems and real life biometric recognition problems even in presence of real environmental constraints such as noise and occlusion. The results indicate the efficacy of proposed method over related techniques and endeavor promising outcomes for biometric applications with noise and occlusion.

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Sikka, Geeta, and Harleen Kaur. "Enriching Module Dependency Graphs for Improved Software Clustering." International Journal of System of Systems Engineering 12, no. 1 (2022): 1. http://dx.doi.org/10.1504/ijsse.2022.10038005.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Li, Xiao Ling, Huai Min Wang, Chang Guo Guo, Bo Ding, and Xiao Yong Li. "A Resource Finding Mechanism for Network Virtualization Environment." Advanced Materials Research 433-440 (January 2012): 5078–86. http://dx.doi.org/10.4028/www.scientific.net/amr.433-440.5078.

Повний текст джерела

Анотація:

There are large numbers of infrastructure resources in network virtualization environment (NVE), how to quickly and accurately find the resources that virtual network required is a challenging problem. Pointing to this problem, a resource finding mechanism for network virtualization environment (NVERFM) is proposed. NVERFM is mainly comprised of three modules, virtual resources publishing module (VRPM), virtual resources clustering framework (VRCF), and virtual resources finding module (VRFM). VRPM is responsible for publishing the infrastructure resources to VRCF; and the published information contains functional and non-functional attributes. VRCF is responsible for classifying the published information into different clustering according to the attributes from high priority to low priority. VRFM mainly completes resource finding based on resource similarity principle. Finding the resource clustering that meet the user’s requirements; and then combinatorial auction mechanism is used to help users choose the optimal infrastructure resource. Finally, experiments are used to validate NVERFM, and the results show that NVERFM can not only help users find the optimal resource, but also improve the efficiency.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Puspitasari, Yenni, Imas Sukaesih Sitanggang, and Rina Trisminingsih. "VISUALIZATION MODULE OF DENSITY-BASED CLUSTERING FOR HOTSPOT DISTRIBUTION IN INDONESIA USING MAPSERVER." Journal of Tropical Silviculture 7, no. 3 (December 28, 2016): S58—S60. http://dx.doi.org/10.29244/j-siltrop.7.3.s58-s60.

Повний текст джерела

Анотація:

A web-based Geographic Information System (GIS) has been built by previous researchers to visualize hotspots data in Indonesia. That GIS still has not contained a hotspot analysis module. Data mining method can be used to analyze hotspot data. This research aims to develop and to integrate a clustering module of hotspot in GIS which has been developed in the previous research. The clustering module for grouping hotspot data was built using the DBSCAN algorithm with PHP programming language. Clustering hotspot data was performed based on year, month, and province. Clustering parameters are epsilon and minimum points (MinPts). Epsilon value that used ranged from 0.01 to 0.1 while MinPts ranges from 1 to 6. The clustering results are shown in form of table which consists of the attribute Province, Regency, Latitude, Longitude and Cluster. Cluster column is the final result of clustering using algorithm DBSCAN. The attribute cluster represents clusters are visualized using the map of Indonesia that was built using MapServer. Visualization can help parties involved in making effective and efficient decisions to prevent forest fires.Key words: clustering, DBSCAN algorithm, geographic information system, hotspot

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Arasteh, Bahman, Amir Seyyedabbasi, Jawad Rasheed, and Adnan M. Abu-Mahfouz. "Program Source-Code Re-Modularization Using a Discretized and Modified Sand Cat Swarm Optimization Algorithm." Symmetry 15, no. 2 (February 2, 2023): 401. http://dx.doi.org/10.3390/sym15020401.

