Clustering in an Object-Oriented Environment

Struyf, Anja; Hubert, Mia; Rousseeuw, Peter J.

doi:10.18637/jss.v001.i04

Cited by 193 publications

(176 citation statements)

References 14 publications

(9 reference statements)

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…The ordination technique was used to evaluate associations among variables (species) that characterized cases (trips) (Gordon, 1999), and to help to interpret the final result obtained with the classification technique. We also used it in those cases in which the association was weak (Struyf et al, 1996).…”

Section: Identification Of the Fisheriesmentioning

confidence: 99%

Deep-water fishing tactics of the Spanish fleet in the Northeast Atlantic. Seasonal and spatial distribution

et al. 2011

View full text Add to dashboard Cite

SUMMARY:The classification and identification of all the Spanish fishing activity targeting deep-sea species was conducted using a non-hierarchical classification technique designed for large matrices (CLARA). Otter trawl and set longlines were the main gears used in deep-sea ecosystems. The otter trawl fleet conducted 3 deep-sea fishing tactics. The only otter trawl fishing tactic targeting deep-sea species was that working in the VI ICES Division and targeting Alepocephalus baiirdi. The other 2 otter trawl fishing tactics targeted shallower shelf demersal resources, deep-sea species being secondary (Phycis blennoides). The longline fleet carried out 7 fishing tactics targeting deep-sea species (Molva spp.; deep water sharks; P. blennoides; Pagellus bogaraveo; and Trichiuridae) and 2 fishing tactics targeting Conger conger, which perform as deepsea fishing tactics in the narrow continental shelf area. This classification, together with knowledge regarding their seasonal performance and spatial distribution, may help to design fisheries sampling protocols and to improve the management of these fleets, thus reducing their impact on deep-sea habitats.Keywords: Northeast Atlantic, métiers, fisheries, deep sea, trawl, longline, multivariate. RESUMEN: Pesquerías españolas de gran profundidad en el Atlántico Nordeste. Estacionalidad y distribución espacial. -Para la clasificación e identificación de todas las pesquerías españolas que actúan sobre especies de gran profundidad se ha utilizado una técnica de cluster no jerárquica diseñada para grandes matrices (CLARA). El arrastre con puertas y el palangre de fondo fueron los aparejos más importantes. Solamente la táctica pesquera de arrastre con puertas desarrollada en la División VI del ICES está dirigida a especies de profundidad, siendo la especie objetivo Alepocephalus baiirdi. Las otras dos tácticas pesqueras con arrastre de puertas son mixtas, teniendo como objetivo especies típicas de plataforma, y teniendo las especies de profundidad como secundarias (Phycis blennoides). La flota de palangre desarrolla siete tácticas pesqueras dirigidas a especies de profundidad: Molva spp.; tiburones de profundidad; P. blennoides; Pagellus bogaraveo; Trichiuridae; y dos pesquerías dirigidas a Conger conger, que se comportan como tácticas pesqueras de profundidad en las zonas de plataforma estrecha. Esta clasificación junto con el conocimiento acerca de su comportamiento estacional y espacial, ayudarán al diseño de los protocolos de muestreo de estas pesquerías así como a la mejora de la gestión de estas pesquerías contribuyendo a una reducción de su impacto en los hábitats profundos.

show abstract

Section: Identification Of the Fisheriesmentioning

confidence: 99%

Deep-water fishing tactics of the Spanish fleet in the Northeast Atlantic. Seasonal and spatial distribution

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Similarly, for Pavia data set [18] (Figure 4), FCM is either the best clustering results or slightly behind hierarchical clustering algorithm [11,12]. For KSC data set [17] (Figure 3), K-means [5,6]and K-medoids [7,8]are giving the best results.Concerning PaviaU data set [18] (Figure 5), FCM is giving better results according to the accuracy and Q Rand measures. However, according to Q Jaccard , Q FM , and Q Hubert , the hierarchical clustering is giving better results.…”

Section: Results and Analysismentioning

confidence: 99%

“…Classification and clustering algorithms are conducted to analyse and study their results on HIS. In this paper we investigated the behaviour of known clustering techniques on HSI, which are: k-means [5,6], Kmedoids [7,8], fuzzy C-Means (FCM) [9,10], hierarchical [11,12], and DBSCAN [13]. Four different HSI data sets are chosen in our experiments, which are: Botswana [17], KSC [17], Pavia [18], and PaviaU [18].…”

Section: Resultsmentioning

confidence: 99%

“…Depending on the spectral content information, clustering methods such as k-means [5,6], K-medoids [7,8], fuzzy C-Means (FCM) [9,10], hierarchical [11,12], and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) [13] are highly exploited [14]. To further enhance the clustering performance, the spatial context information is incorporated with the spectral information to enhance the clustering performance [15].…”

Section: Clustering Techniquesmentioning

confidence: 99%

“…Unlike Kmeans, K-medoids tries to minimize the total dissimilarities between the observations in a cluster and its medoid, which make K-medoids more robust to noise [7]. A medoid of cluster is an observation that have the minimal dissimilarity average to all other observations [8]. Similar to Kmeans, the initial medoids are randomly selected then the assignment and updating step are processed repeatedly.…”

Section: K-medoids Clusteringmentioning

confidence: 99%

See 2 more Smart Citations

Clustering Hyperspectral Data

Alturki¹,

Bchir²

2017

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

show abstract

Viticulture–climate relationships in Greece: the impacts of recent climate trends on harvest date variation

Koufos

Mavromatis

Koundouras

et al. 2013

Intl Journal of Climatology

View full text Add to dashboard Cite

Climate characteristics and relationships with indigenous varieties in Greece are examined to better understand how these varieties perform in their native climate and assess the impact regional climate change has on the Greek wine industry. Thus, harvest dates (ΔH) for eight indigenous varieties and regions, along with climate data, were gathered and systematically explored using linear regression models and principal component analysis for three ‘effective’ growing season time period definitions (calendar year, growing season and ripening period). The eight study regions had marked differences in their general climatic characteristics, mainly between mainland and island areas. ΔH response was not particularly sensitive to time period definition. In five out of eight regions, a systematic shift of ΔH was identified (earlier harvest), mainly driven by changes in maximum and minimum temperatures. Significant trends in climate parameters and viticulture–climate relationships were more evident for island regions when compared to mainland locations. Moreover, areas with late ripening varieties were shown to be less sensitive to climate changes. Only in one region harvest was delayed, possibly due to non‐climate factors. The identification of up‐to‐date climate and grapevine phenology relationships could be an important step for broader and more confident future assessments of climate suitability for viticulture and climate change impacts in Greece, and provide insights into how lesser known varieties might perform in other regions.

show abstract

Clustering in an Object-Oriented Environment

Cited by 193 publications

References 14 publications

Deep-water fishing tactics of the Spanish fleet in the Northeast Atlantic. Seasonal and spatial distribution

Deep-water fishing tactics of the Spanish fleet in the Northeast Atlantic. Seasonal and spatial distribution

Clustering Hyperspectral Data

Viticulture–climate relationships in Greece: the impacts of recent climate trends on harvest date variation

Contact Info

Product

Resources

About