On the Application of Text Clustering in Engineering Change Process

Grieco, A; Pacella, Massimo; Blaco, Marzia

doi:10.1016/j.procir.2016.06.019

Cited by 20 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the SOM process, two performance metrics were implemented: the mean distance (deviation) from the cluster centroid (Grieco et al, 2017) and the Devies-Boulding (DB) index (Davies and Bouldin, 1979). Deviation metrics define the algorithm that minimises an error function computed on the sum of squared distances for each data point in each cluster.…”

Section: Model Baseline Setupmentioning

confidence: 99%

An accurate evaluation of water availability in sub-arid Mediterranean watersheds through SWAT: Cega-Eresma-Adaja

Rivas-Tabares

Tarquis

Willaarts

et al. 2019

Agricultural Water Management

View full text Add to dashboard Cite

Simulation of flow processes in hyper-regulated Mediterranean watersheds is critical when examining general water demand and established ecological flows of River Basin Management Plans. Weather dynamics in the Mediterranean zone in recent decades have been characterised by a natural variation of drought cycles. In addition, exacerbated climate change proves that water fluxes must be estimated with more exhaustive models. The aim of this study is to assess the water balance of the Cega-Eresma-Adaja (CEA) watershed, including a detailed assessment of land uses and management practices to quantify agricultural water demand for the time period 2004-2014. We used the Soil and Water Assessment Tool (SWAT), given that it is a widespread tool that involves complex processes of the water cycle on a basin scale, providing information on water dynamics related to land use as a fundamental characteristic for water balance calculation. The Nash-Sutcliffe coefficient efficiency value, the main index of calibration and validation performance, was 0.86 for the Eresma-Adaja River and 0.67 for the Cega River. This presents a good result considering the large-scale watershed studied. Analysing dry hydrological years, we found that the estimation of ecological flows for sub-arid zones needs to consider the shallow aquifer-river relationship. During spring-summer periods, with very low flow, monitoring the shallow aquifer levels ensures a good ecological status. The study reveals that aspects such as crop rotation, soil management and their associated measures in Mediterranean basins are key factors for water resource management during drought periods. These results are expected to serve stakeholders and river basin authorities in conducting better-integrated water management practices in the watershed.

show abstract

Section: Model Baseline Setupmentioning

confidence: 99%

An accurate evaluation of water availability in sub-arid Mediterranean watersheds through SWAT: Cega-Eresma-Adaja

Rivas-Tabares

Tarquis

Willaarts

et al. 2019

Agricultural Water Management

View full text Add to dashboard Cite

show abstract

“…"As stated in [6]". In the cluster analysis algorithm for learning resources, different class attributes are set for different learning resources to make a representation on the properties of their respective resources.…”

Section: Cluster Analysis Approach For Learning Resourcesmentioning

confidence: 96%

Discovery and Recommendation of First-Hand Learning Resources Based on Public Opinion Cluster Analysis

Zhang

Wang

2017

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Abstract-This paper explores the personalized approach of the public opinion cluster analysis for learning resources based on the server-side predetermined analysis, in order to introduce the personalized learning resource recommender into the traditional online instruction. In allusion to further validation on its implementation, the fuzzy aggregation of learning resources is mined up based on the proposed WRTC algorithm. The personalized learning resource recommender mechanism is then described. In the end, the common evaluation parameters in the personalized recommender model are applied in the evaluation on the system performance. The experiment is carried out with learner's access data online to validate whether the algorithm and the model indicators are effective for the purpose of improving the precision and coverage of learning resources.

show abstract

“…Also, an automated evaluation was implemented, the classification of the attributes and the allocation of values to the attributes has to be done manually. Grieco et al (2017) used a self-organising map on the Bag-of-Words vector representation of ECRs to cluster groups of similar content. The clusters divided the documents according to concerned part or assembly but the assignment of the clusters to the corresponding component needs to be done manually.…”

Section: Related Researchmentioning

confidence: 99%

Derivation of Description Features for Engineering Change Request by Aid of Latent Dirichlet Allocation

Riesener

Dölle

Mendl-Heinisch

et al. 2020

Proc. Des. Soc.: Des. Conf.

View full text Add to dashboard Cite

Complex products and shorter development cycles lead to an increasing number of engineering changes. In order to be able to process these changes more effectively and efficiently, this paper develops a description model as a first step towards a data driven approach of processing engineering change requests. The description model is systematically derived from literature using text mining and natural language processing techniques. An example of the application is given by an automated classification based on similarity calculations between new and historic engineering change requests.

show abstract

On the Application of Text Clustering in Engineering Change Process

Cited by 20 publications

References 13 publications

An accurate evaluation of water availability in sub-arid Mediterranean watersheds through SWAT: Cega-Eresma-Adaja

An accurate evaluation of water availability in sub-arid Mediterranean watersheds through SWAT: Cega-Eresma-Adaja

Discovery and Recommendation of First-Hand Learning Resources Based on Public Opinion Cluster Analysis

Derivation of Description Features for Engineering Change Request by Aid of Latent Dirichlet Allocation

Contact Info

Product

Resources

About