Повний текст джерела

Анотація:

One of expensive stages of the software lifecycle is its maintenance. Software maintenance will be much simpler if its structural models are available. Software module clustering is thought to be a practical reverse engineering method for building software structural models from source code. The most crucial goals in software module clustering are to minimize connections between created clusters, maximize internal connections within clusters, and maximize clustering quality. It is thought that finding the best software clustering model is an NP-complete task. The key shortcomings of the earlier techniques are their low success rates, low stability, and insufficient modularization quality. In this paper, for effective clustering of software source code, a discretized sand cat swarm optimization (SCSO) algorithm has been proposed. The proposed method takes the dependency graph of the source code and generates the best clusters for it. Ten standard and real-world benchmarks were used to assess the performance of the suggested approach. The outcomes show that the quality of clustering is improved when a discretized SCSO algorithm was used to address the software module clustering issue. The suggested method beats the previous heuristic approaches in terms of modularization quality, convergence speed, and success rate.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Zhang, Meng, Guo Xi Li, Wei Li, and Jing Zhong Gong. "Uneven Granular Module Clustering and Intelligent Optimization for Customizable Products." Applied Mechanics and Materials 215-216 (November 2012): 426–32. http://dx.doi.org/10.4028/www.scientific.net/amm.215-216.426.

Повний текст джерела

Анотація:

To solve the problems of the traditional approach to uniform granular module clustering, a new method for module clustering based on uneven granularity and intelligent optimization oriented to the customizable product design was proposed. Considering the impacts of requirements, functions and structures, the integrated fuzzy similarity matrix of parts was built using the correlativity analysis, and then the hierarchical structure was generated through a fuzzy clustering algorithm. All the universes of the granular layers in the hierarchical structure were gathered and the uneven granular module clustering scheme was formally presented. Four quantified indices including customizability index, customer satisfaction degree, design complexity and assembly complexity, were proposed to set up four optimization objective functions. Use nondominated sorting genetic algorithm II to solve the problem in order to obtain the Pareto optimal set. A design case of the single mast storage/retrieval machine was studied to demonstrate the feasibility of the proposed method.

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Altameem, Arwa A., and Alaaeldin M. Hafez. "Behavior Analysis Using Enhanced Fuzzy Clustering and Deep Learning." Electronics 11, no. 19 (October 2, 2022): 3172. http://dx.doi.org/10.3390/electronics11193172.

Повний текст джерела

Анотація:

Companies aim to offer customized treatments, intelligent care, and a seamless experience to their customers. Interactions between a company and its customers largely depend on the company’s ability to learn, understand, and predict customer behaviors. Customer behavior prediction is a pivotal factor in improving a company’s quality of services and thus its growth. Different machine learning techniques have been applied to gather customer data to predict behavioral patterns. Traditional methods are unable to discover hidden patterns in ideal situations and need to be improved to produce more accurate predictions. This work proposes a novel hybrid model comprised of two modules: a novel clustering module on the basis of an optimized fuzzy deep belief network and a customer behavior prediction module on the basis of a deep recurrent neural network. Customers’ previous purchasing characteristics and portfolio details were analyzed by applying learning parameters. In this paper, the deep learning techniques were optimized by applying the butterfly optimization method, which minimizes the maximum error classification problem. The performance of the system was evaluated using experimental analysis. The proposed approach was compared to other single and hybrid-model-based approaches and attained the highest performance in the respective metrics.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Gao, Shu Ying, and Li Li. "Research of Generalized Structure Module Modeling Based on Similar Feature Clustering." Applied Mechanics and Materials 151 (January 2012): 61–65. http://dx.doi.org/10.4028/www.scientific.net/amm.151.61.

Повний текст джерела

Анотація:

he creation of generalized structure module model is studied in this paper. Firstly, the component of generalized structure module is analyzed by the form of sets, then the modeling process of generalized structure module is explained, also the method of similar feature clustering-based for modeling is presented. Finally, an example of the drafting module in flyer frame is given.

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Jha, Monica, and Swarup Roy. "Extracting Functional Modules from RNASeq Counts Using Ensemble of Clustering Based Module Detection Methods." Journal of Computational and Theoretical Nanoscience 15, no. 6 (June 1, 2018): 2359–63. http://dx.doi.org/10.1166/jctn.2018.7469.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Xu, Yi Qiao. "Massive Data Analysis Based MapReduce Structure on Hadoop System." Advanced Materials Research 981 (July 2014): 262–66. http://dx.doi.org/10.4028/www.scientific.net/amr.981.262.

