Social network analysis on industrial symbiosis: A case of Gujiao eco-industrial park

Food waste valorisation: Assessing the effectiveness of collaborative research networks through the lenses of a COST action

Use of fuzzy cognitive maps to develop policy strategies for the optimization of municipal waste management: A case study of the land of fires (Italy)

When all seemed lost. A social network analysis of the waste-related environmental movement in Campania, Italy

Ascertaining the stability of symptom clusters and identifying sentinel symptoms have been top priorities in symptom cluster research. Identifying sentinel symptoms would help to determine the underlying mechanisms of symptom clusters and facilitate effective symptom management. This study aimed to evaluate the stability of symptom clusters during the 1st and 2nd cycles of adjuvant chemotherapy (CTx) and to identify sentinel symptoms. This is a secondary data analysis of data from the Paradigm Shift in Chemotherapy-Induced Nausea and Vomiting (PS-CINV) study. Data utilized were from cancer patients who received adjuvant chemotherapy and completed symptom evaluation in the 1st and 2nd cycles (N = 209). The severity of 20 symptoms was evaluated on a 0-to-10 numeric rating scale. Principal component and hierarchical cluster analyses identified symptom clusters, and principal variable analysis identified sentinel symptoms. Among 20 symptoms, 13 symptoms formed 4 symptom clusters in the 1st cycle: a physical-psychological (pain, dyspnea, sleep disturbance, anxiety, depression), a gastrointestinal (nausea, loss of appetite, taste change), a fatigue-cognitive (fatigue, difficulty concentrating, drowsiness), and a urosexual (urinary problem, sexual problem) symptom cluster. During the 2nd cycle, stable symptom clusters were identified, with merging of the physical-psychological and fatigue-cognitive symptom clusters, resulting in three clusters. Sentinel symptoms were identified in the following order: anxiety, loss of appetite and fatigue (1st cycle) and loss of appetite, depression, and fatigue (2nd cycle). Symptom clusters demonstrated phase-specific stability. The current study identified a core set of symptoms that form stable symptom clusters during the 1st and 2nd cycles of CTx. Principal variable analysis identified sentinel symptoms which could facilitate efficient symptom management.

Stability of symptom clusters and sentinel symptoms during the first two cycles of adjuvant chemotherapy.

From a social network of n nodes connected by l lines, one may produce centrality measures such as closeness, betweenness and so on. In the past, the magnitude of n was around 1,000 or 10,000 at most. Nowadays, some networks have 10,000, 100,000 or even more than that. Thus, the scalability issue needs the attention of researchers. In this short paper, we explore random networks of the size around n = 100,000 by Monte-Carlo method and propose Monte-Carlo algorithms of computing closeness and betweenness centrality measures to study the small world properties of social networks.

/pdf/monte-carlo-methods-for-social-network-analysis-1xflz09b0j.pdf

Monte-Carlo Methods for Social Network Analysis

In most cases of multidimensional scaling(MDS), the distances or dissimilarities among units are assumed tobe symmetric. Thus, it is not an easy task to deal with asymmetric distances. Asymmetric MDS developedso far face diﬃculties in the interpretation of results. This study proposes a much simpler asymmetric MDS,that utilizes the notion of “altitude”. The analogy arises in mountaineering: It is easier (more diﬃcult)to move from the higher (lower) point to the lower (higher). The idea is formulated as a quantiﬁcationproblem, in which the disparity of distances is maximally related to the altitude diﬀerence. The proposedmethod is demonstrated in three examples, in which the altitudes are visualized by rainbow colors to easethe interpretability of users.Keywords: Multidimensional scaling(MDS), similarity, asymmetric distance matrix, altitude model, socialnetwork analysis. 1. 연구배경과 목적 다차원 척도법(multidimensional scaling), 일명 MDS는 n 개 개체 간 유사도(similarity) 또는 비유사도(dissimilarity)가 관측된자료를 저차원 공간에 타점하는 기법이다. Torgerson의고전적(classical)계량형 MDS부터 비계량형(nonmetric) MDS까지 여러 종류가 개발되어 있다. 통상적인MDS 기법들은

/pdf/multidimensional-scaling-of-asymmetric-distance-matrices-30x3s4ocgt.pdf

Multidimensional Scaling of Asymmetric Distance Matrices

Recently we frequently analyze multivariate data with quite large number of variables. In such data sets, virtually duplicated variables may exist simultaneously even though they are conceptually distinguishable. Duplicate variables may cause problems such as the distortion of principal axes in principal component analysis and factor analysis and the distortion of the distances between observations, i.e. the input for cluster analysis. Also in supervised learning or regression analysis, duplicated explanatory variables often cause the instability of fitted models. Since real data analyses are aimed often at multiple purposes, it is necessary to reduce the number of variables to a parsimonious level. The aim of this paper is to propose a practical algorithm for selection of a subset of variables from a given set of p input variables, by the criterion of minimum trace of partial variances of unselected variables unexplained by selected variables. The usefulness of proposed method is demonstrated in visualizing the relationship between selected and unselected variables, in building a predictive model with very large number of independent variables, and in reducing the number of variables and purging/merging categories in categorical data.

/pdf/variable-selection-for-multi-purpose-multivariate-data-s0u80k9i40.pdf

Variable Selection for Multi-Purpose Multivariate Data Analysis

PLS methods are suited for regressing q-variate Y variables on p-variate X variables even in the presence of multicollinearity problem among X variables. Consequently, they are useful for analyzing datasets with smaller number of observations compared to the number of variables, such as NIR(near-infrared) spectroscopy data in chemometrics. In this study, we propose two visualizing methods of p-variate X variables and q-variate Y variable that can be used in connection with PLS analysis.

http://www.ndsl.kr/soc_img/society/kss/GCGHDE/2007/v20n2/GCGHDE_2007_v20n2_345.pdf

Visualizing (X,Y) Data by Partial Least Squares Method

For displaying multivariate numerical data on a 2D plane by the projection, principal components biplot and the GGobi are two main tools of data visualization. The biplot is very useful for capturing the global shape of the dataset, by representing observations and variables simultaneously on a single graph. The GGobi shows a dynamic movie of the images of observations projected onto a sequence of unit vectors floating on the -dimensional sphere. Even though these two methods are certainly very valuable, there are drawbacks. The biplot is too condensed to describe the detailed parts of the data, and the GGobi is too burdensome for ordinary data analyses. In this paper, "the local projective display(LPD)" is proposed for visualizing multivariate numerical data. Main steps of the LDP are 1) -means clustering of the data into subsets, 2) drawing principal components biplots of individual subsets, and 3) sequencing plots by Hurley's (2004) endlink algorithm for cognitive continuity.

Yong-Goo Lee

Papers

Monte-Carlo Methods for Social Network Analysis

Multidimensional Scaling of Asymmetric Distance Matrices

Variable Selection for Multi-Purpose Multivariate Data Analysis

Visualizing (X,Y) Data by Partial Least Squares Method

Local Projective Display of Multivariate Numerical Data