Повний текст джерела

Анотація:

Massive Data analysis is becoming increasingly prominent in a variety of application fields ranging from scientific studies to business researches. In this paper, we demonstrate the necessity and possibility of using MapReduce [1] module on Hadoop System [2]. Furthermore, we conducted MapReduce module to implement Clustering Algorithms [3] on our Hadoop System [4] and improved the efficiency of the Clustering Algorithms sharply. We showed how to design parallel clustering algorithms based on Hadoop System. Experiments by different size of data demonstrate that our purposed clustering algorithms have good performance on speed-up, scale-up and size-up. So, it is suitable for big data mining and analysis.

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Z. Zamli, Kamal, Abdulrahman Alsewari, and Bestoun S. Ahmed. "Multi-Start Jaya Algorithm for Software Module Clustering Problem." Azerbaijan Journal of High Performance Computing 1, no. 1 (August 10, 2018): 87–112. http://dx.doi.org/10.32010/26166127.2018.1.1.87.112.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Murtazin, D. G., and A. S. Belyaeva. "Development of the amplitude spectrum clustering module in Python." Automation, Telemechanization and Communication in Oil Industry, no. 2 (2021): 6–11. http://dx.doi.org/10.33285/0132-2222-2021-2(571)-6-11.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Yoo, Jaewook. "Module Communization for Product Platform Design Using Clustering Analysis." Journal of Society of Korea Industrial and Systems Engineering 37, no. 3 (September 30, 2014): 89–98. http://dx.doi.org/10.11627/jkise.2014.37.3.89.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Praditwong, Kata, Mark Harman, and Xin Yao. "Software Module Clustering as a Multi-Objective Search Problem." IEEE Transactions on Software Engineering 37, no. 2 (March 2011): 264–82. http://dx.doi.org/10.1109/tse.2010.26.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Kumari, A. Charan, and K. Srinivas. "Hyper-heuristic approach for multi-objective software module clustering." Journal of Systems and Software 117 (July 2016): 384–401. http://dx.doi.org/10.1016/j.jss.2016.04.007.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Putri, D., and I. S. Sitanggang. "Clustering Module in OLAP for Horticultural Crops using SpagoBI." IOP Conference Series: Earth and Environmental Science 58 (March 2017): 012001. http://dx.doi.org/10.1088/1755-1315/58/1/012001.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

41

Chen, Yan Hui, and De Jian Zhou. "Min-Max Partition Method of Product Modularization Based on Fuzzy Clustering." Advanced Materials Research 308-310 (August 2011): 273–79. http://dx.doi.org/10.4028/www.scientific.net/amr.308-310.273.

Повний текст джерела

Анотація:

This paper presents a new method of product module partition based on the fuzzy clustering analysis. This method demonstrates the relevant definitions and calculation methods of the initial partition, min-max partition, submodule relevancy and module aggregation etc., and establishes the incidence matrix to respectively carry out the initial partition for the products and calculation of min-max partition according to various incidence relations between parts and components. Taking the submodule as computing unit in each module set, this paper carries out the fuzzy cluster analysis to obtain the module partition results of the products, and finally demonstrates the rationality and effectiveness of this method by taking the example of the working units of the wheel loaders.

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Gao, Zhenghao, and Dan Li. "Blockchain-Based Neural Network Model for Agricultural Product Cold Chain Coordination." Computational Intelligence and Neuroscience 2022 (May 31, 2022): 1–12. http://dx.doi.org/10.1155/2022/1760937.

Повний текст джерела

Анотація:

This paper adopts a blockchain fusion neural network algorithm to conduct an in-depth study on the model of agricultural cold chain coordination. We aim to enable HDFS to meet the demand of storing many small files of various types generated by various stages of agricultural cold chain coordination and then propose an improved balanced merging and index caching strategy based on file types and size grouping. The main three modules are the file preprocessing module, file balanced merging module, and index caching module. The experimental results show that this method can significantly improve the overall performance of HDFS when storing and reading large amounts of small files. Simulation experiments using the UCI test dataset show that the improved spectral clustering algorithm not only reduces the error rate but also significantly reduces the time spent on the clustering process, demonstrating the effectiveness and feasibility of the improved spectral clustering algorithm. The improved spectral clustering algorithm of this paper is used to cluster and analyze nearly one thousand cold chain coordination-related data, and the optimal city is successfully selected as the construction point of a large cold storage transit station. This study can effectively improve the efficiency of cold chain coordination resources and their time utilization and maximize the profit creation for cold chain coordination enterprises, selecting data features for prediction, experimenting with different models and parameters to optimize accuracy, and embedding the resulting learning system for prediction and further operations. The two models of coordination market demand forecasting models and methods are analyzed separately. Finally, after analyzing the prediction results of the two different prediction methods, it is found that it conforms to the actual situation of coordination development in Jiangxi Province. It shows that the coordination market prediction model established in this paper is meaningful and the prediction analysis made has some practical value.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Modi, M., N. G. Jadeja, and K. Zala. "FMFinder: A Functional Module Detector for PPI Networks." Engineering, Technology & Applied Science Research 7, no. 5 (October 19, 2017): 2022–25. http://dx.doi.org/10.48084/etasr.1347.

Повний текст джерела

Анотація:

Bioinformatics is an integrated area of data mining, statistics and computational biology. Protein-Protein Interaction (PPI) network is the most important biological process in living beings. In this network a protein module interacts with another module and so on, forming a large network of proteins. The same set of proteins which takes part in the organic courses of biological actions is detected through the Function Module Detection method. Clustering process when applied in PPI networks is made of proteins which are part of a larger communication network. As a result of this, we can define the limits for module detection as well as clarify the construction of a PPI network. For understating the bio-mechanism of various living beings, a detailed study of FMFinder detection by clustering process is called for.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

S., Gopinath. "Cluster based Optimal Energy Efficient Routing Protocol for Wireless Sensor Networks." Revista Gestão Inovação e Tecnologias 11, no. 2 (June 5, 2021): 1921–32. http://dx.doi.org/10.47059/revistageintec.v11i2.1808.

Повний текст джерела

Анотація:

Balancing the energy consumption and location accuracy is one of the critical tasks in WSN. Energy consumption of sensor nodes is measured in terms of route discovery, packet forwarding and data transmission. In this research work, it is proposed that scheduling based Optimal Energy Clustering Scheme (SOECS) to attain the maximum location accuracy and energy efficiency during route maintenance. It contains three major modules. In first module, the node deployment is done using Gaussian distribution function to route the packets effectively. In second module, Cluster heads are chosen and energy is estimated for optimal cluster heads. In third module, TDMA scheduling algorithm is introduced to improve the energy efficiency using stable routes and scheduling table. The work is evaluated using network simulation tool. The proposed scheme produces high performance than existing schemes.

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Lin, Guoting, Zexun Zheng, Lin Chen, Tianyi Qin, and Jiahui Song. "Multi-Modal 3D Shape Clustering with Dual Contrastive Learning." Applied Sciences 12, no. 15 (July 22, 2022): 7384. http://dx.doi.org/10.3390/app12157384.

Повний текст джерела

Анотація:

3D shape clustering is developing into an important research subject with the wide applications of 3D shapes in computer vision and multimedia fields. Since 3D shapes generally take on various modalities, how to comprehensively exploit the multi-modal properties to boost clustering performance has become a key issue for the 3D shape clustering task. Taking into account the advantages of multiple views and point clouds, this paper proposes the first multi-modal 3D shape clustering method, named the dual contrastive learning network (DCL-Net), to discover the clustering partitions of unlabeled 3D shapes. First, by simultaneously performing cross-view contrastive learning within multi-view modality and cross-modal contrastive learning between the point cloud and multi-view modalities in the representation space, a representation-level dual contrastive learning module is developed, which aims to capture discriminative 3D shape features for clustering. Meanwhile, an assignment-level dual contrastive learning module is designed by further ensuring the consistency of clustering assignments within the multi-view modality, as well as between the point cloud and multi-view modalities, thus obtaining more compact clustering partitions. Experiments on two commonly used 3D shape benchmarks demonstrate the effectiveness of the proposed DCL-Net.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Boubekki, Ahcène, Michael Kampffmeyer, Ulf Brefeld, and Robert Jenssen. "Joint optimization of an autoencoder for clustering and embedding." Machine Learning 110, no. 7 (June 21, 2021): 1901–37. http://dx.doi.org/10.1007/s10994-021-06015-5.

Повний текст джерела

Анотація:

AbstractDeep embedded clustering has become a dominating approach to unsupervised categorization of objects with deep neural networks. The optimization of the most popular methods alternates between the training of a deep autoencoder and a k-means clustering of the autoencoder’s embedding. The diachronic setting, however, prevents the former to benefit from valuable information acquired by the latter. In this paper, we present an alternative where the autoencoder and the clustering are learned simultaneously. This is achieved by providing novel theoretical insight, where we show that the objective function of a certain class of Gaussian mixture models (GMM’s) can naturally be rephrased as the loss function of a one-hidden layer autoencoder thus inheriting the built-in clustering capabilities of the GMM. That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding. Experiments confirm the equivalence between the clustering module and Gaussian mixture models. Further evaluations affirm the empirical relevance of our deep architecture as it outperforms related baselines on several data sets.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Roberts, Wade R., and Eric H. Roalson. "Co-expression clustering across flower development identifies modules for diverse floral forms in Achimenes (Gesneriaceae)." PeerJ 8 (March 11, 2020): e8778. http://dx.doi.org/10.7717/peerj.8778.

Повний текст джерела

Анотація:

Background Genetic pathways involved with flower color and shape are thought to play an important role in the development of flowers associated with different pollination syndromes, such as those associated with bee, butterfly, or hummingbird pollination. Because pollination syndromes are complex traits that are orchestrated by multiple genes and pathways, the gene regulatory networks have not been explored. Gene co-expression networks provide a systems level approach to identify important contributors to floral diversification. Methods RNA-sequencing was used to assay gene expression across two stages of flower development (an early bud and an intermediate stage) in 10 species of Achimenes (Gesneriaceae). Two stage-specific co-expression networks were created from 9,503 orthologs and analyzed to identify module hubs and the network periphery. Module association with bee, butterfly, and hummingbird pollination syndromes was tested using phylogenetic mixed models. The relationship between network connectivity and evolutionary rates (dN/dS) was tested using linear models. Results Networks contained 65 and 62 modules that were largely preserved between developmental stages and contained few stage-specific modules. Over a third of the modules in both networks were associated with flower color, shape, and pollination syndrome. Within these modules, several hub nodes were identified that related to the production of anthocyanin and carotenoid pigments and the development of flower shape. Evolutionary rates were decreased in highly connected genes and elevated in peripheral genes. Discussion This study aids in the understanding of the genetic architecture and network properties underlying the development of floral form and provides valuable candidate modules and genes for future studies.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Song, Zhiwei, Brittany Baur, and Sushmita Roy. "Benchmarking graph representation learning algorithms for detecting modules in molecular networks." F1000Research 12 (August 7, 2023): 941. http://dx.doi.org/10.12688/f1000research.134526.1.

Повний текст джерела

Анотація:

Background: A common task in molecular network analysis is the detection of community structures or modules. Such modules are frequently associated with shared biological functions and are often disrupted in disease. Detection of community structure entails clustering nodes in the graph, and many algorithms apply a clustering algorithm on an input node embedding. Graph representation learning offers a powerful framework to learn node embeddings to perform various downstream tasks such as clustering. Deep embedding methods based on graph neural networks can have substantially better performance on machine learning tasks on graphs, including module detection; however, existing studies have focused on social and citation networks. It is currently unclear if deep embedding methods offer any advantage over shallow embedding methods for detecting modules in molecular networks. Methods: Here, we investigated deep and shallow graph representation learning algorithms on synthetic and real cell-type specific gene interaction networks to detect gene modules and identify pathways affected by sequence nucleotide polymorphisms. We used multiple criteria to assess the quality of the clusters based on connectivity as well as overrepresentation of biological processes. Results: On synthetic networks, deep embedding based on a variational graph autoencoder had superior performance as measured by modularity metrics, followed closely by shallow methods, node2vec and Graph Laplacian embedding. However, the performance of the deep methods worsens when the overall connectivity between clusters increases. On real molecular networks, deep embedding methods did not have a clear advantage and the performance depended upon the properties of the graph and the metrics. Conclusions: Deep graph representation learning algorithms for module detection-based tasks can be beneficial for some biological networks, but the performance depends upon the metrics and graph properties. Across different network types, Graph Laplacian embedding followed by node2vec are the best performing algorithms.

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Liu, Chenghua, Zhuolin Liao, Yixuan Ma, and Kun Zhan. "Stationary Diffusion State Neural Estimation for Multiview Clustering." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (June 28, 2022): 7542–49. http://dx.doi.org/10.1609/aaai.v36i7.20719.

Повний текст джерела

Анотація:

Although many graph-based clustering methods attempt to model the stationary diffusion state in their objectives, their performance limits to using a predefined graph. We argue that the estimation of the stationary diffusion state can be achieved by gradient descent over neural networks. We specifically design the Stationary Diffusion State Neural Estimation (SDSNE) to exploit multiview structural graph information for co-supervised learning. We explore how to design a graph neural network specially for unsupervised multiview learning and integrate multiple graphs into a unified consensus graph by a shared self-attentional module. The view-shared self-attentional module utilizes the graph structure to learn a view-consistent global graph. Meanwhile, instead of using auto-encoder in most unsupervised learning graph neural networks, SDSNE uses a co-supervised strategy with structure information to supervise the model learning. The co-supervised strategy as the loss function guides SDSNE in achieving the stationary state. With the help of the loss and the self-attentional module, we learn to obtain a graph in which nodes in each connected component fully connect by the same weight. Experiments on several multiview datasets demonstrate effectiveness of SDSNE in terms of six clustering evaluation metrics.

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Heinkel, Florian, Libin Abraham, Mary Ko, Joseph Chao, Horacio Bach, Lok Tin Hui, Haoran Li, et al. "Phase separation and clustering of an ABC transporter in Mycobacterium tuberculosis." Proceedings of the National Academy of Sciences 116, no. 33 (July 31, 2019): 16326–31. http://dx.doi.org/10.1073/pnas.1820683116.

Повний текст джерела

Анотація:

Phase separation drives numerous cellular processes, ranging from the formation of membrane-less organelles to the cooperative assembly of signaling proteins. Features such as multivalency and intrinsic disorder that enable condensate formation are found not only in cytosolic and nuclear proteins, but also in membrane-associated proteins. The ABC transporter Rv1747, which is important for Mycobacterium tuberculosis (Mtb) growth in infected hosts, has a cytoplasmic regulatory module consisting of 2 phosphothreonine-binding Forkhead-associated domains joined by an intrinsically disordered linker with multiple phospho-acceptor threonines. Here we demonstrate that the regulatory modules of Rv1747 and its homolog in Mycobacterium smegmatis form liquid-like condensates as a function of concentration and phosphorylation. The serine/threonine kinases and sole phosphatase of Mtb tune phosphorylation-enhanced phase separation and differentially colocalize with the resulting condensates. The Rv1747 regulatory module also phase-separates on supported lipid bilayers and forms dynamic foci when expressed heterologously in live yeast and M. smegmatis cells. Consistent with these observations, single-molecule localization microscopy reveals that the endogenous Mtb transporter forms higher-order clusters within the Mycobacterium membrane. Collectively, these data suggest a key role for phase separation in the function of these mycobacterial ABC transporters and their regulation via intracellular signaling.

Стилі APA, Harvard, Vancouver, ISO та ін.

Статті в журналах з теми "Module clustering"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями